Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

110 files changed, 4599 insertions, 3696 deletions

diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c
index fc27d4b52e5f..49f189423063 100644
--- a/fs/afs/netdevices.c
+++ b/fs/afs/netdevices.c
@@ -8,6 +8,7 @@
 #include <linux/inetdevice.h>
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
+#include <net/net_namespace.h>
 #include "internal.h"
 
 /*
@@ -23,7 +24,7 @@ int afs_get_MAC_address(u8 *mac, size_t maclen)
 		BUG();
 
 	rtnl_lock();
-	dev = __dev_getfirstbyhwtype(ARPHRD_ETHER);
+	dev = __dev_getfirstbyhwtype(&init_net, ARPHRD_ETHER);
 	if (dev) {
 		memcpy(mac, dev->dev_addr, maclen);
 		ret = 0;
@@ -47,7 +48,7 @@ int afs_get_ipv4_interfaces(struct afs_interface *bufs, size_t maxbufs,
 	ASSERT(maxbufs > 0);
 
 	rtnl_lock();
-	for_each_netdev(dev) {
+	for_each_netdev(&init_net, dev) {
 		if (dev->type == ARPHRD_LOOPBACK && !wantloopback)
 			continue;
 		idev = __in_dev_get_rtnl(dev);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 4482a0673b15..b1013f34085d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1514,9 +1514,6 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 	int thread_status_size = 0;
 	elf_addr_t *auxv;
 	unsigned long mm_flags;
-#ifdef ELF_CORE_WRITE_EXTRA_NOTES
-	int extra_notes_size;
-#endif
 
 	/*
 	 * We no longer stop all VM operations.
@@ -1645,10 +1642,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		
 		sz += thread_status_size;
 
-#ifdef ELF_CORE_WRITE_EXTRA_NOTES
-		extra_notes_size = ELF_CORE_EXTRA_NOTES_SIZE;
-		sz += extra_notes_size;
-#endif
+		sz += elf_coredump_extra_notes_size();
 
 		fill_elf_note_phdr(&phdr, sz, offset);
 		offset += sz;
@@ -1698,10 +1692,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		if (!writenote(notes + i, file, &foffset))
 			goto end_coredump;
 
-#ifdef ELF_CORE_WRITE_EXTRA_NOTES
-	ELF_CORE_WRITE_EXTRA_NOTES;
-	foffset += extra_notes_size;
-#endif
+	if (elf_coredump_extra_notes_write(file, &foffset))
+		goto end_coredump;
 
 	/* write out the thread status notes section */
 	list_for_each(t, &thread_list) {
diff --git a/fs/bio.c b/fs/bio.c
index 29a44c1b64c6..5f604f269dfa 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -798,13 +798,9 @@ void bio_unmap_user(struct bio *bio)
 	bio_put(bio);
 }
 
-static int bio_map_kern_endio(struct bio *bio, unsigned int bytes_done, int err)
+static void bio_map_kern_endio(struct bio *bio, int err)
 {
-	if (bio->bi_size)
-		return 1;
-
 	bio_put(bio);
-	return 0;
 }
 
 
@@ -1002,34 +998,26 @@ void bio_check_pages_dirty(struct bio *bio)
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
- * @bytes_done:	number of bytes completed
  * @error:	error, if any
  *
  * Description:
- *   bio_endio() will end I/O on @bytes_done number of bytes. This may be
- *   just a partial part of the bio, or it may be the whole bio. bio_endio()
- *   is the preferred way to end I/O on a bio, it takes care of decrementing
- *   bi_size and clearing BIO_UPTODATE on error. @error is 0 on success, and
- *   and one of the established -Exxxx (-EIO, for instance) error values in
- *   case something went wrong. Noone should call bi_end_io() directly on
- *   a bio unless they own it and thus know that it has an end_io function.
+ *   bio_endio() will end I/O on the whole bio. bio_endio() is the
+ *   preferred way to end I/O on a bio, it takes care of clearing
+ *   BIO_UPTODATE on error. @error is 0 on success, and and one of the
+ *   established -Exxxx (-EIO, for instance) error values in case
+ *   something went wrong. Noone should call bi_end_io() directly on a
+ *   bio unless they own it and thus know that it has an end_io
+ *   function.
  **/
-void bio_endio(struct bio *bio, unsigned int bytes_done, int error)
+void bio_endio(struct bio *bio, int error)
 {
 	if (error)
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-
-	if (unlikely(bytes_done > bio->bi_size)) {
-		printk("%s: want %u bytes done, only %u left\n", __FUNCTION__,
-						bytes_done, bio->bi_size);
-		bytes_done = bio->bi_size;
-	}
-
-	bio->bi_size -= bytes_done;
-	bio->bi_sector += (bytes_done >> 9);
+	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = -EIO;
 
 	if (bio->bi_end_io)
-		bio->bi_end_io(bio, bytes_done, error);
+		bio->bi_end_io(bio, error);
 }
 
 void bio_pair_release(struct bio_pair *bp)
@@ -1037,37 +1025,29 @@ void bio_pair_release(struct bio_pair *bp)
 	if (atomic_dec_and_test(&bp->cnt)) {
 		struct bio *master = bp->bio1.bi_private;
 
-		bio_endio(master, master->bi_size, bp->error);
+		bio_endio(master, bp->error);
 		mempool_free(bp, bp->bio2.bi_private);
 	}
 }
 
-static int bio_pair_end_1(struct bio * bi, unsigned int done, int err)
+static void bio_pair_end_1(struct bio *bi, int err)
 {
 	struct bio_pair *bp = container_of(bi, struct bio_pair, bio1);
 
 	if (err)
 		bp->error = err;
 
-	if (bi->bi_size)
-		return 1;
-
 	bio_pair_release(bp);
-	return 0;
 }
 
-static int bio_pair_end_2(struct bio * bi, unsigned int done, int err)
+static void bio_pair_end_2(struct bio *bi, int err)
 {
 	struct bio_pair *bp = container_of(bi, struct bio_pair, bio2);
 
 	if (err)
 		bp->error = err;
 
-	if (bi->bi_size)
-		return 1;
-
 	bio_pair_release(bp);
-	return 0;
 }
 
 /*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2980eabe5779..6339a30879b7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -172,7 +172,7 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 }
 
 #if 0
-static int blk_end_aio(struct bio *bio, unsigned int bytes_done, int error)
+static void blk_end_aio(struct bio *bio, int error)
 {
 	struct kiocb *iocb = bio->bi_private;
 	atomic_t *bio_count = &iocb->ki_bio_count;
diff --git a/fs/buffer.c b/fs/buffer.c
index 0e5ec371ce72..75b51dfa5e03 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2634,13 +2634,10 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 	return tmp.b_blocknr;
 }
 
-static int end_bio_bh_io_sync(struct bio *bio, unsigned int bytes_done, int err)
+static void end_bio_bh_io_sync(struct bio *bio, int err)
 {
 	struct buffer_head *bh = bio->bi_private;
 
-	if (bio->bi_size)
-		return 1;
-
 	if (err == -EOPNOTSUPP) {
 		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
 		set_bit(BH_Eopnotsupp, &bh->b_state);
@@ -2648,7 +2645,6 @@ static int end_bio_bh_io_sync(struct bio *bio, unsigned int bytes_done, int err)
 
 	bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
 	bio_put(bio);
-	return 0;
 }
 
 int submit_bh(int rw, struct buffer_head * bh)
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 37310b0e8107..9c3fd07f35e0 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -21,7 +21,6 @@
 #include <linux/if.h>
 #include <linux/if_bridge.h>
 #include <linux/slab.h>
-#include <linux/hdreg.h>
 #include <linux/raid/md.h>
 #include <linux/kd.h>
 #include <linux/dirent.h>
@@ -33,12 +32,10 @@
 #include <linux/vt.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/fd.h>
 #include <linux/ppp_defs.h>
 #include <linux/if_ppp.h>
 #include <linux/if_pppox.h>
 #include <linux/mtio.h>
-#include <linux/cdrom.h>
 #include <linux/auto_fs.h>
 #include <linux/auto_fs4.h>
 #include <linux/tty.h>
@@ -48,7 +45,6 @@
 #include <linux/netdevice.h>
 #include <linux/raw.h>
 #include <linux/smb_fs.h>
-#include <linux/blkpg.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/rtc.h>
@@ -62,7 +58,6 @@
 #include <linux/i2c-dev.h>
 #include <linux/wireless.h>
 #include <linux/atalk.h>
-#include <linux/blktrace_api.h>
 #include <linux/loop.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -324,22 +319,21 @@ struct ifconf32 {
 
 static int dev_ifname32(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
-	struct net_device *dev;
-	struct ifreq32 ifr32;
+	struct ifreq __user *uifr;
 	int err;
 
-	if (copy_from_user(&ifr32, compat_ptr(arg), sizeof(ifr32)))
+	uifr = compat_alloc_user_space(sizeof(struct ifreq));
+	if (copy_in_user(uifr, compat_ptr(arg), sizeof(struct ifreq32)));
 		return -EFAULT;
 
-	dev = dev_get_by_index(ifr32.ifr_ifindex);
-	if (!dev)
-		return -ENODEV;
+	err = sys_ioctl(fd, SIOCGIFNAME, (unsigned long)uifr);
+	if (err)
+		return err;
+
+	if (copy_in_user(compat_ptr(arg), uifr, sizeof(struct ifreq32)))
+		return -EFAULT;
 
-	strlcpy(ifr32.ifr_name, dev->name, sizeof(ifr32.ifr_name));
-	dev_put(dev);
-	
-	err = copy_to_user(compat_ptr(arg), &ifr32, sizeof(ifr32));
-	return (err ? -EFAULT : 0);
+	return 0;
 }
 
 static int dev_ifconf(unsigned int fd, unsigned int cmd, unsigned long arg)
@@ -668,53 +662,6 @@ out:
 #endif
 
 #ifdef CONFIG_BLOCK
-struct hd_geometry32 {
-	unsigned char heads;
-	unsigned char sectors;
-	unsigned short cylinders;
-	u32 start;
-};
-                        
-static int hdio_getgeo(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	mm_segment_t old_fs = get_fs();
-	struct hd_geometry geo;
-	struct hd_geometry32 __user *ugeo;
-	int err;
-	
-	set_fs (KERNEL_DS);
-	err = sys_ioctl(fd, HDIO_GETGEO, (unsigned long)&geo);
-	set_fs (old_fs);
-	ugeo = compat_ptr(arg);
-	if (!err) {
-		err = copy_to_user (ugeo, &geo, 4);
-		err |= __put_user (geo.start, &ugeo->start);
-		if (err)
-			err = -EFAULT;
-	}
-	return err;
-}
-
-static int hdio_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	mm_segment_t old_fs = get_fs();
-	unsigned long kval;
-	unsigned int __user *uvp;
-	int error;
-
-	set_fs(KERNEL_DS);
-	error = sys_ioctl(fd, cmd, (long)&kval);
-	set_fs(old_fs);
-
-	if(error == 0) {
-		uvp = compat_ptr(arg);
-		if(put_user(kval, uvp))
-			error = -EFAULT;
-	}
-	return error;
-}
-
-
 typedef struct sg_io_hdr32 {
 	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
 	compat_int_t dxfer_direction;	/* [i] data transfer direction  */
@@ -1089,108 +1036,6 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
 	return err ? -EFAULT: 0;
 }
 
-struct cdrom_read_audio32 {
-	union cdrom_addr	addr;
-	u8			addr_format;
-	compat_int_t		nframes;
-	compat_caddr_t		buf;
-};
-
-struct cdrom_generic_command32 {
-	unsigned char	cmd[CDROM_PACKET_SIZE];
-	compat_caddr_t	buffer;
-	compat_uint_t	buflen;
-	compat_int_t	stat;
-	compat_caddr_t	sense;
-	unsigned char	data_direction;
-	compat_int_t	quiet;
-	compat_int_t	timeout;
-	compat_caddr_t	reserved[1];
-};
-  
-static int cdrom_do_read_audio(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	struct cdrom_read_audio __user *cdread_audio;
-	struct cdrom_read_audio32 __user *cdread_audio32;
-	__u32 data;
-	void __user *datap;
-
-	cdread_audio = compat_alloc_user_space(sizeof(*cdread_audio));
-	cdread_audio32 = compat_ptr(arg);
-
-	if (copy_in_user(&cdread_audio->addr,
-			 &cdread_audio32->addr,
-			 (sizeof(*cdread_audio32) -
-			  sizeof(compat_caddr_t))))
-	 	return -EFAULT;
-
-	if (get_user(data, &cdread_audio32->buf))
-		return -EFAULT;
-	datap = compat_ptr(data);
-	if (put_user(datap, &cdread_audio->buf))
-		return -EFAULT;
-
-	return sys_ioctl(fd, cmd, (unsigned long) cdread_audio);
-}
-
-static int cdrom_do_generic_command(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	struct cdrom_generic_command __user *cgc;
-	struct cdrom_generic_command32 __user *cgc32;
-	u32 data;
-	unsigned char dir;
-	int itmp;
-
-	cgc = compat_alloc_user_space(sizeof(*cgc));
-	cgc32 = compat_ptr(arg);
-
-	if (copy_in_user(&cgc->cmd, &cgc32->cmd, sizeof(cgc->cmd)) ||
-	    get_user(data, &cgc32->buffer) ||
-	    put_user(compat_ptr(data), &cgc->buffer) ||
-	    copy_in_user(&cgc->buflen, &cgc32->buflen,
-			 (sizeof(unsigned int) + sizeof(int))) ||
-	    get_user(data, &cgc32->sense) ||
-	    put_user(compat_ptr(data), &cgc->sense) ||
-	    get_user(dir, &cgc32->data_direction) ||
-	    put_user(dir, &cgc->data_direction) ||
-	    get_user(itmp, &cgc32->quiet) ||
-	    put_user(itmp, &cgc->quiet) ||
-	    get_user(itmp, &cgc32->timeout) ||
-	    put_user(itmp, &cgc->timeout) ||
-	    get_user(data, &cgc32->reserved[0]) ||
-	    put_user(compat_ptr(data), &cgc->reserved[0]))
-		return -EFAULT;
-
-	return sys_ioctl(fd, cmd, (unsigned long) cgc);
-}
-
-static int cdrom_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	int err;
-
-	switch(cmd) {
-	case CDROMREADAUDIO:
-		err = cdrom_do_read_audio(fd, cmd, arg);
-		break;
-
-	case CDROM_SEND_PACKET:
-		err = cdrom_do_generic_command(fd, cmd, arg);
-		break;
-
-	default:
-		do {
-			static int count;
-			if (++count <= 20)
-				printk("cdrom_ioctl: Unknown cmd fd(%d) "
-				       "cmd(%08x) arg(%08x)\n",
-				       (int)fd, (unsigned int)cmd, (unsigned int)arg);
-		} while(0);
-		err = -EINVAL;
-		break;
-	};
-
-	return err;
-}
 #endif /* CONFIG_BLOCK */
 
 #ifdef CONFIG_VT
@@ -1536,71 +1381,11 @@ ret_einval(unsigned int fd, unsigned int cmd, unsigned long arg)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_BLOCK
-static int broken_blkgetsize(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	/* The mkswap binary hard codes it to Intel value :-((( */
-	return w_long(fd, BLKGETSIZE, arg);
-}
-
-struct blkpg_ioctl_arg32 {
-	compat_int_t op;
-	compat_int_t flags;
-	compat_int_t datalen;
-	compat_caddr_t data;
-};
-
-static int blkpg_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	struct blkpg_ioctl_arg32 __user *ua32 = compat_ptr(arg);
-	struct blkpg_ioctl_arg __user *a = compat_alloc_user_space(sizeof(*a));
-	compat_caddr_t udata;
-	compat_int_t n;
-	int err;
-	
-	err = get_user(n, &ua32->op);
-	err |= put_user(n, &a->op);
-	err |= get_user(n, &ua32->flags);
-	err |= put_user(n, &a->flags);
-	err |= get_user(n, &ua32->datalen);
-	err |= put_user(n, &a->datalen);
-	err |= get_user(udata, &ua32->data);
-	err |= put_user(compat_ptr(udata), &a->data);
-	if (err)
-		return err;
-
-	return sys_ioctl(fd, cmd, (unsigned long)a);
-}
-#endif
-
 static int ioc_settimeout(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	return rw_long(fd, AUTOFS_IOC_SETTIMEOUT, arg);
 }
 
-#ifdef CONFIG_BLOCK
-/* Fix sizeof(sizeof()) breakage */
-#define BLKBSZGET_32   _IOR(0x12,112,int)
-#define BLKBSZSET_32   _IOW(0x12,113,int)
-#define BLKGETSIZE64_32        _IOR(0x12,114,int)
-
-static int do_blkbszget(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-       return sys_ioctl(fd, BLKBSZGET, (unsigned long)compat_ptr(arg));
-}
-
-static int do_blkbszset(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-       return sys_ioctl(fd, BLKBSZSET, (unsigned long)compat_ptr(arg));
-}
-
-static int do_blkgetsize64(unsigned int fd, unsigned int cmd,
-                          unsigned long arg)
-{
-       return sys_ioctl(fd, BLKGETSIZE64, (unsigned long)compat_ptr(arg));
-}
-#endif
-
 /* Bluetooth ioctls */
 #define HCIUARTSETPROTO	_IOW('U', 200, int)
 #define HCIUARTGETPROTO	_IOR('U', 201, int)
@@ -1620,333 +1405,6 @@ static int do_blkgetsize64(unsigned int fd, unsigned int cmd,
 #define HIDPGETCONNLIST	_IOR('H', 210, int)
 #define HIDPGETCONNINFO	_IOR('H', 211, int)
 
-#ifdef CONFIG_BLOCK
-struct floppy_struct32 {
-	compat_uint_t	size;
-	compat_uint_t	sect;
-	compat_uint_t	head;
-	compat_uint_t	track;
-	compat_uint_t	stretch;
-	unsigned char	gap;
-	unsigned char	rate;
-	unsigned char	spec1;
-	unsigned char	fmt_gap;
-	const compat_caddr_t name;
-};
-
-struct floppy_drive_params32 {
-	char		cmos;
-	compat_ulong_t	max_dtr;
-	compat_ulong_t	hlt;
-	compat_ulong_t	hut;
-	compat_ulong_t	srt;
-	compat_ulong_t	spinup;
-	compat_ulong_t	spindown;
-	unsigned char	spindown_offset;
-	unsigned char	select_delay;
-	unsigned char	rps;
-	unsigned char	tracks;
-	compat_ulong_t	timeout;
-	unsigned char	interleave_sect;
-	struct floppy_max_errors max_errors;
-	char		flags;
-	char		read_track;
-	short		autodetect[8];
-	compat_int_t	checkfreq;
-	compat_int_t	native_format;
-};
-
-struct floppy_drive_struct32 {
-	signed char	flags;
-	compat_ulong_t	spinup_date;
-	compat_ulong_t	select_date;
-	compat_ulong_t	first_read_date;
-	short		probed_format;
-	short		track;
-	short		maxblock;
-	short		maxtrack;
-	compat_int_t	generation;
-	compat_int_t	keep_data;
-	compat_int_t	fd_ref;
-	compat_int_t	fd_device;
-	compat_int_t	last_checked;
-	compat_caddr_t dmabuf;
-	compat_int_t	bufblocks;
-};
-
-struct floppy_fdc_state32 {
-	compat_int_t	spec1;
-	compat_int_t	spec2;
-	compat_int_t	dtr;
-	unsigned char	version;
-	unsigned char	dor;
-	compat_ulong_t	address;
-	unsigned int	rawcmd:2;
-	unsigned int	reset:1;
-	unsigned int	need_configure:1;
-	unsigned int	perp_mode:2;
-	unsigned int	has_fifo:1;
-	unsigned int	driver_version;
-	unsigned char	track[4];
-};
-
-struct floppy_write_errors32 {
-	unsigned int	write_errors;
-	compat_ulong_t	first_error_sector;
-	compat_int_t	first_error_generation;
-	compat_ulong_t	last_error_sector;
-	compat_int_t	last_error_generation;
-	compat_uint_t	badness;
-};
-
-#define FDSETPRM32 _IOW(2, 0x42, struct floppy_struct32)
-#define FDDEFPRM32 _IOW(2, 0x43, struct floppy_struct32)
-#define FDGETPRM32 _IOR(2, 0x04, struct floppy_struct32)
-#define FDSETDRVPRM32 _IOW(2, 0x90, struct floppy_drive_params32)
-#define FDGETDRVPRM32 _IOR(2, 0x11, struct floppy_drive_params32)
-#define FDGETDRVSTAT32 _IOR(2, 0x12, struct floppy_drive_struct32)
-#define FDPOLLDRVSTAT32 _IOR(2, 0x13, struct floppy_drive_struct32)
-#define FDGETFDCSTAT32 _IOR(2, 0x15, struct floppy_fdc_state32)
-#define FDWERRORGET32  _IOR(2, 0x17, struct floppy_write_errors32)
-
-static struct {
-	unsigned int	cmd32;
-	unsigned int	cmd;
-} fd_ioctl_trans_table[] = {
-	{ FDSETPRM32, FDSETPRM },
-	{ FDDEFPRM32, FDDEFPRM },
-	{ FDGETPRM32, FDGETPRM },
-	{ FDSETDRVPRM32, FDSETDRVPRM },
-	{ FDGETDRVPRM32, FDGETDRVPRM },
-	{ FDGETDRVSTAT32, FDGETDRVSTAT },
-	{ FDPOLLDRVSTAT32, FDPOLLDRVSTAT },
-	{ FDGETFDCSTAT32, FDGETFDCSTAT },
-	{ FDWERRORGET32, FDWERRORGET }
-};
-
-#define NR_FD_IOCTL_TRANS ARRAY_SIZE(fd_ioctl_trans_table)
-
-static int fd_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
-	mm_segment_t old_fs = get_fs();
-	void *karg = NULL;
-	unsigned int kcmd = 0;
-	int i, err;
-
-	for (i = 0; i < NR_FD_IOCTL_TRANS; i++)
-		if (cmd == fd_ioctl_trans_table[i].cmd32) {
-			kcmd = fd_ioctl_trans_table[i].cmd;
-			break;
-		}
-	if (!kcmd)
-		return -EINVAL;
-
-	switch (cmd) {
-		case FDSETPRM32:
-		case FDDEFPRM32:
-		case FDGETPRM32:
-		{
-			compat_uptr_t name;
-			struct floppy_struct32 __user *uf;
-			struct floppy_struct *f;
-
-			uf = compat_ptr(arg);
-			f = karg = kmalloc(sizeof(struct floppy_struct), GFP_KERNEL);
-			if (!karg)
-				return -ENOMEM;
-			if (cmd == FDGETPRM32)
-				break;
-			err = __get_user(f->size, &uf->size);
-			err |= __get_user(f->sect, &uf->sect);
-			err |= __get_user(f->head, &uf->head);
-			err |= __get_user(f->track, &uf->track);
-			err |= __get_user(f->stretch, &uf->stretch);
-			err |= __get_user(f->gap, &uf->gap);
-			err |= __get_user(f->rate, &uf->rate);
-			err |= __get_user(f->spec1, &uf->spec1);
-			err |= __get_user(f->fmt_gap, &uf->fmt_gap);
-			err |= __get_user(name, &uf->name);
-			f->name = compat_ptr(name);
-			if (err) {
-				err = -EFAULT;
-				goto out;
-			}
-			break;
-		}
-		case FDSETDRVPRM32:
-		case FDGETDRVPRM32:
-		{
-			struct floppy_drive_params32 __user *uf;
-			struct floppy_drive_params *f;
-
-			uf = compat_ptr(arg);
-			f = karg = kmalloc(sizeof(struct floppy_drive_params), GFP_KERNEL);
-			if (!karg)
-				return -ENOMEM;
-			if (cmd == FDGETDRVPRM32)
-				break;
-			err = __get_user(f->cmos, &uf->cmos);
-			err |= __get_user(f->max_dtr, &uf->max_dtr);
-			err |= __get_user(f->hlt, &uf->hlt);
-			err |= __get_user(f->hut, &uf->hut);
-			err |= __get_user(f->srt, &uf->srt);
-			err |= __get_user(f->spinup, &uf->spinup);
-			err |= __get_user(f->spindown, &uf->spindown);
-			err |= __get_user(f->spindown_offset, &uf->spindown_offset);
-			err |= __get_user(f->select_delay, &uf->select_delay);
-			err |= __get_user(f->rps, &uf->rps);
-			err |= __get_user(f->tracks, &uf->tracks);
-			err |= __get_user(f->timeout, &uf->timeout);
-			err |= __get_user(f->interleave_sect, &uf->interleave_sect);
-			err |= __copy_from_user(&f->max_errors, &uf->max_errors, sizeof(f->max_errors));
-			err |= __get_user(f->flags, &uf->flags);
-			err |= __get_user(f->read_track, &uf->read_track);
-			err |= __copy_from_user(f->autodetect, uf->autodetect, sizeof(f->autodetect));
-			err |= __get_user(f->checkfreq, &uf->checkfreq);
-			err |= __get_user(f->native_format, &uf->native_format);
-			if (err) {
-				err = -EFAULT;
-				goto out;
-			}
-			break;
-		}
-		case FDGETDRVSTAT32:
-		case FDPOLLDRVSTAT32:
-			karg = kmalloc(sizeof(struct floppy_drive_struct), GFP_KERNEL);
-			if (!karg)
-				return -ENOMEM;
-			break;
-		case FDGETFDCSTAT32:
-			karg = kmalloc(sizeof(struct floppy_fdc_state), GFP_KERNEL);
-			if (!karg)
-				return -ENOMEM;
-			break;
-		case FDWERRORGET32:
-			karg = kmalloc(sizeof(struct floppy_write_errors), GFP_KERNEL);
-			if (!karg)
-				return -ENOMEM;
-			break;
-		default:
-			return -EINVAL;
-	}
-	set_fs (KERNEL_DS);
-	err = sys_ioctl (fd, kcmd, (unsigned long)karg);
-	set_fs (old_fs);
-	if (err)
-		goto out;
-	switch (cmd) {
-		case FDGETPRM32:
-		{
-			struct floppy_struct *f = karg;
-			struct floppy_struct32 __user *uf = compat_ptr(arg);
-
-			err = __put_user(f->size, &uf->size);
-			err |= __put_user(f->sect, &uf->sect);
-			err |= __put_user(f->head, &uf->head);
-			err |= __put_user(f->track, &uf->track);
-			err |= __put_user(f->stretch, &uf->stretch);
-			err |= __put_user(f->gap, &uf->gap);
-			err |= __put_user(f->rate, &uf->rate);
-			err |= __put_user(f->spec1, &uf->spec1);
-			err |= __put_user(f->fmt_gap, &uf->fmt_gap);
-			err |= __put_user((u64)f->name, (compat_caddr_t __user *)&uf->name);
-			break;
-		}
-		case FDGETDRVPRM32:
-		{
-			struct floppy_drive_params32 __user *uf;
-			struct floppy_drive_params *f = karg;
-
-			uf = compat_ptr(arg);
-			err = __put_user(f->cmos, &uf->cmos);
-			err |= __put_user(f->max_dtr, &uf->max_dtr);
-			err |= __put_user(f->hlt, &uf->hlt);
-			err |= __put_user(f->hut, &uf->hut);
-			err |= __put_user(f->srt, &uf->srt);
-			err |= __put_user(f->spinup, &uf->spinup);
-			err |= __put_user(f->spindown, &uf->spindown);
-			err |= __put_user(f->spindown_offset, &uf->spindown_offset);
-			err |= __put_user(f->select_delay, &uf->select_delay);
-			err |= __put_user(f->rps, &uf->rps);
-			err |= __put_user(f->tracks, &uf->tracks);
-			err |= __put_user(f->timeout, &uf->timeout);
-			err |= __put_user(f->interleave_sect, &uf->interleave_sect);
-			err |= __copy_to_user(&uf->max_errors, &f->max_errors, sizeof(f->max_errors));
-			err |= __put_user(f->flags, &uf->flags);
-			err |= __put_user(f->read_track, &uf->read_track);
-			err |= __copy_to_user(uf->autodetect, f->autodetect, sizeof(f->autodetect));
-			err |= __put_user(f->checkfreq, &uf->checkfreq);
-			err |= __put_user(f->native_format, &uf->native_format);
-			break;
-		}
-		case FDGETDRVSTAT32:
-		case FDPOLLDRVSTAT32:
-		{
-			struct floppy_drive_struct32 __user *uf;
-			struct floppy_drive_struct *f = karg;
-
-			uf = compat_ptr(arg);
-			err = __put_user(f->flags, &uf->flags);
-			err |= __put_user(f->spinup_date, &uf->spinup_date);
-			err |= __put_user(f->select_date, &uf->select_date);
-			err |= __put_user(f->first_read_date, &uf->first_read_date);
-			err |= __put_user(f->probed_format, &uf->probed_format);
-			err |= __put_user(f->track, &uf->track);
-			err |= __put_user(f->maxblock, &uf->maxblock);
-			err |= __put_user(f->maxtrack, &uf->maxtrack);
-			err |= __put_user(f->generation, &uf->generation);
-			err |= __put_user(f->keep_data, &uf->keep_data);
-			err |= __put_user(f->fd_ref, &uf->fd_ref);
-			err |= __put_user(f->fd_device, &uf->fd_device);
-			err |= __put_user(f->last_checked, &uf->last_checked);
-			err |= __put_user((u64)f->dmabuf, &uf->dmabuf);
-			err |= __put_user((u64)f->bufblocks, &uf->bufblocks);
-			break;
-		}
-		case FDGETFDCSTAT32:
-		{
-			struct floppy_fdc_state32 __user *uf;
-			struct floppy_fdc_state *f = karg;
-
-			uf = compat_ptr(arg);
-			err = __put_user(f->spec1, &uf->spec1);
-			err |= __put_user(f->spec2, &uf->spec2);
-			err |= __put_user(f->dtr, &uf->dtr);
-			err |= __put_user(f->version, &uf->version);
-			err |= __put_user(f->dor, &uf->dor);
-			err |= __put_user(f->address, &uf->address);
-			err |= __copy_to_user((char __user *)&uf->address + sizeof(uf->address),
-					   (char *)&f->address + sizeof(f->address), sizeof(int));
-			err |= __put_user(f->driver_version, &uf->driver_version);
-			err |= __copy_to_user(uf->track, f->track, sizeof(f->track));
-			break;
-		}
-		case FDWERRORGET32:
-		{
-			struct floppy_write_errors32 __user *uf;
-			struct floppy_write_errors *f = karg;
-
-			uf = compat_ptr(arg);
-			err = __put_user(f->write_errors, &uf->write_errors);
-			err |= __put_user(f->first_error_sector, &uf->first_error_sector);
-			err |= __put_user(f->first_error_generation, &uf->first_error_generation);
-			err |= __put_user(f->last_error_sector, &uf->last_error_sector);
-			err |= __put_user(f->last_error_generation, &uf->last_error_generation);
-			err |= __put_user(f->badness, &uf->badness);
-			break;
-		}
-		default:
-			break;
-	}
-	if (err)
-		err = -EFAULT;
-
-out:
-	kfree(karg);
-	return err;
-}
-#endif
-
 struct mtd_oob_buf32 {
 	u_int32_t start;
 	u_int32_t length;
@@ -2506,60 +1964,6 @@ COMPATIBLE_IOCTL(FIONREAD)  /* This is also TIOCINQ */
 /* 0x00 */
 COMPATIBLE_IOCTL(FIBMAP)
 COMPATIBLE_IOCTL(FIGETBSZ)
-/* 0x03 -- HD/IDE ioctl's used by hdparm and friends.
- *         Some need translations, these do not.
- */
-COMPATIBLE_IOCTL(HDIO_GET_IDENTITY)
-COMPATIBLE_IOCTL(HDIO_DRIVE_TASK)
-COMPATIBLE_IOCTL(HDIO_DRIVE_CMD)
-ULONG_IOCTL(HDIO_SET_MULTCOUNT)
-ULONG_IOCTL(HDIO_SET_UNMASKINTR)
-ULONG_IOCTL(HDIO_SET_KEEPSETTINGS)
-ULONG_IOCTL(HDIO_SET_32BIT)
-ULONG_IOCTL(HDIO_SET_NOWERR)
-ULONG_IOCTL(HDIO_SET_DMA)
-ULONG_IOCTL(HDIO_SET_PIO_MODE)
-ULONG_IOCTL(HDIO_SET_NICE)
-ULONG_IOCTL(HDIO_SET_WCACHE)
-ULONG_IOCTL(HDIO_SET_ACOUSTIC)
-ULONG_IOCTL(HDIO_SET_BUSSTATE)
-ULONG_IOCTL(HDIO_SET_ADDRESS)
-COMPATIBLE_IOCTL(HDIO_SCAN_HWIF)
-/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */
-COMPATIBLE_IOCTL(0x330)
-/* 0x02 -- Floppy ioctls */
-COMPATIBLE_IOCTL(FDMSGON)
-COMPATIBLE_IOCTL(FDMSGOFF)
-COMPATIBLE_IOCTL(FDSETEMSGTRESH)
-COMPATIBLE_IOCTL(FDFLUSH)
-COMPATIBLE_IOCTL(FDWERRORCLR)
-COMPATIBLE_IOCTL(FDSETMAXERRS)
-COMPATIBLE_IOCTL(FDGETMAXERRS)
-COMPATIBLE_IOCTL(FDGETDRVTYP)
-COMPATIBLE_IOCTL(FDEJECT)
-COMPATIBLE_IOCTL(FDCLRPRM)
-COMPATIBLE_IOCTL(FDFMTBEG)
-COMPATIBLE_IOCTL(FDFMTEND)
-COMPATIBLE_IOCTL(FDRESET)
-COMPATIBLE_IOCTL(FDTWADDLE)
-COMPATIBLE_IOCTL(FDFMTTRK)
-COMPATIBLE_IOCTL(FDRAWCMD)
-/* 0x12 */
-#ifdef CONFIG_BLOCK
-COMPATIBLE_IOCTL(BLKRASET)
-COMPATIBLE_IOCTL(BLKROSET)
-COMPATIBLE_IOCTL(BLKROGET)
-COMPATIBLE_IOCTL(BLKRRPART)
-COMPATIBLE_IOCTL(BLKFLSBUF)
-COMPATIBLE_IOCTL(BLKSECTSET)
-COMPATIBLE_IOCTL(BLKSSZGET)
-COMPATIBLE_IOCTL(BLKTRACESTART)
-COMPATIBLE_IOCTL(BLKTRACESTOP)
-COMPATIBLE_IOCTL(BLKTRACESETUP)
-COMPATIBLE_IOCTL(BLKTRACETEARDOWN)
-ULONG_IOCTL(BLKRASET)
-ULONG_IOCTL(BLKFRASET)
-#endif
 /* RAID */
 COMPATIBLE_IOCTL(RAID_VERSION)
 COMPATIBLE_IOCTL(GET_ARRAY_INFO)
@@ -2807,50 +2211,6 @@ COMPATIBLE_IOCTL(PPGETMODE)
 COMPATIBLE_IOCTL(PPGETPHASE)
 COMPATIBLE_IOCTL(PPGETFLAGS)
 COMPATIBLE_IOCTL(PPSETFLAGS)
-/* CDROM stuff */
-COMPATIBLE_IOCTL(CDROMPAUSE)
-COMPATIBLE_IOCTL(CDROMRESUME)
-COMPATIBLE_IOCTL(CDROMPLAYMSF)
-COMPATIBLE_IOCTL(CDROMPLAYTRKIND)
-COMPATIBLE_IOCTL(CDROMREADTOCHDR)
-COMPATIBLE_IOCTL(CDROMREADTOCENTRY)
-COMPATIBLE_IOCTL(CDROMSTOP)
-COMPATIBLE_IOCTL(CDROMSTART)
-COMPATIBLE_IOCTL(CDROMEJECT)
-COMPATIBLE_IOCTL(CDROMVOLCTRL)
-COMPATIBLE_IOCTL(CDROMSUBCHNL)
-ULONG_IOCTL(CDROMEJECT_SW)
-COMPATIBLE_IOCTL(CDROMMULTISESSION)
-COMPATIBLE_IOCTL(CDROM_GET_MCN)
-COMPATIBLE_IOCTL(CDROMRESET)
-COMPATIBLE_IOCTL(CDROMVOLREAD)
-COMPATIBLE_IOCTL(CDROMSEEK)
-COMPATIBLE_IOCTL(CDROMPLAYBLK)
-COMPATIBLE_IOCTL(CDROMCLOSETRAY)
-ULONG_IOCTL(CDROM_SET_OPTIONS)
-ULONG_IOCTL(CDROM_CLEAR_OPTIONS)
-ULONG_IOCTL(CDROM_SELECT_SPEED)
-ULONG_IOCTL(CDROM_SELECT_DISC)
-ULONG_IOCTL(CDROM_MEDIA_CHANGED)
-ULONG_IOCTL(CDROM_DRIVE_STATUS)
-COMPATIBLE_IOCTL(CDROM_DISC_STATUS)
-COMPATIBLE_IOCTL(CDROM_CHANGER_NSLOTS)
-ULONG_IOCTL(CDROM_LOCKDOOR)
-ULONG_IOCTL(CDROM_DEBUG)
-COMPATIBLE_IOCTL(CDROM_GET_CAPABILITY)
-/* Ignore cdrom.h about these next 5 ioctls, they absolutely do
- * not take a struct cdrom_read, instead they take a struct cdrom_msf
- * which is compatible.
- */
-COMPATIBLE_IOCTL(CDROMREADMODE2)
-COMPATIBLE_IOCTL(CDROMREADMODE1)
-COMPATIBLE_IOCTL(CDROMREADRAW)
-COMPATIBLE_IOCTL(CDROMREADCOOKED)
-COMPATIBLE_IOCTL(CDROMREADALL)
-/* DVD ioctls */
-COMPATIBLE_IOCTL(DVD_READ_STRUCT)
-COMPATIBLE_IOCTL(DVD_WRITE_STRUCT)
-COMPATIBLE_IOCTL(DVD_AUTH)
 /* pktcdvd */
 COMPATIBLE_IOCTL(PACKET_CTRL_CMD)
 /* Big A */
@@ -3336,33 +2696,6 @@ HANDLE_IOCTL(SIOCGSTAMP, do_siocgstamp)
 HANDLE_IOCTL(SIOCGSTAMPNS, do_siocgstampns)
 #endif
 #ifdef CONFIG_BLOCK
-HANDLE_IOCTL(HDIO_GETGEO, hdio_getgeo)
-HANDLE_IOCTL(BLKRAGET, w_long)
-HANDLE_IOCTL(BLKGETSIZE, w_long)
-HANDLE_IOCTL(0x1260, broken_blkgetsize)
-HANDLE_IOCTL(BLKFRAGET, w_long)
-HANDLE_IOCTL(BLKSECTGET, w_long)
-HANDLE_IOCTL(BLKPG, blkpg_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_UNMASKINTR, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_MULTCOUNT, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_KEEPSETTINGS, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_32BIT, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_NOWERR, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_DMA, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_NICE, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_WCACHE, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_ACOUSTIC, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_ADDRESS, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_BUSSTATE, hdio_ioctl_trans)
-HANDLE_IOCTL(FDSETPRM32, fd_ioctl_trans)
-HANDLE_IOCTL(FDDEFPRM32, fd_ioctl_trans)
-HANDLE_IOCTL(FDGETPRM32, fd_ioctl_trans)
-HANDLE_IOCTL(FDSETDRVPRM32, fd_ioctl_trans)
-HANDLE_IOCTL(FDGETDRVPRM32, fd_ioctl_trans)
-HANDLE_IOCTL(FDGETDRVSTAT32, fd_ioctl_trans)
-HANDLE_IOCTL(FDPOLLDRVSTAT32, fd_ioctl_trans)
-HANDLE_IOCTL(FDGETFDCSTAT32, fd_ioctl_trans)
-HANDLE_IOCTL(FDWERRORGET32, fd_ioctl_trans)
 HANDLE_IOCTL(SG_IO,sg_ioctl_trans)
 HANDLE_IOCTL(SG_GET_REQUEST_TABLE, sg_grt_trans)
 #endif
@@ -3373,8 +2706,6 @@ HANDLE_IOCTL(PPPIOCSACTIVE32, ppp_sock_fprog_ioctl_trans)
 #ifdef CONFIG_BLOCK
 HANDLE_IOCTL(MTIOCGET32, mt_ioctl_trans)
 HANDLE_IOCTL(MTIOCPOS32, mt_ioctl_trans)
-HANDLE_IOCTL(CDROMREADAUDIO, cdrom_ioctl_trans)
-HANDLE_IOCTL(CDROM_SEND_PACKET, cdrom_ioctl_trans)
 #endif
 #define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,unsigned int)
 HANDLE_IOCTL(AUTOFS_IOC_SETTIMEOUT32, ioc_settimeout)
@@ -3415,9 +2746,6 @@ HANDLE_IOCTL(SONET_GETFRAMING, do_atm_ioctl)
 HANDLE_IOCTL(SONET_GETFRSENSE, do_atm_ioctl)
 /* block stuff */
 #ifdef CONFIG_BLOCK
-HANDLE_IOCTL(BLKBSZGET_32, do_blkbszget)
-HANDLE_IOCTL(BLKBSZSET_32, do_blkbszset)
-HANDLE_IOCTL(BLKGETSIZE64_32, do_blkgetsize64)
 /* Raw devices */
 HANDLE_IOCTL(RAW_SETBIND, raw_ioctl)
 HANDLE_IOCTL(RAW_GETBIND, raw_ioctl)
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 2e124e0075c5..a9b99c0dc2e7 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -221,6 +221,42 @@ struct dentry *debugfs_create_u64(const char *name, mode_t mode,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_u64);
 
+DEFINE_SIMPLE_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n");
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set, "0x%04llx\n");
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set, "0x%08llx\n");
+
+/**
+ * debugfs_create_x8 - create a debugfs file that is used to read and write an unsigned 8-bit value
+ * debugfs_create_x16 - create a debugfs file that is used to read and write an unsigned 16-bit value
+ * debugfs_create_x32 - create a debugfs file that is used to read and write an unsigned 32-bit value
+ *
+ * These functions are exactly the same as the above functions, (but use a hex
+ * output for the decimal challenged) for details look at the above unsigned
+ * decimal functions.
+ */
+struct dentry *debugfs_create_x8(const char *name, mode_t mode,
+				 struct dentry *parent, u8 *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_x8);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_x8);
+
+struct dentry *debugfs_create_x16(const char *name, mode_t mode,
+				 struct dentry *parent, u16 *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_x16);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_x16);
+
+struct dentry *debugfs_create_x32(const char *name, mode_t mode,
+				 struct dentry *parent, u32 *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_x32);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_x32);
+
 static ssize_t read_file_bool(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos)
 {
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 901dc55e9f54..b5928a7b6a5a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -264,15 +264,12 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio);
 /*
  * Asynchronous IO callback. 
  */
-static int dio_bio_end_aio(struct bio *bio, unsigned int bytes_done, int error)
+static void dio_bio_end_aio(struct bio *bio, int error)
 {
 	struct dio *dio = bio->bi_private;
 	unsigned long remaining;
 	unsigned long flags;
 
-	if (bio->bi_size)
-		return 1;
-
 	/* cleanup the bio */
 	dio_bio_complete(dio, bio);
 
@@ -287,8 +284,6 @@ static int dio_bio_end_aio(struct bio *bio, unsigned int bytes_done, int error)
 		aio_complete(dio->iocb, ret, 0);
 		kfree(dio);
 	}
-
-	return 0;
 }
 
 /*
@@ -298,21 +293,17 @@ static int dio_bio_end_aio(struct bio *bio, unsigned int bytes_done, int error)
  * During I/O bi_private points at the dio.  After I/O, bi_private is used to
  * implement a singly-linked list of completed BIOs, at dio->bio_list.
  */
-static int dio_bio_end_io(struct bio *bio, unsigned int bytes_done, int error)
+static void dio_bio_end_io(struct bio *bio, int error)
 {
 	struct dio *dio = bio->bi_private;
 	unsigned long flags;
 
-	if (bio->bi_size)
-		return 1;
-
 	spin_lock_irqsave(&dio->bio_lock, flags);
 	bio->bi_private = dio->bio_list;
 	dio->bio_list = bio;
 	if (--dio->refcount == 1 && dio->waiter)
 		wake_up_process(dio->waiter);
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
-	return 0;
 }
 
 static int
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 74901e981e10..d2fc2384c3be 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -491,6 +491,7 @@ struct dlm_ls {
 	uint64_t		ls_recover_seq;
 	struct dlm_recover	*ls_recover_args;
 	struct rw_semaphore	ls_in_recovery;	/* block local requests */
+	struct rw_semaphore	ls_recv_active;	/* block dlm_recv */
 	struct list_head	ls_requestqueue;/* queue remote requests */
 	struct mutex		ls_requestqueue_mutex;
 	char			*ls_recover_buf;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 2082daf083d8..3915b8e14146 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -3638,55 +3638,8 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
 	dlm_put_lkb(lkb);
 }
 
-int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery)
+static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms)
 {
-	struct dlm_message *ms = (struct dlm_message *) hd;
-	struct dlm_ls *ls;
-	int error = 0;
-
-	if (!recovery)
-		dlm_message_in(ms);
-
-	ls = dlm_find_lockspace_global(hd->h_lockspace);
-	if (!ls) {
-		log_print("drop message %d from %d for unknown lockspace %d",
-			  ms->m_type, nodeid, hd->h_lockspace);
-		return -EINVAL;
-	}
-
-	/* recovery may have just ended leaving a bunch of backed-up requests
-	   in the requestqueue; wait while dlm_recoverd clears them */
-
-	if (!recovery)
-		dlm_wait_requestqueue(ls);
-
-	/* recovery may have just started while there were a bunch of
-	   in-flight requests -- save them in requestqueue to be processed
-	   after recovery.  we can't let dlm_recvd block on the recovery
-	   lock.  if dlm_recoverd is calling this function to clear the
-	   requestqueue, it needs to be interrupted (-EINTR) if another
-	   recovery operation is starting. */
-
-	while (1) {
-		if (dlm_locking_stopped(ls)) {
-			if (recovery) {
-				error = -EINTR;
-				goto out;
-			}
-			error = dlm_add_requestqueue(ls, nodeid, hd);
-			if (error == -EAGAIN)
-				continue;
-			else {
-				error = -EINTR;
-				goto out;
-			}
-		}
-
-		if (dlm_lock_recovery_try(ls))
-			break;
-		schedule();
-	}
-
 	switch (ms->m_type) {
 
 	/* messages sent to a master node */
@@ -3761,17 +3714,90 @@ int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery)
 		log_error(ls, "unknown message type %d", ms->m_type);
 	}
 
-	dlm_unlock_recovery(ls);
- out:
-	dlm_put_lockspace(ls);
 	dlm_astd_wake();
-	return error;
 }
 
+/* If the lockspace is in recovery mode (locking stopped), then normal
+   messages are saved on the requestqueue for processing after recovery is
+   done.  When not in recovery mode, we wait for dlm_recoverd to drain saved
+   messages off the requestqueue before we process new ones. This occurs right
+   after recovery completes when we transition from saving all messages on
+   requestqueue, to processing all the saved messages, to processing new
+   messages as they arrive. */
 
-/*
- * Recovery related
- */
+static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms,
+				int nodeid)
+{
+	if (dlm_locking_stopped(ls)) {
+		dlm_add_requestqueue(ls, nodeid, (struct dlm_header *) ms);
+	} else {
+		dlm_wait_requestqueue(ls);
+		_receive_message(ls, ms);
+	}
+}
+
+/* This is called by dlm_recoverd to process messages that were saved on
+   the requestqueue. */
+
+void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms)
+{
+	_receive_message(ls, ms);
+}
+
+/* This is called by the midcomms layer when something is received for
+   the lockspace.  It could be either a MSG (normal message sent as part of
+   standard locking activity) or an RCOM (recovery message sent as part of
+   lockspace recovery). */
+
+void dlm_receive_buffer(struct dlm_header *hd, int nodeid)
+{
+	struct dlm_message *ms = (struct dlm_message *) hd;
+	struct dlm_rcom *rc = (struct dlm_rcom *) hd;
+	struct dlm_ls *ls;
+	int type = 0;
+
+	switch (hd->h_cmd) {
+	case DLM_MSG:
+		dlm_message_in(ms);
+		type = ms->m_type;
+		break;
+	case DLM_RCOM:
+		dlm_rcom_in(rc);
+		type = rc->rc_type;
+		break;
+	default:
+		log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid);
+		return;
+	}
+
+	if (hd->h_nodeid != nodeid) {
+		log_print("invalid h_nodeid %d from %d lockspace %x",
+			  hd->h_nodeid, nodeid, hd->h_lockspace);
+		return;
+	}
+
+	ls = dlm_find_lockspace_global(hd->h_lockspace);
+	if (!ls) {
+		log_print("invalid h_lockspace %x from %d cmd %d type %d",
+			  hd->h_lockspace, nodeid, hd->h_cmd, type);
+
+		if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
+			dlm_send_ls_not_ready(nodeid, rc);
+		return;
+	}
+
+	/* this rwsem allows dlm_ls_stop() to wait for all dlm_recv threads to
+	   be inactive (in this ls) before transitioning to recovery mode */
+
+	down_read(&ls->ls_recv_active);
+	if (hd->h_cmd == DLM_MSG)
+		dlm_receive_message(ls, ms, nodeid);
+	else
+		dlm_receive_rcom(ls, rc, nodeid);
+	up_read(&ls->ls_recv_active);
+
+	dlm_put_lockspace(ls);
+}
 
 static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb)
 {
@@ -4429,7 +4455,8 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 
 	if (lvb_in && ua->lksb.sb_lvbptr)
 		memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN);
-	ua->castparam = ua_tmp->castparam;
+	if (ua_tmp->castparam)
+		ua->castparam = ua_tmp->castparam;
 	ua->user_lksb = ua_tmp->user_lksb;
 
 	error = set_unlock_args(flags, ua, &args);
@@ -4474,7 +4501,8 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 		goto out;
 
 	ua = (struct dlm_user_args *)lkb->lkb_astparam;
-	ua->castparam = ua_tmp->castparam;
+	if (ua_tmp->castparam)
+		ua->castparam = ua_tmp->castparam;
 	ua->user_lksb = ua_tmp->user_lksb;
 
 	error = set_unlock_args(flags, ua, &args);
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 1720313c22df..ada04680a1e5 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -16,7 +16,8 @@
 void dlm_print_rsb(struct dlm_rsb *r);
 void dlm_dump_rsb(struct dlm_rsb *r);
 void dlm_print_lkb(struct dlm_lkb *lkb);
-int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery);
+void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms);
+void dlm_receive_buffer(struct dlm_header *hd, int nodeid);
 int dlm_modes_compat(int mode1, int mode2);
 int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
 	unsigned int flags, struct dlm_rsb **r_ret);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 1dc72105ab12..6353a8384520 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -167,7 +167,6 @@ static struct kobj_type dlm_ktype = {
 };
 
 static struct kset dlm_kset = {
-	.kobj   = {.name = "dlm",},
 	.ktype  = &dlm_ktype,
 };
 
@@ -228,6 +227,7 @@ int dlm_lockspace_init(void)
 	INIT_LIST_HEAD(&lslist);
 	spin_lock_init(&lslist_lock);
 
+	kobject_set_name(&dlm_kset.kobj, "dlm");
 	kobj_set_kset_s(&dlm_kset, kernel_subsys);
 	error = kset_register(&dlm_kset);
 	if (error)
@@ -519,6 +519,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 	ls->ls_recover_seq = 0;
 	ls->ls_recover_args = NULL;
 	init_rwsem(&ls->ls_in_recovery);
+	init_rwsem(&ls->ls_recv_active);
 	INIT_LIST_HEAD(&ls->ls_requestqueue);
 	mutex_init(&ls->ls_requestqueue_mutex);
 	mutex_init(&ls->ls_clear_proc_locks);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 9e9d2e82f40f..58bf3f5cdbe2 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -334,18 +334,8 @@ static void close_connection(struct connection *con, bool and_other)
 		con->rx_page = NULL;
 	}
 
-	/* If we are an 'othercon' then NULL the pointer to us
-	   from the parent and tidy ourself up */
-	if (test_bit(CF_IS_OTHERCON, &con->flags)) {
-		struct connection *parent = __nodeid2con(con->nodeid, 0);
-		parent->othercon = NULL;
-		kmem_cache_free(con_cache, con);
-	}
-	else {
-		/* Parent connections get reused */
-		con->retries = 0;
-		mutex_unlock(&con->sock_mutex);
-	}
+	con->retries = 0;
+	mutex_unlock(&con->sock_mutex);
 }
 
 /* We only send shutdown messages to nodes that are not part of the cluster */
@@ -731,6 +721,8 @@ static int tcp_accept_from_sock(struct connection *con)
 			INIT_WORK(&othercon->swork, process_send_sockets);
 			INIT_WORK(&othercon->rwork, process_recv_sockets);
 			set_bit(CF_IS_OTHERCON, &othercon->flags);
+		}
+		if (!othercon->sock) {
 			newcon->othercon = othercon;
 			othercon->sock = newsock;
 			newsock->sk->sk_user_data = othercon;
@@ -1272,14 +1264,15 @@ static void send_to_sock(struct connection *con)
 		if (len) {
 			ret = sendpage(con->sock, e->page, offset, len,
 				       msg_flags);
-			if (ret == -EAGAIN || ret == 0)
+			if (ret == -EAGAIN || ret == 0) {
+				cond_resched();
 				goto out;
+			}
 			if (ret <= 0)
 				goto send_error;
-		} else {
+		}
 			/* Don't starve people filling buffers */
 			cond_resched();
-		}
 
 		spin_lock(&con->writequeue_lock);
 		e->offset += ret;
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index d09977528f69..e9cdcab306e2 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -18,10 +18,6 @@
 #include "rcom.h"
 #include "config.h"
 
-/*
- * Following called by dlm_recoverd thread
- */
-
 static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
 {
 	struct dlm_member *memb = NULL;
@@ -250,18 +246,30 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
 	return error;
 }
 
-/*
- * Following called from lockspace.c
- */
+/* Userspace guarantees that dlm_ls_stop() has completed on all nodes before
+   dlm_ls_start() is called on any of them to start the new recovery. */
 
 int dlm_ls_stop(struct dlm_ls *ls)
 {
 	int new;
 
 	/*
-	 * A stop cancels any recovery that's in progress (see RECOVERY_STOP,
-	 * dlm_recovery_stopped()) and prevents any new locks from being
-	 * processed (see RUNNING, dlm_locking_stopped()).
+	 * Prevent dlm_recv from being in the middle of something when we do
+	 * the stop.  This includes ensuring dlm_recv isn't processing a
+	 * recovery message (rcom), while dlm_recoverd is aborting and
+	 * resetting things from an in-progress recovery.  i.e. we want
+	 * dlm_recoverd to abort its recovery without worrying about dlm_recv
+	 * processing an rcom at the same time.  Stopping dlm_recv also makes
+	 * it easy for dlm_receive_message() to check locking stopped and add a
+	 * message to the requestqueue without races.
+	 */
+
+	down_write(&ls->ls_recv_active);
+
+	/*
+	 * Abort any recovery that's in progress (see RECOVERY_STOP,
+	 * dlm_recovery_stopped()) and tell any other threads running in the
+	 * dlm to quit any processing (see RUNNING, dlm_locking_stopped()).
 	 */
 
 	spin_lock(&ls->ls_recover_lock);
@@ -271,8 +279,14 @@ int dlm_ls_stop(struct dlm_ls *ls)
 	spin_unlock(&ls->ls_recover_lock);
 
 	/*
+	 * Let dlm_recv run again, now any normal messages will be saved on the
+	 * requestqueue for later.
+	 */
+
+	up_write(&ls->ls_recv_active);
+
+	/*
 	 * This in_recovery lock does two things:
-	 *
 	 * 1) Keeps this function from returning until all threads are out
 	 *    of locking routines and locking is truely stopped.
 	 * 2) Keeps any new requests from being processed until it's unlocked
@@ -284,9 +298,8 @@ int dlm_ls_stop(struct dlm_ls *ls)
 
 	/*
 	 * The recoverd suspend/resume makes sure that dlm_recoverd (if
-	 * running) has noticed the clearing of RUNNING above and quit
-	 * processing the previous recovery.  This will be true for all nodes
-	 * before any nodes start the new recovery.
+	 * running) has noticed RECOVERY_STOP above and quit processing the
+	 * previous recovery.
 	 */
 
 	dlm_recoverd_suspend(ls);
diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c
index a5126e0c68a6..f8c69dda16a0 100644
--- a/fs/dlm/midcomms.c
+++ b/fs/dlm/midcomms.c
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -27,7 +27,6 @@
 #include "dlm_internal.h"
 #include "lowcomms.h"
 #include "config.h"
-#include "rcom.h"
 #include "lock.h"
 #include "midcomms.h"
 
@@ -117,19 +116,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base,
 		offset &= (limit - 1);
 		len -= msglen;
 
-		switch (msg->h_cmd) {
-		case DLM_MSG:
-			dlm_receive_message(msg, nodeid, 0);
-			break;
-
-		case DLM_RCOM:
-			dlm_receive_rcom(msg, nodeid);
-			break;
-
-		default:
-			log_print("unknown msg type %x from %u: %u %u %u %u",
-				  msg->h_cmd, nodeid, msglen, len, offset, ret);
-		}
+		dlm_receive_buffer(msg, nodeid);
 	}
 
 	if (msg != (struct dlm_header *) __tmp)
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index 188b91c027e4..ae2fd97fa4ad 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -386,7 +386,10 @@ static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
 	dlm_recover_process_copy(ls, rc_in);
 }
 
-static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
+/* If the lockspace doesn't exist then still send a status message
+   back; it's possible that it just doesn't have its global_id yet. */
+
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
 {
 	struct dlm_rcom *rc;
 	struct rcom_config *rf;
@@ -446,28 +449,11 @@ static int is_old_reply(struct dlm_ls *ls, struct dlm_rcom *rc)
 	return rv;
 }
 
-/* Called by dlm_recvd; corresponds to dlm_receive_message() but special
+/* Called by dlm_recv; corresponds to dlm_receive_message() but special
    recovery-only comms are sent through here. */
 
-void dlm_receive_rcom(struct dlm_header *hd, int nodeid)
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
 {
-	struct dlm_rcom *rc = (struct dlm_rcom *) hd;
-	struct dlm_ls *ls;
-
-	dlm_rcom_in(rc);
-
-	/* If the lockspace doesn't exist then still send a status message
-	   back; it's possible that it just doesn't have its global_id yet. */
-
-	ls = dlm_find_lockspace_global(hd->h_lockspace);
-	if (!ls) {
-		log_print("lockspace %x from %d type %x not found",
-			  hd->h_lockspace, nodeid, rc->rc_type);
-		if (rc->rc_type == DLM_RCOM_STATUS)
-			send_ls_not_ready(nodeid, rc);
-		return;
-	}
-
 	if (dlm_recovery_stopped(ls) && (rc->rc_type != DLM_RCOM_STATUS)) {
 		log_debug(ls, "ignoring recovery message %x from %d",
 			  rc->rc_type, nodeid);
@@ -477,12 +463,6 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid)
 	if (is_old_reply(ls, rc))
 		goto out;
 
-	if (nodeid != rc->rc_header.h_nodeid) {
-		log_error(ls, "bad rcom nodeid %d from %d",
-			  rc->rc_header.h_nodeid, nodeid);
-		goto out;
-	}
-
 	switch (rc->rc_type) {
 	case DLM_RCOM_STATUS:
 		receive_rcom_status(ls, rc);
@@ -520,6 +500,6 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid)
 		DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type););
 	}
  out:
-	dlm_put_lockspace(ls);
+	return;
 }
 
diff --git a/fs/dlm/rcom.h b/fs/dlm/rcom.h
index d7984321ff41..b09abd29ba38 100644
--- a/fs/dlm/rcom.h
+++ b/fs/dlm/rcom.h
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -18,7 +18,8 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid);
 int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name,int last_len);
 int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid);
 int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
-void dlm_receive_rcom(struct dlm_header *hd, int nodeid);
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid);
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in);
 
 #endif
 
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 66575997861c..4b89e20eebe7 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -24,19 +24,28 @@
 
 
 /* If the start for which we're re-enabling locking (seq) has been superseded
-   by a newer stop (ls_recover_seq), we need to leave locking disabled. */
+   by a newer stop (ls_recover_seq), we need to leave locking disabled.
+
+   We suspend dlm_recv threads here to avoid the race where dlm_recv a) sees
+   locking stopped and b) adds a message to the requestqueue, but dlm_recoverd
+   enables locking and clears the requestqueue between a and b. */
 
 static int enable_locking(struct dlm_ls *ls, uint64_t seq)
 {
 	int error = -EINTR;
 
+	down_write(&ls->ls_recv_active);
+
 	spin_lock(&ls->ls_recover_lock);
 	if (ls->ls_recover_seq == seq) {
 		set_bit(LSFL_RUNNING, &ls->ls_flags);
+		/* unblocks processes waiting to enter the dlm */
 		up_write(&ls->ls_in_recovery);
 		error = 0;
 	}
 	spin_unlock(&ls->ls_recover_lock);
+
+	up_write(&ls->ls_recv_active);
 	return error;
 }
 
diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c
index 65008d79c96d..0de04f17ccea 100644
--- a/fs/dlm/requestqueue.c
+++ b/fs/dlm/requestqueue.c
@@ -1,7 +1,7 @@
 /******************************************************************************
 *******************************************************************************
 **
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -20,7 +20,7 @@
 struct rq_entry {
 	struct list_head list;
 	int nodeid;
-	char request[1];
+	char request[0];
 };
 
 /*
@@ -30,42 +30,39 @@ struct rq_entry {
  * lockspace is enabled on some while still suspended on others.
  */
 
-int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd)
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd)
 {
 	struct rq_entry *e;
 	int length = hd->h_length;
-	int rv = 0;
 
 	e = kmalloc(sizeof(struct rq_entry) + length, GFP_KERNEL);
 	if (!e) {
-		log_print("dlm_add_requestqueue: out of memory\n");
-		return 0;
+		log_print("dlm_add_requestqueue: out of memory len %d", length);
+		return;
 	}
 
 	e->nodeid = nodeid;
 	memcpy(e->request, hd, length);
 
-	/* We need to check dlm_locking_stopped() after taking the mutex to
-	   avoid a race where dlm_recoverd enables locking and runs
-	   process_requestqueue between our earlier dlm_locking_stopped check
-	   and this addition to the requestqueue. */
-
 	mutex_lock(&ls->ls_requestqueue_mutex);
-	if (dlm_locking_stopped(ls))
-		list_add_tail(&e->list, &ls->ls_requestqueue);
-	else {
-		log_debug(ls, "dlm_add_requestqueue skip from %d", nodeid);
-		kfree(e);
-		rv = -EAGAIN;
-	}
+	list_add_tail(&e->list, &ls->ls_requestqueue);
 	mutex_unlock(&ls->ls_requestqueue_mutex);
-	return rv;
 }
 
+/*
+ * Called by dlm_recoverd to process normal messages saved while recovery was
+ * happening.  Normal locking has been enabled before this is called.  dlm_recv
+ * upon receiving a message, will wait for all saved messages to be drained
+ * here before processing the message it got.  If a new dlm_ls_stop() arrives
+ * while we're processing these saved messages, it may block trying to suspend
+ * dlm_recv if dlm_recv is waiting for us in dlm_wait_requestqueue.  In that
+ * case, we don't abort since locking_stopped is still 0.  If dlm_recv is not
+ * waiting for us, then this processing may be aborted due to locking_stopped.
+ */
+
 int dlm_process_requestqueue(struct dlm_ls *ls)
 {
 	struct rq_entry *e;
-	struct dlm_header *hd;
 	int error = 0;
 
 	mutex_lock(&ls->ls_requestqueue_mutex);
@@ -79,14 +76,7 @@ int dlm_process_requestqueue(struct dlm_ls *ls)
 		e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list);
 		mutex_unlock(&ls->ls_requestqueue_mutex);
 
-		hd = (struct dlm_header *) e->request;
-		error = dlm_receive_message(hd, e->nodeid, 1);
-
-		if (error == -EINTR) {
-			/* entry is left on requestqueue */
-			log_debug(ls, "process_requestqueue abort eintr");
-			break;
-		}
+		dlm_receive_message_saved(ls, (struct dlm_message *)e->request);
 
 		mutex_lock(&ls->ls_requestqueue_mutex);
 		list_del(&e->list);
@@ -106,10 +96,12 @@ int dlm_process_requestqueue(struct dlm_ls *ls)
 
 /*
  * After recovery is done, locking is resumed and dlm_recoverd takes all the
- * saved requests and processes them as they would have been by dlm_recvd.  At
- * the same time, dlm_recvd will start receiving new requests from remote
- * nodes.  We want to delay dlm_recvd processing new requests until
- * dlm_recoverd has finished processing the old saved requests.
+ * saved requests and processes them as they would have been by dlm_recv.  At
+ * the same time, dlm_recv will start receiving new requests from remote nodes.
+ * We want to delay dlm_recv processing new requests until dlm_recoverd has
+ * finished processing the old saved requests.  We don't check for locking
+ * stopped here because dlm_ls_stop won't stop locking until it's suspended us
+ * (dlm_recv).
  */
 
 void dlm_wait_requestqueue(struct dlm_ls *ls)
@@ -118,8 +110,6 @@ void dlm_wait_requestqueue(struct dlm_ls *ls)
 		mutex_lock(&ls->ls_requestqueue_mutex);
 		if (list_empty(&ls->ls_requestqueue))
 			break;
-		if (dlm_locking_stopped(ls))
-			break;
 		mutex_unlock(&ls->ls_requestqueue_mutex);
 		schedule();
 	}
diff --git a/fs/dlm/requestqueue.h b/fs/dlm/requestqueue.h
index 6a53ea03335d..aba34fc05ee4 100644
--- a/fs/dlm/requestqueue.h
+++ b/fs/dlm/requestqueue.h
@@ -1,7 +1,7 @@
 /******************************************************************************
 *******************************************************************************
 **
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -13,7 +13,7 @@
 #ifndef __REQUESTQUEUE_DOT_H__
 #define __REQUESTQUEUE_DOT_H__
 
-int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd);
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd);
 int dlm_process_requestqueue(struct dlm_ls *ls);
 void dlm_wait_requestqueue(struct dlm_ls *ls);
 void dlm_purge_requestqueue(struct dlm_ls *ls);
diff --git a/fs/ecryptfs/netlink.c b/fs/ecryptfs/netlink.c
index fe9186312d7c..9aa345121e09 100644
--- a/fs/ecryptfs/netlink.c
+++ b/fs/ecryptfs/netlink.c
@@ -165,22 +165,10 @@ static int ecryptfs_process_nl_quit(struct sk_buff *skb)
  * it to its desired netlink context element and wake up the process
  * that is waiting for a response.
  */
-static void ecryptfs_receive_nl_message(struct sock *sk, int len)
+static void ecryptfs_receive_nl_message(struct sk_buff *skb)
 {
-	struct sk_buff *skb;
 	struct nlmsghdr *nlh;
-	int rc = 0;	/* skb_recv_datagram requires this */
 
-receive:
-	skb = skb_recv_datagram(sk, 0, 0, &rc);
-	if (rc == -EINTR)
-		goto receive;
-	else if (rc < 0) {
-		ecryptfs_printk(KERN_ERR, "Error occurred while "
-				"receiving eCryptfs netlink message; "
-				"rc = [%d]\n", rc);
-		return;
-	}
 	nlh = nlmsg_hdr(skb);
 	if (!NLMSG_OK(nlh, skb->len)) {
 		ecryptfs_printk(KERN_ERR, "Received corrupt netlink "
@@ -227,7 +215,7 @@ int ecryptfs_init_netlink(void)
 {
 	int rc;
 
-	ecryptfs_nl_sock = netlink_kernel_create(NETLINK_ECRYPTFS, 0,
+	ecryptfs_nl_sock = netlink_kernel_create(&init_net, NETLINK_ECRYPTFS, 0,
 						 ecryptfs_receive_nl_message,
 						 NULL, THIS_MODULE);
 	if (!ecryptfs_nl_sock) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a4b142a6a2c7..8d23b0b38717 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index cd805a66880d..93fa427bb5f5 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -93,9 +93,10 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 		map_bh(bh, inode->i_sb, block);
 
 	set_buffer_uptodate(bh);
+	if (!gfs2_is_jdata(ip))
+		mark_buffer_dirty(bh);
 	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
-	mark_buffer_dirty(bh);
 
 	if (release) {
 		unlock_page(page);
@@ -1085,6 +1086,33 @@ static int do_shrink(struct gfs2_inode *ip, u64 size)
 	return error;
 }
 
+static int do_touch(struct gfs2_inode *ip, u64 size)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		return error;
+
+	down_write(&ip->i_rw_mutex);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto do_touch_out;
+
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+do_touch_out:
+	up_write(&ip->i_rw_mutex);
+	gfs2_trans_end(sdp);
+	return error;
+}
+
 /**
  * gfs2_truncatei - make a file a given size
  * @ip: the inode
@@ -1105,8 +1133,11 @@ int gfs2_truncatei(struct gfs2_inode *ip, u64 size)
 
 	if (size > ip->i_di.di_size)
 		error = do_grow(ip, size);
-	else
+	else if (size < ip->i_di.di_size)
 		error = do_shrink(ip, size);
+	else
+		/* update time stamps */
+		error = do_touch(ip, size);
 
 	return error;
 }
diff --git a/fs/gfs2/daemon.c b/fs/gfs2/daemon.c
index 3548d9f31e0d..3731ab0771d5 100644
--- a/fs/gfs2/daemon.c
+++ b/fs/gfs2/daemon.c
@@ -35,30 +35,6 @@
    The kthread functions used to start these daemons block and flush signals. */
 
 /**
- * gfs2_scand - Look for cached glocks and inodes to toss from memory
- * @sdp: Pointer to GFS2 superblock
- *
- * One of these daemons runs, finding candidates to add to sd_reclaim_list.
- * See gfs2_glockd()
- */
-
-int gfs2_scand(void *data)
-{
-	struct gfs2_sbd *sdp = data;
-	unsigned long t;
-
-	while (!kthread_should_stop()) {
-		gfs2_scand_internal(sdp);
-		t = gfs2_tune_get(sdp, gt_scand_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
-	return 0;
-}
-
-/**
  * gfs2_glockd - Reclaim unused glock structures
  * @sdp: Pointer to GFS2 superblock
  *
diff --git a/fs/gfs2/daemon.h b/fs/gfs2/daemon.h
index 801007120fb2..0de9b3557955 100644
--- a/fs/gfs2/daemon.h
+++ b/fs/gfs2/daemon.h
@@ -10,7 +10,6 @@
 #ifndef __DAEMON_DOT_H__
 #define __DAEMON_DOT_H__
 
-int gfs2_scand(void *data);
 int gfs2_glockd(void *data);
 int gfs2_recoverd(void *data);
 int gfs2_logd(void *data);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 2beb2f401aa2..9949bb746a52 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1043,6 +1043,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	error = gfs2_meta_inode_buffer(dip, &dibh);
 	if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
+		gfs2_trans_add_bh(dip->i_gl, dibh, 1);
 		dip->i_di.di_blocks++;
 		gfs2_set_inode_blocks(&dip->i_inode);
 		gfs2_dinode_out(dip, dibh->b_data);
@@ -1501,7 +1502,7 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name)
 		inode = gfs2_inode_lookup(dir->i_sb, 
 				be16_to_cpu(dent->de_type),
 				be64_to_cpu(dent->de_inum.no_addr),
-				be64_to_cpu(dent->de_inum.no_formal_ino));
+				be64_to_cpu(dent->de_inum.no_formal_ino), 0);
 		brelse(bh);
 		return inode;
 	}
diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c
index 1ab3e9d73886..aa8dbf303f6d 100644
--- a/fs/gfs2/eaops.c
+++ b/fs/gfs2/eaops.c
@@ -200,28 +200,28 @@ static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
 	return gfs2_ea_remove_i(ip, er);
 }
 
-static struct gfs2_eattr_operations gfs2_user_eaops = {
+static const struct gfs2_eattr_operations gfs2_user_eaops = {
 	.eo_get = user_eo_get,
 	.eo_set = user_eo_set,
 	.eo_remove = user_eo_remove,
 	.eo_name = "user",
 };
 
-struct gfs2_eattr_operations gfs2_system_eaops = {
+const struct gfs2_eattr_operations gfs2_system_eaops = {
 	.eo_get = system_eo_get,
 	.eo_set = system_eo_set,
 	.eo_remove = system_eo_remove,
 	.eo_name = "system",
 };
 
-static struct gfs2_eattr_operations gfs2_security_eaops = {
+static const struct gfs2_eattr_operations gfs2_security_eaops = {
 	.eo_get = security_eo_get,
 	.eo_set = security_eo_set,
 	.eo_remove = security_eo_remove,
 	.eo_name = "security",
 };
 
-struct gfs2_eattr_operations *gfs2_ea_ops[] = {
+const struct gfs2_eattr_operations *gfs2_ea_ops[] = {
 	NULL,
 	&gfs2_user_eaops,
 	&gfs2_system_eaops,
diff --git a/fs/gfs2/eaops.h b/fs/gfs2/eaops.h
index 508b4f7a2449..da2f7fbbb40d 100644
--- a/fs/gfs2/eaops.h
+++ b/fs/gfs2/eaops.h
@@ -22,9 +22,9 @@ struct gfs2_eattr_operations {
 
 unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
 
-extern struct gfs2_eattr_operations gfs2_system_eaops;
+extern const struct gfs2_eattr_operations gfs2_system_eaops;
 
-extern struct gfs2_eattr_operations *gfs2_ea_ops[];
+extern const struct gfs2_eattr_operations *gfs2_ea_ops[];
 
 #endif /* __EAOPS_DOT_H__ */
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3f0974e1afef..a37efe4aae6f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -25,8 +25,10 @@
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
-#include <linux/module.h>
-#include <linux/kallsyms.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -48,7 +50,6 @@ struct glock_iter {
 	int hash;                     /* hash bucket index         */
 	struct gfs2_sbd *sdp;         /* incore superblock         */
 	struct gfs2_glock *gl;        /* current glock struct      */
-	struct hlist_head *hb_list;   /* current hash bucket ptr   */
 	struct seq_file *seq;         /* sequence file for debugfs */
 	char string[512];             /* scratch space             */
 };
@@ -59,8 +60,13 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
 static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
 static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
 static void gfs2_glock_drop_th(struct gfs2_glock *gl);
+static void run_queue(struct gfs2_glock *gl);
+
 static DECLARE_RWSEM(gfs2_umount_flush_sem);
 static struct dentry *gfs2_root;
+static struct task_struct *scand_process;
+static unsigned int scand_secs = 5;
+static struct workqueue_struct *glock_workqueue;
 
 #define GFS2_GL_HASH_SHIFT      15
 #define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
@@ -276,6 +282,18 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
 	return gl;
 }
 
+static void glock_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+
+	spin_lock(&gl->gl_spin);
+	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
+		set_bit(GLF_DEMOTE, &gl->gl_flags);
+	run_queue(gl);
+	spin_unlock(&gl->gl_spin);
+	gfs2_glock_put(gl);
+}
+
 /**
  * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
  * @sdp: The GFS2 superblock
@@ -315,6 +333,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
 	gl->gl_state = LM_ST_UNLOCKED;
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
 	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;
@@ -323,10 +342,12 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_req_bh = NULL;
 	gl->gl_vn = 0;
 	gl->gl_stamp = jiffies;
+	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;
 	gl->gl_sbd = sdp;
 	gl->gl_aspace = NULL;
 	lops_init_le(&gl->gl_le, &gfs2_glock_lops);
+	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 
 	/* If this glock protects actual on-disk data or metadata blocks,
 	   create a VFS inode to manage the pages/buffers holding them. */
@@ -440,6 +461,8 @@ static void wait_on_holder(struct gfs2_holder *gh)
 
 static void gfs2_demote_wake(struct gfs2_glock *gl)
 {
+	BUG_ON(!spin_is_locked(&gl->gl_spin));
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
         clear_bit(GLF_DEMOTE, &gl->gl_flags);
         smp_mb__after_clear_bit();
         wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
@@ -545,12 +568,14 @@ static int rq_demote(struct gfs2_glock *gl)
 		return 0;
 	}
 	set_bit(GLF_LOCK, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
 	if (gl->gl_demote_state == LM_ST_UNLOCKED ||
-	    gl->gl_state != LM_ST_EXCLUSIVE)
+	    gl->gl_state != LM_ST_EXCLUSIVE) {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_drop_th(gl);
-	else
+	} else {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_xmote_th(gl, NULL);
+	}
 	spin_lock(&gl->gl_spin);
 
 	return 0;
@@ -679,24 +704,25 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
  * practise: LM_ST_SHARED and LM_ST_UNLOCKED
  */
 
-static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remote)
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+			    int remote, unsigned long delay)
 {
+	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
+
 	spin_lock(&gl->gl_spin);
-	if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+	set_bit(bit, &gl->gl_flags);
+	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
 		gl->gl_demote_state = state;
 		gl->gl_demote_time = jiffies;
 		if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
 		    gl->gl_object) {
-			struct inode *inode = igrab(gl->gl_object);
+			gfs2_glock_schedule_for_reclaim(gl);
 			spin_unlock(&gl->gl_spin);
-			if (inode) {
-				d_prune_aliases(inode);
-				iput(inode);
-			}
 			return;
 		}
-	} else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
-		gl->gl_demote_state = state;
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+			gl->gl_demote_state != state) {
+		gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
 	spin_unlock(&gl->gl_spin);
 }
@@ -723,6 +749,7 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 	}
 
 	gl->gl_state = new_state;
+	gl->gl_tchange = jiffies;
 }
 
 /**
@@ -760,10 +787,20 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
 
 	if (!gh) {
 		gl->gl_stamp = jiffies;
-		if (ret & LM_OUT_CANCELED)
+		if (ret & LM_OUT_CANCELED) {
 			op_done = 0;
-		else
+		} else {
+			spin_lock(&gl->gl_spin);
+			if (gl->gl_state != gl->gl_demote_state) {
+				gl->gl_req_bh = NULL;
+				spin_unlock(&gl->gl_spin);
+				gfs2_glock_drop_th(gl);
+				gfs2_glock_put(gl);
+				return;
+			}
 			gfs2_demote_wake(gl);
+			spin_unlock(&gl->gl_spin);
+		}
 	} else {
 		spin_lock(&gl->gl_spin);
 		list_del_init(&gh->gh_list);
@@ -799,7 +836,6 @@ out:
 		gl->gl_req_gh = NULL;
 		gl->gl_req_bh = NULL;
 		clear_bit(GLF_LOCK, &gl->gl_flags);
-		run_queue(gl);
 		spin_unlock(&gl->gl_spin);
 	}
 
@@ -817,7 +853,7 @@ out:
  *
  */
 
-void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	int flags = gh ? gh->gh_flags : 0;
@@ -871,7 +907,6 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 	gfs2_assert_warn(sdp, !ret);
 
 	state_change(gl, LM_ST_UNLOCKED);
-	gfs2_demote_wake(gl);
 
 	if (glops->go_inval)
 		glops->go_inval(gl, DIO_METADATA);
@@ -884,10 +919,10 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 	}
 
 	spin_lock(&gl->gl_spin);
+	gfs2_demote_wake(gl);
 	gl->gl_req_gh = NULL;
 	gl->gl_req_bh = NULL;
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
 
 	gfs2_glock_put(gl);
@@ -1067,24 +1102,31 @@ static void add_to_queue(struct gfs2_holder *gh)
 	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
 		BUG();
 
-	existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				gl->gl_name.ln_type, gl->gl_state);
-		BUG();
-	}
-
-	existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		BUG();
+	if (!(gh->gh_flags & GL_FLOCK)) {
+		existing = find_holder_by_owner(&gl->gl_holders, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       existing->gh_gl->gl_name.ln_type, 
+			       existing->gh_gl->gl_state);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       gl->gl_name.ln_type, gl->gl_state);
+			BUG();
+		}
+		
+		existing = find_holder_by_owner(&gl->gl_waiters3, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			BUG();
+		}
 	}
 
 	if (gh->gh_flags & LM_FLAG_PRIORITY)
@@ -1195,9 +1237,10 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned delay = 0;
 
 	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED, 0);
+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 
 	gfs2_glmutex_lock(gl);
 
@@ -1215,8 +1258,14 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	}
 
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
+
+	gfs2_glock_hold(gl);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 void gfs2_glock_dq_wait(struct gfs2_holder *gh)
@@ -1443,18 +1492,21 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
 			unsigned int state)
 {
 	struct gfs2_glock *gl;
+	unsigned long delay = 0;
+	unsigned long holdtime;
+	unsigned long now = jiffies;
 
 	gl = gfs2_glock_find(sdp, name);
 	if (!gl)
 		return;
 
-	handle_callback(gl, state, 1);
-
-	spin_lock(&gl->gl_spin);
-	run_queue(gl);
-	spin_unlock(&gl->gl_spin);
+	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+	if (time_before(now, holdtime))
+		delay = holdtime - now;
 
-	gfs2_glock_put(gl);
+	handle_callback(gl, state, 1, delay);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 /**
@@ -1495,7 +1547,8 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
 			return;
 		if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
 			gl->gl_req_bh(gl, async->lc_ret);
-		gfs2_glock_put(gl);
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put(gl);
 		up_read(&gfs2_umount_flush_sem);
 		return;
 	}
@@ -1588,7 +1641,7 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 
@@ -1617,7 +1670,7 @@ static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
 		goto out;
 	gl = list_entry(head->first, struct gfs2_glock, gl_list);
 	while(1) {
-		if (gl->gl_sbd == sdp) {
+		if (!sdp || gl->gl_sbd == sdp) {
 			gfs2_glock_hold(gl);
 			read_unlock(gl_lock_addr(hash));
 			if (prev)
@@ -1635,6 +1688,7 @@ out:
 	read_unlock(gl_lock_addr(hash));
 	if (prev)
 		gfs2_glock_put(prev);
+	cond_resched();
 	return has_entries;
 }
 
@@ -1663,20 +1717,6 @@ out_schedule:
 }
 
 /**
- * gfs2_scand_internal - Look for glocks and inodes to toss from memory
- * @sdp: the filesystem
- *
- */
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp)
-{
-	unsigned int x;
-
-	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
-		examine_bucket(scan_glock, sdp, x);
-}
-
-/**
  * clear_glock - look at a glock and see if we can free it from glock cache
  * @gl: the glock to look at
  *
@@ -1701,7 +1741,7 @@ static void clear_glock(struct gfs2_glock *gl)
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED)
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 }
@@ -1843,7 +1883,7 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
 
 	spin_lock(&gl->gl_spin);
 
-	print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
+	print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
 		   (unsigned long long)gl->gl_name.ln_number);
 	print_dbg(gi, "  gl_flags =");
 	for (x = 0; x < 32; x++) {
@@ -1963,6 +2003,35 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
 	return error;
 }
 
+/**
+ * gfs2_scand - Look for cached glocks and inodes to toss from memory
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * One of these daemons runs, finding candidates to add to sd_reclaim_list.
+ * See gfs2_glockd()
+ */
+
+static int gfs2_scand(void *data)
+{
+	unsigned x;
+	unsigned delay;
+
+	while (!kthread_should_stop()) {
+		for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+			examine_bucket(scan_glock, NULL, x);
+		if (freezing(current))
+			refrigerator();
+		delay = scand_secs;
+		if (delay < 1)
+			delay = 1;
+		schedule_timeout_interruptible(delay * HZ);
+	}
+
+	return 0;
+}
+
+
+
 int __init gfs2_glock_init(void)
 {
 	unsigned i;
@@ -1974,52 +2043,69 @@ int __init gfs2_glock_init(void)
 		rwlock_init(&gl_hash_locks[i]);
 	}
 #endif
+
+	scand_process = kthread_run(gfs2_scand, NULL, "gfs2_scand");
+	if (IS_ERR(scand_process))
+		return PTR_ERR(scand_process);
+
+	glock_workqueue = create_workqueue("glock_workqueue");
+	if (IS_ERR(glock_workqueue)) {
+		kthread_stop(scand_process);
+		return PTR_ERR(glock_workqueue);
+	}
+
 	return 0;
 }
 
+void gfs2_glock_exit(void)
+{
+	destroy_workqueue(glock_workqueue);
+	kthread_stop(scand_process);
+}
+
+module_param(scand_secs, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs");
+
 static int gfs2_glock_iter_next(struct glock_iter *gi)
 {
+	struct gfs2_glock *gl;
+
+restart:
 	read_lock(gl_lock_addr(gi->hash));
-	while (1) {
-		if (!gi->hb_list) {  /* If we don't have a hash bucket yet */
-			gi->hb_list = &gl_hash_table[gi->hash].hb_list;
-			if (hlist_empty(gi->hb_list)) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				if (gi->hash >= GFS2_GL_HASH_SIZE) {
-					read_unlock(gl_lock_addr(gi->hash));
-					return 1;
-				}
-				else
-					continue;
-			}
-			if (!hlist_empty(gi->hb_list)) {
-				gi->gl = list_entry(gi->hb_list->first,
-						    struct gfs2_glock,
-						    gl_list);
-			}
-		} else {
-			if (gi->gl->gl_list.next == NULL) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				continue;
-			}
-			gi->gl = list_entry(gi->gl->gl_list.next,
-					    struct gfs2_glock, gl_list);
-		}
+	gl = gi->gl;
+	if (gl) {
+		gi->gl = hlist_entry(gl->gl_list.next,
+				     struct gfs2_glock, gl_list);
 		if (gi->gl)
-			break;
+			gfs2_glock_hold(gi->gl);
 	}
 	read_unlock(gl_lock_addr(gi->hash));
+	if (gl)
+		gfs2_glock_put(gl);
+	if (gl && gi->gl == NULL)
+		gi->hash++;
+	while(gi->gl == NULL) {
+		if (gi->hash >= GFS2_GL_HASH_SIZE)
+			return 1;
+		read_lock(gl_lock_addr(gi->hash));
+		gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+				     struct gfs2_glock, gl_list);
+		if (gi->gl)
+			gfs2_glock_hold(gi->gl);
+		read_unlock(gl_lock_addr(gi->hash));
+		gi->hash++;
+	}
+
+	if (gi->sdp != gi->gl->gl_sbd)
+		goto restart;
+
 	return 0;
 }
 
 static void gfs2_glock_iter_free(struct glock_iter *gi)
 {
+	if (gi->gl)
+		gfs2_glock_put(gi->gl);
 	kfree(gi);
 }
 
@@ -2033,9 +2119,8 @@ static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
 
 	gi->sdp = sdp;
 	gi->hash = 0;
-	gi->gl = NULL;
-	gi->hb_list = NULL;
 	gi->seq = NULL;
+	gi->gl = NULL;
 	memset(gi->string, 0, sizeof(gi->string));
 
 	if (gfs2_glock_iter_next(gi)) {
@@ -2055,7 +2140,7 @@ static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
 	if (!gi)
 		return NULL;
 
-	while (n--) {
+	while(n--) {
 		if (gfs2_glock_iter_next(gi)) {
 			gfs2_glock_iter_free(gi);
 			return NULL;
@@ -2082,7 +2167,9 @@ static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
 
 static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
 {
-	/* nothing for now */
+	struct glock_iter *gi = iter_ptr;
+	if (gi)
+		gfs2_glock_iter_free(gi);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
@@ -2095,7 +2182,7 @@ static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
 	return 0;
 }
 
-static struct seq_operations gfs2_glock_seq_ops = {
+static const struct seq_operations gfs2_glock_seq_ops = {
 	.start = gfs2_glock_seq_start,
 	.next  = gfs2_glock_seq_next,
 	.stop  = gfs2_glock_seq_stop,
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 7721ca3fff9e..b16f604eea9f 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -26,6 +26,7 @@
 #define GL_SKIP			0x00000100
 #define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
+#define GL_FLOCK		0x00000800
 #define GL_NOCANCEL		0x00001000
 
 #define GLR_TRYFAILED		13
@@ -132,11 +133,11 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data);
 
 void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl);
 void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp);
 void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
 
 int __init gfs2_glock_init(void);
+void gfs2_glock_exit(void);
+
 int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
 void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
 int gfs2_register_debugfs(void);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 777ca46010e8..4670dcb2a877 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -41,7 +41,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	struct list_head *head = &gl->gl_ail_list;
 	struct gfs2_bufdata *bd;
 	struct buffer_head *bh;
-	u64 blkno;
 	int error;
 
 	blocks = atomic_read(&gl->gl_ail_count);
@@ -57,19 +56,12 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 		bd = list_entry(head->next, struct gfs2_bufdata,
 				bd_ail_gl_list);
 		bh = bd->bd_bh;
-		blkno = bh->b_blocknr;
+		gfs2_remove_from_ail(NULL, bd);
+		bd->bd_bh = NULL;
+		bh->b_private = NULL;
+		bd->bd_blkno = bh->b_blocknr;
 		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
-
-		bd->bd_ail = NULL;
-		list_del(&bd->bd_ail_st_list);
-		list_del(&bd->bd_ail_gl_list);
-		atomic_dec(&gl->gl_ail_count);
-		brelse(bh);
-		gfs2_log_unlock(sdp);
-
-		gfs2_trans_add_revoke(sdp, blkno);
-
-		gfs2_log_lock(sdp);
+		gfs2_trans_add_revoke(sdp, bd);
 	}
 	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
 	gfs2_log_unlock(sdp);
@@ -156,9 +148,11 @@ static void inode_go_sync(struct gfs2_glock *gl)
 		ip = NULL;
 
 	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
-		if (ip)
+		if (ip && !gfs2_is_jdata(ip))
 			filemap_fdatawrite(ip->i_inode.i_mapping);
 		gfs2_log_flush(gl->gl_sbd, gl);
+		if (ip && gfs2_is_jdata(ip))
+			filemap_fdatawrite(ip->i_inode.i_mapping);
 		gfs2_meta_sync(gl);
 		if (ip) {
 			struct address_space *mapping = ip->i_inode.i_mapping;
@@ -452,6 +446,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
 	.go_lock = inode_go_lock,
 	.go_unlock = inode_go_unlock,
 	.go_type = LM_TYPE_INODE,
+	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
@@ -462,6 +457,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
 	.go_type = LM_TYPE_RGRP,
+	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_trans_glops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 170ba93829c0..eaddfb5a8e6f 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -11,6 +11,7 @@
 #define __INCORE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/workqueue.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -113,7 +114,13 @@ struct gfs2_bufdata {
 	struct buffer_head *bd_bh;
 	struct gfs2_glock *bd_gl;
 
-	struct list_head bd_list_tr;
+	union {
+		struct list_head list_tr;
+		u64 blkno;
+	} u;
+#define bd_list_tr u.list_tr
+#define bd_blkno u.blkno
+
 	struct gfs2_log_element bd_le;
 
 	struct gfs2_ail *bd_ail;
@@ -130,6 +137,7 @@ struct gfs2_glock_operations {
 	int (*go_lock) (struct gfs2_holder *gh);
 	void (*go_unlock) (struct gfs2_holder *gh);
 	const int go_type;
+	const unsigned long go_min_hold_time;
 };
 
 enum {
@@ -161,6 +169,7 @@ enum {
 	GLF_LOCK		= 1,
 	GLF_STICKY		= 2,
 	GLF_DEMOTE		= 3,
+	GLF_PENDING_DEMOTE	= 4,
 	GLF_DIRTY		= 5,
 };
 
@@ -193,6 +202,7 @@ struct gfs2_glock {
 
 	u64 gl_vn;
 	unsigned long gl_stamp;
+	unsigned long gl_tchange;
 	void *gl_object;
 
 	struct list_head gl_reclaim;
@@ -203,6 +213,7 @@ struct gfs2_glock {
 	struct gfs2_log_element gl_le;
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
+	struct delayed_work gl_work;
 };
 
 struct gfs2_alloc {
@@ -293,11 +304,6 @@ struct gfs2_file {
 	struct gfs2_holder f_fl_gh;
 };
 
-struct gfs2_revoke {
-	struct gfs2_log_element rv_le;
-	u64 rv_blkno;
-};
-
 struct gfs2_revoke_replay {
 	struct list_head rr_list;
 	u64 rr_blkno;
@@ -335,12 +341,6 @@ struct gfs2_quota_data {
 	unsigned long qd_last_touched;
 };
 
-struct gfs2_log_buf {
-	struct list_head lb_list;
-	struct buffer_head *lb_bh;
-	struct buffer_head *lb_real;
-};
-
 struct gfs2_trans {
 	unsigned long tr_ip;
 
@@ -429,7 +429,6 @@ struct gfs2_tune {
 	unsigned int gt_log_flush_secs;
 	unsigned int gt_jindex_refresh_secs; /* Check for new journal index */
 
-	unsigned int gt_scand_secs;
 	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
 	unsigned int gt_quotad_secs;
@@ -574,7 +573,6 @@ struct gfs2_sbd {
 
 	/* Daemon stuff */
 
-	struct task_struct *sd_scand_process;
 	struct task_struct *sd_recoverd_process;
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;
@@ -609,13 +607,13 @@ struct gfs2_sbd {
 	unsigned int sd_log_num_revoke;
 	unsigned int sd_log_num_rg;
 	unsigned int sd_log_num_databuf;
-	unsigned int sd_log_num_jdata;
 
 	struct list_head sd_log_le_gl;
 	struct list_head sd_log_le_buf;
 	struct list_head sd_log_le_revoke;
 	struct list_head sd_log_le_rg;
 	struct list_head sd_log_le_databuf;
+	struct list_head sd_log_le_ordered;
 
 	unsigned int sd_log_blks_free;
 	struct mutex sd_log_reserve_mutex;
@@ -627,7 +625,8 @@ struct gfs2_sbd {
 
 	unsigned long sd_log_flush_time;
 	struct rw_semaphore sd_log_flush_lock;
-	struct list_head sd_log_flush_list;
+	atomic_t sd_log_in_flight;
+	wait_queue_head_t sd_log_flush_wait;
 
 	unsigned int sd_log_flush_head;
 	u64 sd_log_flush_wrapped;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 34f7bcdea1e9..5f6dc32946cd 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -77,6 +77,49 @@ static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
 	return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
 }
 
+struct gfs2_skip_data {
+	u64	no_addr;
+	int	skipped;
+};
+
+static int iget_skip_test(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (ip->i_no_addr == data->no_addr && inode->i_private != NULL){
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){
+			data->skipped = 1;
+			return 0;
+		}
+		return 1;
+	}
+	return 0;
+}
+
+static int iget_skip_set(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (data->skipped)
+		return 1;
+	inode->i_ino = (unsigned long)(data->no_addr);
+	ip->i_no_addr = data->no_addr;
+	return 0;
+}
+
+static struct inode *gfs2_iget_skip(struct super_block *sb,
+				    u64 no_addr)
+{
+	struct gfs2_skip_data data;
+	unsigned long hash = (unsigned long)no_addr;
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data);
+}
+
 /**
  * GFS2 lookup code fills in vfs inode contents based on info obtained
  * from directory entry inside gfs2_inode_lookup(). This has caused issues
@@ -112,6 +155,7 @@ void gfs2_set_iop(struct inode *inode)
  * @sb: The super block
  * @no_addr: The inode number
  * @type: The type of the inode
+ * @skip_freeing: set this not return an inode if it is currently being freed.
  *
  * Returns: A VFS inode, or an error
  */
@@ -119,13 +163,19 @@ void gfs2_set_iop(struct inode *inode)
 struct inode *gfs2_inode_lookup(struct super_block *sb, 
 				unsigned int type,
 				u64 no_addr,
-				u64 no_formal_ino)
+				u64 no_formal_ino, int skip_freeing)
 {
-	struct inode *inode = gfs2_iget(sb, no_addr);
-	struct gfs2_inode *ip = GFS2_I(inode);
+	struct inode *inode;
+	struct gfs2_inode *ip;
 	struct gfs2_glock *io_gl;
 	int error;
 
+	if (skip_freeing)
+		inode = gfs2_iget_skip(sb, no_addr);
+	else
+		inode = gfs2_iget(sb, no_addr);
+	ip = GFS2_I(inode);
+
 	if (!inode)
 		return ERR_PTR(-ENOBUFS);
 
@@ -244,6 +294,11 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	return 0;
 }
 
+static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh)
+{
+	ip->i_cache[0] = bh;
+}
+
 /**
  * gfs2_inode_refresh - Refresh the incore copy of the dinode
  * @ip: The GFS2 inode
@@ -688,7 +743,7 @@ out:
 static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 			const struct gfs2_inum_host *inum, unsigned int mode,
 			unsigned int uid, unsigned int gid,
-			const u64 *generation, dev_t dev)
+			const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_dinode *di;
@@ -743,13 +798,15 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 	di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
 	di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
 	memset(&di->di_reserved, 0, sizeof(di->di_reserved));
+	
+	set_buffer_uptodate(dibh);
 
-	brelse(dibh);
+	*bhp = dibh;
 }
 
 static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 		       unsigned int mode, const struct gfs2_inum_host *inum,
-		       const u64 *generation, dev_t dev)
+		       const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	unsigned int uid, gid;
@@ -770,7 +827,7 @@ static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 	if (error)
 		goto out_quota;
 
-	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev);
+	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp);
 	gfs2_quota_change(dip, +1, uid, gid);
 	gfs2_trans_end(sdp);
 
@@ -909,6 +966,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
 	int error;
 	u64 generation;
+	struct buffer_head *bh=NULL;
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -935,16 +993,18 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	if (error)
 		goto fail_gunlock;
 
-	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev);
+	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh);
 	if (error)
 		goto fail_gunlock2;
 
 	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode),
 					inum.no_addr,
-					inum.no_formal_ino);
+					inum.no_formal_ino, 0);
 	if (IS_ERR(inode))
 		goto fail_gunlock2;
 
+	gfs2_inode_bh(GFS2_I(inode), bh);
+
 	error = gfs2_inode_refresh(GFS2_I(inode));
 	if (error)
 		goto fail_gunlock2;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 4517ac82c01c..351ac87ab384 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -49,7 +49,8 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
 void gfs2_inode_attr_in(struct gfs2_inode *ip);
 void gfs2_set_iop(struct inode *inode);
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				u64 no_addr, u64 no_formal_ino);
+				u64 no_addr, u64 no_formal_ino,
+				int skip_freeing);
 struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
 int gfs2_inode_refresh(struct gfs2_inode *ip);
diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h
index 24d70f73b651..9e8265d28377 100644
--- a/fs/gfs2/locking/dlm/lock_dlm.h
+++ b/fs/gfs2/locking/dlm/lock_dlm.h
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/list.h>
diff --git a/fs/gfs2/locking/dlm/plock.c b/fs/gfs2/locking/dlm/plock.c
index fba1f1d87e4f..1f7b038530b4 100644
--- a/fs/gfs2/locking/dlm/plock.c
+++ b/fs/gfs2/locking/dlm/plock.c
@@ -346,15 +346,16 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 
 static unsigned int dev_poll(struct file *file, poll_table *wait)
 {
+	unsigned int mask = 0;
+
 	poll_wait(file, &send_wq, wait);
 
 	spin_lock(&ops_lock);
-	if (!list_empty(&send_list)) {
-		spin_unlock(&ops_lock);
-		return POLLIN | POLLRDNORM;
-	}
+	if (!list_empty(&send_list))
+		mask = POLLIN | POLLRDNORM;
 	spin_unlock(&ops_lock);
-	return 0;
+
+	return mask;
 }
 
 static const struct file_operations dev_fops = {
diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c
index d9fe3ca40e18..ae9e6a25fe2b 100644
--- a/fs/gfs2/locking/dlm/sysfs.c
+++ b/fs/gfs2/locking/dlm/sysfs.c
@@ -190,7 +190,6 @@ static struct kobj_type gdlm_ktype = {
 };
 
 static struct kset gdlm_kset = {
-	.kobj   = {.name = "lock_dlm",},
 	.ktype  = &gdlm_ktype,
 };
 
@@ -224,6 +223,7 @@ int gdlm_sysfs_init(void)
 {
 	int error;
 
+	kobject_set_name(&gdlm_kset.kobj, "lock_dlm");
 	kobj_set_kset_s(&gdlm_kset, kernel_subsys);
 	error = kset_register(&gdlm_kset);
 	if (error)
diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c
index 1aca51e45092..bd938f06481d 100644
--- a/fs/gfs2/locking/dlm/thread.c
+++ b/fs/gfs2/locking/dlm/thread.c
@@ -268,20 +268,16 @@ static inline int check_drop(struct gdlm_ls *ls)
 	return 0;
 }
 
-static int gdlm_thread(void *data)
+static int gdlm_thread(void *data, int blist)
 {
 	struct gdlm_ls *ls = (struct gdlm_ls *) data;
 	struct gdlm_lock *lp = NULL;
-	int blist = 0;
 	uint8_t complete, blocking, submit, drop;
 	DECLARE_WAITQUEUE(wait, current);
 
 	/* Only thread1 is allowed to do blocking callbacks since gfs
 	   may wait for a completion callback within a blocking cb. */
 
-	if (current == ls->thread1)
-		blist = 1;
-
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		add_wait_queue(&ls->thread_wait, &wait);
@@ -333,12 +329,22 @@ static int gdlm_thread(void *data)
 	return 0;
 }
 
+static int gdlm_thread1(void *data)
+{
+	return gdlm_thread(data, 1);
+}
+
+static int gdlm_thread2(void *data)
+{
+	return gdlm_thread(data, 0);
+}
+
 int gdlm_init_threads(struct gdlm_ls *ls)
 {
 	struct task_struct *p;
 	int error;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm1");
+	p = kthread_run(gdlm_thread1, ls, "lock_dlm1");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm1 thread %d", error);
@@ -346,7 +352,7 @@ int gdlm_init_threads(struct gdlm_ls *ls)
 	}
 	ls->thread1 = p;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm2");
+	p = kthread_run(gdlm_thread2, ls, "lock_dlm2");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm2 thread %d", error);
diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c
index 0d149c8c493a..d3b8ce6fbbe3 100644
--- a/fs/gfs2/locking/nolock/main.c
+++ b/fs/gfs2/locking/nolock/main.c
@@ -9,7 +9,6 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/fs.h>
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f49a12e24086..7df702473252 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -60,6 +60,26 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 }
 
 /**
+ * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
+ * @mapping: The associated mapping (maybe NULL)
+ * @bd: The gfs2_bufdata to remove
+ *
+ * The log lock _must_ be held when calling this function
+ *
+ */
+
+void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd)
+{
+	bd->bd_ail = NULL;
+	list_del_init(&bd->bd_ail_st_list);
+	list_del_init(&bd->bd_ail_gl_list);
+	atomic_dec(&bd->bd_gl->gl_ail_count);
+	if (mapping)
+		gfs2_meta_cache_flush(GFS2_I(mapping->host));
+	brelse(bd->bd_bh);
+}
+
+/**
  * gfs2_ail1_start_one - Start I/O on a part of the AIL
  * @sdp: the filesystem
  * @tr: the part of the AIL
@@ -83,17 +103,9 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 
 			gfs2_assert(sdp, bd->bd_ail == ai);
 
-			if (!bh){
-				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-                                continue;
-                        }
-
 			if (!buffer_busy(bh)) {
-				if (!buffer_uptodate(bh)) {
-					gfs2_log_unlock(sdp);
+				if (!buffer_uptodate(bh))
 					gfs2_io_error_bh(sdp, bh);
-					gfs2_log_lock(sdp);
-				}
 				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
 				continue;
 			}
@@ -103,9 +115,16 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 
 			list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
 
+			get_bh(bh);
 			gfs2_log_unlock(sdp);
-			wait_on_buffer(bh);
-			ll_rw_block(WRITE, 1, &bh);
+			lock_buffer(bh);
+			if (test_clear_buffer_dirty(bh)) {
+				bh->b_end_io = end_buffer_write_sync;
+				submit_bh(WRITE, bh);
+			} else {
+				unlock_buffer(bh);
+				brelse(bh);
+			}
 			gfs2_log_lock(sdp);
 
 			retry = 1;
@@ -130,11 +149,6 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
 					 bd_ail_st_list) {
 		bh = bd->bd_bh;
 
-		if (!bh){
-			list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-			continue;
-		}
-
 		gfs2_assert(sdp, bd->bd_ail == ai);
 
 		if (buffer_busy(bh)) {
@@ -155,13 +169,14 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
 
 static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
 {
-	struct list_head *head = &sdp->sd_ail1_list;
+	struct list_head *head;
 	u64 sync_gen;
 	struct list_head *first;
 	struct gfs2_ail *first_ai, *ai, *tmp;
 	int done = 0;
 
 	gfs2_log_lock(sdp);
+	head = &sdp->sd_ail1_list;
 	if (list_empty(head)) {
 		gfs2_log_unlock(sdp);
 		return;
@@ -233,11 +248,7 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 		bd = list_entry(head->prev, struct gfs2_bufdata,
 				bd_ail_st_list);
 		gfs2_assert(sdp, bd->bd_ail == ai);
-		bd->bd_ail = NULL;
-		list_del(&bd->bd_ail_st_list);
-		list_del(&bd->bd_ail_gl_list);
-		atomic_dec(&bd->bd_gl->gl_ail_count);
-		brelse(bd->bd_bh);
+		gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
 	}
 }
 
@@ -439,10 +450,10 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
 	return tail;
 }
 
-static inline void log_incr_head(struct gfs2_sbd *sdp)
+void gfs2_log_incr_head(struct gfs2_sbd *sdp)
 {
 	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
-		gfs2_assert_withdraw(sdp, sdp->sd_log_flush_head == sdp->sd_log_head);
+		BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
 
 	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
 		sdp->sd_log_flush_head = 0;
@@ -451,6 +462,23 @@ static inline void log_incr_head(struct gfs2_sbd *sdp)
 }
 
 /**
+ * gfs2_log_write_endio - End of I/O for a log buffer
+ * @bh: The buffer head
+ * @uptodate: I/O Status
+ *
+ */
+
+static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
+{
+	struct gfs2_sbd *sdp = bh->b_private;
+	bh->b_private = NULL;
+
+	end_buffer_write_sync(bh, uptodate);
+	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+		wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
  * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
  * @sdp: The GFS2 superblock
  *
@@ -460,25 +488,43 @@ static inline void log_incr_head(struct gfs2_sbd *sdp)
 struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
 {
 	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct gfs2_log_buf *lb;
 	struct buffer_head *bh;
 
-	lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL);
-	list_add(&lb->lb_list, &sdp->sd_log_flush_list);
-
-	bh = lb->lb_bh = sb_getblk(sdp->sd_vfs, blkno);
+	bh = sb_getblk(sdp->sd_vfs, blkno);
 	lock_buffer(bh);
 	memset(bh->b_data, 0, bh->b_size);
 	set_buffer_uptodate(bh);
 	clear_buffer_dirty(bh);
-	unlock_buffer(bh);
-
-	log_incr_head(sdp);
+	gfs2_log_incr_head(sdp);
+	atomic_inc(&sdp->sd_log_in_flight);
+	bh->b_private = sdp;
+	bh->b_end_io = gfs2_log_write_endio;
 
 	return bh;
 }
 
 /**
+ * gfs2_fake_write_endio - 
+ * @bh: The buffer head
+ * @uptodate: The I/O Status
+ *
+ */
+
+static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
+{
+	struct buffer_head *real_bh = bh->b_private;
+	struct gfs2_bufdata *bd = real_bh->b_private;
+	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
+
+	end_buffer_write_sync(bh, uptodate);
+	free_buffer_head(bh);
+	unlock_buffer(real_bh);
+	brelse(real_bh);
+	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+		wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
  * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
  * @sdp: the filesystem
  * @data: the data the buffer_head should point to
@@ -490,22 +536,20 @@ struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
 				      struct buffer_head *real)
 {
 	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct gfs2_log_buf *lb;
 	struct buffer_head *bh;
 
-	lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL);
-	list_add(&lb->lb_list, &sdp->sd_log_flush_list);
-	lb->lb_real = real;
-
-	bh = lb->lb_bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
+	bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
 	atomic_set(&bh->b_count, 1);
-	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate);
+	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
 	set_bh_page(bh, real->b_page, bh_offset(real));
 	bh->b_blocknr = blkno;
 	bh->b_size = sdp->sd_sb.sb_bsize;
 	bh->b_bdev = sdp->sd_vfs->s_bdev;
+	bh->b_private = real;
+	bh->b_end_io = gfs2_fake_write_endio;
 
-	log_incr_head(sdp);
+	gfs2_log_incr_head(sdp);
+	atomic_inc(&sdp->sd_log_in_flight);
 
 	return bh;
 }
@@ -572,45 +616,75 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 		gfs2_assert_withdraw(sdp, !pull);
 
 	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
-	log_incr_head(sdp);
+	gfs2_log_incr_head(sdp);
 }
 
 static void log_flush_commit(struct gfs2_sbd *sdp)
 {
-	struct list_head *head = &sdp->sd_log_flush_list;
-	struct gfs2_log_buf *lb;
-	struct buffer_head *bh;
-	int flushcount = 0;
+	DEFINE_WAIT(wait);
+
+	if (atomic_read(&sdp->sd_log_in_flight)) {
+		do {
+			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_in_flight))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_in_flight));
+		finish_wait(&sdp->sd_log_flush_wait, &wait);
+	}
 
-	while (!list_empty(head)) {
-		lb = list_entry(head->next, struct gfs2_log_buf, lb_list);
-		list_del(&lb->lb_list);
-		bh = lb->lb_bh;
+	log_write_header(sdp, 0, 0);
+}
 
-		wait_on_buffer(bh);
-		if (!buffer_uptodate(bh))
-			gfs2_io_error_bh(sdp, bh);
-		if (lb->lb_real) {
-			while (atomic_read(&bh->b_count) != 1)  /* Grrrr... */
-				schedule();
-			free_buffer_head(bh);
-		} else
+static void gfs2_ordered_write(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+	LIST_HEAD(written);
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
+		list_move(&bd->bd_le.le_list, &written);
+		bh = bd->bd_bh;
+		if (!buffer_dirty(bh))
+			continue;
+		get_bh(bh);
+		gfs2_log_unlock(sdp);
+		lock_buffer(bh);
+		if (test_clear_buffer_dirty(bh)) {
+			bh->b_end_io = end_buffer_write_sync;
+			submit_bh(WRITE, bh);
+		} else {
+			unlock_buffer(bh);
 			brelse(bh);
-		kfree(lb);
-		flushcount++;
+		}
+		gfs2_log_lock(sdp);
 	}
+	list_splice(&written, &sdp->sd_log_le_ordered);
+	gfs2_log_unlock(sdp);
+}
 
-	/* If nothing was journaled, the header is unplanned and unwanted. */
-	if (flushcount) {
-		log_write_header(sdp, 0, 0);
-	} else {
-		unsigned int tail;
-		tail = current_tail(sdp);
+static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
 
-		gfs2_ail1_empty(sdp, 0);
-		if (sdp->sd_log_tail != tail)
-			log_pull_tail(sdp, tail);
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list);
+		bh = bd->bd_bh;
+		if (buffer_locked(bh)) {
+			get_bh(bh);
+			gfs2_log_unlock(sdp);
+			wait_on_buffer(bh);
+			brelse(bh);
+			gfs2_log_lock(sdp);
+			continue;
+		}
+		list_del_init(&bd->bd_le.le_list);
 	}
+	gfs2_log_unlock(sdp);
 }
 
 /**
@@ -640,10 +714,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 	INIT_LIST_HEAD(&ai->ai_ail1_list);
 	INIT_LIST_HEAD(&ai->ai_ail2_list);
 
-	gfs2_assert_withdraw(sdp,
-			     sdp->sd_log_num_buf + sdp->sd_log_num_jdata ==
-			     sdp->sd_log_commited_buf +
-			     sdp->sd_log_commited_databuf);
+	if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
+		printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
+		       sdp->sd_log_commited_buf);
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
+		printk(KERN_INFO "GFS2: log databuf %u %u\n",
+		       sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
+		gfs2_assert_withdraw(sdp, 0);
+	}
 	gfs2_assert_withdraw(sdp,
 			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
 
@@ -651,8 +731,11 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 	sdp->sd_log_flush_wrapped = 0;
 	ai->ai_first = sdp->sd_log_flush_head;
 
+	gfs2_ordered_write(sdp);
 	lops_before_commit(sdp);
-	if (!list_empty(&sdp->sd_log_flush_list))
+	gfs2_ordered_wait(sdp);
+
+	if (sdp->sd_log_head != sdp->sd_log_flush_head)
 		log_flush_commit(sdp);
 	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
 		gfs2_log_lock(sdp);
@@ -744,7 +827,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
-	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_jdata);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 8e7aa0f29109..dae282400627 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -52,12 +52,14 @@ int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags);
 
 int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
 void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
+void gfs2_log_incr_head(struct gfs2_sbd *sdp);
 
 struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
 struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
 				      struct buffer_head *real);
 void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
 void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd);
 
 void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 3b395c41b2f3..6c27cea761c6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -27,7 +27,104 @@
 #include "trans.h"
 #include "util.h"
 
-static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+/**
+ * gfs2_pin - Pin a buffer in memory
+ * @sdp: The superblock
+ * @bh: The buffer to be pinned
+ *
+ * The log lock must be held when calling this function
+ */
+static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
+
+	clear_buffer_dirty(bh);
+	if (test_set_buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+	if (!buffer_uptodate(bh))
+		gfs2_io_error_bh(sdp, bh);
+	bd = bh->b_private;
+	/* If this buffer is in the AIL and it has already been written
+	 * to in-place disk block, remove it from the AIL.
+	 */
+	if (bd->bd_ail)
+		list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+	get_bh(bh);
+}
+
+/**
+ * gfs2_unpin - Unpin a buffer
+ * @sdp: the filesystem the buffer belongs to
+ * @bh: The buffer to unpin
+ * @ai:
+ *
+ */
+
+static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd = bh->b_private;
+
+	gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
+
+	if (!buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+
+	lock_buffer(bh);
+	mark_buffer_dirty(bh);
+	clear_buffer_pinned(bh);
+
+	gfs2_log_lock(sdp);
+	if (bd->bd_ail) {
+		list_del(&bd->bd_ail_st_list);
+		brelse(bh);
+	} else {
+		struct gfs2_glock *gl = bd->bd_gl;
+		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
+		atomic_inc(&gl->gl_ail_count);
+	}
+	bd->bd_ail = ai;
+	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
+}
+
+
+static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh)
+{
+	return (struct gfs2_log_descriptor *)bh->b_data;
+}
+
+static inline __be64 *bh_log_ptr(struct buffer_head *bh)
+{
+	struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+	return (__force __be64 *)(ld + 1);
+}
+
+static inline __be64 *bh_ptr_end(struct buffer_head *bh)
+{
+	return (__force __be64 *)(bh->b_data + bh->b_size);
+}
+
+
+static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type)
+{
+	struct buffer_head *bh = gfs2_log_get_buf(sdp);
+	struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+	ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
+	ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
+	ld->ld_type = cpu_to_be32(ld_type);
+	ld->ld_length = 0;
+	ld->ld_data1 = 0;
+	ld->ld_data2 = 0;
+	memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
+	return bh;
+}
+
+static void __glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 {
 	struct gfs2_glock *gl;
 	struct gfs2_trans *tr = current->journal_info;
@@ -38,15 +135,19 @@ static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
 		return;
 
-	gfs2_log_lock(sdp);
-	if (!list_empty(&le->le_list)){
-		gfs2_log_unlock(sdp);
+	if (!list_empty(&le->le_list))
 		return;
-	}
+
 	gfs2_glock_hold(gl);
 	set_bit(GLF_DIRTY, &gl->gl_flags);
 	sdp->sd_log_num_gl++;
 	list_add(&le->le_list, &sdp->sd_log_le_gl);
+}
+
+static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	gfs2_log_lock(sdp);
+	__glock_lo_add(sdp, le);
 	gfs2_log_unlock(sdp);
 }
 
@@ -71,30 +172,25 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
 	struct gfs2_trans *tr;
 
+	lock_buffer(bd->bd_bh);
 	gfs2_log_lock(sdp);
-	if (!list_empty(&bd->bd_list_tr)) {
-		gfs2_log_unlock(sdp);
-		return;
-	}
+	if (!list_empty(&bd->bd_list_tr))
+		goto out;
 	tr = current->journal_info;
 	tr->tr_touched = 1;
 	tr->tr_num_buf++;
 	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
-	gfs2_log_unlock(sdp);
-
 	if (!list_empty(&le->le_list))
-		return;
-
-	gfs2_trans_add_gl(bd->bd_gl);
-
+		goto out;
+	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
 	gfs2_meta_check(sdp, bd->bd_bh);
 	gfs2_pin(sdp, bd->bd_bh);
-	gfs2_log_lock(sdp);
 	sdp->sd_log_num_buf++;
 	list_add(&le->le_list, &sdp->sd_log_le_buf);
-	gfs2_log_unlock(sdp);
-
 	tr->tr_num_buf_new++;
+out:
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
 }
 
 static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -117,8 +213,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 	struct buffer_head *bh;
 	struct gfs2_log_descriptor *ld;
 	struct gfs2_bufdata *bd1 = NULL, *bd2;
-	unsigned int total = sdp->sd_log_num_buf;
-	unsigned int offset = BUF_OFFSET;
+	unsigned int total;
 	unsigned int limit;
 	unsigned int num;
 	unsigned n;
@@ -127,22 +222,20 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 	limit = buf_limit(sdp);
 	/* for 4k blocks, limit = 503 */
 
+	gfs2_log_lock(sdp);
+	total = sdp->sd_log_num_buf;
 	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
 	while(total) {
 		num = total;
 		if (total > limit)
 			num = limit;
-		bh = gfs2_log_get_buf(sdp);
-		ld = (struct gfs2_log_descriptor *)bh->b_data;
-		ptr = (__be64 *)(bh->b_data + offset);
-		ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
-		ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
-		ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
-		ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_METADATA);
+		gfs2_log_unlock(sdp);
+		bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA);
+		gfs2_log_lock(sdp);
+		ld = bh_log_desc(bh);
+		ptr = bh_log_ptr(bh);
 		ld->ld_length = cpu_to_be32(num + 1);
 		ld->ld_data1 = cpu_to_be32(num);
-		ld->ld_data2 = cpu_to_be32(0);
-		memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
 
 		n = 0;
 		list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf,
@@ -152,21 +245,27 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 				break;
 		}
 
-		set_buffer_dirty(bh);
-		ll_rw_block(WRITE, 1, &bh);
+		gfs2_log_unlock(sdp);
+		submit_bh(WRITE, bh);
+		gfs2_log_lock(sdp);
 
 		n = 0;
 		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
 					     bd_le.le_list) {
+			get_bh(bd2->bd_bh);
+			gfs2_log_unlock(sdp);
+			lock_buffer(bd2->bd_bh);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
-			set_buffer_dirty(bh);
-			ll_rw_block(WRITE, 1, &bh);
+			submit_bh(WRITE, bh);
+			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
 		}
 
+		BUG_ON(total < num);
 		total -= num;
 	}
+	gfs2_log_unlock(sdp);
 }
 
 static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
@@ -270,11 +369,8 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	tr = current->journal_info;
 	tr->tr_touched = 1;
 	tr->tr_num_revoke++;
-
-	gfs2_log_lock(sdp);
 	sdp->sd_log_num_revoke++;
 	list_add(&le->le_list, &sdp->sd_log_le_revoke);
-	gfs2_log_unlock(sdp);
 }
 
 static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
@@ -284,32 +380,25 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	struct buffer_head *bh;
 	unsigned int offset;
 	struct list_head *head = &sdp->sd_log_le_revoke;
-	struct gfs2_revoke *rv;
+	struct gfs2_bufdata *bd;
 
 	if (!sdp->sd_log_num_revoke)
 		return;
 
-	bh = gfs2_log_get_buf(sdp);
-	ld = (struct gfs2_log_descriptor *)bh->b_data;
-	ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
-	ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
-	ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
-	ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_REVOKE);
+	bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE);
+	ld = bh_log_desc(bh);
 	ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke,
 						    sizeof(u64)));
 	ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke);
-	ld->ld_data2 = cpu_to_be32(0);
-	memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
 	offset = sizeof(struct gfs2_log_descriptor);
 
 	while (!list_empty(head)) {
-		rv = list_entry(head->next, struct gfs2_revoke, rv_le.le_list);
-		list_del_init(&rv->rv_le.le_list);
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
-			set_buffer_dirty(bh);
-			ll_rw_block(WRITE, 1, &bh);
+			submit_bh(WRITE, bh);
 
 			bh = gfs2_log_get_buf(sdp);
 			mh = (struct gfs2_meta_header *)bh->b_data;
@@ -319,15 +408,14 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 			offset = sizeof(struct gfs2_meta_header);
 		}
 
-		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno);
-		kfree(rv);
+		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
 
 		offset += sizeof(u64);
 	}
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 
-	set_buffer_dirty(bh);
-	ll_rw_block(WRITE, 1, &bh);
+	submit_bh(WRITE, bh);
 }
 
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -466,222 +554,136 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct address_space *mapping = bd->bd_bh->b_page->mapping;
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 
+	lock_buffer(bd->bd_bh);
 	gfs2_log_lock(sdp);
-	if (!list_empty(&bd->bd_list_tr)) {
-		gfs2_log_unlock(sdp);
-		return;
-	}
+	if (!list_empty(&bd->bd_list_tr))
+		goto out;
 	tr->tr_touched = 1;
 	if (gfs2_is_jdata(ip)) {
 		tr->tr_num_buf++;
 		list_add(&bd->bd_list_tr, &tr->tr_list_buf);
 	}
-	gfs2_log_unlock(sdp);
 	if (!list_empty(&le->le_list))
-		return;
+		goto out;
 
-	gfs2_trans_add_gl(bd->bd_gl);
+	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
 	if (gfs2_is_jdata(ip)) {
-		sdp->sd_log_num_jdata++;
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_databuf_new++;
+		sdp->sd_log_num_databuf++;
+		list_add(&le->le_list, &sdp->sd_log_le_databuf);
+	} else {
+		list_add(&le->le_list, &sdp->sd_log_le_ordered);
 	}
-	gfs2_log_lock(sdp);
-	sdp->sd_log_num_databuf++;
-	list_add(&le->le_list, &sdp->sd_log_le_databuf);
+out:
 	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
 }
 
-static int gfs2_check_magic(struct buffer_head *bh)
+static void gfs2_check_magic(struct buffer_head *bh)
 {
-	struct page *page = bh->b_page;
 	void *kaddr;
 	__be32 *ptr;
-	int rv = 0;
 
-	kaddr = kmap_atomic(page, KM_USER0);
+	clear_buffer_escaped(bh);
+	kaddr = kmap_atomic(bh->b_page, KM_USER0);
 	ptr = kaddr + bh_offset(bh);
 	if (*ptr == cpu_to_be32(GFS2_MAGIC))
-		rv = 1;
+		set_buffer_escaped(bh);
 	kunmap_atomic(kaddr, KM_USER0);
-
-	return rv;
 }
 
-/**
- * databuf_lo_before_commit - Scan the data buffers, writing as we go
- *
- * Here we scan through the lists of buffers and make the assumption
- * that any buffer thats been pinned is being journaled, and that
- * any unpinned buffer is an ordered write data buffer and therefore
- * will be written back rather than journaled.
- */
-static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
+static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			      struct list_head *list, struct list_head *done,
+			      unsigned int n)
 {
-	LIST_HEAD(started);
-	struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt;
-	struct buffer_head *bh = NULL,*bh1 = NULL;
+	struct buffer_head *bh1;
 	struct gfs2_log_descriptor *ld;
-	unsigned int limit;
-	unsigned int total_dbuf;
-	unsigned int total_jdata = sdp->sd_log_num_jdata;
-	unsigned int num, n;
-	__be64 *ptr = NULL;
+	struct gfs2_bufdata *bd;
+	__be64 *ptr;
+
+	if (!bh)
+		return;
 
-	limit = databuf_limit(sdp);
+	ld = bh_log_desc(bh);
+	ld->ld_length = cpu_to_be32(n + 1);
+	ld->ld_data1 = cpu_to_be32(n);
 
-	/*
-	 * Start writing ordered buffers, write journaled buffers
-	 * into the log along with a header
-	 */
+	ptr = bh_log_ptr(bh);
+	
+	get_bh(bh);
+	submit_bh(WRITE, bh);
 	gfs2_log_lock(sdp);
-	total_dbuf = sdp->sd_log_num_databuf;
-	bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf,
-				       bd_le.le_list);
-	while(total_dbuf) {
-		num = total_jdata;
-		if (num > limit)
-			num = limit;
-		n = 0;
-		list_for_each_entry_safe_continue(bd1, bdt,
-						  &sdp->sd_log_le_databuf,
-						  bd_le.le_list) {
-			/* store off the buffer head in a local ptr since
-			 * gfs2_bufdata might change when we drop the log lock
-			 */
-			bh1 = bd1->bd_bh;
-
-			/* An ordered write buffer */
-			if (bh1 && !buffer_pinned(bh1)) {
-				list_move(&bd1->bd_le.le_list, &started);
-				if (bd1 == bd2) {
-					bd2 = NULL;
-					bd2 = list_prepare_entry(bd2,
-							&sdp->sd_log_le_databuf,
-							bd_le.le_list);
-				}
-				total_dbuf--;
-				if (bh1) {
-					if (buffer_dirty(bh1)) {
-						get_bh(bh1);
-
-						gfs2_log_unlock(sdp);
-
-						ll_rw_block(SWRITE, 1, &bh1);
-						brelse(bh1);
-
-						gfs2_log_lock(sdp);
-					}
-					continue;
-				}
-				continue;
-			} else if (bh1) { /* A journaled buffer */
-				int magic;
-				gfs2_log_unlock(sdp);
-				if (!bh) {
-					bh = gfs2_log_get_buf(sdp);
-					ld = (struct gfs2_log_descriptor *)
-					     bh->b_data;
-					ptr = (__be64 *)(bh->b_data +
-							 DATABUF_OFFSET);
-					ld->ld_header.mh_magic =
-						cpu_to_be32(GFS2_MAGIC);
-					ld->ld_header.mh_type =
-						cpu_to_be32(GFS2_METATYPE_LD);
-					ld->ld_header.mh_format =
-						cpu_to_be32(GFS2_FORMAT_LD);
-					ld->ld_type =
-						cpu_to_be32(GFS2_LOG_DESC_JDATA);
-					ld->ld_length = cpu_to_be32(num + 1);
-					ld->ld_data1 = cpu_to_be32(num);
-					ld->ld_data2 = cpu_to_be32(0);
-					memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
-				}
-				magic = gfs2_check_magic(bh1);
-				*ptr++ = cpu_to_be64(bh1->b_blocknr);
-				*ptr++ = cpu_to_be64((__u64)magic);
-				clear_buffer_escaped(bh1);
-				if (unlikely(magic != 0))
-					set_buffer_escaped(bh1);
-				gfs2_log_lock(sdp);
-				if (++n >= num)
-					break;
-			} else if (!bh1) {
-				total_dbuf--;
-				sdp->sd_log_num_databuf--;
-				list_del_init(&bd1->bd_le.le_list);
-				if (bd1 == bd2) {
-					bd2 = NULL;
-					bd2 = list_prepare_entry(bd2,
-						&sdp->sd_log_le_databuf,
-						bd_le.le_list);
-                                }
-				kmem_cache_free(gfs2_bufdata_cachep, bd1);
-			}
+	while(!list_empty(list)) {
+		bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
+		list_move_tail(&bd->bd_le.le_list, done);
+		get_bh(bd->bd_bh);
+		while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) {
+			gfs2_log_incr_head(sdp);
+			ptr += 2;
 		}
 		gfs2_log_unlock(sdp);
-		if (bh) {
-			set_buffer_mapped(bh);
-			set_buffer_dirty(bh);
-			ll_rw_block(WRITE, 1, &bh);
-			bh = NULL;
+		lock_buffer(bd->bd_bh);
+		if (buffer_escaped(bd->bd_bh)) {
+			void *kaddr;
+			bh1 = gfs2_log_get_buf(sdp);
+			kaddr = kmap_atomic(bd->bd_bh->b_page, KM_USER0);
+			memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh),
+			       bh1->b_size);
+			kunmap_atomic(kaddr, KM_USER0);
+			*(__be32 *)bh1->b_data = 0;
+			clear_buffer_escaped(bd->bd_bh);
+			unlock_buffer(bd->bd_bh);
+			brelse(bd->bd_bh);
+		} else {
+			bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
 		}
-		n = 0;
+		submit_bh(WRITE, bh1);
 		gfs2_log_lock(sdp);
-		list_for_each_entry_continue(bd2, &sdp->sd_log_le_databuf,
-					     bd_le.le_list) {
-			if (!bd2->bd_bh)
-				continue;
-			/* copy buffer if it needs escaping */
-			gfs2_log_unlock(sdp);
-			if (unlikely(buffer_escaped(bd2->bd_bh))) {
-				void *kaddr;
-				struct page *page = bd2->bd_bh->b_page;
-				bh = gfs2_log_get_buf(sdp);
-				kaddr = kmap_atomic(page, KM_USER0);
-				memcpy(bh->b_data,
-				       kaddr + bh_offset(bd2->bd_bh),
-				       sdp->sd_sb.sb_bsize);
-				kunmap_atomic(kaddr, KM_USER0);
-				*(__be32 *)bh->b_data = 0;
-			} else {
-				bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
-			}
-			set_buffer_dirty(bh);
-			ll_rw_block(WRITE, 1, &bh);
-			gfs2_log_lock(sdp);
-			if (++n >= num)
-				break;
-		}
-		bh = NULL;
-		BUG_ON(total_dbuf < num);
-		total_dbuf -= num;
-		total_jdata -= num;
+		ptr += 2;
 	}
 	gfs2_log_unlock(sdp);
+	brelse(bh);
+}
 
-	/* Wait on all ordered buffers */
-	while (!list_empty(&started)) {
-		gfs2_log_lock(sdp);
-		bd1 = list_entry(started.next, struct gfs2_bufdata,
-				 bd_le.le_list);
-		list_del_init(&bd1->bd_le.le_list);
-		sdp->sd_log_num_databuf--;
-		bh = bd1->bd_bh;
-		if (bh) {
-			bh->b_private = NULL;
-			get_bh(bh);
-			gfs2_log_unlock(sdp);
-			wait_on_buffer(bh);
-			brelse(bh);
-		} else
-			gfs2_log_unlock(sdp);
+/**
+ * databuf_lo_before_commit - Scan the data buffers, writing as we go
+ *
+ */
 
-		kmem_cache_free(gfs2_bufdata_cachep, bd1);
-	}
+static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
+{
+	struct gfs2_bufdata *bd = NULL;
+	struct buffer_head *bh = NULL;
+	unsigned int n = 0;
+	__be64 *ptr = NULL, *end = NULL;
+	LIST_HEAD(processed);
+	LIST_HEAD(in_progress);
 
-	/* We've removed all the ordered write bufs here, so only jdata left */
-	gfs2_assert_warn(sdp, sdp->sd_log_num_databuf == sdp->sd_log_num_jdata);
+	gfs2_log_lock(sdp);
+	while (!list_empty(&sdp->sd_log_le_databuf)) {
+		if (ptr == end) {
+			gfs2_log_unlock(sdp);
+			gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+			n = 0;
+			bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA);
+			ptr = bh_log_ptr(bh);
+			end = bh_ptr_end(bh) - 1;
+			gfs2_log_lock(sdp);
+			continue;
+		}
+		bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list);
+		list_move_tail(&bd->bd_le.le_list, &in_progress);
+		gfs2_check_magic(bd->bd_bh);
+		*ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr);
+		*ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0);
+		n++;
+	}
+	gfs2_log_unlock(sdp);
+	gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+	gfs2_log_lock(sdp);
+	list_splice(&processed, &sdp->sd_log_le_databuf);
+	gfs2_log_unlock(sdp);
 }
 
 static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -765,11 +767,9 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
 		list_del_init(&bd->bd_le.le_list);
 		sdp->sd_log_num_databuf--;
-		sdp->sd_log_num_jdata--;
 		gfs2_unpin(sdp, bd->bd_bh, ai);
 	}
 	gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf);
-	gfs2_assert_warn(sdp, !sdp->sd_log_num_jdata);
 }
 
 
@@ -817,10 +817,10 @@ const struct gfs2_log_operations gfs2_databuf_lops = {
 
 const struct gfs2_log_operations *gfs2_log_ops[] = {
 	&gfs2_glock_lops,
+	&gfs2_databuf_lops,
 	&gfs2_buf_lops,
-	&gfs2_revoke_lops,
 	&gfs2_rg_lops,
-	&gfs2_databuf_lops,
+	&gfs2_revoke_lops,
 	NULL,
 };
 
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index d5d4e68b8807..79c91fd8381b 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -107,6 +107,8 @@ static int __init init_gfs2_fs(void)
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
 fail:
+	gfs2_glock_exit();
+
 	if (gfs2_bufdata_cachep)
 		kmem_cache_destroy(gfs2_bufdata_cachep);
 
@@ -127,6 +129,7 @@ fail:
 
 static void __exit exit_gfs2_fs(void)
 {
+	gfs2_glock_exit();
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 8da343b34ae7..4da423985e4f 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -297,74 +297,35 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 		unlock_page(bh->b_page);
 }
 
-/**
- * gfs2_pin - Pin a buffer in memory
- * @sdp: the filesystem the buffer belongs to
- * @bh: The buffer to be pinned
- *
- */
-
-void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host);
 	struct gfs2_bufdata *bd = bh->b_private;
-
-	gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
-
-	if (test_set_buffer_pinned(bh))
-		gfs2_assert_withdraw(sdp, 0);
-
-	wait_on_buffer(bh);
-
-	/* If this buffer is in the AIL and it has already been written
-	   to in-place disk block, remove it from the AIL. */
-
-	gfs2_log_lock(sdp);
-	if (bd->bd_ail && !buffer_in_io(bh))
-		list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
-	gfs2_log_unlock(sdp);
-
-	clear_buffer_dirty(bh);
-	wait_on_buffer(bh);
-
-	if (!buffer_uptodate(bh))
-		gfs2_io_error_bh(sdp, bh);
-
-	get_bh(bh);
-}
-
-/**
- * gfs2_unpin - Unpin a buffer
- * @sdp: the filesystem the buffer belongs to
- * @bh: The buffer to unpin
- * @ai:
- *
- */
-
-void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
-	        struct gfs2_ail *ai)
-{
-	struct gfs2_bufdata *bd = bh->b_private;
-
-	gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
-
-	if (!buffer_pinned(bh))
-		gfs2_assert_withdraw(sdp, 0);
-
-	mark_buffer_dirty(bh);
-	clear_buffer_pinned(bh);
-
-	gfs2_log_lock(sdp);
-	if (bd->bd_ail) {
-		list_del(&bd->bd_ail_st_list);
+	if (test_clear_buffer_pinned(bh)) {
+		list_del_init(&bd->bd_le.le_list);
+		if (meta) {
+			gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
+			sdp->sd_log_num_buf--;
+			tr->tr_num_buf_rm++;
+		} else {
+			gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
+			sdp->sd_log_num_databuf--;
+			tr->tr_num_databuf_rm++;
+		}
+		tr->tr_touched = 1;
 		brelse(bh);
-	} else {
-		struct gfs2_glock *gl = bd->bd_gl;
-		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
-		atomic_inc(&gl->gl_ail_count);
 	}
-	bd->bd_ail = ai;
-	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
-	gfs2_log_unlock(sdp);
+	if (bd) {
+		if (bd->bd_ail) {
+			gfs2_remove_from_ail(NULL, bd);
+			bh->b_private = NULL;
+			bd->bd_bh = NULL;
+			bd->bd_blkno = bh->b_blocknr;
+			gfs2_trans_add_revoke(sdp, bd);
+		}
+	}
+	clear_buffer_dirty(bh);
+	clear_buffer_uptodate(bh);
 }
 
 /**
@@ -383,44 +344,11 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
 	while (blen) {
 		bh = getbuf(ip->i_gl, bstart, NO_CREATE);
 		if (bh) {
-			struct gfs2_bufdata *bd = bh->b_private;
-
-			if (test_clear_buffer_pinned(bh)) {
-				struct gfs2_trans *tr = current->journal_info;
-				struct gfs2_inode *bh_ip =
-					GFS2_I(bh->b_page->mapping->host);
-
-				gfs2_log_lock(sdp);
-				list_del_init(&bd->bd_le.le_list);
-				gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
-				sdp->sd_log_num_buf--;
-				gfs2_log_unlock(sdp);
-				if (bh_ip->i_inode.i_private != NULL)
-					tr->tr_num_databuf_rm++;
-				else
-					tr->tr_num_buf_rm++;
-				brelse(bh);
-			}
-			if (bd) {
-				gfs2_log_lock(sdp);
-				if (bd->bd_ail) {
-					u64 blkno = bh->b_blocknr;
-					bd->bd_ail = NULL;
-					list_del(&bd->bd_ail_st_list);
-					list_del(&bd->bd_ail_gl_list);
-					atomic_dec(&bd->bd_gl->gl_ail_count);
-					brelse(bh);
-					gfs2_log_unlock(sdp);
-					gfs2_trans_add_revoke(sdp, blkno);
-				} else
-					gfs2_log_unlock(sdp);
-			}
-
 			lock_buffer(bh);
-			clear_buffer_dirty(bh);
-			clear_buffer_uptodate(bh);
+			gfs2_log_lock(sdp);
+			gfs2_remove_from_journal(bh, current->journal_info, 1);
+			gfs2_log_unlock(sdp);
 			unlock_buffer(bh);
-
 			brelse(bh);
 		}
 
@@ -446,10 +374,10 @@ void gfs2_meta_cache_flush(struct gfs2_inode *ip)
 
 	for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) {
 		bh_slot = &ip->i_cache[x];
-		if (!*bh_slot)
-			break;
-		brelse(*bh_slot);
-		*bh_slot = NULL;
+		if (*bh_slot) {
+			brelse(*bh_slot);
+			*bh_slot = NULL;
+		}
 	}
 
 	spin_unlock(&ip->i_spin);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 527bf19d9690..b7048222ebb4 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -50,9 +50,9 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 
 void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 			 int meta);
-void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
-void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		struct gfs2_ail *ai);
+
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
+			      int meta);
 
 void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
 
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index 4864659555d4..b941f9f9f958 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -42,6 +42,7 @@ enum {
 	Opt_nosuiddir,
 	Opt_data_writeback,
 	Opt_data_ordered,
+	Opt_err,
 };
 
 static match_table_t tokens = {
@@ -64,7 +65,8 @@ static match_table_t tokens = {
 	{Opt_suiddir, "suiddir"},
 	{Opt_nosuiddir, "nosuiddir"},
 	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"}
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_err, NULL}
 };
 
 /**
@@ -237,6 +239,7 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
 			break;
+		case Opt_err:
 		default:
 			fs_info(sdp, "unknown option: %s\n", o);
 			error = -EINVAL;
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index 42a5f58f6fca..873a511ef2be 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -90,7 +90,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 	error = gfs2_block_map(inode, lblock, 0, bh_result);
 	if (error)
 		return error;
-	if (bh_result->b_blocknr == 0)
+	if (!buffer_mapped(bh_result))
 		return -EIO;
 	return 0;
 }
@@ -414,7 +414,8 @@ static int gfs2_prepare_write(struct file *file, struct page *page,
 	if (ind_blocks || data_blocks)
 		rblocks += RES_STATFS + RES_QUOTA;
 
-	error = gfs2_trans_begin(sdp, rblocks, 0);
+	error = gfs2_trans_begin(sdp, rblocks,
+				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
 	if (error)
 		goto out_trans_fail;
 
@@ -616,58 +617,50 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
 	return dblock;
 }
 
-static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
+static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
 {
 	struct gfs2_bufdata *bd;
 
+	lock_buffer(bh);
 	gfs2_log_lock(sdp);
+	clear_buffer_dirty(bh);
 	bd = bh->b_private;
 	if (bd) {
-		bd->bd_bh = NULL;
-		bh->b_private = NULL;
-		if (!bd->bd_ail && list_empty(&bd->bd_le.le_list))
-			kmem_cache_free(gfs2_bufdata_cachep, bd);
+		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+			list_del_init(&bd->bd_le.le_list);
+		else
+			gfs2_remove_from_journal(bh, current->journal_info, 0);
 	}
-	gfs2_log_unlock(sdp);
-
-	lock_buffer(bh);
-	clear_buffer_dirty(bh);
 	bh->b_bdev = NULL;
 	clear_buffer_mapped(bh);
 	clear_buffer_req(bh);
 	clear_buffer_new(bh);
-	clear_buffer_delay(bh);
+	gfs2_log_unlock(sdp);
 	unlock_buffer(bh);
 }
 
 static void gfs2_invalidatepage(struct page *page, unsigned long offset)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-	struct buffer_head *head, *bh, *next;
-	unsigned int curr_off = 0;
+	struct buffer_head *bh, *head;
+	unsigned long pos = 0;
 
 	BUG_ON(!PageLocked(page));
 	if (offset == 0)
 		ClearPageChecked(page);
 	if (!page_has_buffers(page))
-		return;
+		goto out;
 
 	bh = head = page_buffers(page);
 	do {
-		unsigned int next_off = curr_off + bh->b_size;
-		next = bh->b_this_page;
-
-		if (offset <= curr_off)
-			discard_buffer(sdp, bh);
-
-		curr_off = next_off;
-		bh = next;
+		if (offset <= pos)
+			gfs2_discard(sdp, bh);
+		pos += bh->b_size;
+		bh = bh->b_this_page;
 	} while (bh != head);
-
-	if (!offset)
+out:
+	if (offset == 0)
 		try_to_release_page(page, 0);
-
-	return;
 }
 
 /**
@@ -736,59 +729,6 @@ out:
 }
 
 /**
- * stuck_releasepage - We're stuck in gfs2_releasepage().  Print stuff out.
- * @bh: the buffer we're stuck on
- *
- */
-
-static void stuck_releasepage(struct buffer_head *bh)
-{
-	struct inode *inode = bh->b_page->mapping->host;
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_bufdata *bd = bh->b_private;
-	struct gfs2_glock *gl;
-static unsigned limit = 0;
-
-	if (limit > 3)
-		return;
-	limit++;
-
-	fs_warn(sdp, "stuck in gfs2_releasepage() %p\n", inode);
-	fs_warn(sdp, "blkno = %llu, bh->b_count = %d\n",
-		(unsigned long long)bh->b_blocknr, atomic_read(&bh->b_count));
-	fs_warn(sdp, "pinned = %u\n", buffer_pinned(bh));
-	fs_warn(sdp, "bh->b_private = %s\n", (bd) ? "!NULL" : "NULL");
-
-	if (!bd)
-		return;
-
-	gl = bd->bd_gl;
-
-	fs_warn(sdp, "gl = (%u, %llu)\n",
-		gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number);
-
-	fs_warn(sdp, "bd_list_tr = %s, bd_le.le_list = %s\n",
-		(list_empty(&bd->bd_list_tr)) ? "no" : "yes",
-		(list_empty(&bd->bd_le.le_list)) ? "no" : "yes");
-
-	if (gl->gl_ops == &gfs2_inode_glops) {
-		struct gfs2_inode *ip = gl->gl_object;
-		unsigned int x;
-
-		if (!ip)
-			return;
-
-		fs_warn(sdp, "ip = %llu %llu\n",
-			(unsigned long long)ip->i_no_formal_ino,
-			(unsigned long long)ip->i_no_addr);
-
-		for (x = 0; x < GFS2_MAX_META_HEIGHT; x++)
-			fs_warn(sdp, "ip->i_cache[%u] = %s\n",
-				x, (ip->i_cache[x]) ? "!NULL" : "NULL");
-	}
-}
-
-/**
  * gfs2_releasepage - free the metadata associated with a page
  * @page: the page that's being released
  * @gfp_mask: passed from Linux VFS, ignored by us
@@ -805,41 +745,39 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
 	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
 	struct buffer_head *bh, *head;
 	struct gfs2_bufdata *bd;
-	unsigned long t = jiffies + gfs2_tune_get(sdp, gt_stall_secs) * HZ;
 
 	if (!page_has_buffers(page))
-		goto out;
+		return 0;
 
+	gfs2_log_lock(sdp);
 	head = bh = page_buffers(page);
 	do {
-		while (atomic_read(&bh->b_count)) {
-			if (!atomic_read(&aspace->i_writecount))
-				return 0;
-
-			if (!(gfp_mask & __GFP_WAIT))
-				return 0;
-
-			if (time_after_eq(jiffies, t)) {
-				stuck_releasepage(bh);
-				/* should we withdraw here? */
-				return 0;
-			}
-
-			yield();
-		}
-
+		if (atomic_read(&bh->b_count))
+			goto cannot_release;
+		bd = bh->b_private;
+		if (bd && bd->bd_ail)
+			goto cannot_release;
 		gfs2_assert_warn(sdp, !buffer_pinned(bh));
 		gfs2_assert_warn(sdp, !buffer_dirty(bh));
+		bh = bh->b_this_page;
+	} while(bh != head);
+	gfs2_log_unlock(sdp);
 
+	head = bh = page_buffers(page);
+	do {
 		gfs2_log_lock(sdp);
 		bd = bh->b_private;
 		if (bd) {
 			gfs2_assert_warn(sdp, bd->bd_bh == bh);
 			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
-			gfs2_assert_warn(sdp, !bd->bd_ail);
-			bd->bd_bh = NULL;
-			if (!list_empty(&bd->bd_le.le_list))
-				bd = NULL;
+			if (!list_empty(&bd->bd_le.le_list)) {
+				if (!buffer_pinned(bh))
+					list_del_init(&bd->bd_le.le_list);
+				else
+					bd = NULL;
+			}
+			if (bd)
+				bd->bd_bh = NULL;
 			bh->b_private = NULL;
 		}
 		gfs2_log_unlock(sdp);
@@ -849,8 +787,10 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
 		bh = bh->b_this_page;
 	} while (bh != head);
 
-out:
 	return try_to_free_buffers(page);
+cannot_release:
+	gfs2_log_unlock(sdp);
+	return 0;
 }
 
 const struct address_space_operations gfs2_file_aops = {
diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c
index b8312edee0e4..e2d1347796a9 100644
--- a/fs/gfs2/ops_export.c
+++ b/fs/gfs2/ops_export.c
@@ -237,7 +237,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj)
 
 	inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
 					inum->no_addr,
-					0);
+					0, 0);
 	if (!inode)
 		goto fail;
 	if (IS_ERR(inode)) {
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 94d76ace0b95..46a9e10ff17b 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -571,7 +571,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 
 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE 
+		| GL_FLOCK;
 
 	mutex_lock(&fp->f_fl_mutex);
 
@@ -579,21 +580,19 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (gl) {
 		if (fl_gh->gh_state == state)
 			goto out;
-		gfs2_glock_hold(gl);
 		flock_lock_file_wait(file,
 				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_uninit(fl_gh);
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
 		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
 				      ip->i_no_addr, &gfs2_flock_glops,
 				      CREATE, &gl);
 		if (error)
 			goto out;
+		gfs2_holder_init(gl, state, flags, fl_gh);
+		gfs2_glock_put(gl);
 	}
-
-	gfs2_holder_init(gl, state, flags, fl_gh);
-	gfs2_glock_put(gl);
-
 	error = gfs2_glock_nq(fl_gh);
 	if (error) {
 		gfs2_holder_uninit(fl_gh);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index cf5aa5050548..17de58e83d92 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -28,18 +28,18 @@
 #include "lm.h"
 #include "mount.h"
 #include "ops_fstype.h"
+#include "ops_dentry.h"
 #include "ops_super.h"
 #include "recovery.h"
 #include "rgrp.h"
 #include "super.h"
 #include "sys.h"
 #include "util.h"
+#include "log.h"
 
 #define DO 0
 #define UNDO 1
 
-extern struct dentry_operations gfs2_dops;
-
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp;
@@ -82,13 +82,15 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
 	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
 	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
 
 	mutex_init(&sdp->sd_log_reserve_mutex);
 	INIT_LIST_HEAD(&sdp->sd_ail1_list);
 	INIT_LIST_HEAD(&sdp->sd_ail2_list);
 
 	init_rwsem(&sdp->sd_log_flush_lock);
-	INIT_LIST_HEAD(&sdp->sd_log_flush_list);
+	atomic_set(&sdp->sd_log_in_flight, 0);
+	init_waitqueue_head(&sdp->sd_log_flush_wait);
 
 	INIT_LIST_HEAD(&sdp->sd_revoke_list);
 
@@ -145,7 +147,8 @@ static int init_names(struct gfs2_sbd *sdp, int silent)
 	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
 	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
 
-	while ((table = strchr(sdp->sd_table_name, '/')))
+	table = sdp->sd_table_name;
+	while ((table = strchr(table, '/')))
 		*table = '_';
 
 out:
@@ -161,14 +164,6 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
 	if (undo)
 		goto fail_trans;
 
-	p = kthread_run(gfs2_scand, sdp, "gfs2_scand");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start scand thread: %d\n", error);
-		return error;
-	}
-	sdp->sd_scand_process = p;
-
 	for (sdp->sd_glockd_num = 0;
 	     sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
 	     sdp->sd_glockd_num++) {
@@ -229,14 +224,13 @@ fail:
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
 
-	kthread_stop(sdp->sd_scand_process);
 	return error;
 }
 
 static inline struct inode *gfs2_lookup_root(struct super_block *sb,
 					     u64 no_addr)
 {
-	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
+	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
 }
 
 static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
@@ -301,8 +295,9 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
 		fs_err(sdp, "can't get root dentry\n");
 		error = -ENOMEM;
 		iput(inode);
-	}
-	sb->s_root->d_op = &gfs2_dops;
+	} else
+		sb->s_root->d_op = &gfs2_dops;
+	
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
 	return error;
@@ -368,7 +363,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | GL_EXACT,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal inode glock: %d\n",
@@ -818,7 +813,6 @@ static struct super_block* get_gfs2_sb(const char *dev_name)
 	struct nameidata nd;
 	struct file_system_type *fstype;
 	struct super_block *sb = NULL, *s;
-	struct list_head *l;
 	int error;
 
 	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
@@ -830,8 +824,7 @@ static struct super_block* get_gfs2_sb(const char *dev_name)
 	error = vfs_getattr(nd.mnt, nd.dentry, &stat);
 
 	fstype = get_fs_type("gfs2");
-	list_for_each(l, &fstype->fs_supers) {
-		s = list_entry(l, struct super_block, s_instances);
+	list_for_each_entry(s, &fstype->fs_supers, s_instances) {
 		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
 		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
 			sb = s;
@@ -861,7 +854,7 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 		error = -ENOENT;
 		goto error;
 	}
-	sdp = (struct gfs2_sbd*) sb->s_fs_info;
+	sdp = sb->s_fs_info;
 	if (sdp->sd_vfs_meta) {
 		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
 		error = -EBUSY;
@@ -896,7 +889,10 @@ error:
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	gfs2_delete_debugfs_file(sb->s_fs_info);
+	if (sb->s_fs_info) {
+		gfs2_delete_debugfs_file(sb->s_fs_info);
+		gfs2_meta_syncfs(sb->s_fs_info);
+	}
 	kill_block_super(sb);
 }
 
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 911c115b5c6c..291f0c7eaa3b 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -69,7 +69,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
 			mark_inode_dirty(inode);
 			break;
 		} else if (PTR_ERR(inode) != -EEXIST ||
-			   (nd->intent.open.flags & O_EXCL)) {
+			   (nd && (nd->intent.open.flags & O_EXCL))) {
 			gfs2_holder_uninit(ghs);
 			return PTR_ERR(inode);
 		}
@@ -278,17 +278,25 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
 
-	error = gfs2_glock_nq_m(3, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_dir_del(dip, &dentry->d_name);
         if (error)
@@ -298,12 +306,15 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 out_end_trans:
 	gfs2_trans_end(sdp);
-out_gunlock:
-	gfs2_glock_dq_m(3, ghs);
-out:
-	gfs2_holder_uninit(ghs);
-	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
 	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
@@ -894,12 +905,17 @@ static int gfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
 static int setattr_size(struct inode *inode, struct iattr *attr)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	int error;
 
 	if (attr->ia_size != ip->i_di.di_size) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
 		if (error)
 			return error;
+		error = vmtruncate(inode, attr->ia_size);
+		gfs2_trans_end(sdp);
+		if (error) 
+			return error;
 	}
 
 	error = gfs2_truncatei(ip, attr->ia_size);
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index 603d940f1159..950f31460e8b 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -92,7 +92,6 @@ static void gfs2_put_super(struct super_block *sb)
 	kthread_stop(sdp->sd_recoverd_process);
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
-	kthread_stop(sdp->sd_scand_process);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		error = gfs2_make_fs_ro(sdp);
@@ -456,12 +455,15 @@ static void gfs2_delete_inode(struct inode *inode)
 	}
 
 	error = gfs2_dinode_dealloc(ip);
-	/*
-	 * Must do this before unlock to avoid trying to write back
-	 * potentially dirty data now that inode no longer exists
-	 * on disk.
-	 */
+	if (error)
+		goto out_unlock;
+
+	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_unlock;
+	/* Needs to be done before glock release & also in a transaction */
 	truncate_inode_pages(&inode->i_data, 0);
+	gfs2_trans_end(sdp);
 
 out_unlock:
 	gfs2_glock_dq(&ip->i_iopen_gh);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6e546ee8f3d4..addb51e0f135 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -70,6 +70,7 @@ struct gfs2_quota_host {
 	u64 qu_limit;
 	u64 qu_warn;
 	s64 qu_value;
+	u32 qu_ll_next;
 };
 
 struct gfs2_quota_change_host {
@@ -580,6 +581,7 @@ static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf)
 	qu->qu_limit = be64_to_cpu(str->qu_limit);
 	qu->qu_warn = be64_to_cpu(str->qu_warn);
 	qu->qu_value = be64_to_cpu(str->qu_value);
+	qu->qu_ll_next = be32_to_cpu(str->qu_ll_next);
 }
 
 static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)
@@ -589,6 +591,7 @@ static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)
 	str->qu_limit = cpu_to_be64(qu->qu_limit);
 	str->qu_warn = cpu_to_be64(qu->qu_warn);
 	str->qu_value = cpu_to_be64(qu->qu_value);
+	str->qu_ll_next = cpu_to_be32(qu->qu_ll_next);
 	memset(&str->qu_reserved, 0, sizeof(str->qu_reserved));
 }
 
@@ -614,6 +617,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	s64 value;
 	int err = -EIO;
 
+	if (gfs2_is_stuffed(ip)) {
+		struct gfs2_alloc *al = NULL;
+		al = gfs2_alloc_get(ip);
+		/* just request 1 blk */
+		al->al_requested = 1;
+		gfs2_inplace_reserve(ip);
+		gfs2_unstuff_dinode(ip, NULL);
+		gfs2_inplace_release(ip);
+		gfs2_alloc_put(ip);
+	}
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 5ada38c99a2c..beb6c7ac0086 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -469,7 +469,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 		};
 
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP, &ji_gh);
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
 		if (error)
 			goto fail_gunlock_j;
 	} else {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ce48c4594ec8..708c287e1d0e 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -31,6 +31,7 @@
 #include "inode.h"
 
 #define BFITNOENT ((u32)~0)
+#define NO_BLOCK ((u64)~0)
 
 /*
  * These routines are used by the resource group routines (rgrp.c)
@@ -116,8 +117,7 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
  * @buffer: the buffer that holds the bitmaps
  * @buflen: the length (in bytes) of the buffer
  * @goal: start search at this block's bit-pair (within @buffer)
- * @old_state: GFS2_BLKST_XXX the state of the block we're looking for;
- *       bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0)
+ * @old_state: GFS2_BLKST_XXX the state of the block we're looking for.
  *
  * Scope of @goal and returned block number is only within this bitmap buffer,
  * not entire rgrp or filesystem.  @buffer will be offset from the actual
@@ -137,9 +137,13 @@ static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
 	byte = buffer + (goal / GFS2_NBBY);
 	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
 	end = buffer + buflen;
-	alloc = (old_state & 1) ? 0 : 0x55;
+	alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0;
 
 	while (byte < end) {
+		/* If we're looking for a free block we can eliminate all
+		   bitmap settings with 0x55, which represents four data
+		   blocks in a row.  If we're looking for a data block, we can
+		   eliminate 0x00 which corresponds to four free blocks. */
 		if ((*byte & 0x55) == alloc) {
 			blk += (8 - bit) >> 1;
 
@@ -859,23 +863,28 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
 static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 {
 	struct inode *inode;
-	u32 goal = 0;
+	u32 goal = 0, block;
 	u64 no_addr;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
 
 	for(;;) {
 		if (goal >= rgd->rd_data)
 			break;
-		goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
-				    GFS2_BLKST_UNLINKED);
-		if (goal == BFITNOENT)
+		down_write(&sdp->sd_log_flush_lock);
+		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
+				     GFS2_BLKST_UNLINKED);
+		up_write(&sdp->sd_log_flush_lock);
+		if (block == BFITNOENT)
 			break;
-		no_addr = goal + rgd->rd_data0;
+		/* rgblk_search can return a block < goal, so we need to
+		   keep it marching forward. */
+		no_addr = block + rgd->rd_data0;
 		goal++;
-		if (no_addr < *last_unlinked)
+		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
-					  no_addr, -1);
+					  no_addr, -1, 1);
 		if (!IS_ERR(inode))
 			return inode;
 	}
@@ -1152,7 +1161,7 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
 	struct gfs2_alloc *al = &ip->i_alloc;
 	struct inode *inode;
 	int error = 0;
-	u64 last_unlinked = 0;
+	u64 last_unlinked = NO_BLOCK;
 
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;
@@ -1289,7 +1298,9 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
-		if (bi->bi_clone)
+		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
+		   bitmaps, so we must search the originals for that. */
+		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
 			blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset,
 					  bi->bi_len, goal, old_state);
 		else
@@ -1305,9 +1316,7 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 		goal = 0;
 	}
 
-	if (old_state != new_state) {
-		gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT);
-
+	if (blk != BFITNOENT && old_state != new_state) {
 		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
 		gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset,
 			    bi->bi_len, blk, new_state);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index f916b9740c75..dd3e737f528e 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -58,7 +58,6 @@ void gfs2_tune_init(struct gfs2_tune *gt)
 	gt->gt_incore_log_blocks = 1024;
 	gt->gt_log_flush_secs = 60;
 	gt->gt_jindex_refresh_secs = 60;
-	gt->gt_scand_secs = 15;
 	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quotad_secs = 5;
@@ -160,18 +159,15 @@ int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 }
 
 
-static int end_bio_io_page(struct bio *bio, unsigned int bytes_done, int error)
+static void end_bio_io_page(struct bio *bio, int error)
 {
 	struct page *page = bio->bi_private;
-	if (bio->bi_size)
-		return 1;
 
 	if (!error)
 		SetPageUptodate(page);
 	else
 		printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
 	unlock_page(page);
-	return 0;
 }
 
 static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index c26c21b53c19..06e0b7768d97 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -222,7 +222,6 @@ static struct kobj_type gfs2_ktype = {
 };
 
 static struct kset gfs2_kset = {
-	.kobj   = {.name = "gfs2"},
 	.ktype  = &gfs2_ktype,
 };
 
@@ -442,7 +441,6 @@ TUNE_ATTR(quota_simul_sync, 1);
 TUNE_ATTR(quota_cache_secs, 1);
 TUNE_ATTR(stall_secs, 1);
 TUNE_ATTR(statfs_quantum, 1);
-TUNE_ATTR_DAEMON(scand_secs, scand_process);
 TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process);
 TUNE_ATTR_DAEMON(logd_secs, logd_process);
 TUNE_ATTR_DAEMON(quotad_secs, quotad_process);
@@ -464,7 +462,6 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_quota_cache_secs.attr,
 	&tune_attr_stall_secs.attr,
 	&tune_attr_statfs_quantum.attr,
-	&tune_attr_scand_secs.attr,
 	&tune_attr_recoverd_secs.attr,
 	&tune_attr_logd_secs.attr,
 	&tune_attr_quotad_secs.attr,
@@ -553,6 +550,7 @@ int gfs2_sys_init(void)
 {
 	gfs2_sys_margs = NULL;
 	spin_lock_init(&gfs2_sys_margs_lock);
+	kobject_set_name(&gfs2_kset.kobj, "gfs2");
 	kobj_set_kset_s(&gfs2_kset, fs_subsys);
 	return kset_register(&gfs2_kset);
 }
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index f8dabf8446bb..717983e2c2ae 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -142,25 +142,25 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
 	lops_add(sdp, &bd->bd_le);
 }
 
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 {
-	struct gfs2_revoke *rv = kmalloc(sizeof(struct gfs2_revoke),
-					 GFP_NOFS | __GFP_NOFAIL);
-	lops_init_le(&rv->rv_le, &gfs2_revoke_lops);
-	rv->rv_blkno = blkno;
-	lops_add(sdp, &rv->rv_le);
+	BUG_ON(!list_empty(&bd->bd_le.le_list));
+	BUG_ON(!list_empty(&bd->bd_ail_st_list));
+	BUG_ON(!list_empty(&bd->bd_ail_gl_list));
+	lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
+	lops_add(sdp, &bd->bd_le);
 }
 
 void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 {
-	struct gfs2_revoke *rv;
+	struct gfs2_bufdata *bd;
 	int found = 0;
 
 	gfs2_log_lock(sdp);
 
-	list_for_each_entry(rv, &sdp->sd_log_le_revoke, rv_le.le_list) {
-		if (rv->rv_blkno == blkno) {
-			list_del(&rv->rv_le.le_list);
+	list_for_each_entry(bd, &sdp->sd_log_le_revoke, bd_le.le_list) {
+		if (bd->bd_blkno == blkno) {
+			list_del_init(&bd->bd_le.le_list);
 			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
 			sdp->sd_log_num_revoke--;
 			found = 1;
@@ -172,7 +172,7 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 
 	if (found) {
 		struct gfs2_trans *tr = current->journal_info;
-		kfree(rv);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
 		tr->tr_num_revoke_rm++;
 	}
 }
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index 23d4cbe1de5b..043d5f4b9c4c 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -32,7 +32,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp);
 
 void gfs2_trans_add_gl(struct gfs2_glock *gl);
 void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno);
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno);
 void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
 
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index de3e4a506dbc..ccfd02944053 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -2162,7 +2162,7 @@ static void lbmStartIO(struct lbuf * bp)
 	/* check if journaling to disk has been disabled */
 	if (log->no_integrity) {
 		bio->bi_size = 0;
-		lbmIODone(bio, 0, 0);
+		lbmIODone(bio, 0);
 	} else {
 		submit_bio(WRITE_SYNC, bio);
 		INCREMENT(lmStat.submitted);
@@ -2200,16 +2200,13 @@ static int lbmIOWait(struct lbuf * bp, int flag)
  *
  * executed at INTIODONE level
  */
-static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error)
+static void lbmIODone(struct bio *bio, int error)
 {
 	struct lbuf *bp = bio->bi_private;
 	struct lbuf *nextbp, *tail;
 	struct jfs_log *log;
 	unsigned long flags;
 
-	if (bio->bi_size)
-		return 1;
-
 	/*
 	 * get back jfs buffer bound to the i/o buffer
 	 */
@@ -2237,8 +2234,6 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error)
 
 		/* wakeup I/O initiator */
 		LCACHE_WAKEUP(&bp->l_ioevent);
-
-		return 0;
 	}
 
 	/*
@@ -2263,7 +2258,6 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error)
 	if (bp->l_flag & lbmDIRECT) {
 		LCACHE_WAKEUP(&bp->l_ioevent);
 		LCACHE_UNLOCK(flags);
-		return 0;
 	}
 
 	tail = log->wqueue;
@@ -2342,8 +2336,6 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error)
 
 		LCACHE_UNLOCK(flags);	/* unlock+enable */
 	}
-
-	return 0;
 }
 
 int jfsIOWait(void *arg)
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 62e96be02acf..941369c1ac8d 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -280,14 +280,10 @@ static void last_read_complete(struct page *page)
 	unlock_page(page);
 }
 
-static int metapage_read_end_io(struct bio *bio, unsigned int bytes_done,
-				int err)
+static void metapage_read_end_io(struct bio *bio, int err)
 {
 	struct page *page = bio->bi_private;
 
-	if (bio->bi_size)
-		return 1;
-
 	if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
 		printk(KERN_ERR "metapage_read_end_io: I/O error\n");
 		SetPageError(page);
@@ -295,8 +291,6 @@ static int metapage_read_end_io(struct bio *bio, unsigned int bytes_done,
 
 	dec_io(page, last_read_complete);
 	bio_put(bio);
-
-	return 0;
 }
 
 static void remove_from_logsync(struct metapage *mp)
@@ -341,23 +335,18 @@ static void last_write_complete(struct page *page)
 	end_page_writeback(page);
 }
 
-static int metapage_write_end_io(struct bio *bio, unsigned int bytes_done,
-				 int err)
+static void metapage_write_end_io(struct bio *bio, int err)
 {
 	struct page *page = bio->bi_private;
 
 	BUG_ON(!PagePrivate(page));
 
-	if (bio->bi_size)
-		return 1;
-
 	if (! test_bit(BIO_UPTODATE, &bio->bi_flags)) {
 		printk(KERN_ERR "metapage_write_end_io: I/O error\n");
 		SetPageError(page);
 	}
 	dec_io(page, last_write_complete);
 	bio_put(bio);
-	return 0;
 }
 
 static int metapage_writepage(struct page *page, struct writeback_control *wbc)
diff --git a/fs/mpage.c b/fs/mpage.c
index c1698f2291aa..b1c3e5890508 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -39,14 +39,11 @@
  * status of that page is hard.  See end_buffer_async_read() for the details.
  * There is no point in duplicating all that complexity.
  */
-static int mpage_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
+static void mpage_end_io_read(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
 
-	if (bio->bi_size)
-		return 1;
-
 	do {
 		struct page *page = bvec->bv_page;
 
@@ -62,17 +59,13 @@ static int mpage_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
 		unlock_page(page);
 	} while (bvec >= bio->bi_io_vec);
 	bio_put(bio);
-	return 0;
 }
 
-static int mpage_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
+static void mpage_end_io_write(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
 
-	if (bio->bi_size)
-		return 1;
-
 	do {
 		struct page *page = bvec->bv_page;
 
@@ -87,7 +80,6 @@ static int mpage_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
 		end_page_writeback(page);
 	} while (bvec >= bio->bi_io_vec);
 	bio_put(bio);
-	return 0;
 }
 
 static struct bio *mpage_bio_submit(int rw, struct bio *bio)
diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index af4ef808fa94..345798ebd366 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -17,6 +17,18 @@ ToDo/Notes:
 	  happen is unclear however so it is worth waiting until someone hits
 	  the problem.
 
+2.1.29 - Fix a deadlock at mount time.
+
+	- During mount the VFS holds s_umount lock on the superblock.  So when
+	  we try to empty the journal $LogFile contents by calling
+	  ntfs_attr_set() when the machine does not have much memory and the
+	  journal is large ntfs_attr_set() results in the VM trying to balance
+	  dirty pages which in turn tries to that the s_umount lock and thus we
+	  get a deadlock.  The solution is to not use ntfs_attr_set() and
+	  instead do the zeroing by hand at the block level rather than page
+	  cache level.
+	- Fix sparse warnings.
+
 2.1.28 - Fix a deadlock.
 
 	- Fix deadlock in fs/ntfs/inode.c::ntfs_put_inode().  Thanks to Sergey
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index 825508385565..58b6be992544 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
 	     index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
 	     unistr.o upcase.o
 
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.28\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.29\"
 
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 6e5c2534f4bc..cfdc7900d271 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -2,7 +2,7 @@
  * aops.c - NTFS kernel address space operations and page cache handling.
  *	    Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -396,7 +396,7 @@ static int ntfs_readpage(struct file *file, struct page *page)
 	loff_t i_size;
 	struct inode *vi;
 	ntfs_inode *ni, *base_ni;
-	u8 *kaddr;
+	u8 *addr;
 	ntfs_attr_search_ctx *ctx;
 	MFT_RECORD *mrec;
 	unsigned long flags;
@@ -491,15 +491,15 @@ retry_readpage:
 		/* Race with shrinking truncate. */
 		attr_len = i_size;
 	}
-	kaddr = kmap_atomic(page, KM_USER0);
+	addr = kmap_atomic(page, KM_USER0);
 	/* Copy the data to the page. */
-	memcpy(kaddr, (u8*)ctx->attr +
+	memcpy(addr, (u8*)ctx->attr +
 			le16_to_cpu(ctx->attr->data.resident.value_offset),
 			attr_len);
 	/* Zero the remainder of the page. */
-	memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+	memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
 	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
+	kunmap_atomic(addr, KM_USER0);
 put_unm_err_out:
 	ntfs_attr_put_search_ctx(ctx);
 unm_err_out:
@@ -1344,7 +1344,7 @@ static int ntfs_writepage(struct page *page, struct writeback_control *wbc)
 	loff_t i_size;
 	struct inode *vi = page->mapping->host;
 	ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi);
-	char *kaddr;
+	char *addr;
 	ntfs_attr_search_ctx *ctx = NULL;
 	MFT_RECORD *m = NULL;
 	u32 attr_len;
@@ -1484,14 +1484,14 @@ retry_writepage:
 		/* Shrinking cannot fail. */
 		BUG_ON(err);
 	}
-	kaddr = kmap_atomic(page, KM_USER0);
+	addr = kmap_atomic(page, KM_USER0);
 	/* Copy the data from the page to the mft record. */
 	memcpy((u8*)ctx->attr +
 			le16_to_cpu(ctx->attr->data.resident.value_offset),
-			kaddr, attr_len);
+			addr, attr_len);
 	/* Zero out of bounds area in the page cache page. */
-	memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
-	kunmap_atomic(kaddr, KM_USER0);
+	memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+	kunmap_atomic(addr, KM_USER0);
 	flush_dcache_page(page);
 	flush_dcache_mft_record_page(ctx->ntfs_ino);
 	/* We are done with the page. */
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 1c08fefe487a..92dabdcf2b80 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -1,7 +1,7 @@
 /**
  * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -2500,7 +2500,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 	struct page *page;
 	u8 *kaddr;
 	pgoff_t idx, end;
-	unsigned int start_ofs, end_ofs, size;
+	unsigned start_ofs, end_ofs, size;
 
 	ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
 			(long long)ofs, (long long)cnt, val);
@@ -2548,6 +2548,8 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		kunmap_atomic(kaddr, KM_USER0);
 		set_page_dirty(page);
 		page_cache_release(page);
+		balance_dirty_pages_ratelimited(mapping);
+		cond_resched();
 		if (idx == end)
 			goto done;
 		idx++;
@@ -2604,6 +2606,8 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		kunmap_atomic(kaddr, KM_USER0);
 		set_page_dirty(page);
 		page_cache_release(page);
+		balance_dirty_pages_ratelimited(mapping);
+		cond_resched();
 	}
 done:
 	ntfs_debug("Done.");
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ffcc504a1667..c814204d4ea0 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
  * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -26,7 +26,6 @@
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
-#include <linux/sched.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -362,7 +361,7 @@ static inline void ntfs_fault_in_pages_readable(const char __user *uaddr,
 	volatile char c;
 
 	/* Set @end to the first byte outside the last page we care about. */
-	end = (const char __user*)PAGE_ALIGN((ptrdiff_t __user)uaddr + bytes);
+	end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes);
 
 	while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end))
 		;
@@ -532,7 +531,8 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
 	blocksize_bits = vol->sb->s_blocksize_bits;
 	u = 0;
 	do {
-		struct page *page = pages[u];
+		page = pages[u];
+		BUG_ON(!page);
 		/*
 		 * create_empty_buffers() will create uptodate/dirty buffers if
 		 * the page is uptodate/dirty.
@@ -1291,7 +1291,7 @@ static inline size_t ntfs_copy_from_user(struct page **pages,
 		size_t bytes)
 {
 	struct page **last_page = pages + nr_pages;
-	char *kaddr;
+	char *addr;
 	size_t total = 0;
 	unsigned len;
 	int left;
@@ -1300,13 +1300,13 @@ static inline size_t ntfs_copy_from_user(struct page **pages,
 		len = PAGE_CACHE_SIZE - ofs;
 		if (len > bytes)
 			len = bytes;
-		kaddr = kmap_atomic(*pages, KM_USER0);
-		left = __copy_from_user_inatomic(kaddr + ofs, buf, len);
-		kunmap_atomic(kaddr, KM_USER0);
+		addr = kmap_atomic(*pages, KM_USER0);
+		left = __copy_from_user_inatomic(addr + ofs, buf, len);
+		kunmap_atomic(addr, KM_USER0);
 		if (unlikely(left)) {
 			/* Do it the slow way. */
-			kaddr = kmap(*pages);
-			left = __copy_from_user(kaddr + ofs, buf, len);
+			addr = kmap(*pages);
+			left = __copy_from_user(addr + ofs, buf, len);
 			kunmap(*pages);
 			if (unlikely(left))
 				goto err_out;
@@ -1408,26 +1408,26 @@ static inline size_t ntfs_copy_from_user_iovec(struct page **pages,
 		size_t *iov_ofs, size_t bytes)
 {
 	struct page **last_page = pages + nr_pages;
-	char *kaddr;
+	char *addr;
 	size_t copied, len, total = 0;
 
 	do {
 		len = PAGE_CACHE_SIZE - ofs;
 		if (len > bytes)
 			len = bytes;
-		kaddr = kmap_atomic(*pages, KM_USER0);
-		copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs,
+		addr = kmap_atomic(*pages, KM_USER0);
+		copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
 				*iov, *iov_ofs, len);
-		kunmap_atomic(kaddr, KM_USER0);
+		kunmap_atomic(addr, KM_USER0);
 		if (unlikely(copied != len)) {
 			/* Do it the slow way. */
-			kaddr = kmap(*pages);
-			copied = __ntfs_copy_from_user_iovec_inatomic(kaddr + ofs,
+			addr = kmap(*pages);
+			copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs,
 					*iov, *iov_ofs, len);
 			/*
 			 * Zero the rest of the target like __copy_from_user().
 			 */
-			memset(kaddr + ofs + copied, 0, len - copied);
+			memset(addr + ofs + copied, 0, len - copied);
 			kunmap(*pages);
 			if (unlikely(copied != len))
 				goto err_out;
@@ -1735,8 +1735,6 @@ static int ntfs_commit_pages_after_write(struct page **pages,
 	read_unlock_irqrestore(&ni->size_lock, flags);
 	BUG_ON(initialized_size != i_size);
 	if (end > initialized_size) {
-		unsigned long flags;
-
 		write_lock_irqsave(&ni->size_lock, flags);
 		ni->initialized_size = end;
 		i_size_write(vi, end);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index b532a730cec2..e9da092e2772 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -34,7 +34,6 @@
 #include "dir.h"
 #include "debug.h"
 #include "inode.h"
-#include "attrib.h"
 #include "lcnalloc.h"
 #include "malloc.h"
 #include "mft.h"
@@ -2500,8 +2499,6 @@ retry_truncate:
 	/* Resize the attribute record to best fit the new attribute size. */
 	if (new_size < vol->mft_record_size &&
 			!ntfs_resident_attr_value_resize(m, a, new_size)) {
-		unsigned long flags;
-
 		/* The resize succeeded! */
 		flush_dcache_mft_record_page(ctx->ntfs_ino);
 		mark_mft_record_dirty(ctx->ntfs_ino);
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
index acfed325f4ec..d7932e95b1fd 100644
--- a/fs/ntfs/logfile.c
+++ b/fs/ntfs/logfile.c
@@ -1,7 +1,7 @@
 /*
  * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2002-2005 Anton Altaparmakov
+ * Copyright (c) 2002-2007 Anton Altaparmakov
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -724,24 +724,139 @@ bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp)
  */
 bool ntfs_empty_logfile(struct inode *log_vi)
 {
-	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
+	VCN vcn, end_vcn;
+	ntfs_inode *log_ni = NTFS_I(log_vi);
+	ntfs_volume *vol = log_ni->vol;
+	struct super_block *sb = vol->sb;
+	runlist_element *rl;
+	unsigned long flags;
+	unsigned block_size, block_size_bits;
+	int err;
+	bool should_wait = true;
 
 	ntfs_debug("Entering.");
-	if (!NVolLogFileEmpty(vol)) {
-		int err;
-		
-		err = ntfs_attr_set(NTFS_I(log_vi), 0, i_size_read(log_vi),
-				0xff);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to fill $LogFile with "
-					"0xff bytes (error code %i).", err);
-			return false;
-		}
-		/* Set the flag so we do not have to do it again on remount. */
-		NVolSetLogFileEmpty(vol);
+	if (NVolLogFileEmpty(vol)) {
+		ntfs_debug("Done.");
+		return true;
 	}
+	/*
+	 * We cannot use ntfs_attr_set() because we may be still in the middle
+	 * of a mount operation.  Thus we do the emptying by hand by first
+	 * zapping the page cache pages for the $LogFile/$DATA attribute and
+	 * then emptying each of the buffers in each of the clusters specified
+	 * by the runlist by hand.
+	 */
+	block_size = sb->s_blocksize;
+	block_size_bits = sb->s_blocksize_bits;
+	vcn = 0;
+	read_lock_irqsave(&log_ni->size_lock, flags);
+	end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >>
+			vol->cluster_size_bits;
+	read_unlock_irqrestore(&log_ni->size_lock, flags);
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	down_write(&log_ni->runlist.lock);
+	rl = log_ni->runlist.rl;
+	if (unlikely(!rl || vcn < rl->vcn || !rl->length)) {
+map_vcn:
+		err = ntfs_map_runlist_nolock(log_ni, vcn, NULL);
+		if (err) {
+			ntfs_error(sb, "Failed to map runlist fragment (error "
+					"%d).", -err);
+			goto err;
+		}
+		rl = log_ni->runlist.rl;
+		BUG_ON(!rl || vcn < rl->vcn || !rl->length);
+	}
+	/* Seek to the runlist element containing @vcn. */
+	while (rl->length && vcn >= rl[1].vcn)
+		rl++;
+	do {
+		LCN lcn;
+		sector_t block, end_block;
+		s64 len;
+
+		/*
+		 * If this run is not mapped map it now and start again as the
+		 * runlist will have been updated.
+		 */
+		lcn = rl->lcn;
+		if (unlikely(lcn == LCN_RL_NOT_MAPPED)) {
+			vcn = rl->vcn;
+			goto map_vcn;
+		}
+		/* If this run is not valid abort with an error. */
+		if (unlikely(!rl->length || lcn < LCN_HOLE))
+			goto rl_err;
+		/* Skip holes. */
+		if (lcn == LCN_HOLE)
+			continue;
+		block = lcn << vol->cluster_size_bits >> block_size_bits;
+		len = rl->length;
+		if (rl[1].vcn > end_vcn)
+			len = end_vcn - rl->vcn;
+		end_block = (lcn + len) << vol->cluster_size_bits >>
+				block_size_bits;
+		/* Iterate over the blocks in the run and empty them. */
+		do {
+			struct buffer_head *bh;
+
+			/* Obtain the buffer, possibly not uptodate. */
+			bh = sb_getblk(sb, block);
+			BUG_ON(!bh);
+			/* Setup buffer i/o submission. */
+			lock_buffer(bh);
+			bh->b_end_io = end_buffer_write_sync;
+			get_bh(bh);
+			/* Set the entire contents of the buffer to 0xff. */
+			memset(bh->b_data, -1, block_size);
+			if (!buffer_uptodate(bh))
+				set_buffer_uptodate(bh);
+			if (buffer_dirty(bh))
+				clear_buffer_dirty(bh);
+			/*
+			 * Submit the buffer and wait for i/o to complete but
+			 * only for the first buffer so we do not miss really
+			 * serious i/o errors.  Once the first buffer has
+			 * completed ignore errors afterwards as we can assume
+			 * that if one buffer worked all of them will work.
+			 */
+			submit_bh(WRITE, bh);
+			if (should_wait) {
+				should_wait = false;
+				wait_on_buffer(bh);
+				if (unlikely(!buffer_uptodate(bh)))
+					goto io_err;
+			}
+			brelse(bh);
+		} while (++block < end_block);
+	} while ((++rl)->vcn < end_vcn);
+	up_write(&log_ni->runlist.lock);
+	/*
+	 * Zap the pages again just in case any got instantiated whilst we were
+	 * emptying the blocks by hand.  FIXME: We may not have completed
+	 * writing to all the buffer heads yet so this may happen too early.
+	 * We really should use a kernel thread to do the emptying
+	 * asynchronously and then we can also set the volume dirty and output
+	 * an error message if emptying should fail.
+	 */
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	/* Set the flag so we do not have to do it again on remount. */
+	NVolSetLogFileEmpty(vol);
 	ntfs_debug("Done.");
 	return true;
+io_err:
+	ntfs_error(sb, "Failed to write buffer.  Unmount and run chkdsk.");
+	goto dirty_err;
+rl_err:
+	ntfs_error(sb, "Runlist is corrupt.  Unmount and run chkdsk.");
+dirty_err:
+	NVolSetErrors(vol);
+	err = -EIO;
+err:
+	up_write(&log_ni->runlist.lock);
+	ntfs_error(sb, "Failed to fill $LogFile with 0xff bytes (error %d).",
+			-err);
+	return false;
 }
 
 #endif /* NTFS_RW */
diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c
index 9afd72c7ad0d..56a9a6d25a2a 100644
--- a/fs/ntfs/runlist.c
+++ b/fs/ntfs/runlist.c
@@ -1,7 +1,7 @@
 /**
  * runlist.c - NTFS runlist handling code.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
  * Copyright (c) 2002-2005 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -1714,7 +1714,7 @@ extend_hole:
 					sizeof(*rl));
 		/* Adjust the beginning of the tail if necessary. */
 		if (end > rl->vcn) {
-			s64 delta = end - rl->vcn;
+			delta = end - rl->vcn;
 			rl->vcn = end;
 			rl->length -= delta;
 			/* Only adjust the lcn if it is real. */
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 778a850b4634..4ba7f0bdc248 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -354,7 +354,6 @@ struct ocfs2_insert_type {
 	enum ocfs2_append_type	ins_appending;
 	enum ocfs2_contig_type	ins_contig;
 	int			ins_contig_index;
-	int			ins_free_records;
 	int			ins_tree_depth;
 };
 
@@ -362,7 +361,6 @@ struct ocfs2_merge_ctxt {
 	enum ocfs2_contig_type	c_contig_type;
 	int			c_has_empty_extent;
 	int			c_split_covers_rec;
-	int			c_used_tail_recs;
 };
 
 /*
@@ -2808,36 +2806,28 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
 				     struct ocfs2_merge_ctxt *ctxt)
 
 {
-	int ret = 0, delete_tail_recs = 0;
+	int ret = 0;
 	struct ocfs2_extent_list *el = path_leaf_el(left_path);
 	struct ocfs2_extent_rec *rec = &el->l_recs[split_index];
 
 	BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
 
-	if (ctxt->c_split_covers_rec) {
-		delete_tail_recs++;
-
-		if (ctxt->c_contig_type == CONTIG_LEFTRIGHT ||
-		    ctxt->c_has_empty_extent)
-			delete_tail_recs++;
-
-		if (ctxt->c_has_empty_extent) {
-			/*
-			 * The merge code will need to create an empty
-			 * extent to take the place of the newly
-			 * emptied slot. Remove any pre-existing empty
-			 * extents - having more than one in a leaf is
-			 * illegal.
-			 */
-			ret = ocfs2_rotate_tree_left(inode, handle, left_path,
-						     dealloc);
-			if (ret) {
-				mlog_errno(ret);
-				goto out;
-			}
-			split_index--;
-			rec = &el->l_recs[split_index];
+	if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
+		/*
+		 * The merge code will need to create an empty
+		 * extent to take the place of the newly
+		 * emptied slot. Remove any pre-existing empty
+		 * extents - having more than one in a leaf is
+		 * illegal.
+		 */
+		ret = ocfs2_rotate_tree_left(inode, handle, left_path,
+					     dealloc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
 		}
+		split_index--;
+		rec = &el->l_recs[split_index];
 	}
 
 	if (ctxt->c_contig_type == CONTIG_LEFTRIGHT) {
@@ -3593,6 +3583,7 @@ static int ocfs2_figure_insert_type(struct inode *inode,
 				    struct buffer_head *di_bh,
 				    struct buffer_head **last_eb_bh,
 				    struct ocfs2_extent_rec *insert_rec,
+				    int *free_records,
 				    struct ocfs2_insert_type *insert)
 {
 	int ret;
@@ -3633,7 +3624,7 @@ static int ocfs2_figure_insert_type(struct inode *inode,
 	 * XXX: This test is simplistic, we can search for empty
 	 * extent records too.
 	 */
-	insert->ins_free_records = le16_to_cpu(el->l_count) -
+	*free_records = le16_to_cpu(el->l_count) -
 		le16_to_cpu(el->l_next_free_rec);
 
 	if (!insert->ins_tree_depth) {
@@ -3730,10 +3721,13 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
 			struct ocfs2_alloc_context *meta_ac)
 {
 	int status;
+	int uninitialized_var(free_records);
 	struct buffer_head *last_eb_bh = NULL;
 	struct ocfs2_insert_type insert = {0, };
 	struct ocfs2_extent_rec rec;
 
+	BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
+
 	mlog(0, "add %u clusters at position %u to inode %llu\n",
 	     new_clusters, cpos, (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
@@ -3752,7 +3746,7 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
 	rec.e_flags = flags;
 
 	status = ocfs2_figure_insert_type(inode, fe_bh, &last_eb_bh, &rec,
-					  &insert);
+					  &free_records, &insert);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -3762,9 +3756,9 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
 	     "Insert.contig_index: %d, Insert.free_records: %d, "
 	     "Insert.tree_depth: %d\n",
 	     insert.ins_appending, insert.ins_contig, insert.ins_contig_index,
-	     insert.ins_free_records, insert.ins_tree_depth);
+	     free_records, insert.ins_tree_depth);
 
-	if (insert.ins_contig == CONTIG_NONE && insert.ins_free_records == 0) {
+	if (insert.ins_contig == CONTIG_NONE && free_records == 0) {
 		status = ocfs2_grow_tree(inode, handle, fe_bh,
 					 &insert.ins_tree_depth, &last_eb_bh,
 					 meta_ac);
@@ -3847,26 +3841,17 @@ leftright:
 
 	if (le16_to_cpu(rightmost_el->l_next_free_rec) ==
 	    le16_to_cpu(rightmost_el->l_count)) {
-		int old_depth = depth;
-
 		ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, last_eb_bh,
 				      meta_ac);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
 		}
-
-		if (old_depth != depth) {
-			eb = (struct ocfs2_extent_block *)(*last_eb_bh)->b_data;
-			rightmost_el = &eb->h_list;
-		}
 	}
 
 	memset(&insert, 0, sizeof(struct ocfs2_insert_type));
 	insert.ins_appending = APPEND_NONE;
 	insert.ins_contig = CONTIG_NONE;
-	insert.ins_free_records = le16_to_cpu(rightmost_el->l_count)
-		- le16_to_cpu(rightmost_el->l_next_free_rec);
 	insert.ins_tree_depth = depth;
 
 	insert_range = le32_to_cpu(split_rec.e_cpos) +
@@ -4015,11 +4000,6 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
 	} else
 		rightmost_el = path_root_el(path);
 
-	ctxt.c_used_tail_recs = le16_to_cpu(rightmost_el->l_next_free_rec);
-	if (ctxt.c_used_tail_recs > 0 &&
-	    ocfs2_is_empty_extent(&rightmost_el->l_recs[0]))
-		ctxt.c_used_tail_recs--;
-
 	if (rec->e_cpos == split_rec->e_cpos &&
 	    rec->e_leaf_clusters == split_rec->e_leaf_clusters)
 		ctxt.c_split_covers_rec = 1;
@@ -4028,10 +4008,9 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
 
 	ctxt.c_has_empty_extent = ocfs2_is_empty_extent(&el->l_recs[0]);
 
-	mlog(0, "index: %d, contig: %u, used_tail_recs: %u, "
-	     "has_empty: %u, split_covers: %u\n", split_index,
-	     ctxt.c_contig_type, ctxt.c_used_tail_recs,
-	     ctxt.c_has_empty_extent, ctxt.c_split_covers_rec);
+	mlog(0, "index: %d, contig: %u, has_empty: %u, split_covers: %u\n",
+	     split_index, ctxt.c_contig_type, ctxt.c_has_empty_extent,
+	     ctxt.c_split_covers_rec);
 
 	if (ctxt.c_contig_type == CONTIG_NONE) {
 		if (ctxt.c_split_covers_rec)
@@ -4180,27 +4159,18 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
 
 	if (le16_to_cpu(rightmost_el->l_next_free_rec) ==
 	    le16_to_cpu(rightmost_el->l_count)) {
-		int old_depth = depth;
-
 		ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, &last_eb_bh,
 				      meta_ac);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
 		}
-
-		if (old_depth != depth) {
-			eb = (struct ocfs2_extent_block *)last_eb_bh->b_data;
-			rightmost_el = &eb->h_list;
-		}
 	}
 
 	memset(&insert, 0, sizeof(struct ocfs2_insert_type));
 	insert.ins_appending = APPEND_NONE;
 	insert.ins_contig = CONTIG_NONE;
 	insert.ins_split = SPLIT_RIGHT;
-	insert.ins_free_records = le16_to_cpu(rightmost_el->l_count)
-		- le16_to_cpu(rightmost_el->l_next_free_rec);
 	insert.ins_tree_depth = depth;
 
 	ret = ocfs2_do_insert_extent(inode, handle, di_bh, &split_rec, &insert);
@@ -5665,12 +5635,50 @@ static int ocfs2_ordered_zero_func(handle_t *handle, struct buffer_head *bh)
 	return ocfs2_journal_dirty_data(handle, bh);
 }
 
+static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
+				     unsigned int from, unsigned int to,
+				     struct page *page, int zero, u64 *phys)
+{
+	int ret, partial = 0;
+
+	ret = ocfs2_map_page_blocks(page, phys, inode, from, to, 0);
+	if (ret)
+		mlog_errno(ret);
+
+	if (zero)
+		zero_user_page(page, from, to - from, KM_USER0);
+
+	/*
+	 * Need to set the buffers we zero'd into uptodate
+	 * here if they aren't - ocfs2_map_page_blocks()
+	 * might've skipped some
+	 */
+	if (ocfs2_should_order_data(inode)) {
+		ret = walk_page_buffers(handle,
+					page_buffers(page),
+					from, to, &partial,
+					ocfs2_ordered_zero_func);
+		if (ret < 0)
+			mlog_errno(ret);
+	} else {
+		ret = walk_page_buffers(handle, page_buffers(page),
+					from, to, &partial,
+					ocfs2_writeback_zero_func);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	if (!partial)
+		SetPageUptodate(page);
+
+	flush_dcache_page(page);
+}
+
 static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start,
 				     loff_t end, struct page **pages,
 				     int numpages, u64 phys, handle_t *handle)
 {
-	int i, ret, partial = 0;
-	void *kaddr;
+	int i;
 	struct page *page;
 	unsigned int from, to = PAGE_CACHE_SIZE;
 	struct super_block *sb = inode->i_sb;
@@ -5691,87 +5699,31 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start,
 		BUG_ON(from > PAGE_CACHE_SIZE);
 		BUG_ON(to > PAGE_CACHE_SIZE);
 
-		ret = ocfs2_map_page_blocks(page, &phys, inode, from, to, 0);
-		if (ret)
-			mlog_errno(ret);
-
-		kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr + from, 0, to - from);
-		kunmap_atomic(kaddr, KM_USER0);
-
-		/*
-		 * Need to set the buffers we zero'd into uptodate
-		 * here if they aren't - ocfs2_map_page_blocks()
-		 * might've skipped some
-		 */
-		if (ocfs2_should_order_data(inode)) {
-			ret = walk_page_buffers(handle,
-						page_buffers(page),
-						from, to, &partial,
-						ocfs2_ordered_zero_func);
-			if (ret < 0)
-				mlog_errno(ret);
-		} else {
-			ret = walk_page_buffers(handle, page_buffers(page),
-						from, to, &partial,
-						ocfs2_writeback_zero_func);
-			if (ret < 0)
-				mlog_errno(ret);
-		}
-
-		if (!partial)
-			SetPageUptodate(page);
-
-		flush_dcache_page(page);
+		ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1,
+					 &phys);
 
 		start = (page->index + 1) << PAGE_CACHE_SHIFT;
 	}
 out:
-	if (pages) {
-		for (i = 0; i < numpages; i++) {
-			page = pages[i];
-			unlock_page(page);
-			mark_page_accessed(page);
-			page_cache_release(page);
-		}
-	}
+	if (pages)
+		ocfs2_unlock_and_free_pages(pages, numpages);
 }
 
 static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
-				struct page **pages, int *num, u64 *phys)
+				struct page **pages, int *num)
 {
-	int i, numpages = 0, ret = 0;
-	unsigned int ext_flags;
+	int numpages, ret = 0;
 	struct super_block *sb = inode->i_sb;
 	struct address_space *mapping = inode->i_mapping;
 	unsigned long index;
 	loff_t last_page_bytes;
 
-	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb)));
 	BUG_ON(start > end);
 
-	if (start == end)
-		goto out;
-
 	BUG_ON(start >> OCFS2_SB(sb)->s_clustersize_bits !=
 	       (end - 1) >> OCFS2_SB(sb)->s_clustersize_bits);
 
-	ret = ocfs2_extent_map_get_blocks(inode, start >> sb->s_blocksize_bits,
-					  phys, NULL, &ext_flags);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
-	/* Tail is a hole. */
-	if (*phys == 0)
-		goto out;
-
-	/* Tail is marked as unwritten, we can count on write to zero
-	 * in that case. */
-	if (ext_flags & OCFS2_EXT_UNWRITTEN)
-		goto out;
-
+	numpages = 0;
 	last_page_bytes = PAGE_ALIGN(end);
 	index = start >> PAGE_CACHE_SHIFT;
 	do {
@@ -5788,14 +5740,8 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
 
 out:
 	if (ret != 0) {
-		if (pages) {
-			for (i = 0; i < numpages; i++) {
-				if (pages[i]) {
-					unlock_page(pages[i]);
-					page_cache_release(pages[i]);
-				}
-			}
-		}
+		if (pages)
+			ocfs2_unlock_and_free_pages(pages, numpages);
 		numpages = 0;
 	}
 
@@ -5816,18 +5762,20 @@ out:
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 				  u64 range_start, u64 range_end)
 {
-	int ret, numpages;
+	int ret = 0, numpages;
 	struct page **pages = NULL;
 	u64 phys;
+	unsigned int ext_flags;
+	struct super_block *sb = inode->i_sb;
 
 	/*
 	 * File systems which don't support sparse files zero on every
 	 * extend.
 	 */
-	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+	if (!ocfs2_sparse_alloc(OCFS2_SB(sb)))
 		return 0;
 
-	pages = kcalloc(ocfs2_pages_per_cluster(inode->i_sb),
+	pages = kcalloc(ocfs2_pages_per_cluster(sb),
 			sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
 		ret = -ENOMEM;
@@ -5835,16 +5783,31 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		goto out;
 	}
 
-	ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages,
-				   &numpages, &phys);
+	if (range_start == range_end)
+		goto out;
+
+	ret = ocfs2_extent_map_get_blocks(inode,
+					  range_start >> sb->s_blocksize_bits,
+					  &phys, NULL, &ext_flags);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
 	}
 
-	if (numpages == 0)
+	/*
+	 * Tail is a hole, or is marked unwritten. In either case, we
+	 * can count on read and write to return/push zero's.
+	 */
+	if (phys == 0 || ext_flags & OCFS2_EXT_UNWRITTEN)
 		goto out;
 
+	ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages,
+				   &numpages);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
 	ocfs2_zero_cluster_pages(inode, range_start, range_end, pages,
 				 numpages, phys, handle);
 
@@ -5865,6 +5828,178 @@ out:
 	return ret;
 }
 
+static void ocfs2_zero_dinode_id2(struct inode *inode, struct ocfs2_dinode *di)
+{
+	unsigned int blocksize = 1 << inode->i_sb->s_blocksize_bits;
+
+	memset(&di->id2, 0, blocksize - offsetof(struct ocfs2_dinode, id2));
+}
+
+void ocfs2_dinode_new_extent_list(struct inode *inode,
+				  struct ocfs2_dinode *di)
+{
+	ocfs2_zero_dinode_id2(inode, di);
+	di->id2.i_list.l_tree_depth = 0;
+	di->id2.i_list.l_next_free_rec = 0;
+	di->id2.i_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(inode->i_sb));
+}
+
+void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_inline_data *idata = &di->id2.i_data;
+
+	spin_lock(&oi->ip_lock);
+	oi->ip_dyn_features |= OCFS2_INLINE_DATA_FL;
+	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
+	spin_unlock(&oi->ip_lock);
+
+	/*
+	 * We clear the entire i_data structure here so that all
+	 * fields can be properly initialized.
+	 */
+	ocfs2_zero_dinode_id2(inode, di);
+
+	idata->id_count = cpu_to_le16(ocfs2_max_inline_data(inode->i_sb));
+}
+
+int ocfs2_convert_inline_data_to_extents(struct inode *inode,
+					 struct buffer_head *di_bh)
+{
+	int ret, i, has_data, num_pages = 0;
+	handle_t *handle;
+	u64 uninitialized_var(block);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_alloc_context *data_ac = NULL;
+	struct page **pages = NULL;
+	loff_t end = osb->s_clustersize;
+
+	has_data = i_size_read(inode) ? 1 : 0;
+
+	if (has_data) {
+		pages = kcalloc(ocfs2_pages_per_cluster(osb->sb),
+				sizeof(struct page *), GFP_NOFS);
+		if (pages == NULL) {
+			ret = -ENOMEM;
+			mlog_errno(ret);
+			goto out;
+		}
+
+		ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_INLINE_TO_EXTENTS_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock;
+	}
+
+	ret = ocfs2_journal_access(handle, inode, di_bh,
+				   OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	if (has_data) {
+		u32 bit_off, num;
+		unsigned int page_end;
+		u64 phys;
+
+		ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off,
+					   &num);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+
+		/*
+		 * Save two copies, one for insert, and one that can
+		 * be changed by ocfs2_map_and_dirty_page() below.
+		 */
+		block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
+
+		/*
+		 * Non sparse file systems zero on extend, so no need
+		 * to do that now.
+		 */
+		if (!ocfs2_sparse_alloc(osb) &&
+		    PAGE_CACHE_SIZE < osb->s_clustersize)
+			end = PAGE_CACHE_SIZE;
+
+		ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+
+		/*
+		 * This should populate the 1st page for us and mark
+		 * it up to date.
+		 */
+		ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+
+		page_end = PAGE_CACHE_SIZE;
+		if (PAGE_CACHE_SIZE > osb->s_clustersize)
+			page_end = osb->s_clustersize;
+
+		for (i = 0; i < num_pages; i++)
+			ocfs2_map_and_dirty_page(inode, handle, 0, page_end,
+						 pages[i], i > 0, &phys);
+	}
+
+	spin_lock(&oi->ip_lock);
+	oi->ip_dyn_features &= ~OCFS2_INLINE_DATA_FL;
+	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
+	spin_unlock(&oi->ip_lock);
+
+	ocfs2_dinode_new_extent_list(inode, di);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+	if (has_data) {
+		/*
+		 * An error at this point should be extremely rare. If
+		 * this proves to be false, we could always re-build
+		 * the in-inode data from our pages.
+		 */
+		ret = ocfs2_insert_extent(osb, handle, inode, di_bh,
+					  0, block, 1, 0, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+
+		inode->i_blocks = ocfs2_inode_sector_count(inode);
+	}
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_unlock:
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+
+out:
+	if (pages) {
+		ocfs2_unlock_and_free_pages(pages, num_pages);
+		kfree(pages);
+	}
+
+	return ret;
+}
+
 /*
  * It is expected, that by the time you call this function,
  * inode->i_size and fe->i_size have been adjusted.
@@ -6090,6 +6225,81 @@ bail:
 	return status;
 }
 
+/*
+ * 'start' is inclusive, 'end' is not.
+ */
+int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
+			  unsigned int start, unsigned int end, int trunc)
+{
+	int ret;
+	unsigned int numbytes;
+	handle_t *handle;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_inline_data *idata = &di->id2.i_data;
+
+	if (end > i_size_read(inode))
+		end = i_size_read(inode);
+
+	BUG_ON(start >= end);
+
+	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
+	    !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
+	    !ocfs2_supports_inline_data(osb)) {
+		ocfs2_error(inode->i_sb,
+			    "Inline data flags for inode %llu don't agree! "
+			    "Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			    le16_to_cpu(di->i_dyn_features),
+			    OCFS2_I(inode)->ip_dyn_features,
+			    osb->s_feature_incompat);
+		ret = -EROFS;
+		goto out;
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_journal_access(handle, inode, di_bh,
+				   OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	numbytes = end - start;
+	memset(idata->id_data + start, 0, numbytes);
+
+	/*
+	 * No need to worry about the data page here - it's been
+	 * truncated already and inline data doesn't need it for
+	 * pushing zero's to disk, so we'll let readpage pick it up
+	 * later.
+	 */
+	if (trunc) {
+		i_size_write(inode, start);
+		di->i_size = cpu_to_le64(start);
+	}
+
+	inode->i_blocks = ocfs2_inode_sector_count(inode);
+	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+
+	di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
+	di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out:
+	return ret;
+}
+
 static void ocfs2_free_truncate_context(struct ocfs2_truncate_context *tc)
 {
 	/*
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 990df48ae8d3..42ff94bd8011 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -62,6 +62,11 @@ static inline int ocfs2_extend_meta_needed(struct ocfs2_dinode *fe)
 	return le16_to_cpu(fe->id2.i_list.l_tree_depth) + 2;
 }
 
+void ocfs2_dinode_new_extent_list(struct inode *inode, struct ocfs2_dinode *di);
+void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di);
+int ocfs2_convert_inline_data_to_extents(struct inode *inode,
+					 struct buffer_head *di_bh);
+
 int ocfs2_truncate_log_init(struct ocfs2_super *osb);
 void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb);
 void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
@@ -115,6 +120,8 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 			  struct inode *inode,
 			  struct buffer_head *fe_bh,
 			  struct ocfs2_truncate_context *tc);
+int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
+			  unsigned int start, unsigned int end, int trunc);
 
 int ocfs2_find_leaf(struct inode *inode, struct ocfs2_extent_list *root_el,
 		    u32 cpos, struct buffer_head **leaf_bh);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index f37f25c931f5..34d10452c56d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -206,9 +206,70 @@ bail:
 	return err;
 }
 
+int ocfs2_read_inline_data(struct inode *inode, struct page *page,
+			   struct buffer_head *di_bh)
+{
+	void *kaddr;
+	unsigned int size;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+
+	if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
+		ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno);
+		return -EROFS;
+	}
+
+	size = i_size_read(inode);
+
+	if (size > PAGE_CACHE_SIZE ||
+	    size > ocfs2_max_inline_data(inode->i_sb)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %llu has with inline data has bad size: %u",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno, size);
+		return -EROFS;
+	}
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	if (size)
+		memcpy(kaddr, di->id2.i_data.id_data, size);
+	/* Clear the remaining part of the page */
+	memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
+
+	ret = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &di_bh,
+			       OCFS2_BH_CACHED, inode);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_read_inline_data(inode, page, di_bh);
+out:
+	unlock_page(page);
+
+	brelse(di_bh);
+	return ret;
+}
+
 static int ocfs2_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT;
 	int ret, unlock = 1;
 
@@ -222,7 +283,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 		goto out;
 	}
 
-	if (down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem) == 0) {
+	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
 		ret = AOP_TRUNCATED_PAGE;
 		goto out_meta_unlock;
 	}
@@ -252,7 +313,10 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 		goto out_alloc;
 	}
 
-	ret = block_read_full_page(page, ocfs2_get_block);
+	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		ret = ocfs2_readpage_inline(inode, page);
+	else
+		ret = block_read_full_page(page, ocfs2_get_block);
 	unlock = 0;
 
 	ocfs2_data_unlock(inode, 0);
@@ -301,12 +365,8 @@ int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
 {
 	int ret;
 
-	down_read(&OCFS2_I(inode)->ip_alloc_sem);
-
 	ret = block_prepare_write(page, from, to, ocfs2_get_block);
 
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
-
 	return ret;
 }
 
@@ -401,7 +461,9 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 	}
 
-	err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, NULL);
+	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
+		err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL,
+						  NULL);
 
 	if (!INODE_JOURNAL(inode)) {
 		up_read(&OCFS2_I(inode)->ip_alloc_sem);
@@ -415,7 +477,6 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 		goto bail;
 	}
 
-
 bail:
 	status = err ? 0 : p_blkno;
 
@@ -570,6 +631,13 @@ static ssize_t ocfs2_direct_IO(int rw,
 
 	mlog_entry_void();
 
+	/*
+	 * Fallback to buffered I/O if we see an inode without
+	 * extents.
+	 */
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
 	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
 		/*
 		 * We get PR data locks even for O_DIRECT.  This
@@ -834,18 +902,22 @@ struct ocfs2_write_ctxt {
 	struct ocfs2_cached_dealloc_ctxt w_dealloc;
 };
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 {
 	int i;
 
-	for(i = 0; i < wc->w_num_pages; i++) {
-		if (wc->w_pages[i] == NULL)
-			continue;
-
-		unlock_page(wc->w_pages[i]);
-		mark_page_accessed(wc->w_pages[i]);
-		page_cache_release(wc->w_pages[i]);
+	for(i = 0; i < num_pages; i++) {
+		if (pages[i]) {
+			unlock_page(pages[i]);
+			mark_page_accessed(pages[i]);
+			page_cache_release(pages[i]);
+		}
 	}
+}
+
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 
 	brelse(wc->w_di_bh);
 	kfree(wc);
@@ -1360,6 +1432,160 @@ out:
 	return ret;
 }
 
+static int ocfs2_write_begin_inline(struct address_space *mapping,
+				    struct inode *inode,
+				    struct ocfs2_write_ctxt *wc)
+{
+	int ret;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct page *page;
+	handle_t *handle;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
+
+	page = find_or_create_page(mapping, 0, GFP_NOFS);
+	if (!page) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+	/*
+	 * If we don't set w_num_pages then this page won't get unlocked
+	 * and freed on cleanup of the write context.
+	 */
+	wc->w_pages[0] = wc->w_target_page = page;
+	wc->w_num_pages = 1;
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_journal_access(handle, inode, wc->w_di_bh,
+				   OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		ocfs2_commit_trans(osb, handle);
+
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
+		ocfs2_set_inode_data_inline(inode, di);
+
+	if (!PageUptodate(page)) {
+		ret = ocfs2_read_inline_data(inode, page, wc->w_di_bh);
+		if (ret) {
+			ocfs2_commit_trans(osb, handle);
+
+			goto out;
+		}
+	}
+
+	wc->w_handle = handle;
+out:
+	return ret;
+}
+
+int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size)
+{
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+
+	if (new_size < le16_to_cpu(di->id2.i_data.id_count))
+		return 1;
+	return 0;
+}
+
+static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
+					  struct inode *inode, loff_t pos,
+					  unsigned len, struct page *mmap_page,
+					  struct ocfs2_write_ctxt *wc)
+{
+	int ret, written = 0;
+	loff_t end = pos + len;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+	mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n",
+	     (unsigned long long)oi->ip_blkno, len, (unsigned long long)pos,
+	     oi->ip_dyn_features);
+
+	/*
+	 * Handle inodes which already have inline data 1st.
+	 */
+	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		if (mmap_page == NULL &&
+		    ocfs2_size_fits_inline_data(wc->w_di_bh, end))
+			goto do_inline_write;
+
+		/*
+		 * The write won't fit - we have to give this inode an
+		 * inline extent list now.
+		 */
+		ret = ocfs2_convert_inline_data_to_extents(inode, wc->w_di_bh);
+		if (ret)
+			mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * Check whether the inode can accept inline data.
+	 */
+	if (oi->ip_clusters != 0 || i_size_read(inode) != 0)
+		return 0;
+
+	/*
+	 * Check whether the write can fit.
+	 */
+	if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb))
+		return 0;
+
+do_inline_write:
+	ret = ocfs2_write_begin_inline(mapping, inode, wc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * This signals to the caller that the data can be written
+	 * inline.
+	 */
+	written = 1;
+out:
+	return written ? written : ret;
+}
+
+/*
+ * This function only does anything for file systems which can't
+ * handle sparse files.
+ *
+ * What we want to do here is fill in any hole between the current end
+ * of allocation and the end of our write. That way the rest of the
+ * write path can treat it as an non-allocating write, which has no
+ * special case code for sparse/nonsparse files.
+ */
+static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos,
+					unsigned len,
+					struct ocfs2_write_ctxt *wc)
+{
+	int ret;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	loff_t newsize = pos + len;
+
+	if (ocfs2_sparse_alloc(osb))
+		return 0;
+
+	if (newsize <= i_size_read(inode))
+		return 0;
+
+	ret = ocfs2_extend_no_holes(inode, newsize, newsize - len);
+	if (ret)
+		mlog_errno(ret);
+
+	return ret;
+}
+
 int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata,
@@ -1381,6 +1607,25 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 		return ret;
 	}
 
+	if (ocfs2_supports_inline_data(osb)) {
+		ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len,
+						     mmap_page, wc);
+		if (ret == 1) {
+			ret = 0;
+			goto success;
+		}
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	ret = ocfs2_expand_nonsparse_inode(inode, pos, len, wc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
 	ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc,
 					&extents_to_split);
 	if (ret) {
@@ -1462,6 +1707,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 
+success:
 	*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
@@ -1529,6 +1775,31 @@ out_fail:
 	return ret;
 }
 
+static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
+				   unsigned len, unsigned *copied,
+				   struct ocfs2_dinode *di,
+				   struct ocfs2_write_ctxt *wc)
+{
+	void *kaddr;
+
+	if (unlikely(*copied < len)) {
+		if (!PageUptodate(wc->w_target_page)) {
+			*copied = 0;
+			return;
+		}
+	}
+
+	kaddr = kmap_atomic(wc->w_target_page, KM_USER0);
+	memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	mlog(0, "Data written to inode at offset %llu. "
+	     "id_count = %u, copied = %u, i_dyn_features = 0x%x\n",
+	     (unsigned long long)pos, *copied,
+	     le16_to_cpu(di->id2.i_data.id_count),
+	     le16_to_cpu(di->i_dyn_features));
+}
+
 int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
@@ -1542,6 +1813,11 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	handle_t *handle = wc->w_handle;
 	struct page *tmppage;
 
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ocfs2_write_end_inline(inode, pos, len, &copied, di, wc);
+		goto out_write_size;
+	}
+
 	if (unlikely(copied < len)) {
 		if (!PageUptodate(wc->w_target_page))
 			copied = 0;
@@ -1579,6 +1855,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		block_commit_write(tmppage, from, to);
 	}
 
+out_write_size:
 	pos += copied;
 	if (pos > inode->i_size) {
 		i_size_write(inode, pos);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 389579bd64e3..113560877dbb 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -34,6 +34,8 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 			  struct inode *inode, unsigned int from,
 			  unsigned int to, int new);
 
+void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages);
+
 int walk_page_buffers(	handle_t *handle,
 			struct buffer_head *head,
 			unsigned from,
@@ -59,6 +61,10 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page);
 
+int ocfs2_read_inline_data(struct inode *inode, struct page *page,
+			   struct buffer_head *di_bh);
+int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size);
+
 /* all ocfs2_dio_end_io()'s fault */
 #define ocfs2_iocb_is_rw_locked(iocb) \
 	test_bit(0, (unsigned long *)&iocb->private)
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 2bd7f788cf34..f14b541fab95 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -216,8 +216,7 @@ static void o2hb_wait_on_io(struct o2hb_region *reg,
 	wait_for_completion(&wc->wc_io_complete);
 }
 
-static int o2hb_bio_end_io(struct bio *bio,
-			   unsigned int bytes_done,
+static void o2hb_bio_end_io(struct bio *bio,
 			   int error)
 {
 	struct o2hb_bio_wait_ctxt *wc = bio->bi_private;
@@ -227,12 +226,8 @@ static int o2hb_bio_end_io(struct bio *bio,
 		wc->wc_error = error;
 	}
 
-	if (bio->bi_size)
-		return 1;
-
 	o2hb_bio_wait_dec(wc, 1);
 	bio_put(bio);
-	return 0;
 }
 
 /* Setup a Bio to cover I/O against num_slots slots starting at
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index e9e042b93dbf..a4882c8df945 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -143,7 +143,7 @@ static struct kobj_type mlog_ktype = {
 };
 
 static struct kset mlog_kset = {
-	.kobj   = {.name = "logmask", .ktype = &mlog_ktype},
+	.kobj   = {.ktype = &mlog_ktype},
 };
 
 int mlog_sys_init(struct kset *o2cb_subsys)
@@ -156,6 +156,7 @@ int mlog_sys_init(struct kset *o2cb_subsys)
 	}
 	mlog_attr_ptrs[i] = NULL;
 
+	kobject_set_name(&mlog_kset.kobj, "logmask");
 	kobj_set_kset_s(&mlog_kset, *o2cb_subsys);
 	return kset_register(&mlog_kset);
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 0d5fdde959c8..7453b70c1a19 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -55,10 +55,16 @@
 #include "journal.h"
 #include "namei.h"
 #include "suballoc.h"
+#include "super.h"
 #include "uptodate.h"
 
 #include "buffer_head_io.h"
 
+#define NAMEI_RA_CHUNKS  2
+#define NAMEI_RA_BLOCKS  4
+#define NAMEI_RA_SIZE        (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
+#define NAMEI_RA_INDEX(c,b)  (((c) * NAMEI_RA_BLOCKS) + (b))
+
 static unsigned char ocfs2_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
@@ -66,12 +72,614 @@ static unsigned char ocfs2_filetype_table[] = {
 static int ocfs2_extend_dir(struct ocfs2_super *osb,
 			    struct inode *dir,
 			    struct buffer_head *parent_fe_bh,
+			    unsigned int blocks_wanted,
 			    struct buffer_head **new_de_bh);
+static int ocfs2_do_extend_dir(struct super_block *sb,
+			       handle_t *handle,
+			       struct inode *dir,
+			       struct buffer_head *parent_fe_bh,
+			       struct ocfs2_alloc_context *data_ac,
+			       struct ocfs2_alloc_context *meta_ac,
+			       struct buffer_head **new_bh);
+
 /*
- * ocfs2_readdir()
+ * bh passed here can be an inode block or a dir data block, depending
+ * on the inode inline data flag.
+ */
+static int ocfs2_check_dir_entry(struct inode * dir,
+				 struct ocfs2_dir_entry * de,
+				 struct buffer_head * bh,
+				 unsigned long offset)
+{
+	const char *error_msg = NULL;
+	const int rlen = le16_to_cpu(de->rec_len);
+
+	if (rlen < OCFS2_DIR_REC_LEN(1))
+		error_msg = "rec_len is smaller than minimal";
+	else if (rlen % 4 != 0)
+		error_msg = "rec_len % 4 != 0";
+	else if (rlen < OCFS2_DIR_REC_LEN(de->name_len))
+		error_msg = "rec_len is too small for name_len";
+	else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
+		error_msg = "directory entry across blocks";
+
+	if (error_msg != NULL)
+		mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
+		     "offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n",
+		     (unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg,
+		     offset, (unsigned long long)le64_to_cpu(de->inode), rlen,
+		     de->name_len);
+	return error_msg == NULL ? 1 : 0;
+}
+
+static inline int ocfs2_match(int len,
+			      const char * const name,
+			      struct ocfs2_dir_entry *de)
+{
+	if (len != de->name_len)
+		return 0;
+	if (!de->inode)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+/*
+ * Returns 0 if not found, -1 on failure, and 1 on success
+ */
+static int inline ocfs2_search_dirblock(struct buffer_head *bh,
+					struct inode *dir,
+					const char *name, int namelen,
+					unsigned long offset,
+					char *first_de,
+					unsigned int bytes,
+					struct ocfs2_dir_entry **res_dir)
+{
+	struct ocfs2_dir_entry *de;
+	char *dlimit, *de_buf;
+	int de_len;
+	int ret = 0;
+
+	mlog_entry_void();
+
+	de_buf = first_de;
+	dlimit = de_buf + bytes;
+
+	while (de_buf < dlimit) {
+		/* this code is executed quadratically often */
+		/* do minimal checking `by hand' */
+
+		de = (struct ocfs2_dir_entry *) de_buf;
+
+		if (de_buf + namelen <= dlimit &&
+		    ocfs2_match(namelen, name, de)) {
+			/* found a match - just to be sure, do a full check */
+			if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+				ret = -1;
+				goto bail;
+			}
+			*res_dir = de;
+			ret = 1;
+			goto bail;
+		}
+
+		/* prevent looping on a bad block */
+		de_len = le16_to_cpu(de->rec_len);
+		if (de_len <= 0) {
+			ret = -1;
+			goto bail;
+		}
+
+		de_buf += de_len;
+		offset += de_len;
+	}
+
+bail:
+	mlog_exit(ret);
+	return ret;
+}
+
+static struct buffer_head *ocfs2_find_entry_id(const char *name,
+					       int namelen,
+					       struct inode *dir,
+					       struct ocfs2_dir_entry **res_dir)
+{
+	int ret, found;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_inline_data *data;
+
+	ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
+			       &di_bh, OCFS2_BH_CACHED, dir);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	data = &di->id2.i_data;
+
+	found = ocfs2_search_dirblock(di_bh, dir, name, namelen, 0,
+				      data->id_data, i_size_read(dir), res_dir);
+	if (found == 1)
+		return di_bh;
+
+	brelse(di_bh);
+out:
+	return NULL;
+}
+
+struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
+					struct inode *dir,
+					struct ocfs2_dir_entry **res_dir)
+{
+	struct super_block *sb;
+	struct buffer_head *bh_use[NAMEI_RA_SIZE];
+	struct buffer_head *bh, *ret = NULL;
+	unsigned long start, block, b;
+	int ra_max = 0;		/* Number of bh's in the readahead
+				   buffer, bh_use[] */
+	int ra_ptr = 0;		/* Current index into readahead
+				   buffer */
+	int num = 0;
+	int nblocks, i, err;
+
+	mlog_entry_void();
+
+	sb = dir->i_sb;
+
+	nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
+	start = OCFS2_I(dir)->ip_dir_start_lookup;
+	if (start >= nblocks)
+		start = 0;
+	block = start;
+
+restart:
+	do {
+		/*
+		 * We deal with the read-ahead logic here.
+		 */
+		if (ra_ptr >= ra_max) {
+			/* Refill the readahead buffer */
+			ra_ptr = 0;
+			b = block;
+			for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
+				/*
+				 * Terminate if we reach the end of the
+				 * directory and must wrap, or if our
+				 * search has finished at this block.
+				 */
+				if (b >= nblocks || (num && block == start)) {
+					bh_use[ra_max] = NULL;
+					break;
+				}
+				num++;
+
+				bh = ocfs2_bread(dir, b++, &err, 1);
+				bh_use[ra_max] = bh;
+			}
+		}
+		if ((bh = bh_use[ra_ptr++]) == NULL)
+			goto next;
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh)) {
+			/* read error, skip block & hope for the best */
+			ocfs2_error(dir->i_sb, "reading directory %llu, "
+				    "offset %lu\n",
+				    (unsigned long long)OCFS2_I(dir)->ip_blkno,
+				    block);
+			brelse(bh);
+			goto next;
+		}
+		i = ocfs2_search_dirblock(bh, dir, name, namelen,
+					  block << sb->s_blocksize_bits,
+					  bh->b_data, sb->s_blocksize,
+					  res_dir);
+		if (i == 1) {
+			OCFS2_I(dir)->ip_dir_start_lookup = block;
+			ret = bh;
+			goto cleanup_and_exit;
+		} else {
+			brelse(bh);
+			if (i < 0)
+				goto cleanup_and_exit;
+		}
+	next:
+		if (++block >= nblocks)
+			block = 0;
+	} while (block != start);
+
+	/*
+	 * If the directory has grown while we were searching, then
+	 * search the last part of the directory before giving up.
+	 */
+	block = nblocks;
+	nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
+	if (block < nblocks) {
+		start = 0;
+		goto restart;
+	}
+
+cleanup_and_exit:
+	/* Clean up the read-ahead blocks */
+	for (; ra_ptr < ra_max; ra_ptr++)
+		brelse(bh_use[ra_ptr]);
+
+	mlog_exit_ptr(ret);
+	return ret;
+}
+
+/*
+ * Try to find an entry of the provided name within 'dir'.
  *
+ * If nothing was found, NULL is returned. Otherwise, a buffer_head
+ * and pointer to the dir entry are passed back.
+ *
+ * Caller can NOT assume anything about the contents of the
+ * buffer_head - it is passed back only so that it can be passed into
+ * any one of the manipulation functions (add entry, delete entry,
+ * etc). As an example, bh in the extent directory case is a data
+ * block, in the inline-data case it actually points to an inode.
  */
-int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
+struct buffer_head *ocfs2_find_entry(const char *name, int namelen,
+				     struct inode *dir,
+				     struct ocfs2_dir_entry **res_dir)
+{
+	*res_dir = NULL;
+
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return ocfs2_find_entry_id(name, namelen, dir, res_dir);
+
+	return ocfs2_find_entry_el(name, namelen, dir, res_dir);
+}
+
+/*
+ * Update inode number and type of a previously found directory entry.
+ */
+int ocfs2_update_entry(struct inode *dir, handle_t *handle,
+		       struct buffer_head *de_bh, struct ocfs2_dir_entry *de,
+		       struct inode *new_entry_inode)
+{
+	int ret;
+
+	/*
+	 * The same code works fine for both inline-data and extent
+	 * based directories, so no need to split this up.
+	 */
+
+	ret = ocfs2_journal_access(handle, dir, de_bh,
+				   OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	de->inode = cpu_to_le64(OCFS2_I(new_entry_inode)->ip_blkno);
+	ocfs2_set_de_type(de, new_entry_inode->i_mode);
+
+	ocfs2_journal_dirty(handle, de_bh);
+
+out:
+	return ret;
+}
+
+static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
+				struct ocfs2_dir_entry *de_del,
+				struct buffer_head *bh, char *first_de,
+				unsigned int bytes)
+{
+	struct ocfs2_dir_entry *de, *pde;
+	int i, status = -ENOENT;
+
+	mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh);
+
+	i = 0;
+	pde = NULL;
+	de = (struct ocfs2_dir_entry *) first_de;
+	while (i < bytes) {
+		if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
+			status = -EIO;
+			mlog_errno(status);
+			goto bail;
+		}
+		if (de == de_del)  {
+			status = ocfs2_journal_access(handle, dir, bh,
+						      OCFS2_JOURNAL_ACCESS_WRITE);
+			if (status < 0) {
+				status = -EIO;
+				mlog_errno(status);
+				goto bail;
+			}
+			if (pde)
+				pde->rec_len =
+					cpu_to_le16(le16_to_cpu(pde->rec_len) +
+						    le16_to_cpu(de->rec_len));
+			else
+				de->inode = 0;
+			dir->i_version++;
+			status = ocfs2_journal_dirty(handle, bh);
+			goto bail;
+		}
+		i += le16_to_cpu(de->rec_len);
+		pde = de;
+		de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len));
+	}
+bail:
+	mlog_exit(status);
+	return status;
+}
+
+static inline int ocfs2_delete_entry_id(handle_t *handle,
+					struct inode *dir,
+					struct ocfs2_dir_entry *de_del,
+					struct buffer_head *bh)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_inline_data *data;
+
+	ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
+			       &di_bh, OCFS2_BH_CACHED, dir);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	data = &di->id2.i_data;
+
+	ret = __ocfs2_delete_entry(handle, dir, de_del, bh, data->id_data,
+				   i_size_read(dir));
+
+	brelse(di_bh);
+out:
+	return ret;
+}
+
+static inline int ocfs2_delete_entry_el(handle_t *handle,
+					struct inode *dir,
+					struct ocfs2_dir_entry *de_del,
+					struct buffer_head *bh)
+{
+	return __ocfs2_delete_entry(handle, dir, de_del, bh, bh->b_data,
+				    bh->b_size);
+}
+
+/*
+ * ocfs2_delete_entry deletes a directory entry by merging it with the
+ * previous entry
+ */
+int ocfs2_delete_entry(handle_t *handle,
+		       struct inode *dir,
+		       struct ocfs2_dir_entry *de_del,
+		       struct buffer_head *bh)
+{
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return ocfs2_delete_entry_id(handle, dir, de_del, bh);
+
+	return ocfs2_delete_entry_el(handle, dir, de_del, bh);
+}
+
+/*
+ * Check whether 'de' has enough room to hold an entry of
+ * 'new_rec_len' bytes.
+ */
+static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de,
+					 unsigned int new_rec_len)
+{
+	unsigned int de_really_used;
+
+	/* Check whether this is an empty record with enough space */
+	if (le64_to_cpu(de->inode) == 0 &&
+	    le16_to_cpu(de->rec_len) >= new_rec_len)
+		return 1;
+
+	/*
+	 * Record might have free space at the end which we can
+	 * use.
+	 */
+	de_really_used = OCFS2_DIR_REC_LEN(de->name_len);
+	if (le16_to_cpu(de->rec_len) >= (de_really_used + new_rec_len))
+	    return 1;
+
+	return 0;
+}
+
+/* we don't always have a dentry for what we want to add, so people
+ * like orphan dir can call this instead.
+ *
+ * If you pass me insert_bh, I'll skip the search of the other dir
+ * blocks and put the record in there.
+ */
+int __ocfs2_add_entry(handle_t *handle,
+		      struct inode *dir,
+		      const char *name, int namelen,
+		      struct inode *inode, u64 blkno,
+		      struct buffer_head *parent_fe_bh,
+		      struct buffer_head *insert_bh)
+{
+	unsigned long offset;
+	unsigned short rec_len;
+	struct ocfs2_dir_entry *de, *de1;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data;
+	struct super_block *sb = dir->i_sb;
+	int retval, status;
+	unsigned int size = sb->s_blocksize;
+	char *data_start = insert_bh->b_data;
+
+	mlog_entry_void();
+
+	if (!namelen)
+		return -EINVAL;
+
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		data_start = di->id2.i_data.id_data;
+		size = i_size_read(dir);
+
+		BUG_ON(insert_bh != parent_fe_bh);
+	}
+
+	rec_len = OCFS2_DIR_REC_LEN(namelen);
+	offset = 0;
+	de = (struct ocfs2_dir_entry *) data_start;
+	while (1) {
+		BUG_ON((char *)de >= (size + data_start));
+
+		/* These checks should've already been passed by the
+		 * prepare function, but I guess we can leave them
+		 * here anyway. */
+		if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
+			retval = -ENOENT;
+			goto bail;
+		}
+		if (ocfs2_match(namelen, name, de)) {
+			retval = -EEXIST;
+			goto bail;
+		}
+
+		if (ocfs2_dirent_would_fit(de, rec_len)) {
+			dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+			retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh);
+			if (retval < 0) {
+				mlog_errno(retval);
+				goto bail;
+			}
+
+			status = ocfs2_journal_access(handle, dir, insert_bh,
+						      OCFS2_JOURNAL_ACCESS_WRITE);
+			/* By now the buffer is marked for journaling */
+			offset += le16_to_cpu(de->rec_len);
+			if (le64_to_cpu(de->inode)) {
+				de1 = (struct ocfs2_dir_entry *)((char *) de +
+					OCFS2_DIR_REC_LEN(de->name_len));
+				de1->rec_len =
+					cpu_to_le16(le16_to_cpu(de->rec_len) -
+					OCFS2_DIR_REC_LEN(de->name_len));
+				de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
+				de = de1;
+			}
+			de->file_type = OCFS2_FT_UNKNOWN;
+			if (blkno) {
+				de->inode = cpu_to_le64(blkno);
+				ocfs2_set_de_type(de, inode->i_mode);
+			} else
+				de->inode = 0;
+			de->name_len = namelen;
+			memcpy(de->name, name, namelen);
+
+			dir->i_version++;
+			status = ocfs2_journal_dirty(handle, insert_bh);
+			retval = 0;
+			goto bail;
+		}
+		offset += le16_to_cpu(de->rec_len);
+		de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len));
+	}
+
+	/* when you think about it, the assert above should prevent us
+	 * from ever getting here. */
+	retval = -ENOSPC;
+bail:
+
+	mlog_exit(retval);
+	return retval;
+}
+
+static int ocfs2_dir_foreach_blk_id(struct inode *inode,
+				    unsigned long *f_version,
+				    loff_t *f_pos, void *priv,
+				    filldir_t filldir, int *filldir_err)
+{
+	int ret, i, filldir_ret;
+	unsigned long offset = *f_pos;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_inline_data *data;
+	struct ocfs2_dir_entry *de;
+
+	ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
+			       &di_bh, OCFS2_BH_CACHED, inode);
+	if (ret) {
+		mlog(ML_ERROR, "Unable to read inode block for dir %llu\n",
+		     (unsigned long long)OCFS2_I(inode)->ip_blkno);
+		goto out;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	data = &di->id2.i_data;
+
+	while (*f_pos < i_size_read(inode)) {
+revalidate:
+		/* If the dir block has changed since the last call to
+		 * readdir(2), then we might be pointing to an invalid
+		 * dirent right now.  Scan from the start of the block
+		 * to make sure. */
+		if (*f_version != inode->i_version) {
+			for (i = 0; i < i_size_read(inode) && i < offset; ) {
+				de = (struct ocfs2_dir_entry *)
+					(data->id_data + i);
+				/* It's too expensive to do a full
+				 * dirent test each time round this
+				 * loop, but we do have to test at
+				 * least that it is non-zero.  A
+				 * failure will be detected in the
+				 * dirent test below. */
+				if (le16_to_cpu(de->rec_len) <
+				    OCFS2_DIR_REC_LEN(1))
+					break;
+				i += le16_to_cpu(de->rec_len);
+			}
+			*f_pos = offset = i;
+			*f_version = inode->i_version;
+		}
+
+		de = (struct ocfs2_dir_entry *) (data->id_data + *f_pos);
+		if (!ocfs2_check_dir_entry(inode, de, di_bh, *f_pos)) {
+			/* On error, skip the f_pos to the end. */
+			*f_pos = i_size_read(inode);
+			goto out;
+		}
+		offset += le16_to_cpu(de->rec_len);
+		if (le64_to_cpu(de->inode)) {
+			/* We might block in the next section
+			 * if the data destination is
+			 * currently swapped out.  So, use a
+			 * version stamp to detect whether or
+			 * not the directory has been modified
+			 * during the copy operation.
+			 */
+			unsigned long version = *f_version;
+			unsigned char d_type = DT_UNKNOWN;
+
+			if (de->file_type < OCFS2_FT_MAX)
+				d_type = ocfs2_filetype_table[de->file_type];
+
+			filldir_ret = filldir(priv, de->name,
+					      de->name_len,
+					      *f_pos,
+					      le64_to_cpu(de->inode),
+					      d_type);
+			if (filldir_ret) {
+				if (filldir_err)
+					*filldir_err = filldir_ret;
+				break;
+			}
+			if (version != *f_version)
+				goto revalidate;
+		}
+		*f_pos += le16_to_cpu(de->rec_len);
+	}
+
+out:
+	brelse(di_bh);
+
+	return 0;
+}
+
+static int ocfs2_dir_foreach_blk_el(struct inode *inode,
+				    unsigned long *f_version,
+				    loff_t *f_pos, void *priv,
+				    filldir_t filldir, int *filldir_err)
 {
 	int error = 0;
 	unsigned long offset, blk, last_ra_blk = 0;
@@ -79,45 +687,23 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	struct buffer_head * bh, * tmp;
 	struct ocfs2_dir_entry * de;
 	int err;
-	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct super_block * sb = inode->i_sb;
 	unsigned int ra_sectors = 16;
-	int lock_level = 0;
-
-	mlog_entry("dirino=%llu\n",
-		   (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
 	stored = 0;
 	bh = NULL;
 
-	error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
-	if (lock_level && error >= 0) {
-		/* We release EX lock which used to update atime
-		 * and get PR lock again to reduce contention
-		 * on commonly accessed directories. */
-		ocfs2_meta_unlock(inode, 1);
-		lock_level = 0;
-		error = ocfs2_meta_lock(inode, NULL, 0);
-	}
-	if (error < 0) {
-		if (error != -ENOENT)
-			mlog_errno(error);
-		/* we haven't got any yet, so propagate the error. */
-		stored = error;
-		goto bail_nolock;
-	}
+	offset = (*f_pos) & (sb->s_blocksize - 1);
 
-	offset = filp->f_pos & (sb->s_blocksize - 1);
-
-	while (!error && !stored && filp->f_pos < i_size_read(inode)) {
-		blk = (filp->f_pos) >> sb->s_blocksize_bits;
+	while (!error && !stored && *f_pos < i_size_read(inode)) {
+		blk = (*f_pos) >> sb->s_blocksize_bits;
 		bh = ocfs2_bread(inode, blk, &err, 0);
 		if (!bh) {
 			mlog(ML_ERROR,
 			     "directory #%llu contains a hole at offset %lld\n",
 			     (unsigned long long)OCFS2_I(inode)->ip_blkno,
-			     filp->f_pos);
-			filp->f_pos += sb->s_blocksize - offset;
+			     *f_pos);
+			*f_pos += sb->s_blocksize - offset;
 			continue;
 		}
 
@@ -143,7 +729,7 @@ revalidate:
 		 * readdir(2), then we might be pointing to an invalid
 		 * dirent right now.  Scan from the start of the block
 		 * to make sure. */
-		if (filp->f_version != inode->i_version) {
+		if (*f_version != inode->i_version) {
 			for (i = 0; i < sb->s_blocksize && i < offset; ) {
 				de = (struct ocfs2_dir_entry *) (bh->b_data + i);
 				/* It's too expensive to do a full
@@ -158,21 +744,20 @@ revalidate:
 				i += le16_to_cpu(de->rec_len);
 			}
 			offset = i;
-			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+			*f_pos = ((*f_pos) & ~(sb->s_blocksize - 1))
 				| offset;
-			filp->f_version = inode->i_version;
+			*f_version = inode->i_version;
 		}
 
-		while (!error && filp->f_pos < i_size_read(inode)
+		while (!error && *f_pos < i_size_read(inode)
 		       && offset < sb->s_blocksize) {
 			de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
 			if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
 				/* On error, skip the f_pos to the
 				   next block. */
-				filp->f_pos = (filp->f_pos |
-					       (sb->s_blocksize - 1)) + 1;
+				*f_pos = ((*f_pos) | (sb->s_blocksize - 1)) + 1;
 				brelse(bh);
-				goto bail;
+				goto out;
 			}
 			offset += le16_to_cpu(de->rec_len);
 			if (le64_to_cpu(de->inode)) {
@@ -183,36 +768,109 @@ revalidate:
 				 * not the directory has been modified
 				 * during the copy operation.
 				 */
-				unsigned long version = filp->f_version;
+				unsigned long version = *f_version;
 				unsigned char d_type = DT_UNKNOWN;
 
 				if (de->file_type < OCFS2_FT_MAX)
 					d_type = ocfs2_filetype_table[de->file_type];
-				error = filldir(dirent, de->name,
+				error = filldir(priv, de->name,
 						de->name_len,
-						filp->f_pos,
-						ino_from_blkno(sb, le64_to_cpu(de->inode)),
+						*f_pos,
+						le64_to_cpu(de->inode),
 						d_type);
-				if (error)
+				if (error) {
+					if (filldir_err)
+						*filldir_err = error;
 					break;
-				if (version != filp->f_version)
+				}
+				if (version != *f_version)
 					goto revalidate;
 				stored ++;
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			*f_pos += le16_to_cpu(de->rec_len);
 		}
 		offset = 0;
 		brelse(bh);
 	}
 
 	stored = 0;
-bail:
+out:
+	return stored;
+}
+
+static int ocfs2_dir_foreach_blk(struct inode *inode, unsigned long *f_version,
+				 loff_t *f_pos, void *priv, filldir_t filldir,
+				 int *filldir_err)
+{
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return ocfs2_dir_foreach_blk_id(inode, f_version, f_pos, priv,
+						filldir, filldir_err);
+
+	return ocfs2_dir_foreach_blk_el(inode, f_version, f_pos, priv, filldir,
+					filldir_err);
+}
+
+/*
+ * This is intended to be called from inside other kernel functions,
+ * so we fake some arguments.
+ */
+int ocfs2_dir_foreach(struct inode *inode, loff_t *f_pos, void *priv,
+		      filldir_t filldir)
+{
+	int ret = 0, filldir_err = 0;
+	unsigned long version = inode->i_version;
+
+	while (*f_pos < i_size_read(inode)) {
+		ret = ocfs2_dir_foreach_blk(inode, &version, f_pos, priv,
+					    filldir, &filldir_err);
+		if (ret || filldir_err)
+			break;
+	}
+
+	if (ret > 0)
+		ret = -EIO;
+
+	return 0;
+}
+
+/*
+ * ocfs2_readdir()
+ *
+ */
+int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
+{
+	int error = 0;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	int lock_level = 0;
+
+	mlog_entry("dirino=%llu\n",
+		   (unsigned long long)OCFS2_I(inode)->ip_blkno);
+
+	error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+	if (lock_level && error >= 0) {
+		/* We release EX lock which used to update atime
+		 * and get PR lock again to reduce contention
+		 * on commonly accessed directories. */
+		ocfs2_meta_unlock(inode, 1);
+		lock_level = 0;
+		error = ocfs2_meta_lock(inode, NULL, 0);
+	}
+	if (error < 0) {
+		if (error != -ENOENT)
+			mlog_errno(error);
+		/* we haven't got any yet, so propagate the error. */
+		goto bail_nolock;
+	}
+
+	error = ocfs2_dir_foreach_blk(inode, &filp->f_version, &filp->f_pos,
+				      dirent, filldir, NULL);
+
 	ocfs2_meta_unlock(inode, lock_level);
 
 bail_nolock:
-	mlog_exit(stored);
+	mlog_exit(error);
 
-	return stored;
+	return error;
 }
 
 /*
@@ -252,6 +910,23 @@ leave:
 	return status;
 }
 
+/*
+ * Convenience function for callers which just want the block number
+ * mapped to a name and don't require the full dirent info, etc.
+ */
+int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
+			       int namelen, u64 *blkno)
+{
+	int ret;
+	struct buffer_head *bh = NULL;
+	struct ocfs2_dir_entry *dirent = NULL;
+
+	ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &bh, &dirent);
+	brelse(bh);
+
+	return ret;
+}
+
 /* Check for a name within a directory.
  *
  * Return 0 if the name does not exist
@@ -284,77 +959,414 @@ bail:
 	return ret;
 }
 
+struct ocfs2_empty_dir_priv {
+	unsigned seen_dot;
+	unsigned seen_dot_dot;
+	unsigned seen_other;
+};
+static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
+				   loff_t pos, u64 ino, unsigned type)
+{
+	struct ocfs2_empty_dir_priv *p = priv;
+
+	/*
+	 * Check the positions of "." and ".." records to be sure
+	 * they're in the correct place.
+	 */
+	if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) {
+		p->seen_dot = 1;
+		return 0;
+	}
+
+	if (name_len == 2 && !strncmp("..", name, 2) &&
+	    pos == OCFS2_DIR_REC_LEN(1)) {
+		p->seen_dot_dot = 1;
+		return 0;
+	}
+
+	p->seen_other = 1;
+	return 1;
+}
 /*
  * routine to check that the specified directory is empty (for rmdir)
+ *
+ * Returns 1 if dir is empty, zero otherwise.
  */
 int ocfs2_empty_dir(struct inode *inode)
 {
-	unsigned long offset;
-	struct buffer_head * bh;
-	struct ocfs2_dir_entry * de, * de1;
-	struct super_block * sb;
-	int err;
+	int ret;
+	loff_t start = 0;
+	struct ocfs2_empty_dir_priv priv;
+
+	memset(&priv, 0, sizeof(priv));
+
+	ret = ocfs2_dir_foreach(inode, &start, &priv, ocfs2_empty_dir_filldir);
+	if (ret)
+		mlog_errno(ret);
 
-	sb = inode->i_sb;
-	if ((i_size_read(inode) <
-	     (OCFS2_DIR_REC_LEN(1) + OCFS2_DIR_REC_LEN(2))) ||
-	    !(bh = ocfs2_bread(inode, 0, &err, 0))) {
-	    	mlog(ML_ERROR, "bad directory (dir #%llu) - no data block\n",
+	if (!priv.seen_dot || !priv.seen_dot_dot) {
+		mlog(ML_ERROR, "bad directory (dir #%llu) - no `.' or `..'\n",
 		     (unsigned long long)OCFS2_I(inode)->ip_blkno);
+		/*
+		 * XXX: Is it really safe to allow an unlink to continue?
+		 */
 		return 1;
 	}
 
-	de = (struct ocfs2_dir_entry *) bh->b_data;
-	de1 = (struct ocfs2_dir_entry *)
-			((char *)de + le16_to_cpu(de->rec_len));
-	if ((le64_to_cpu(de->inode) != OCFS2_I(inode)->ip_blkno) ||
-			!le64_to_cpu(de1->inode) ||
-			strcmp(".", de->name) ||
-			strcmp("..", de1->name)) {
-	    	mlog(ML_ERROR, "bad directory (dir #%llu) - no `.' or `..'\n",
-		     (unsigned long long)OCFS2_I(inode)->ip_blkno);
-		brelse(bh);
-		return 1;
+	return !priv.seen_other;
+}
+
+static void ocfs2_fill_initial_dirents(struct inode *inode,
+				       struct inode *parent,
+				       char *start, unsigned int size)
+{
+	struct ocfs2_dir_entry *de = (struct ocfs2_dir_entry *)start;
+
+	de->inode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
+	de->name_len = 1;
+	de->rec_len =
+		cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
+	strcpy(de->name, ".");
+	ocfs2_set_de_type(de, S_IFDIR);
+
+	de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len));
+	de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno);
+	de->rec_len = cpu_to_le16(size - OCFS2_DIR_REC_LEN(1));
+	de->name_len = 2;
+	strcpy(de->name, "..");
+	ocfs2_set_de_type(de, S_IFDIR);
+}
+
+/*
+ * This works together with code in ocfs2_mknod_locked() which sets
+ * the inline-data flag and initializes the inline-data section.
+ */
+static int ocfs2_fill_new_dir_id(struct ocfs2_super *osb,
+				 handle_t *handle,
+				 struct inode *parent,
+				 struct inode *inode,
+				 struct buffer_head *di_bh)
+{
+	int ret;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_inline_data *data = &di->id2.i_data;
+	unsigned int size = le16_to_cpu(data->id_count);
+
+	ret = ocfs2_journal_access(handle, inode, di_bh,
+				   OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
 	}
-	offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len);
-	de = (struct ocfs2_dir_entry *)((char *)de1 + le16_to_cpu(de1->rec_len));
-	while (offset < i_size_read(inode) ) {
-		if (!bh || (void *)de >= (void *)(bh->b_data + sb->s_blocksize)) {
-			brelse(bh);
-			bh = ocfs2_bread(inode,
-					 offset >> sb->s_blocksize_bits, &err, 0);
-			if (!bh) {
-				mlog(ML_ERROR, "dir %llu has a hole at %lu\n",
-				     (unsigned long long)OCFS2_I(inode)->ip_blkno, offset);
-				offset += sb->s_blocksize;
-				continue;
-			}
-			de = (struct ocfs2_dir_entry *) bh->b_data;
-		}
-		if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
-			brelse(bh);
-			return 1;
+
+	ocfs2_fill_initial_dirents(inode, parent, data->id_data, size);
+
+	ocfs2_journal_dirty(handle, di_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	i_size_write(inode, size);
+	inode->i_nlink = 2;
+	inode->i_blocks = ocfs2_inode_sector_count(inode);
+
+	ret = ocfs2_mark_inode_dirty(handle, inode, di_bh);
+	if (ret < 0)
+		mlog_errno(ret);
+
+out:
+	return ret;
+}
+
+static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
+				 handle_t *handle,
+				 struct inode *parent,
+				 struct inode *inode,
+				 struct buffer_head *fe_bh,
+				 struct ocfs2_alloc_context *data_ac)
+{
+	int status;
+	struct buffer_head *new_bh = NULL;
+
+	mlog_entry_void();
+
+	status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh,
+				     data_ac, NULL, &new_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	ocfs2_set_new_buffer_uptodate(inode, new_bh);
+
+	status = ocfs2_journal_access(handle, inode, new_bh,
+				      OCFS2_JOURNAL_ACCESS_CREATE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	memset(new_bh->b_data, 0, osb->sb->s_blocksize);
+
+	ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data,
+				   osb->sb->s_blocksize);
+
+	status = ocfs2_journal_dirty(handle, new_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	i_size_write(inode, inode->i_sb->s_blocksize);
+	inode->i_nlink = 2;
+	inode->i_blocks = ocfs2_inode_sector_count(inode);
+	status = ocfs2_mark_inode_dirty(handle, inode, fe_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	status = 0;
+bail:
+	if (new_bh)
+		brelse(new_bh);
+
+	mlog_exit(status);
+	return status;
+}
+
+int ocfs2_fill_new_dir(struct ocfs2_super *osb,
+		       handle_t *handle,
+		       struct inode *parent,
+		       struct inode *inode,
+		       struct buffer_head *fe_bh,
+		       struct ocfs2_alloc_context *data_ac)
+{
+	BUG_ON(!ocfs2_supports_inline_data(osb) && data_ac == NULL);
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return ocfs2_fill_new_dir_id(osb, handle, parent, inode, fe_bh);
+
+	return ocfs2_fill_new_dir_el(osb, handle, parent, inode, fe_bh,
+				     data_ac);
+}
+
+static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
+				     unsigned int new_size)
+{
+	struct ocfs2_dir_entry *de;
+	struct ocfs2_dir_entry *prev_de;
+	char *de_buf, *limit;
+	unsigned int bytes = new_size - old_size;
+
+	limit = start + old_size;
+	de_buf = start;
+	de = (struct ocfs2_dir_entry *)de_buf;
+	do {
+		prev_de = de;
+		de_buf += le16_to_cpu(de->rec_len);
+		de = (struct ocfs2_dir_entry *)de_buf;
+	} while (de_buf < limit);
+
+	le16_add_cpu(&prev_de->rec_len, bytes);
+}
+
+/*
+ * We allocate enough clusters to fulfill "blocks_wanted", but set
+ * i_size to exactly one block. Ocfs2_extend_dir() will handle the
+ * rest automatically for us.
+ *
+ * *first_block_bh is a pointer to the 1st data block allocated to the
+ *  directory.
+ */
+static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
+				   unsigned int blocks_wanted,
+				   struct buffer_head **first_block_bh)
+{
+	int ret, credits = OCFS2_INLINE_TO_EXTENTS_CREDITS;
+	u32 alloc, bit_off, len;
+	struct super_block *sb = dir->i_sb;
+	u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(dir);
+	struct ocfs2_alloc_context *data_ac;
+	struct buffer_head *dirdata_bh = NULL;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	handle_t *handle;
+
+	alloc = ocfs2_clusters_for_bytes(sb, bytes);
+
+	/*
+	 * We should never need more than 2 clusters for this -
+	 * maximum dirent size is far less than one block. In fact,
+	 * the only time we'd need more than one cluster is if
+	 * blocksize == clustersize and the dirent won't fit in the
+	 * extra space that the expansion to a single block gives. As
+	 * of today, that only happens on 4k/4k file systems.
+	 */
+	BUG_ON(alloc > 2);
+
+	ret = ocfs2_reserve_clusters(osb, alloc, &data_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_write(&oi->ip_alloc_sem);
+
+	/*
+	 * Prepare for worst case allocation scenario of two seperate
+	 * extents.
+	 */
+	if (alloc == 2)
+		credits += OCFS2_SUBALLOC_ALLOC;
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_sem;
+	}
+
+	/*
+	 * Try to claim as many clusters as the bitmap can give though
+	 * if we only get one now, that's enough to continue. The rest
+	 * will be claimed after the conversion to extents.
+	 */
+	ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, &len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * Operations are carefully ordered so that we set up the new
+	 * data block first. The conversion from inline data to
+	 * extents follows.
+	 */
+	blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off);
+	dirdata_bh = sb_getblk(sb, blkno);
+	if (!dirdata_bh) {
+		ret = -EIO;
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ocfs2_set_new_buffer_uptodate(dir, dirdata_bh);
+
+	ret = ocfs2_journal_access(handle, dir, dirdata_bh,
+				   OCFS2_JOURNAL_ACCESS_CREATE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir));
+	memset(dirdata_bh->b_data + i_size_read(dir), 0,
+	       sb->s_blocksize - i_size_read(dir));
+	ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir),
+				 sb->s_blocksize);
+
+	ret = ocfs2_journal_dirty(handle, dirdata_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * Set extent, i_size, etc on the directory. After this, the
+	 * inode should contain the same exact dirents as before and
+	 * be fully accessible from system calls.
+	 *
+	 * We let the later dirent insert modify c/mtime - to the user
+	 * the data hasn't changed.
+	 */
+	ret = ocfs2_journal_access(handle, dir, di_bh,
+				   OCFS2_JOURNAL_ACCESS_CREATE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	spin_lock(&oi->ip_lock);
+	oi->ip_dyn_features &= ~OCFS2_INLINE_DATA_FL;
+	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
+	spin_unlock(&oi->ip_lock);
+
+	ocfs2_dinode_new_extent_list(dir, di);
+
+	i_size_write(dir, sb->s_blocksize);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+
+	di->i_size = cpu_to_le64(sb->s_blocksize);
+	di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec);
+	di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec);
+	dir->i_blocks = ocfs2_inode_sector_count(dir);
+
+	/*
+	 * This should never fail as our extent list is empty and all
+	 * related blocks have been journaled already.
+	 */
+	ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 0, blkno, len, 0,
+				  NULL);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_journal_dirty(handle, di_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * We asked for two clusters, but only got one in the 1st
+	 * pass. Claim the 2nd cluster as a separate extent.
+	 */
+	if (alloc > len) {
+		ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off,
+					   &len);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
 		}
-		if (le64_to_cpu(de->inode)) {
-			brelse(bh);
-			return 0;
+		blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off);
+
+		ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 1, blkno,
+					  len, 0, NULL);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
 		}
-		offset += le16_to_cpu(de->rec_len);
-		de = (struct ocfs2_dir_entry *)
-			((char *)de + le16_to_cpu(de->rec_len));
 	}
-	brelse(bh);
-	return 1;
+
+	*first_block_bh = dirdata_bh;
+	dirdata_bh = NULL;
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_sem:
+	up_write(&oi->ip_alloc_sem);
+
+out:
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+
+	brelse(dirdata_bh);
+
+	return ret;
 }
 
 /* returns a bh of the 1st new block in the allocation. */
-int ocfs2_do_extend_dir(struct super_block *sb,
-			handle_t *handle,
-			struct inode *dir,
-			struct buffer_head *parent_fe_bh,
-			struct ocfs2_alloc_context *data_ac,
-			struct ocfs2_alloc_context *meta_ac,
-			struct buffer_head **new_bh)
+static int ocfs2_do_extend_dir(struct super_block *sb,
+			       handle_t *handle,
+			       struct inode *dir,
+			       struct buffer_head *parent_fe_bh,
+			       struct ocfs2_alloc_context *data_ac,
+			       struct ocfs2_alloc_context *meta_ac,
+			       struct buffer_head **new_bh)
 {
 	int status;
 	int extend;
@@ -396,10 +1408,18 @@ bail:
 	return status;
 }
 
-/* assumes you already have a cluster lock on the directory. */
+/*
+ * Assumes you already have a cluster lock on the directory.
+ *
+ * 'blocks_wanted' is only used if we have an inline directory which
+ * is to be turned into an extent based one. The size of the dirent to
+ * insert might be larger than the space gained by growing to just one
+ * block, so we may have to grow the inode by two blocks in that case.
+ */
 static int ocfs2_extend_dir(struct ocfs2_super *osb,
 			    struct inode *dir,
 			    struct buffer_head *parent_fe_bh,
+			    unsigned int blocks_wanted,
 			    struct buffer_head **new_de_bh)
 {
 	int status = 0;
@@ -415,6 +1435,38 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 
 	mlog_entry_void();
 
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		status = ocfs2_expand_inline_dir(dir, parent_fe_bh,
+						 blocks_wanted, &new_bh);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+
+		if (blocks_wanted == 1) {
+			/*
+			 * If the new dirent will fit inside the space
+			 * created by pushing out to one block, then
+			 * we can complete the operation
+			 * here. Otherwise we have to expand i_size
+			 * and format the 2nd block below.
+			 */
+			BUG_ON(new_bh == NULL);
+			goto bail_bh;
+		}
+
+		/*
+		 * Get rid of 'new_bh' - we want to format the 2nd
+		 * data block and return that instead.
+		 */
+		brelse(new_bh);
+		new_bh = NULL;
+
+		dir_i_size = i_size_read(dir);
+		credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
+		goto do_extend;
+	}
+
 	dir_i_size = i_size_read(dir);
 	mlog(0, "extending dir %llu (i_size = %lld)\n",
 	     (unsigned long long)OCFS2_I(dir)->ip_blkno, dir_i_size);
@@ -452,6 +1504,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 		credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
 	}
 
+do_extend:
 	down_write(&OCFS2_I(dir)->ip_alloc_sem);
 	drop_alloc_sem = 1;
 
@@ -497,6 +1550,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 		goto bail;
 	}
 
+bail_bh:
 	*new_de_bh = new_bh;
 	get_bh(*new_de_bh);
 bail:
@@ -517,41 +1571,71 @@ bail:
 	return status;
 }
 
-/*
- * Search the dir for a good spot, extending it if necessary. The
- * block containing an appropriate record is returned in ret_de_bh.
- */
-int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
-				 struct inode *dir,
-				 struct buffer_head *parent_fe_bh,
-				 const char *name,
-				 int namelen,
-				 struct buffer_head **ret_de_bh)
+static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
+				   const char *name, int namelen,
+				   struct buffer_head **ret_de_bh,
+				   unsigned int *blocks_wanted)
 {
-	unsigned long offset;
-	struct buffer_head * bh = NULL;
-	unsigned short rec_len;
-	struct ocfs2_dinode *fe;
-	struct ocfs2_dir_entry *de;
-	struct super_block *sb;
-	int status;
+	int ret;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_dir_entry *de, *last_de = NULL;
+	char *de_buf, *limit;
+	unsigned long offset = 0;
+	unsigned int rec_len, new_rec_len;
+
+	de_buf = di->id2.i_data.id_data;
+	limit = de_buf + i_size_read(dir);
+	rec_len = OCFS2_DIR_REC_LEN(namelen);
 
-	mlog_entry_void();
+	while (de_buf < limit) {
+		de = (struct ocfs2_dir_entry *)de_buf;
 
-	mlog(0, "getting ready to insert namelen %d into dir %llu\n",
-	     namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno);
+		if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
+			ret = -ENOENT;
+			goto out;
+		}
+		if (ocfs2_match(namelen, name, de)) {
+			ret = -EEXIST;
+			goto out;
+		}
+		if (ocfs2_dirent_would_fit(de, rec_len)) {
+			/* Ok, we found a spot. Return this bh and let
+			 * the caller actually fill it in. */
+			*ret_de_bh = di_bh;
+			get_bh(*ret_de_bh);
+			ret = 0;
+			goto out;
+		}
 
-	BUG_ON(!S_ISDIR(dir->i_mode));
-	fe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
-	BUG_ON(le64_to_cpu(fe->i_size) != i_size_read(dir));
+		last_de = de;
+		de_buf += le16_to_cpu(de->rec_len);
+		offset += le16_to_cpu(de->rec_len);
+	}
 
-	sb = dir->i_sb;
+	/*
+	 * We're going to require expansion of the directory - figure
+	 * out how many blocks we'll need so that a place for the
+	 * dirent can be found.
+	 */
+	*blocks_wanted = 1;
+	new_rec_len = le16_to_cpu(last_de->rec_len) + (dir->i_sb->s_blocksize - i_size_read(dir));
+	if (new_rec_len < (rec_len + OCFS2_DIR_REC_LEN(last_de->name_len)))
+		*blocks_wanted = 2;
+
+	ret = -ENOSPC;
+out:
+	return ret;
+}
 
-	if (!namelen) {
-		status = -EINVAL;
-		mlog_errno(status);
-		goto bail;
-	}
+static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
+				   int namelen, struct buffer_head **ret_de_bh)
+{
+	unsigned long offset;
+	struct buffer_head *bh = NULL;
+	unsigned short rec_len;
+	struct ocfs2_dir_entry *de;
+	struct super_block *sb = dir->i_sb;
+	int status;
 
 	bh = ocfs2_bread(dir, 0, &status, 0);
 	if (!bh) {
@@ -568,17 +1652,11 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 			bh = NULL;
 
 			if (i_size_read(dir) <= offset) {
-				status = ocfs2_extend_dir(osb,
-							  dir,
-							  parent_fe_bh,
-							  &bh);
-				if (status < 0) {
-					mlog_errno(status);
-					goto bail;
-				}
-				BUG_ON(!bh);
-				*ret_de_bh = bh;
-				get_bh(*ret_de_bh);
+				/*
+				 * Caller will have to expand this
+				 * directory.
+				 */
+				status = -ENOSPC;
 				goto bail;
 			}
 			bh = ocfs2_bread(dir,
@@ -600,10 +1678,7 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 			status = -EEXIST;
 			goto bail;
 		}
-		if (((le64_to_cpu(de->inode) == 0) &&
-		     (le16_to_cpu(de->rec_len) >= rec_len)) ||
-		    (le16_to_cpu(de->rec_len) >=
-		     (OCFS2_DIR_REC_LEN(de->name_len) + rec_len))) {
+		if (ocfs2_dirent_would_fit(de, rec_len)) {
 			/* Ok, we found a spot. Return this bh and let
 			 * the caller actually fill it in. */
 			*ret_de_bh = bh;
@@ -623,3 +1698,61 @@ bail:
 	mlog_exit(status);
 	return status;
 }
+
+int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
+				 struct inode *dir,
+				 struct buffer_head *parent_fe_bh,
+				 const char *name,
+				 int namelen,
+				 struct buffer_head **ret_de_bh)
+{
+	int ret;
+	unsigned int blocks_wanted = 1;
+	struct buffer_head *bh = NULL;
+
+	mlog(0, "getting ready to insert namelen %d into dir %llu\n",
+	     namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno);
+
+	*ret_de_bh = NULL;
+
+	if (!namelen) {
+		ret = -EINVAL;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = ocfs2_find_dir_space_id(dir, parent_fe_bh, name,
+					      namelen, &bh, &blocks_wanted);
+	} else
+		ret = ocfs2_find_dir_space_el(dir, name, namelen, &bh);
+
+	if (ret && ret != -ENOSPC) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ret == -ENOSPC) {
+		/*
+		 * We have to expand the directory to add this name.
+		 */
+		BUG_ON(bh);
+
+		ret = ocfs2_extend_dir(osb, dir, parent_fe_bh, blocks_wanted,
+				       &bh);
+		if (ret) {
+			if (ret != -ENOSPC)
+				mlog_errno(ret);
+			goto out;
+		}
+
+		BUG_ON(!bh);
+	}
+
+	*ret_de_bh = bh;
+	bh = NULL;
+out:
+	if (bh)
+		brelse(bh);
+	return ret;
+}
diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h
index 3f67e146864a..ce48b9080d87 100644
--- a/fs/ocfs2/dir.h
+++ b/fs/ocfs2/dir.h
@@ -26,17 +26,49 @@
 #ifndef OCFS2_DIR_H
 #define OCFS2_DIR_H
 
+struct buffer_head *ocfs2_find_entry(const char *name,
+				     int namelen,
+				     struct inode *dir,
+				     struct ocfs2_dir_entry **res_dir);
+int ocfs2_delete_entry(handle_t *handle,
+		       struct inode *dir,
+		       struct ocfs2_dir_entry *de_del,
+		       struct buffer_head *bh);
+int __ocfs2_add_entry(handle_t *handle,
+		      struct inode *dir,
+		      const char *name, int namelen,
+		      struct inode *inode, u64 blkno,
+		      struct buffer_head *parent_fe_bh,
+		      struct buffer_head *insert_bh);
+static inline int ocfs2_add_entry(handle_t *handle,
+				  struct dentry *dentry,
+				  struct inode *inode, u64 blkno,
+				  struct buffer_head *parent_fe_bh,
+				  struct buffer_head *insert_bh)
+{
+	return __ocfs2_add_entry(handle, dentry->d_parent->d_inode,
+				 dentry->d_name.name, dentry->d_name.len,
+				 inode, blkno, parent_fe_bh, insert_bh);
+}
+int ocfs2_update_entry(struct inode *dir, handle_t *handle,
+		       struct buffer_head *de_bh, struct ocfs2_dir_entry *de,
+		       struct inode *new_entry_inode);
+
 int ocfs2_check_dir_for_entry(struct inode *dir,
 			      const char *name,
 			      int namelen);
-int ocfs2_empty_dir(struct inode *inode);  /* FIXME: to namei.c */
+int ocfs2_empty_dir(struct inode *inode);
 int ocfs2_find_files_on_disk(const char *name,
 			     int namelen,
 			     u64 *blkno,
 			     struct inode *inode,
 			     struct buffer_head **dirent_bh,
 			     struct ocfs2_dir_entry **dirent);
+int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
+			       int namelen, u64 *blkno);
 int ocfs2_readdir(struct file *filp, void *dirent, filldir_t filldir);
+int ocfs2_dir_foreach(struct inode *inode, loff_t *f_pos, void *priv,
+		      filldir_t filldir);
 int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 				 struct inode *dir,
 				 struct buffer_head *parent_fe_bh,
@@ -44,11 +76,11 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 				 int namelen,
 				 struct buffer_head **ret_de_bh);
 struct ocfs2_alloc_context;
-int ocfs2_do_extend_dir(struct super_block *sb,
-			handle_t *handle,
-			struct inode *dir,
-			struct buffer_head *parent_fe_bh,
-			struct ocfs2_alloc_context *data_ac,
-			struct ocfs2_alloc_context *meta_ac,
-			struct buffer_head **new_bh);
+int ocfs2_fill_new_dir(struct ocfs2_super *osb,
+		       handle_t *handle,
+		       struct inode *parent,
+		       struct inode *inode,
+		       struct buffer_head *fe_bh,
+		       struct ocfs2_alloc_context *data_ac);
+
 #endif /* OCFS2_DIR_H */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index f71250ed166f..41c76ff2fcfb 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1482,6 +1482,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	lvb->lvb_imtime_packed =
 		cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
 	lvb->lvb_iattr    = cpu_to_be32(oi->ip_attr);
+	lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features);
 	lvb->lvb_igeneration = cpu_to_be32(inode->i_generation);
 
 out:
@@ -1515,6 +1516,7 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 	i_size_write(inode, be64_to_cpu(lvb->lvb_isize));
 
 	oi->ip_attr = be32_to_cpu(lvb->lvb_iattr);
+	oi->ip_dyn_features = be16_to_cpu(lvb->lvb_idynfeatures);
 	ocfs2_set_inode_flags(inode);
 
 	/* fast-symlinks are a special case */
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 492bad32a8c0..87a785e41205 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -29,12 +29,12 @@
 
 #include "dcache.h"
 
-#define OCFS2_LVB_VERSION 4
+#define OCFS2_LVB_VERSION 5
 
 struct ocfs2_meta_lvb {
 	__u8         lvb_version;
 	__u8         lvb_reserved0;
-	__be16       lvb_reserved1;
+	__be16       lvb_idynfeatures;
 	__be32       lvb_iclusters;
 	__be32       lvb_iuid;
 	__be32       lvb_igid;
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index bc48177bd183..c3bbc198f9ce 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -88,8 +88,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 	struct dentry *parent;
 	struct inode *inode;
 	struct inode *dir = child->d_inode;
-	struct buffer_head *dirent_bh = NULL;
-	struct ocfs2_dir_entry *dirent;
 
 	mlog_entry("(0x%p, '%.*s')\n", child,
 		   child->d_name.len, child->d_name.name);
@@ -105,8 +103,7 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 		goto bail;
 	}
 
-	status = ocfs2_find_files_on_disk("..", 2, &blkno, dir, &dirent_bh,
-					  &dirent);
+	status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno);
 	if (status < 0) {
 		parent = ERR_PTR(-ENOENT);
 		goto bail_unlock;
@@ -131,9 +128,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 bail_unlock:
 	ocfs2_meta_unlock(dir, 0);
 
-	if (dirent_bh)
-		brelse(dirent_bh);
-
 bail:
 	mlog_exit_ptr(parent);
 
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 03c1d365c78b..c58668a326fe 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -387,6 +387,12 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
 	struct ocfs2_extent_rec *rec;
 	u32 coff;
 
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = -ERANGE;
+		mlog_errno(ret);
+		goto out;
+	}
+
 	ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
 				      num_clusters, extent_flags);
 	if (ret == 0)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index f3bc3658e7a5..a62b14eb4065 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -397,6 +397,15 @@ static int ocfs2_truncate_file(struct inode *inode,
 	unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
 	truncate_inode_pages(inode->i_mapping, new_i_size);
 
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		status = ocfs2_truncate_inline(inode, di_bh, new_i_size,
+					       i_size_read(inode), 0);
+		if (status)
+			mlog_errno(status);
+
+		goto bail_unlock_data;
+	}
+
 	/* alright, we're going to need to do a full blown alloc size
 	 * change. Orphan the inode so that recovery can complete the
 	 * truncate if necessary. This does the task of marking
@@ -779,25 +788,6 @@ leave:
 	return status;
 }
 
-static int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
-				   u32 clusters_to_add, int mark_unwritten)
-{
-	int ret;
-
-	/*
-	 * The alloc sem blocks peope in read/write from reading our
-	 * allocation until we're done changing it. We depend on
-	 * i_mutex to block other extend/truncate calls while we're
-	 * here.
-	 */
-	down_write(&OCFS2_I(inode)->ip_alloc_sem);
-	ret = __ocfs2_extend_allocation(inode, logical_start, clusters_to_add,
-					mark_unwritten);
-	up_write(&OCFS2_I(inode)->ip_alloc_sem);
-
-	return ret;
-}
-
 /* Some parts of this taken from generic_cont_expand, which turned out
  * to be too fragile to do exactly what we need without us having to
  * worry about recursive locking in ->prepare_write() and
@@ -889,25 +879,48 @@ out:
 	return ret;
 }
 
-/* 
- * A tail_to_skip value > 0 indicates that we're being called from
- * ocfs2_file_aio_write(). This has the following implications:
- *
- * - we don't want to update i_size
- * - di_bh will be NULL, which is fine because it's only used in the
- *   case where we want to update i_size.
- * - ocfs2_zero_extend() will then only be filling the hole created
- *   between i_size and the start of the write.
- */
+int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to)
+{
+	int ret;
+	u32 clusters_to_add;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+	clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size);
+	if (clusters_to_add < oi->ip_clusters)
+		clusters_to_add = 0;
+	else
+		clusters_to_add -= oi->ip_clusters;
+
+	if (clusters_to_add) {
+		ret = __ocfs2_extend_allocation(inode, oi->ip_clusters,
+						clusters_to_add, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	/*
+	 * Call this even if we don't add any clusters to the tree. We
+	 * still need to zero the area between the old i_size and the
+	 * new i_size.
+	 */
+	ret = ocfs2_zero_extend(inode, zero_to);
+	if (ret < 0)
+		mlog_errno(ret);
+
+out:
+	return ret;
+}
+
 static int ocfs2_extend_file(struct inode *inode,
 			     struct buffer_head *di_bh,
-			     u64 new_i_size,
-			     size_t tail_to_skip)
+			     u64 new_i_size)
 {
-	int ret = 0;
-	u32 clusters_to_add = 0;
+	int ret = 0, data_locked = 0;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	BUG_ON(!tail_to_skip && !di_bh);
+	BUG_ON(!di_bh);
 
 	/* setattr sometimes calls us like this. */
 	if (new_i_size == 0)
@@ -917,13 +930,18 @@ static int ocfs2_extend_file(struct inode *inode,
   		goto out;
 	BUG_ON(new_i_size < i_size_read(inode));
 
-	if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-		BUG_ON(tail_to_skip != 0);
+	/*
+	 * Fall through for converting inline data, even if the fs
+	 * supports sparse files.
+	 *
+	 * The check for inline data here is legal - nobody can add
+	 * the feature since we have i_mutex. We must check it again
+	 * after acquiring ip_alloc_sem though, as paths like mmap
+	 * might have raced us to converting the inode to extents.
+	 */
+	if (!(oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+	    && ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
 		goto out_update_size;
-	}
-
-	clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size) - 
-		OCFS2_I(inode)->ip_clusters;
 
 	/* 
 	 * protect the pages that ocfs2_zero_extend is going to be
@@ -937,39 +955,52 @@ static int ocfs2_extend_file(struct inode *inode,
 		mlog_errno(ret);
 		goto out;
 	}
+	data_locked = 1;
+
+	/*
+	 * The alloc sem blocks people in read/write from reading our
+	 * allocation until we're done changing it. We depend on
+	 * i_mutex to block other extend/truncate calls while we're
+	 * here.
+	 */
+	down_write(&oi->ip_alloc_sem);
+
+	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		/*
+		 * We can optimize small extends by keeping the inodes
+		 * inline data.
+		 */
+		if (ocfs2_size_fits_inline_data(di_bh, new_i_size)) {
+			up_write(&oi->ip_alloc_sem);
+			goto out_update_size;
+		}
+
+		ret = ocfs2_convert_inline_data_to_extents(inode, di_bh);
+		if (ret) {
+			up_write(&oi->ip_alloc_sem);
 
-	if (clusters_to_add) {
-		ret = ocfs2_extend_allocation(inode,
-					      OCFS2_I(inode)->ip_clusters,
-					      clusters_to_add, 0);
-		if (ret < 0) {
 			mlog_errno(ret);
 			goto out_unlock;
 		}
 	}
 
-	/*
-	 * Call this even if we don't add any clusters to the tree. We
-	 * still need to zero the area between the old i_size and the
-	 * new i_size.
-	 */
-	ret = ocfs2_zero_extend(inode, (u64)new_i_size - tail_to_skip);
+	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		ret = ocfs2_extend_no_holes(inode, new_i_size, new_i_size);
+
+	up_write(&oi->ip_alloc_sem);
+
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out_unlock;
 	}
 
 out_update_size:
-	if (!tail_to_skip) {
-		/* We're being called from ocfs2_setattr() which wants
-		 * us to update i_size */
-		ret = ocfs2_simple_size_update(inode, di_bh, new_i_size);
-		if (ret < 0)
-			mlog_errno(ret);
-	}
+	ret = ocfs2_simple_size_update(inode, di_bh, new_i_size);
+	if (ret < 0)
+		mlog_errno(ret);
 
 out_unlock:
-	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+	if (data_locked)
 		ocfs2_data_unlock(inode, 1);
 
 out:
@@ -1035,7 +1066,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		if (i_size_read(inode) > attr->ia_size)
 			status = ocfs2_truncate_file(inode, bh, attr->ia_size);
 		else
-			status = ocfs2_extend_file(inode, bh, attr->ia_size, 0);
+			status = ocfs2_extend_file(inode, bh, attr->ia_size);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -1243,6 +1274,31 @@ static int ocfs2_allocate_unwritten_extents(struct inode *inode,
 {
 	int ret;
 	u32 cpos, phys_cpos, clusters, alloc_size;
+	u64 end = start + len;
+	struct buffer_head *di_bh = NULL;
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
+				       OCFS2_I(inode)->ip_blkno, &di_bh,
+				       OCFS2_BH_CACHED, inode);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		/*
+		 * Nothing to do if the requested reservation range
+		 * fits within the inode.
+		 */
+		if (ocfs2_size_fits_inline_data(di_bh, end))
+			goto out;
+
+		ret = ocfs2_convert_inline_data_to_extents(inode, di_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
 
 	/*
 	 * We consider both start and len to be inclusive.
@@ -1288,6 +1344,8 @@ next:
 
 	ret = 0;
 out:
+
+	brelse(di_bh);
 	return ret;
 }
 
@@ -1469,6 +1527,14 @@ static int ocfs2_remove_inode_range(struct inode *inode,
 	if (byte_len == 0)
 		return 0;
 
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		ret = ocfs2_truncate_inline(inode, di_bh, byte_start,
+					    byte_start + byte_len, 1);
+		if (ret)
+			mlog_errno(ret);
+		return ret;
+	}
+
 	trunc_start = ocfs2_clusters_for_bytes(osb->sb, byte_start);
 	trunc_len = (byte_start + byte_len) >> osb->s_clustersize_bits;
 	if (trunc_len >= trunc_start)
@@ -1713,15 +1779,13 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
 					 int appending,
 					 int *direct_io)
 {
-	int ret = 0, meta_level = appending;
+	int ret = 0, meta_level = 0;
 	struct inode *inode = dentry->d_inode;
-	u32 clusters;
-	loff_t newsize, saved_pos;
+	loff_t saved_pos, end;
 
 	/* 
-	 * We sample i_size under a read level meta lock to see if our write
-	 * is extending the file, if it is we back off and get a write level
-	 * meta lock.
+	 * We start with a read level meta lock and only jump to an ex
+	 * if we need to make modifications here.
 	 */
 	for(;;) {
 		ret = ocfs2_meta_lock(inode, NULL, meta_level);
@@ -1763,87 +1827,47 @@ static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
 			saved_pos = *ppos;
 		}
 
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-			loff_t end = saved_pos + count;
+		end = saved_pos + count;
 
-			/*
-			 * Skip the O_DIRECT checks if we don't need
-			 * them.
-			 */
-			if (!direct_io || !(*direct_io))
-				break;
-
-			/*
-			 * Allowing concurrent direct writes means
-			 * i_size changes wouldn't be synchronized, so
-			 * one node could wind up truncating another
-			 * nodes writes.
-			 */
-			if (end > i_size_read(inode)) {
-				*direct_io = 0;
-				break;
-			}
-
-			/*
-			 * We don't fill holes during direct io, so
-			 * check for them here. If any are found, the
-			 * caller will have to retake some cluster
-			 * locks and initiate the io as buffered.
-			 */
-			ret = ocfs2_check_range_for_holes(inode, saved_pos,
-							  count);
-			if (ret == 1) {
-				*direct_io = 0;
-				ret = 0;
-			} else if (ret < 0)
-				mlog_errno(ret);
+		/*
+		 * Skip the O_DIRECT checks if we don't need
+		 * them.
+		 */
+		if (!direct_io || !(*direct_io))
 			break;
-		}
 
 		/*
-		 * The rest of this loop is concerned with legacy file
-		 * systems which don't support sparse files.
+		 * There's no sane way to do direct writes to an inode
+		 * with inline data.
 		 */
-
-		newsize = count + saved_pos;
-
-		mlog(0, "pos=%lld newsize=%lld cursize=%lld\n",
-		     (long long) saved_pos, (long long) newsize,
-		     (long long) i_size_read(inode));
-
-		/* No need for a higher level metadata lock if we're
-		 * never going past i_size. */
-		if (newsize <= i_size_read(inode))
+		if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+			*direct_io = 0;
 			break;
-
-		if (meta_level == 0) {
-			ocfs2_meta_unlock(inode, meta_level);
-			meta_level = 1;
-			continue;
 		}
 
-		spin_lock(&OCFS2_I(inode)->ip_lock);
-		clusters = ocfs2_clusters_for_bytes(inode->i_sb, newsize) -
-			OCFS2_I(inode)->ip_clusters;
-		spin_unlock(&OCFS2_I(inode)->ip_lock);
-
-		mlog(0, "Writing at EOF, may need more allocation: "
-		     "i_size = %lld, newsize = %lld, need %u clusters\n",
-		     (long long) i_size_read(inode), (long long) newsize,
-		     clusters);
-
-		/* We only want to continue the rest of this loop if
-		 * our extend will actually require more
-		 * allocation. */
-		if (!clusters)
+		/*
+		 * Allowing concurrent direct writes means
+		 * i_size changes wouldn't be synchronized, so
+		 * one node could wind up truncating another
+		 * nodes writes.
+		 */
+		if (end > i_size_read(inode)) {
+			*direct_io = 0;
 			break;
-
-		ret = ocfs2_extend_file(inode, NULL, newsize, count);
-		if (ret < 0) {
-			if (ret != -ENOSPC)
-				mlog_errno(ret);
-			goto out_unlock;
 		}
+
+		/*
+		 * We don't fill holes during direct io, so
+		 * check for them here. If any are found, the
+		 * caller will have to retake some cluster
+		 * locks and initiate the io as buffered.
+		 */
+		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
+		if (ret == 1) {
+			*direct_io = 0;
+			ret = 0;
+		} else if (ret < 0)
+			mlog_errno(ret);
 		break;
 	}
 
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 36fe27f268ee..066f14add3a8 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -47,6 +47,8 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size,
+			  u64 zero_to);
 int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di,
 			  u32 clusters_to_add, u32 extents_to_split,
 			  struct ocfs2_alloc_context **data_ac,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index c53a6763bbbe..1d5e0cb0fda1 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -241,6 +241,7 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 
 	OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
 	OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr);
+	OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
 
 	inode->i_version = 1;
 	inode->i_generation = le32_to_cpu(fe->i_generation);
@@ -513,6 +514,10 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 
 	fe = (struct ocfs2_dinode *) fe_bh->b_data;
 
+	/*
+	 * This check will also skip truncate of inodes with inline
+	 * data and fast symlinks.
+	 */
 	if (fe->i_clusters) {
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
@@ -1220,6 +1225,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
 	fe->i_clusters = cpu_to_le32(OCFS2_I(inode)->ip_clusters);
 	ocfs2_get_inode_flags(OCFS2_I(inode));
 	fe->i_attr = cpu_to_le32(OCFS2_I(inode)->ip_attr);
+	fe->i_dyn_features = cpu_to_le16(OCFS2_I(inode)->ip_dyn_features);
 	spin_unlock(&OCFS2_I(inode)->ip_lock);
 
 	fe->i_size = cpu_to_le64(i_size_read(inode));
@@ -1257,6 +1263,7 @@ void ocfs2_refresh_inode(struct inode *inode,
 
 	OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
 	OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr);
+	OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
 	ocfs2_set_inode_flags(inode);
 	i_size_write(inode, le64_to_cpu(fe->i_size));
 	inode->i_nlink = le16_to_cpu(fe->i_links_count);
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index a41d0817121b..70e881c55536 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -51,6 +51,7 @@ struct ocfs2_inode_info
 
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
+	u16				ip_dyn_features;
 
 	/* protected by recovery_lock. */
 	struct inode			*ip_next_orphan;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index dbfb20bb27ea..f9d01e25298d 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -35,13 +35,13 @@
 #include "ocfs2.h"
 
 #include "alloc.h"
+#include "dir.h"
 #include "dlmglue.h"
 #include "extent_map.h"
 #include "heartbeat.h"
 #include "inode.h"
 #include "journal.h"
 #include "localalloc.h"
-#include "namei.h"
 #include "slot_map.h"
 #include "super.h"
 #include "vote.h"
@@ -1213,17 +1213,49 @@ bail:
 	return status;
 }
 
+struct ocfs2_orphan_filldir_priv {
+	struct inode		*head;
+	struct ocfs2_super	*osb;
+};
+
+static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len,
+				loff_t pos, u64 ino, unsigned type)
+{
+	struct ocfs2_orphan_filldir_priv *p = priv;
+	struct inode *iter;
+
+	if (name_len == 1 && !strncmp(".", name, 1))
+		return 0;
+	if (name_len == 2 && !strncmp("..", name, 2))
+		return 0;
+
+	/* Skip bad inodes so that recovery can continue */
+	iter = ocfs2_iget(p->osb, ino,
+			  OCFS2_FI_FLAG_ORPHAN_RECOVERY);
+	if (IS_ERR(iter))
+		return 0;
+
+	mlog(0, "queue orphan %llu\n",
+	     (unsigned long long)OCFS2_I(iter)->ip_blkno);
+	/* No locking is required for the next_orphan queue as there
+	 * is only ever a single process doing orphan recovery. */
+	OCFS2_I(iter)->ip_next_orphan = p->head;
+	p->head = iter;
+
+	return 0;
+}
+
 static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 			       int slot,
 			       struct inode **head)
 {
 	int status;
 	struct inode *orphan_dir_inode = NULL;
-	struct inode *iter;
-	unsigned long offset, blk, local;
-	struct buffer_head *bh = NULL;
-	struct ocfs2_dir_entry *de;
-	struct super_block *sb = osb->sb;
+	struct ocfs2_orphan_filldir_priv priv;
+	loff_t pos = 0;
+
+	priv.osb = osb;
+	priv.head = *head;
 
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
 						       ORPHAN_DIR_SYSTEM_INODE,
@@ -1241,77 +1273,15 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 		goto out;
 	}
 
-	offset = 0;
-	iter = NULL;
-	while(offset < i_size_read(orphan_dir_inode)) {
-		blk = offset >> sb->s_blocksize_bits;
-
-		bh = ocfs2_bread(orphan_dir_inode, blk, &status, 0);
-		if (!bh)
-			status = -EINVAL;
-		if (status < 0) {
-			if (bh)
-				brelse(bh);
-			mlog_errno(status);
-			goto out_unlock;
-		}
-
-		local = 0;
-		while(offset < i_size_read(orphan_dir_inode)
-		      && local < sb->s_blocksize) {
-			de = (struct ocfs2_dir_entry *) (bh->b_data + local);
-
-			if (!ocfs2_check_dir_entry(orphan_dir_inode,
-						  de, bh, local)) {
-				status = -EINVAL;
-				mlog_errno(status);
-				brelse(bh);
-				goto out_unlock;
-			}
-
-			local += le16_to_cpu(de->rec_len);
-			offset += le16_to_cpu(de->rec_len);
-
-			/* I guess we silently fail on no inode? */
-			if (!le64_to_cpu(de->inode))
-				continue;
-			if (de->file_type > OCFS2_FT_MAX) {
-				mlog(ML_ERROR,
-				     "block %llu contains invalid de: "
-				     "inode = %llu, rec_len = %u, "
-				     "name_len = %u, file_type = %u, "
-				     "name='%.*s'\n",
-				     (unsigned long long)bh->b_blocknr,
-				     (unsigned long long)le64_to_cpu(de->inode),
-				     le16_to_cpu(de->rec_len),
-				     de->name_len,
-				     de->file_type,
-				     de->name_len,
-				     de->name);
-				continue;
-			}
-			if (de->name_len == 1 && !strncmp(".", de->name, 1))
-				continue;
-			if (de->name_len == 2 && !strncmp("..", de->name, 2))
-				continue;
-
-			iter = ocfs2_iget(osb, le64_to_cpu(de->inode),
-					  OCFS2_FI_FLAG_ORPHAN_RECOVERY);
-			if (IS_ERR(iter))
-				continue;
-
-			mlog(0, "queue orphan %llu\n",
-			     (unsigned long long)OCFS2_I(iter)->ip_blkno);
-			/* No locking is required for the next_orphan
-			 * queue as there is only ever a single
-			 * process doing orphan recovery. */
-			OCFS2_I(iter)->ip_next_orphan = *head;
-			*head = iter;
-		}
-		brelse(bh);
+	status = ocfs2_dir_foreach(orphan_dir_inode, &pos, &priv,
+				   ocfs2_orphan_filldir);
+	if (status) {
+		mlog_errno(status);
+		goto out;
 	}
 
-out_unlock:
+	*head = priv.head;
+
 	ocfs2_meta_unlock(orphan_dir_inode, 0);
 out:
 	mutex_unlock(&orphan_dir_inode->i_mutex);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index ce60aab013aa..4b32e0961568 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -282,6 +282,9 @@ int                  ocfs2_journal_dirty_data(handle_t *handle,
  * prev. group desc. if we relink. */
 #define OCFS2_SUBALLOC_ALLOC (3)
 
+#define OCFS2_INLINE_TO_EXTENTS_CREDITS (OCFS2_SUBALLOC_ALLOC		\
+					 + OCFS2_INODE_UPDATE_CREDITS)
+
 /* dinode + group descriptor update. We don't relink on free yet. */
 #define OCFS2_SUBALLOC_FREE  (2)
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 701e6d04ed5d..729259016c18 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -64,29 +64,6 @@
 
 #include "buffer_head_io.h"
 
-#define NAMEI_RA_CHUNKS  2
-#define NAMEI_RA_BLOCKS  4
-#define NAMEI_RA_SIZE        (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-#define NAMEI_RA_INDEX(c,b)  (((c) * NAMEI_RA_BLOCKS) + (b))
-
-static int inline ocfs2_search_dirblock(struct buffer_head *bh,
-					struct inode *dir,
-					const char *name, int namelen,
-					unsigned long offset,
-					struct ocfs2_dir_entry **res_dir);
-
-static int ocfs2_delete_entry(handle_t *handle,
-			      struct inode *dir,
-			      struct ocfs2_dir_entry *de_del,
-			      struct buffer_head *bh);
-
-static int __ocfs2_add_entry(handle_t *handle,
-			     struct inode *dir,
-			     const char *name, int namelen,
-			     struct inode *inode, u64 blkno,
-			     struct buffer_head *parent_fe_bh,
-			     struct buffer_head *insert_bh);
-
 static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 			      struct inode *dir,
 			      struct dentry *dentry, int mode,
@@ -97,13 +74,6 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 			      struct inode **ret_inode,
 			      struct ocfs2_alloc_context *inode_ac);
 
-static int ocfs2_fill_new_dir(struct ocfs2_super *osb,
-			      handle_t *handle,
-			      struct inode *parent,
-			      struct inode *inode,
-			      struct buffer_head *fe_bh,
-			      struct ocfs2_alloc_context *data_ac);
-
 static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    struct inode *inode,
@@ -123,17 +93,6 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     struct inode *inode,
 				     const char *symname);
 
-static inline int ocfs2_add_entry(handle_t *handle,
-				  struct dentry *dentry,
-				  struct inode *inode, u64 blkno,
-				  struct buffer_head *parent_fe_bh,
-				  struct buffer_head *insert_bh)
-{
-	return __ocfs2_add_entry(handle, dentry->d_parent->d_inode,
-				 dentry->d_name.name, dentry->d_name.len,
-				 inode, blkno, parent_fe_bh, insert_bh);
-}
-
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
 
@@ -142,10 +101,8 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 {
 	int status;
 	u64 blkno;
-	struct buffer_head *dirent_bh = NULL;
 	struct inode *inode = NULL;
 	struct dentry *ret;
-	struct ocfs2_dir_entry *dirent;
 	struct ocfs2_inode_info *oi;
 
 	mlog_entry("(0x%p, 0x%p, '%.*s')\n", dir, dentry,
@@ -167,9 +124,8 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 		goto bail;
 	}
 
-	status = ocfs2_find_files_on_disk(dentry->d_name.name,
-					  dentry->d_name.len, &blkno,
-					  dir, &dirent_bh, &dirent);
+	status = ocfs2_lookup_ino_from_name(dir, dentry->d_name.name,
+					    dentry->d_name.len, &blkno);
 	if (status < 0)
 		goto bail_add;
 
@@ -224,83 +180,12 @@ bail_unlock:
 	ocfs2_meta_unlock(dir, 0);
 
 bail:
-	if (dirent_bh)
-		brelse(dirent_bh);
 
 	mlog_exit_ptr(ret);
 
 	return ret;
 }
 
-static int ocfs2_fill_new_dir(struct ocfs2_super *osb,
-			      handle_t *handle,
-			      struct inode *parent,
-			      struct inode *inode,
-			      struct buffer_head *fe_bh,
-			      struct ocfs2_alloc_context *data_ac)
-{
-	int status;
-	struct buffer_head *new_bh = NULL;
-	struct ocfs2_dir_entry *de = NULL;
-
-	mlog_entry_void();
-
-	status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh,
-				     data_ac, NULL, &new_bh);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-
-	ocfs2_set_new_buffer_uptodate(inode, new_bh);
-
-	status = ocfs2_journal_access(handle, inode, new_bh,
-				      OCFS2_JOURNAL_ACCESS_CREATE);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-	memset(new_bh->b_data, 0, osb->sb->s_blocksize);
-
-	de = (struct ocfs2_dir_entry *) new_bh->b_data;
-	de->inode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
-	de->name_len = 1;
-	de->rec_len =
-		cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
-	strcpy(de->name, ".");
-	ocfs2_set_de_type(de, S_IFDIR);
-	de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len));
-	de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno);
-	de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize -
-				  OCFS2_DIR_REC_LEN(1));
-	de->name_len = 2;
-	strcpy(de->name, "..");
-	ocfs2_set_de_type(de, S_IFDIR);
-
-	status = ocfs2_journal_dirty(handle, new_bh);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-
-	i_size_write(inode, inode->i_sb->s_blocksize);
-	inode->i_nlink = 2;
-	inode->i_blocks = ocfs2_inode_sector_count(inode);
-	status = ocfs2_mark_inode_dirty(handle, inode, fe_bh);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-
-	status = 0;
-bail:
-	if (new_bh)
-		brelse(new_bh);
-
-	mlog_exit(status);
-	return status;
-}
-
 static int ocfs2_mknod(struct inode *dir,
 		       struct dentry *dentry,
 		       int mode,
@@ -365,9 +250,8 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
-	/* are we making a directory? If so, reserve a cluster for his
-	 * 1st extent. */
-	if (S_ISDIR(mode)) {
+	/* Reserve a cluster if creating an extent based directory. */
+	if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) {
 		status = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (status < 0) {
 			if (status != -ENOSPC)
@@ -564,10 +448,21 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 		cpu_to_le32(CURRENT_TIME.tv_nsec);
 	fe->i_dtime = 0;
 
-	fel = &fe->id2.i_list;
-	fel->l_tree_depth = 0;
-	fel->l_next_free_rec = 0;
-	fel->l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(osb->sb));
+	/*
+	 * If supported, directories start with inline data.
+	 */
+	if (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) {
+		u16 feat = le16_to_cpu(fe->i_dyn_features);
+
+		fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL);
+
+		fe->id2.i_data.id_count = cpu_to_le16(ocfs2_max_inline_data(osb->sb));
+	} else {
+		fel = &fe->id2.i_list;
+		fel->l_tree_depth = 0;
+		fel->l_next_free_rec = 0;
+		fel->l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(osb->sb));
+	}
 
 	status = ocfs2_journal_dirty(handle, *new_fe_bh);
 	if (status < 0) {
@@ -1048,11 +943,6 @@ static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2)
 		ocfs2_meta_unlock(inode2, 1);
 }
 
-#define PARENT_INO(buffer) \
-	((struct ocfs2_dir_entry *) \
-	 ((char *)buffer + \
-	  le16_to_cpu(((struct ocfs2_dir_entry *)buffer)->rec_len)))->inode
-
 static int ocfs2_rename(struct inode *old_dir,
 			struct dentry *old_dentry,
 			struct inode *new_dir,
@@ -1070,12 +960,12 @@ static int ocfs2_rename(struct inode *old_dir,
 	struct buffer_head *old_inode_bh = NULL;
 	struct buffer_head *insert_entry_bh = NULL;
 	struct ocfs2_super *osb = NULL;
-	u64 newfe_blkno;
+	u64 newfe_blkno, old_de_ino;
 	handle_t *handle = NULL;
 	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *new_dir_bh = NULL;
-	struct ocfs2_dir_entry *old_de = NULL, *new_de = NULL; // dirent for old_dentry
-							       // and new_dentry
+	struct ocfs2_dir_entry *old_inode_dot_dot_de = NULL, *old_de = NULL,
+		*new_de = NULL;
 	struct buffer_head *new_de_bh = NULL, *old_de_bh = NULL; // bhs for above
 	struct buffer_head *old_inode_de_bh = NULL; // if old_dentry is a dir,
 						    // this is the 1st dirent bh
@@ -1159,27 +1049,35 @@ static int ocfs2_rename(struct inode *old_dir,
 	}
 
 	if (S_ISDIR(old_inode->i_mode)) {
-		status = -EIO;
-		old_inode_de_bh = ocfs2_bread(old_inode, 0, &status, 0);
-		if (!old_inode_de_bh)
+		u64 old_inode_parent;
+
+		status = ocfs2_find_files_on_disk("..", 2, &old_inode_parent,
+						  old_inode, &old_inode_de_bh,
+						  &old_inode_dot_dot_de);
+		if (status) {
+			status = -EIO;
 			goto bail;
+		}
 
-		status = -EIO;
-		if (le64_to_cpu(PARENT_INO(old_inode_de_bh->b_data)) !=
-		    OCFS2_I(old_dir)->ip_blkno)
+		if (old_inode_parent != OCFS2_I(old_dir)->ip_blkno) {
+			status = -EIO;
 			goto bail;
-		status = -EMLINK;
-		if (!new_inode && new_dir!=old_dir &&
-		    new_dir->i_nlink >= OCFS2_LINK_MAX)
+		}
+
+		if (!new_inode && new_dir != old_dir &&
+		    new_dir->i_nlink >= OCFS2_LINK_MAX) {
+			status = -EMLINK;
 			goto bail;
+		}
 	}
 
-	status = -ENOENT;
-	old_de_bh = ocfs2_find_entry(old_dentry->d_name.name,
-				     old_dentry->d_name.len,
-				     old_dir, &old_de);
-	if (!old_de_bh)
+	status = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name,
+					    old_dentry->d_name.len,
+					    &old_de_ino);
+	if (status) {
+		status = -ENOENT;
 		goto bail;
+	}
 
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
@@ -1187,8 +1085,10 @@ static int ocfs2_rename(struct inode *old_dir,
 	 *  and merrily kill the link to whatever was created under the
 	 *  same name. Goodbye sticky bit ;-<
 	 */
-	if (le64_to_cpu(old_de->inode) != OCFS2_I(old_inode)->ip_blkno)
+	if (old_de_ino != OCFS2_I(old_inode)->ip_blkno) {
+		status = -ENOENT;
 		goto bail;
+	}
 
 	/* check if the target already exists (in which case we need
 	 * to delete it */
@@ -1321,20 +1221,13 @@ static int ocfs2_rename(struct inode *old_dir,
 		}
 
 		/* change the dirent to point to the correct inode */
-		status = ocfs2_journal_access(handle, new_dir, new_de_bh,
-					      OCFS2_JOURNAL_ACCESS_WRITE);
+		status = ocfs2_update_entry(new_dir, handle, new_de_bh,
+					    new_de, old_inode);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail;
 		}
-		new_de->inode = cpu_to_le64(OCFS2_I(old_inode)->ip_blkno);
-		new_de->file_type = old_de->file_type;
 		new_dir->i_version++;
-		status = ocfs2_journal_dirty(handle, new_de_bh);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
 
 		if (S_ISDIR(new_inode->i_mode))
 			newfe->i_links_count = 0;
@@ -1370,7 +1263,21 @@ static int ocfs2_rename(struct inode *old_dir,
 	} else
 		mlog_errno(status);
 
-	/* now that the name has been added to new_dir, remove the old name */
+	/*
+	 * Now that the name has been added to new_dir, remove the old name.
+	 *
+	 * We don't keep any directory entry context around until now
+	 * because the insert might have changed the type of directory
+	 * we're dealing with.
+	 */
+	old_de_bh = ocfs2_find_entry(old_dentry->d_name.name,
+				     old_dentry->d_name.len,
+				     old_dir, &old_de);
+	if (!old_de_bh) {
+		status = -EIO;
+		goto bail;
+	}
+
 	status = ocfs2_delete_entry(handle, old_dir, old_de, old_de_bh);
 	if (status < 0) {
 		mlog_errno(status);
@@ -1383,12 +1290,8 @@ static int ocfs2_rename(struct inode *old_dir,
 	}
 	old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME;
 	if (old_inode_de_bh) {
-		status = ocfs2_journal_access(handle, old_inode,
-					     old_inode_de_bh,
-					     OCFS2_JOURNAL_ACCESS_WRITE);
-		PARENT_INO(old_inode_de_bh->b_data) =
-			cpu_to_le64(OCFS2_I(new_dir)->ip_blkno);
-		status = ocfs2_journal_dirty(handle, old_inode_de_bh);
+		status = ocfs2_update_entry(old_inode, handle, old_inode_de_bh,
+					    old_inode_dot_dot_de, new_dir);
 		old_dir->i_nlink--;
 		if (new_inode) {
 			new_inode->i_nlink--;
@@ -1767,329 +1670,6 @@ bail:
 	return status;
 }
 
-int ocfs2_check_dir_entry(struct inode * dir,
-			  struct ocfs2_dir_entry * de,
-			  struct buffer_head * bh,
-			  unsigned long offset)
-{
-	const char *error_msg = NULL;
-	const int rlen = le16_to_cpu(de->rec_len);
-
-	if (rlen < OCFS2_DIR_REC_LEN(1))
-		error_msg = "rec_len is smaller than minimal";
-	else if (rlen % 4 != 0)
-		error_msg = "rec_len % 4 != 0";
-	else if (rlen < OCFS2_DIR_REC_LEN(de->name_len))
-		error_msg = "rec_len is too small for name_len";
-	else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
-		error_msg = "directory entry across blocks";
-
-	if (error_msg != NULL)
-		mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
-		     "offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n",
-		     (unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg,
-		     offset, (unsigned long long)le64_to_cpu(de->inode), rlen,
-		     de->name_len);
-	return error_msg == NULL ? 1 : 0;
-}
-
-/* we don't always have a dentry for what we want to add, so people
- * like orphan dir can call this instead.
- *
- * If you pass me insert_bh, I'll skip the search of the other dir
- * blocks and put the record in there.
- */
-static int __ocfs2_add_entry(handle_t *handle,
-			     struct inode *dir,
-			     const char *name, int namelen,
-			     struct inode *inode, u64 blkno,
-			     struct buffer_head *parent_fe_bh,
-			     struct buffer_head *insert_bh)
-{
-	unsigned long offset;
-	unsigned short rec_len;
-	struct ocfs2_dir_entry *de, *de1;
-	struct super_block *sb;
-	int retval, status;
-
-	mlog_entry_void();
-
-	sb = dir->i_sb;
-
-	if (!namelen)
-		return -EINVAL;
-
-	rec_len = OCFS2_DIR_REC_LEN(namelen);
-	offset = 0;
-	de = (struct ocfs2_dir_entry *) insert_bh->b_data;
-	while (1) {
-		BUG_ON((char *)de >= sb->s_blocksize + insert_bh->b_data);
-		/* These checks should've already been passed by the
-		 * prepare function, but I guess we can leave them
-		 * here anyway. */
-		if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
-			retval = -ENOENT;
-			goto bail;
-		}
-		if (ocfs2_match(namelen, name, de)) {
-			retval = -EEXIST;
-			goto bail;
-		}
-		if (((le64_to_cpu(de->inode) == 0) &&
-		     (le16_to_cpu(de->rec_len) >= rec_len)) ||
-		    (le16_to_cpu(de->rec_len) >=
-		     (OCFS2_DIR_REC_LEN(de->name_len) + rec_len))) {
-			dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-			retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh);
-			if (retval < 0) {
-				mlog_errno(retval);
-				goto bail;
-			}
-
-			status = ocfs2_journal_access(handle, dir, insert_bh,
-						      OCFS2_JOURNAL_ACCESS_WRITE);
-			/* By now the buffer is marked for journaling */
-			offset += le16_to_cpu(de->rec_len);
-			if (le64_to_cpu(de->inode)) {
-				de1 = (struct ocfs2_dir_entry *)((char *) de +
-					OCFS2_DIR_REC_LEN(de->name_len));
-				de1->rec_len =
-					cpu_to_le16(le16_to_cpu(de->rec_len) -
-					OCFS2_DIR_REC_LEN(de->name_len));
-				de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
-				de = de1;
-			}
-			de->file_type = OCFS2_FT_UNKNOWN;
-			if (blkno) {
-				de->inode = cpu_to_le64(blkno);
-				ocfs2_set_de_type(de, inode->i_mode);
-			} else
-				de->inode = 0;
-			de->name_len = namelen;
-			memcpy(de->name, name, namelen);
-
-			dir->i_version++;
-			status = ocfs2_journal_dirty(handle, insert_bh);
-			retval = 0;
-			goto bail;
-		}
-		offset += le16_to_cpu(de->rec_len);
-		de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len));
-	}
-
-	/* when you think about it, the assert above should prevent us
-	 * from ever getting here. */
-	retval = -ENOSPC;
-bail:
-
-	mlog_exit(retval);
-	return retval;
-}
-
-
-/*
- * ocfs2_delete_entry deletes a directory entry by merging it with the
- * previous entry
- */
-static int ocfs2_delete_entry(handle_t *handle,
-			      struct inode *dir,
-			      struct ocfs2_dir_entry *de_del,
-			      struct buffer_head *bh)
-{
-	struct ocfs2_dir_entry *de, *pde;
-	int i, status = -ENOENT;
-
-	mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh);
-
-	i = 0;
-	pde = NULL;
-	de = (struct ocfs2_dir_entry *) bh->b_data;
-	while (i < bh->b_size) {
-		if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
-			status = -EIO;
-			mlog_errno(status);
-			goto bail;
-		}
-		if (de == de_del)  {
-			status = ocfs2_journal_access(handle, dir, bh,
-						      OCFS2_JOURNAL_ACCESS_WRITE);
-			if (status < 0) {
-				status = -EIO;
-				mlog_errno(status);
-				goto bail;
-			}
-			if (pde)
-				pde->rec_len =
-					cpu_to_le16(le16_to_cpu(pde->rec_len) +
-						    le16_to_cpu(de->rec_len));
-			else
-				de->inode = 0;
-			dir->i_version++;
-			status = ocfs2_journal_dirty(handle, bh);
-			goto bail;
-		}
-		i += le16_to_cpu(de->rec_len);
-		pde = de;
-		de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len));
-	}
-bail:
-	mlog_exit(status);
-	return status;
-}
-
-/*
- * Returns 0 if not found, -1 on failure, and 1 on success
- */
-static int inline ocfs2_search_dirblock(struct buffer_head *bh,
-					struct inode *dir,
-					const char *name, int namelen,
-					unsigned long offset,
-					struct ocfs2_dir_entry **res_dir)
-{
-	struct ocfs2_dir_entry *de;
-	char *dlimit, *de_buf;
-	int de_len;
-	int ret = 0;
-
-	mlog_entry_void();
-
-	de_buf = bh->b_data;
-	dlimit = de_buf + dir->i_sb->s_blocksize;
-
-	while (de_buf < dlimit) {
-		/* this code is executed quadratically often */
-		/* do minimal checking `by hand' */
-
-		de = (struct ocfs2_dir_entry *) de_buf;
-
-		if (de_buf + namelen <= dlimit &&
-		    ocfs2_match(namelen, name, de)) {
-			/* found a match - just to be sure, do a full check */
-			if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
-				ret = -1;
-				goto bail;
-			}
-			*res_dir = de;
-			ret = 1;
-			goto bail;
-		}
-
-		/* prevent looping on a bad block */
-		de_len = le16_to_cpu(de->rec_len);
-		if (de_len <= 0) {
-			ret = -1;
-			goto bail;
-		}
-
-		de_buf += de_len;
-		offset += de_len;
-	}
-
-bail:
-	mlog_exit(ret);
-	return ret;
-}
-
-struct buffer_head *ocfs2_find_entry(const char *name, int namelen,
-				     struct inode *dir,
-				     struct ocfs2_dir_entry **res_dir)
-{
-	struct super_block *sb;
-	struct buffer_head *bh_use[NAMEI_RA_SIZE];
-	struct buffer_head *bh, *ret = NULL;
-	unsigned long start, block, b;
-	int ra_max = 0;		/* Number of bh's in the readahead
-				   buffer, bh_use[] */
-	int ra_ptr = 0;		/* Current index into readahead
-				   buffer */
-	int num = 0;
-	int nblocks, i, err;
-
-	mlog_entry_void();
-
-	*res_dir = NULL;
-	sb = dir->i_sb;
-
-	nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
-	start = OCFS2_I(dir)->ip_dir_start_lookup;
-	if (start >= nblocks)
-		start = 0;
-	block = start;
-
-restart:
-	do {
-		/*
-		 * We deal with the read-ahead logic here.
-		 */
-		if (ra_ptr >= ra_max) {
-			/* Refill the readahead buffer */
-			ra_ptr = 0;
-			b = block;
-			for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
-				/*
-				 * Terminate if we reach the end of the
-				 * directory and must wrap, or if our
-				 * search has finished at this block.
-				 */
-				if (b >= nblocks || (num && block == start)) {
-					bh_use[ra_max] = NULL;
-					break;
-				}
-				num++;
-
-				bh = ocfs2_bread(dir, b++, &err, 1);
-				bh_use[ra_max] = bh;
-			}
-		}
-		if ((bh = bh_use[ra_ptr++]) == NULL)
-			goto next;
-		wait_on_buffer(bh);
-		if (!buffer_uptodate(bh)) {
-			/* read error, skip block & hope for the best */
-			ocfs2_error(dir->i_sb, "reading directory %llu, "
-				    "offset %lu\n",
-				    (unsigned long long)OCFS2_I(dir)->ip_blkno,
-				    block);
-			brelse(bh);
-			goto next;
-		}
-		i = ocfs2_search_dirblock(bh, dir, name, namelen,
-					  block << sb->s_blocksize_bits,
-					  res_dir);
-		if (i == 1) {
-			OCFS2_I(dir)->ip_dir_start_lookup = block;
-			ret = bh;
-			goto cleanup_and_exit;
-		} else {
-			brelse(bh);
-			if (i < 0)
-				goto cleanup_and_exit;
-		}
-	next:
-		if (++block >= nblocks)
-			block = 0;
-	} while (block != start);
-
-	/*
-	 * If the directory has grown while we were searching, then
-	 * search the last part of the directory before giving up.
-	 */
-	block = nblocks;
-	nblocks = i_size_read(dir) >> sb->s_blocksize_bits;
-	if (block < nblocks) {
-		start = 0;
-		goto restart;
-	}
-
-cleanup_and_exit:
-	/* Clean up the read-ahead blocks */
-	for (; ra_ptr < ra_max; ra_ptr++)
-		brelse(bh_use[ra_ptr]);
-
-	mlog_exit_ptr(ret);
-	return ret;
-}
-
 static int ocfs2_blkno_stringify(u64 blkno, char *name)
 {
 	int status, namelen;
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index 0975c7b7212b..688aef64c879 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -30,29 +30,10 @@ extern const struct inode_operations ocfs2_dir_iops;
 
 struct dentry *ocfs2_get_parent(struct dentry *child);
 
-int ocfs2_check_dir_entry (struct inode *dir,
-			   struct ocfs2_dir_entry *de,
-			   struct buffer_head *bh,
-			   unsigned long offset);
-struct buffer_head *ocfs2_find_entry(const char *name,
-				     int namelen,
-				     struct inode *dir,
-				     struct ocfs2_dir_entry **res_dir);
 int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
 		     struct buffer_head *orphan_dir_bh);
 
-static inline int ocfs2_match(int len,
-			      const char * const name,
-			      struct ocfs2_dir_entry *de)
-{
-	if (len != de->name_len)
-		return 0;
-	if (!de->inode)
-		return 0;
-	return !memcmp(name, de->name, len);
-}
-
 #endif /* OCFS2_NAMEI_H */
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 58307853fb4a..60a23e1906b0 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -319,6 +319,13 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb)
 	return 0;
 }
 
+static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb)
+{
+	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA)
+		return 1;
+	return 0;
+}
+
 /* set / clear functions because cluster events can make these happen
  * in parallel so we want the transitions to be atomic. this also
  * means that any future flags osb_flags must be protected by spinlock
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 82f8a75b207e..6ef876759a73 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -87,7 +87,8 @@
 
 #define OCFS2_FEATURE_COMPAT_SUPP	OCFS2_FEATURE_COMPAT_BACKUP_SB
 #define OCFS2_FEATURE_INCOMPAT_SUPP	(OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT \
-					 | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC)
+					 | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \
+					 | OCFS2_FEATURE_INCOMPAT_INLINE_DATA)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	OCFS2_FEATURE_RO_COMPAT_UNWRITTEN
 
 /*
@@ -111,6 +112,20 @@
 #define OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC	0x0010
 
 /*
+ * Tunefs sets this incompat flag before starting an operation which
+ * would require cleanup on abort. This is done to protect users from
+ * inadvertently mounting the fs after an aborted run without
+ * fsck-ing.
+ *
+ * s_tunefs_flags on the super block describes precisely which
+ * operations were in progress.
+ */
+#define OCFS2_FEATURE_INCOMPAT_TUNEFS_INPROG	0x0020
+
+/* Support for data packed into inode blocks */
+#define OCFS2_FEATURE_INCOMPAT_INLINE_DATA	0x0040
+
+/*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
  */
@@ -130,6 +145,11 @@
 #define OCFS2_MAX_BACKUP_SUPERBLOCKS	6
 
 /*
+ * Flags on ocfs2_super_block.s_tunefs_flags
+ */
+#define OCFS2_TUNEFS_INPROG_REMOVE_SLOT		0x0001	/* Removing slots */
+
+/*
  * Flags on ocfs2_dinode.i_flags
  */
 #define OCFS2_VALID_FL		(0x00000001)	/* Inode is valid */
@@ -146,6 +166,17 @@
 #define OCFS2_CHAIN_FL		(0x00000400)	/* Chain allocator */
 #define OCFS2_DEALLOC_FL	(0x00000800)	/* Truncate log */
 
+/*
+ * Flags on ocfs2_dinode.i_dyn_features
+ *
+ * These can change much more often than i_flags. When adding flags,
+ * keep in mind that i_dyn_features is only 16 bits wide.
+ */
+#define OCFS2_INLINE_DATA_FL	(0x0001)	/* Data stored in inode block */
+#define OCFS2_HAS_XATTR_FL	(0x0002)
+#define OCFS2_INLINE_XATTR_FL	(0x0004)
+#define OCFS2_INDEXED_DIR_FL	(0x0008)
+
 /* Inode attributes, keep in sync with EXT2 */
 #define OCFS2_SECRM_FL		(0x00000001)	/* Secure deletion */
 #define OCFS2_UNRM_FL		(0x00000002)	/* Undelete */
@@ -447,8 +478,8 @@ struct ocfs2_super_block {
 	__le32 s_clustersize_bits;	/* Clustersize for this fs */
 /*40*/	__le16 s_max_slots;		/* Max number of simultaneous mounts
 					   before tunefs required */
-	__le16 s_reserved1;
-	__le32 s_reserved2;
+	__le16 s_tunefs_flag;
+	__le32 s_reserved1;
 	__le64 s_first_cluster_group;	/* Block offset of 1st cluster
 					 * group header */
 /*50*/	__u8  s_label[OCFS2_MAX_VOL_LABEL_LEN];	/* Label for mounting, etc. */
@@ -471,6 +502,19 @@ struct ocfs2_local_alloc
 };
 
 /*
+ * Data-in-inode header. This is only used if i_dyn_features has
+ * OCFS2_INLINE_DATA_FL set.
+ */
+struct ocfs2_inline_data
+{
+/*00*/	__le16	id_count;	/* Number of bytes that can be used
+				 * for data, starting at id_data */
+	__le16	id_reserved0;
+	__le32	id_reserved1;
+	__u8	id_data[0];	/* Start of user data */
+};
+
+/*
  * On disk inode for OCFS2
  */
 struct ocfs2_dinode {
@@ -502,7 +546,7 @@ struct ocfs2_dinode {
 	__le32 i_attr;
 	__le16 i_orphaned_slot;		/* Only valid when OCFS2_ORPHANED_FL
 					   was set in i_flags */
-	__le16 i_reserved1;
+	__le16 i_dyn_features;
 /*70*/	__le64 i_reserved2[8];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
@@ -528,6 +572,7 @@ struct ocfs2_dinode {
 		struct ocfs2_chain_list		i_chain;
 		struct ocfs2_extent_list	i_list;
 		struct ocfs2_truncate_log	i_dealloc;
+		struct ocfs2_inline_data	i_data;
 		__u8               		i_symlink[0];
 	} id2;
 /* Actual on-disk size is one block */
@@ -577,6 +622,12 @@ static inline int ocfs2_fast_symlink_chars(struct super_block *sb)
 		 offsetof(struct ocfs2_dinode, id2.i_symlink);
 }
 
+static inline int ocfs2_max_inline_data(struct super_block *sb)
+{
+	return sb->s_blocksize -
+		offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+}
+
 static inline int ocfs2_extent_recs_per_inode(struct super_block *sb)
 {
 	int size;
@@ -656,6 +707,11 @@ static inline int ocfs2_fast_symlink_chars(int blocksize)
 	return blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink);
 }
 
+static inline int ocfs2_max_inline_data(int blocksize)
+{
+	return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+}
+
 static inline int ocfs2_extent_recs_per_inode(int blocksize)
 {
 	int size;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c034b5129c1e..0e2a1b45bf92 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -39,6 +39,7 @@
 #include <linux/parser.h>
 #include <linux/crc32.h>
 #include <linux/debugfs.h>
+#include <linux/mount.h>
 
 #include <cluster/nodemanager.h>
 
@@ -91,6 +92,7 @@ struct mount_options
 static int ocfs2_parse_options(struct super_block *sb, char *options,
 			       struct mount_options *mopt,
 			       int is_remount);
+static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt);
 static void ocfs2_put_super(struct super_block *sb);
 static int ocfs2_mount_volume(struct super_block *sb);
 static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
@@ -105,7 +107,7 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait);
 
 static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb);
 static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb);
-static int ocfs2_release_system_inodes(struct ocfs2_super *osb);
+static void ocfs2_release_system_inodes(struct ocfs2_super *osb);
 static int ocfs2_fill_local_node_info(struct ocfs2_super *osb);
 static int ocfs2_check_volume(struct ocfs2_super *osb);
 static int ocfs2_verify_volume(struct ocfs2_dinode *di,
@@ -133,6 +135,7 @@ static const struct super_operations ocfs2_sops = {
 	.write_super	= ocfs2_write_super,
 	.put_super	= ocfs2_put_super,
 	.remount_fs	= ocfs2_remount,
+	.show_options   = ocfs2_show_options,
 };
 
 enum {
@@ -177,7 +180,7 @@ static void ocfs2_write_super(struct super_block *sb)
 
 static int ocfs2_sync_fs(struct super_block *sb, int wait)
 {
-	int status = 0;
+	int status;
 	tid_t target;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 
@@ -275,9 +278,9 @@ bail:
 	return status;
 }
 
-static int ocfs2_release_system_inodes(struct ocfs2_super *osb)
+static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
 {
-	int status = 0, i;
+	int i;
 	struct inode *inode;
 
 	mlog_entry_void();
@@ -302,8 +305,7 @@ static int ocfs2_release_system_inodes(struct ocfs2_super *osb)
 		osb->root_inode = NULL;
 	}
 
-	mlog_exit(status);
-	return status;
+	mlog_exit(0);
 }
 
 /* We're allocating fs objects, use GFP_NOFS */
@@ -453,7 +455,7 @@ static int ocfs2_sb_probe(struct super_block *sb,
 			  struct buffer_head **bh,
 			  int *sector_size)
 {
-	int status = 0, tmpstat;
+	int status, tmpstat;
 	struct ocfs1_vol_disk_hdr *hdr;
 	struct ocfs2_dinode *di;
 	int blksize;
@@ -830,6 +832,41 @@ bail:
 	return status;
 }
 
+static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct ocfs2_super *osb = OCFS2_SB(mnt->mnt_sb);
+	unsigned long opts = osb->s_mount_opt;
+
+	if (opts & OCFS2_MOUNT_HB_LOCAL)
+		seq_printf(s, ",_netdev,heartbeat=local");
+	else
+		seq_printf(s, ",heartbeat=none");
+
+	if (opts & OCFS2_MOUNT_NOINTR)
+		seq_printf(s, ",nointr");
+
+	if (opts & OCFS2_MOUNT_DATA_WRITEBACK)
+		seq_printf(s, ",data=writeback");
+	else
+		seq_printf(s, ",data=ordered");
+
+	if (opts & OCFS2_MOUNT_BARRIER)
+		seq_printf(s, ",barrier=1");
+
+	if (opts & OCFS2_MOUNT_ERRORS_PANIC)
+		seq_printf(s, ",errors=panic");
+	else
+		seq_printf(s, ",errors=remount-ro");
+
+	if (osb->preferred_slot != OCFS2_INVALID_SLOT)
+		seq_printf(s, ",preferred_slot=%d", osb->preferred_slot);
+
+	if (osb->s_atime_quantum != OCFS2_DEFAULT_ATIME_QUANTUM)
+		seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum);
+
+	return 0;
+}
+
 static int __init ocfs2_init(void)
 {
 	int status;
@@ -1209,12 +1246,13 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 		tmp = ocfs2_request_umount_vote(osb);
 		if (tmp < 0)
 			mlog_errno(tmp);
+	}
 
-		if (osb->slot_num != OCFS2_INVALID_SLOT)
-			ocfs2_put_slot(osb);
+	if (osb->slot_num != OCFS2_INVALID_SLOT)
+		ocfs2_put_slot(osb);
 
+	if (osb->dlm)
 		ocfs2_super_unlock(osb, 1);
-	}
 
 	ocfs2_release_system_inodes(osb);
 
@@ -1275,7 +1313,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 				  struct buffer_head *bh,
 				  int sector_size)
 {
-	int status = 0;
+	int status;
 	int i, cbits, bbits;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
 	struct inode *inode = NULL;
@@ -1596,7 +1634,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
 
 static int ocfs2_check_volume(struct ocfs2_super *osb)
 {
-	int status = 0;
+	int status;
 	int dirty;
 	int local;
 	struct ocfs2_dinode *local_alloc = NULL; /* only used if we
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index 5df6e35d09b1..fd2e846e3e6f 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -100,17 +100,14 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	char namebuf[40];
 	struct inode *inode = NULL;
 	u64 blkno;
-	struct buffer_head *dirent_bh = NULL;
-	struct ocfs2_dir_entry *de = NULL;
 	int status = 0;
 
 	ocfs2_sprintf_system_inode_name(namebuf,
 					sizeof(namebuf),
 					type, slot);
 
-	status = ocfs2_find_files_on_disk(namebuf, strlen(namebuf),
-					  &blkno, osb->sys_root_inode,
-					  &dirent_bh, &de);
+	status = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
+					    strlen(namebuf), &blkno);
 	if (status < 0) {
 		goto bail;
 	}
@@ -122,8 +119,7 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 		goto bail;
 	}
 bail:
-	if (dirent_bh)
-		brelse(dirent_bh);
+
 	return inode;
 }
 
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 783c57ec07d3..722e12e5acc7 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -381,10 +381,12 @@ void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len,
 	p->partno = part;
 	p->policy = disk->policy;
 
-	if (isdigit(disk->kobj.name[strlen(disk->kobj.name)-1]))
-		snprintf(p->kobj.name,KOBJ_NAME_LEN,"%sp%d",disk->kobj.name,part);
+	if (isdigit(disk->kobj.k_name[strlen(disk->kobj.k_name)-1]))
+		kobject_set_name(&p->kobj, "%sp%d",
+				 kobject_name(&disk->kobj), part);
 	else
-		snprintf(p->kobj.name,KOBJ_NAME_LEN,"%s%d",disk->kobj.name,part);
+		kobject_set_name(&p->kobj, "%s%d",
+				 kobject_name(&disk->kobj),part);
 	p->kobj.parent = &disk->kobj;
 	p->kobj.ktype = &ktype_part;
 	kobject_init(&p->kobj);
@@ -477,9 +479,9 @@ void register_disk(struct gendisk *disk)
 	struct hd_struct *p;
 	int err;
 
-	strlcpy(disk->kobj.name,disk->disk_name,KOBJ_NAME_LEN);
+	kobject_set_name(&disk->kobj, "%s", disk->disk_name);
 	/* ewww... some of these buggers have / in name... */
-	s = strchr(disk->kobj.name, '/');
+	s = strchr(disk->kobj.k_name, '/');
 	if (s)
 		*s = '!';
 	if ((err = kobject_add(&disk->kobj)))
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index bce38e3f06cb..ebaba0213546 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -11,6 +11,7 @@ proc-y       += inode.o root.o base.o generic.o array.o \
 		proc_tty.o proc_misc.o
 
 proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
+proc-$(CONFIG_NET)		+= proc_net.o
 proc-$(CONFIG_PROC_KCORE)	+= kcore.o
 proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
 proc-$(CONFIG_PROC_DEVICETREE)	+= proc_devtree.o
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index b215c3524fa6..1820eb2ef762 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -16,6 +16,11 @@ extern int proc_sys_init(void);
 #else
 static inline void proc_sys_init(void) { }
 #endif
+#ifdef CONFIG_NET
+extern int proc_net_init(void);
+#else
+static inline int proc_net_init(void) { return 0; }
+#endif
 
 struct vmalloc_info {
 	unsigned long	used;
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
new file mode 100644
index 000000000000..2e91fb756e9a
--- /dev/null
+++ b/fs/proc/proc_net.c
@@ -0,0 +1,200 @@
+/*
+ *  linux/fs/proc/net.c
+ *
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmission.com>
+ *
+ *  proc net directory handling functions
+ */
+
+#include <asm/uaccess.h>
+
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/smp_lock.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+
+#include "internal.h"
+
+
+struct proc_dir_entry *proc_net_create(struct net *net,
+	const char *name, mode_t mode, get_info_t *get_info)
+{
+	return create_proc_info_entry(name,mode, net->proc_net, get_info);
+}
+EXPORT_SYMBOL_GPL(proc_net_create);
+
+struct proc_dir_entry *proc_net_fops_create(struct net *net,
+	const char *name, mode_t mode, const struct file_operations *fops)
+{
+	struct proc_dir_entry *res;
+
+	res = create_proc_entry(name, mode, net->proc_net);
+	if (res)
+		res->proc_fops = fops;
+	return res;
+}
+EXPORT_SYMBOL_GPL(proc_net_fops_create);
+
+void proc_net_remove(struct net *net, const char *name)
+{
+	remove_proc_entry(name, net->proc_net);
+}
+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 struct proc_dir_entry *proc_net_shadow;
+
+static struct dentry *proc_net_shadow_dentry(struct dentry *parent,
+						struct proc_dir_entry *de)
+{
+	struct dentry *shadow = NULL;
+	struct inode *inode;
+	if (!de)
+		goto out;
+	de_get(de);
+	inode = proc_get_inode(parent->d_inode->i_sb, de->low_ino, de);
+	if (!inode)
+		goto out_de_put;
+	shadow = d_alloc_name(parent, de->name);
+	if (!shadow)
+		goto out_iput;
+	shadow->d_op = parent->d_op; /* proc_dentry_operations */
+	d_instantiate(shadow, inode);
+out:
+	return shadow;
+out_iput:
+	iput(inode);
+out_de_put:
+	de_put(de);
+	goto out;
+}
+
+static void *proc_net_follow_link(struct dentry *parent, struct nameidata *nd)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct dentry *shadow;
+	shadow = proc_net_shadow_dentry(parent, net->proc_net);
+	if (!shadow)
+		return ERR_PTR(-ENOENT);
+
+	dput(nd->dentry);
+	/* My dentry count is 1 and that should be enough as the
+	 * shadow dentry is thrown away immediately.
+	 */
+	nd->dentry = shadow;
+	return NULL;
+}
+
+static struct dentry *proc_net_lookup(struct inode *dir, struct dentry *dentry,
+				      struct nameidata *nd)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct dentry *shadow;
+
+	shadow = proc_net_shadow_dentry(nd->dentry, net->proc_net);
+	if (!shadow)
+		return ERR_PTR(-ENOENT);
+
+	dput(nd->dentry);
+	nd->dentry = shadow;
+
+	return shadow->d_inode->i_op->lookup(shadow->d_inode, dentry, nd);
+}
+
+static int proc_net_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct dentry *shadow;
+	int ret;
+
+	shadow = proc_net_shadow_dentry(dentry->d_parent, net->proc_net);
+	if (!shadow)
+		return -ENOENT;
+	ret = shadow->d_inode->i_op->setattr(shadow, iattr);
+	dput(shadow);
+	return ret;
+}
+
+static const struct file_operations proc_net_dir_operations = {
+	.read			= generic_read_dir,
+};
+
+static struct inode_operations proc_net_dir_inode_operations = {
+	.follow_link	= proc_net_follow_link,
+	.lookup		= proc_net_lookup,
+	.setattr	= proc_net_setattr,
+};
+
+static __net_init int proc_net_ns_init(struct net *net)
+{
+	struct proc_dir_entry *root, *netd, *net_statd;
+	int err;
+
+	err = -ENOMEM;
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		goto out;
+
+	err = -EEXIST;
+	netd = proc_mkdir("net", root);
+	if (!netd)
+		goto free_root;
+
+	err = -EEXIST;
+	net_statd = proc_mkdir("stat", netd);
+	if (!net_statd)
+		goto free_net;
+
+	root->data = net;
+	netd->data = net;
+	net_statd->data = net;
+
+	net->proc_net_root = root;
+	net->proc_net = netd;
+	net->proc_net_stat = net_statd;
+	err = 0;
+
+out:
+	return err;
+free_net:
+	remove_proc_entry("net", root);
+free_root:
+	kfree(root);
+	goto out;
+}
+
+static __net_exit void proc_net_ns_exit(struct net *net)
+{
+	remove_proc_entry("stat", net->proc_net);
+	remove_proc_entry("net", net->proc_net_root);
+	kfree(net->proc_net_root);
+}
+
+struct pernet_operations __net_initdata proc_net_ns_ops = {
+	.init = proc_net_ns_init,
+	.exit = proc_net_ns_exit,
+};
+
+int __init proc_net_init(void)
+{
+	proc_net_shadow = proc_mkdir("net", NULL);
+	proc_net_shadow->proc_iops = &proc_net_dir_inode_operations;
+	proc_net_shadow->proc_fops = &proc_net_dir_operations;
+
+	return register_pernet_subsys(&proc_net_ns_ops);
+}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 41f17037f738..cf3046638b09 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -21,7 +21,7 @@
 
 #include "internal.h"
 
-struct proc_dir_entry *proc_net, *proc_net_stat, *proc_bus, *proc_root_fs, *proc_root_driver;
+struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver;
 
 static int proc_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
@@ -61,8 +61,8 @@ void __init proc_root_init(void)
 		return;
 	}
 	proc_misc_init();
-	proc_net = proc_mkdir("net", NULL);
-	proc_net_stat = proc_mkdir("net/stat", NULL);
+
+	proc_net_init();
 
 #ifdef CONFIG_SYSVIPC
 	proc_mkdir("sysvipc", NULL);
@@ -159,7 +159,5 @@ EXPORT_SYMBOL(create_proc_entry);
 EXPORT_SYMBOL(remove_proc_entry);
 EXPORT_SYMBOL(proc_root);
 EXPORT_SYMBOL(proc_root_fs);
-EXPORT_SYMBOL(proc_net);
-EXPORT_SYMBOL(proc_net_stat);
 EXPORT_SYMBOL(proc_bus);
 EXPORT_SYMBOL(proc_root_driver);
diff --git a/fs/seq_file.c b/fs/seq_file.c
index bbb19be260ce..ca71c115bdaa 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -429,6 +429,39 @@ int seq_release_private(struct inode *inode, struct file *file)
 }
 EXPORT_SYMBOL(seq_release_private);
 
+void *__seq_open_private(struct file *f, const struct seq_operations *ops,
+		int psize)
+{
+	int rc;
+	void *private;
+	struct seq_file *seq;
+
+	private = kzalloc(psize, GFP_KERNEL);
+	if (private == NULL)
+		goto out;
+
+	rc = seq_open(f, ops);
+	if (rc < 0)
+		goto out_free;
+
+	seq = f->private_data;
+	seq->private = private;
+	return private;
+
+out_free:
+	kfree(private);
+out:
+	return NULL;
+}
+EXPORT_SYMBOL(__seq_open_private);
+
+int seq_open_private(struct file *filp, const struct seq_operations *ops,
+		int psize)
+{
+	return __seq_open_private(filp, ops, psize) ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL(seq_open_private);
+
 int seq_putc(struct seq_file *m, char c)
 {
 	if (m->count < m->size) {
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 5afe2a26f5d8..006fc64227dd 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -1,9 +1,15 @@
 /*
- * bin.c - binary file operations for sysfs.
+ * fs/sysfs/bin.c - sysfs binary file implementation
  *
  * Copyright (c) 2003 Patrick Mochel
  * Copyright (c) 2003 Matthew Wilcox
  * Copyright (c) 2004 Silicon Graphics, Inc.
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
  */
 
 #undef DEBUG
@@ -14,9 +20,9 @@
 #include <linux/kobject.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
 
 #include <asm/uaccess.h>
-#include <asm/semaphore.h>
 
 #include "sysfs.h"
 
@@ -30,8 +36,8 @@ static int
 fill_read(struct dentry *dentry, char *buffer, loff_t off, size_t count)
 {
 	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	int rc;
 
 	/* need attr_sd for attr, its parent for kobj */
@@ -87,8 +93,8 @@ static int
 flush_write(struct dentry *dentry, char *buffer, loff_t offset, size_t count)
 {
 	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	int rc;
 
 	/* need attr_sd for attr, its parent for kobj */
@@ -140,8 +146,8 @@ static int mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct bin_buffer *bb = file->private_data;
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	int rc;
 
 	mutex_lock(&bb->mutex);
@@ -167,12 +173,12 @@ static int mmap(struct file *file, struct vm_area_struct *vma)
 static int open(struct inode * inode, struct file * file)
 {
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr;
+	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
 	struct bin_buffer *bb = NULL;
 	int error;
 
-	/* need attr_sd for attr */
-	if (!sysfs_get_active(attr_sd))
+	/* binary file operations requires both @sd and its parent */
+	if (!sysfs_get_active_two(attr_sd))
 		return -ENODEV;
 
 	error = -EACCES;
@@ -193,13 +199,12 @@ static int open(struct inode * inode, struct file * file)
 	mutex_init(&bb->mutex);
 	file->private_data = bb;
 
-	/* open succeeded, put active reference and pin attr_sd */
-	sysfs_put_active(attr_sd);
-	sysfs_get(attr_sd);
+	/* open succeeded, put active references */
+	sysfs_put_active_two(attr_sd);
 	return 0;
 
  err_out:
-	sysfs_put_active(attr_sd);
+	sysfs_put_active_two(attr_sd);
 	kfree(bb);
 	return error;
 }
@@ -211,7 +216,6 @@ static int release(struct inode * inode, struct file * file)
 
 	if (bb->mmapped)
 		sysfs_put_active_two(attr_sd);
-	sysfs_put(attr_sd);
 	kfree(bb->buffer);
 	kfree(bb);
 	return 0;
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 83e76b3813c9..9161db4d6b5c 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -1,5 +1,13 @@
 /*
- * dir.c - Operations for sysfs directories.
+ * fs/sysfs/dir.c - sysfs core and dir operation implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
  */
 
 #undef DEBUG
@@ -11,10 +19,11 @@
 #include <linux/namei.h>
 #include <linux/idr.h>
 #include <linux/completion.h>
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 #include "sysfs.h"
 
 DEFINE_MUTEX(sysfs_mutex);
+DEFINE_MUTEX(sysfs_rename_mutex);
 spinlock_t sysfs_assoc_lock = SPIN_LOCK_UNLOCKED;
 
 static spinlock_t sysfs_ino_lock = SPIN_LOCK_UNLOCKED;
@@ -25,18 +34,28 @@ static DEFINE_IDA(sysfs_ino_ida);
  *	@sd: sysfs_dirent of interest
  *
  *	Link @sd into its sibling list which starts from
- *	sd->s_parent->s_children.
+ *	sd->s_parent->s_dir.children.
  *
  *	Locking:
  *	mutex_lock(sysfs_mutex)
  */
-void sysfs_link_sibling(struct sysfs_dirent *sd)
+static void sysfs_link_sibling(struct sysfs_dirent *sd)
 {
 	struct sysfs_dirent *parent_sd = sd->s_parent;
+	struct sysfs_dirent **pos;
 
 	BUG_ON(sd->s_sibling);
-	sd->s_sibling = parent_sd->s_children;
-	parent_sd->s_children = sd;
+
+	/* Store directory entries in order by ino.  This allows
+	 * readdir to properly restart without having to add a
+	 * cursor into the s_dir.children list.
+	 */
+	for (pos = &parent_sd->s_dir.children; *pos; pos = &(*pos)->s_sibling) {
+		if (sd->s_ino < (*pos)->s_ino)
+			break;
+	}
+	sd->s_sibling = *pos;
+	*pos = sd;
 }
 
 /**
@@ -44,16 +63,17 @@ void sysfs_link_sibling(struct sysfs_dirent *sd)
  *	@sd: sysfs_dirent of interest
  *
  *	Unlink @sd from its sibling list which starts from
- *	sd->s_parent->s_children.
+ *	sd->s_parent->s_dir.children.
  *
  *	Locking:
  *	mutex_lock(sysfs_mutex)
  */
-void sysfs_unlink_sibling(struct sysfs_dirent *sd)
+static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
 {
 	struct sysfs_dirent **pos;
 
-	for (pos = &sd->s_parent->s_children; *pos; pos = &(*pos)->s_sibling) {
+	for (pos = &sd->s_parent->s_dir.children; *pos;
+	     pos = &(*pos)->s_sibling) {
 		if (*pos == sd) {
 			*pos = sd->s_sibling;
 			sd->s_sibling = NULL;
@@ -67,96 +87,39 @@ void sysfs_unlink_sibling(struct sysfs_dirent *sd)
  *	@sd: sysfs_dirent of interest
  *
  *	Get dentry for @sd.  Dentry is looked up if currently not
- *	present.  This function climbs sysfs_dirent tree till it
- *	reaches a sysfs_dirent with valid dentry attached and descends
- *	down from there looking up dentry for each step.
+ *	present.  This function descends from the root looking up
+ *	dentry for each step.
  *
  *	LOCKING:
- *	Kernel thread context (may sleep)
+ *	mutex_lock(sysfs_rename_mutex)
  *
  *	RETURNS:
  *	Pointer to found dentry on success, ERR_PTR() value on error.
  */
 struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
 {
-	struct sysfs_dirent *cur;
-	struct dentry *parent_dentry, *dentry;
-	int i, depth;
-
-	/* Find the first parent which has valid s_dentry and get the
-	 * dentry.
-	 */
-	mutex_lock(&sysfs_mutex);
- restart0:
-	spin_lock(&sysfs_assoc_lock);
- restart1:
-	spin_lock(&dcache_lock);
+	struct dentry *dentry = dget(sysfs_sb->s_root);
 
-	dentry = NULL;
-	depth = 0;
-	cur = sd;
-	while (!cur->s_dentry || !cur->s_dentry->d_inode) {
-		if (cur->s_flags & SYSFS_FLAG_REMOVED) {
-			dentry = ERR_PTR(-ENOENT);
-			depth = 0;
-			break;
-		}
-		cur = cur->s_parent;
-		depth++;
-	}
-	if (!IS_ERR(dentry))
-		dentry = dget_locked(cur->s_dentry);
+	while (dentry->d_fsdata != sd) {
+		struct sysfs_dirent *cur;
+		struct dentry *parent;
 
-	spin_unlock(&dcache_lock);
-	spin_unlock(&sysfs_assoc_lock);
-
-	/* from the found dentry, look up depth times */
-	while (depth--) {
-		/* find and get depth'th ancestor */
-		for (cur = sd, i = 0; cur && i < depth; i++)
+		/* find the first ancestor which hasn't been looked up */
+		cur = sd;
+		while (cur->s_parent != dentry->d_fsdata)
 			cur = cur->s_parent;
 
-		/* This can happen if tree structure was modified due
-		 * to move/rename.  Restart.
-		 */
-		if (i != depth) {
-			dput(dentry);
-			goto restart0;
-		}
-
-		sysfs_get(cur);
-
-		mutex_unlock(&sysfs_mutex);
-
 		/* look it up */
-		parent_dentry = dentry;
-		dentry = lookup_one_len_kern(cur->s_name, parent_dentry,
+		parent = dentry;
+		mutex_lock(&parent->d_inode->i_mutex);
+		dentry = lookup_one_len_kern(cur->s_name, parent,
 					     strlen(cur->s_name));
-		dput(parent_dentry);
-
-		if (IS_ERR(dentry)) {
-			sysfs_put(cur);
-			return dentry;
-		}
+		mutex_unlock(&parent->d_inode->i_mutex);
+		dput(parent);
 
-		mutex_lock(&sysfs_mutex);
-		spin_lock(&sysfs_assoc_lock);
-
-		/* This, again, can happen if tree structure has
-		 * changed and we looked up the wrong thing.  Restart.
-		 */
-		if (cur->s_dentry != dentry) {
-			dput(dentry);
-			sysfs_put(cur);
-			goto restart1;
-		}
-
-		spin_unlock(&sysfs_assoc_lock);
-
-		sysfs_put(cur);
+		if (IS_ERR(dentry))
+			break;
 	}
-
-	mutex_unlock(&sysfs_mutex);
 	return dentry;
 }
 
@@ -319,7 +282,7 @@ void release_sysfs_dirent(struct sysfs_dirent * sd)
 	parent_sd = sd->s_parent;
 
 	if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
-		sysfs_put(sd->s_elem.symlink.target_sd);
+		sysfs_put(sd->s_symlink.target_sd);
 	if (sysfs_type(sd) & SYSFS_COPY_NAME)
 		kfree(sd->s_name);
 	kfree(sd->s_iattr);
@@ -335,22 +298,7 @@ static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
 {
 	struct sysfs_dirent * sd = dentry->d_fsdata;
 
-	if (sd) {
-		/* sd->s_dentry is protected with sysfs_assoc_lock.
-		 * This allows sysfs_drop_dentry() to dereference it.
-		 */
-		spin_lock(&sysfs_assoc_lock);
-
-		/* The dentry might have been deleted or another
-		 * lookup could have happened updating sd->s_dentry to
-		 * point the new dentry.  Ignore if it isn't pointing
-		 * to this dentry.
-		 */
-		if (sd->s_dentry == dentry)
-			sd->s_dentry = NULL;
-		spin_unlock(&sysfs_assoc_lock);
-		sysfs_put(sd);
-	}
+	sysfs_put(sd);
 	iput(inode);
 }
 
@@ -378,7 +326,6 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
 
 	atomic_set(&sd->s_count, 1);
 	atomic_set(&sd->s_active, 0);
-	atomic_set(&sd->s_event, 1);
 
 	sd->s_name = name;
 	sd->s_mode = mode;
@@ -393,30 +340,6 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
 	return NULL;
 }
 
-/**
- *	sysfs_attach_dentry - associate sysfs_dirent with dentry
- *	@sd: target sysfs_dirent
- *	@dentry: dentry to associate
- *
- *	Associate @sd with @dentry.  This is protected by
- *	sysfs_assoc_lock to avoid race with sysfs_d_iput().
- *
- *	LOCKING:
- *	mutex_lock(sysfs_mutex)
- */
-static void sysfs_attach_dentry(struct sysfs_dirent *sd, struct dentry *dentry)
-{
-	dentry->d_op = &sysfs_dentry_ops;
-	dentry->d_fsdata = sysfs_get(sd);
-
-	/* protect sd->s_dentry against sysfs_d_iput */
-	spin_lock(&sysfs_assoc_lock);
-	sd->s_dentry = dentry;
-	spin_unlock(&sysfs_assoc_lock);
-
-	d_rehash(dentry);
-}
-
 static int sysfs_ilookup_test(struct inode *inode, void *arg)
 {
 	struct sysfs_dirent *sd = arg;
@@ -480,10 +403,8 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  *	@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.  @sd is NOT
- *	linked into the children list of the parent.  The caller
- *	should invoke sysfs_link_sibling() after this function
- *	completes if @sd needs to be on the children list.
+ *	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
@@ -491,15 +412,30 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  *
  *	LOCKING:
  *	Determined by sysfs_addrm_start().
+ *
+ *	RETURNS:
+ *	0 on success, -EEXIST if entry with the given name already
+ *	exists.
  */
-void 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)) {
+		printk(KERN_WARNING "sysfs: duplicate filename '%s' "
+		       "can not be created\n", sd->s_name);
+		WARN_ON(1);
+		return -EEXIST;
+	}
+
 	sd->s_parent = sysfs_get(acxt->parent_sd);
 
 	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
 		inc_nlink(acxt->parent_inode);
 
 	acxt->cnt++;
+
+	sysfs_link_sibling(sd);
+
+	return 0;
 }
 
 /**
@@ -508,9 +444,7 @@ void sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
  *	@sd: sysfs_dirent to be added
  *
  *	Mark @sd removed and drop nlink of parent inode if @sd is a
- *	directory.  @sd is NOT unlinked from the children list of the
- *	parent.  The caller is repsonsible for removing @sd from the
- *	children list before calling this function.
+ *	directory.  @sd is unlinked from the children list.
  *
  *	This function should be called between calls to
  *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
@@ -521,7 +455,9 @@ void 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)
 {
-	BUG_ON(sd->s_sibling || (sd->s_flags & SYSFS_FLAG_REMOVED));
+	BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
+
+	sysfs_unlink_sibling(sd);
 
 	sd->s_flags |= SYSFS_FLAG_REMOVED;
 	sd->s_sibling = acxt->removed;
@@ -540,53 +476,49 @@ void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
  *	Drop dentry for @sd.  @sd must have been unlinked from its
  *	parent on entry to this function such that it can't be looked
  *	up anymore.
- *
- *	@sd->s_dentry which is protected with sysfs_assoc_lock points
- *	to the currently associated dentry but we're not holding a
- *	reference to it and racing with dput().  Grab dcache_lock and
- *	verify dentry before dropping it.  If @sd->s_dentry is NULL or
- *	dput() beats us, no need to bother.
  */
 static void sysfs_drop_dentry(struct sysfs_dirent *sd)
 {
-	struct dentry *dentry = NULL;
 	struct inode *inode;
+	struct dentry *dentry;
 
-	/* We're not holding a reference to ->s_dentry dentry but the
-	 * field will stay valid as long as sysfs_assoc_lock is held.
+	inode = ilookup(sysfs_sb, sd->s_ino);
+	if (!inode)
+		return;
+
+	/* Drop any existing dentries associated with sd.
+	 *
+	 * For the dentry to be properly freed we need to grab a
+	 * reference to the dentry under the dcache lock,  unhash it,
+	 * and then put it.  The playing with the dentry count allows
+	 * dput to immediately free the dentry  if it is not in use.
 	 */
-	spin_lock(&sysfs_assoc_lock);
+repeat:
 	spin_lock(&dcache_lock);
-
-	/* drop dentry if it's there and dput() didn't kill it yet */
-	if (sd->s_dentry && sd->s_dentry->d_inode) {
-		dentry = dget_locked(sd->s_dentry);
+	list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+		if (d_unhashed(dentry))
+			continue;
+		dget_locked(dentry);
 		spin_lock(&dentry->d_lock);
 		__d_drop(dentry);
 		spin_unlock(&dentry->d_lock);
+		spin_unlock(&dcache_lock);
+		dput(dentry);
+		goto repeat;
 	}
-
 	spin_unlock(&dcache_lock);
-	spin_unlock(&sysfs_assoc_lock);
-
-	/* dentries for shadowed inodes are pinned, unpin */
-	if (dentry && sysfs_is_shadowed_inode(dentry->d_inode))
-		dput(dentry);
-	dput(dentry);
 
 	/* adjust nlink and update timestamp */
-	inode = ilookup(sysfs_sb, sd->s_ino);
-	if (inode) {
-		mutex_lock(&inode->i_mutex);
+	mutex_lock(&inode->i_mutex);
 
-		inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = CURRENT_TIME;
+	drop_nlink(inode);
+	if (sysfs_type(sd) == SYSFS_DIR)
 		drop_nlink(inode);
-		if (sysfs_type(sd) == SYSFS_DIR)
-			drop_nlink(inode);
 
-		mutex_unlock(&inode->i_mutex);
-		iput(inode);
-	}
+	mutex_unlock(&inode->i_mutex);
+
+	iput(inode);
 }
 
 /**
@@ -599,11 +531,8 @@ static void sysfs_drop_dentry(struct sysfs_dirent *sd)
  *
  *	LOCKING:
  *	All mutexes acquired by sysfs_addrm_start() are released.
- *
- *	RETURNS:
- *	Number of added/removed sysfs_dirents since sysfs_addrm_start().
  */
-int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
+void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
 {
 	/* release resources acquired by sysfs_addrm_start() */
 	mutex_unlock(&sysfs_mutex);
@@ -629,8 +558,6 @@ int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
 		sysfs_deactivate(sd);
 		sysfs_put(sd);
 	}
-
-	return acxt->cnt;
 }
 
 /**
@@ -651,8 +578,8 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
 {
 	struct sysfs_dirent *sd;
 
-	for (sd = parent_sd->s_children; sd; sd = sd->s_sibling)
-		if (sysfs_type(sd) && !strcmp(sd->s_name, name))
+	for (sd = parent_sd->s_dir.children; sd; sd = sd->s_sibling)
+		if (!strcmp(sd->s_name, name))
 			return sd;
 	return NULL;
 }
@@ -690,28 +617,25 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
 	struct sysfs_addrm_cxt acxt;
 	struct sysfs_dirent *sd;
+	int rc;
 
 	/* allocate */
 	sd = sysfs_new_dirent(name, mode, SYSFS_DIR);
 	if (!sd)
 		return -ENOMEM;
-	sd->s_elem.dir.kobj = kobj;
+	sd->s_dir.kobj = kobj;
 
 	/* link in */
 	sysfs_addrm_start(&acxt, parent_sd);
+	rc = sysfs_add_one(&acxt, sd);
+	sysfs_addrm_finish(&acxt);
 
-	if (!sysfs_find_dirent(parent_sd, name)) {
-		sysfs_add_one(&acxt, sd);
-		sysfs_link_sibling(sd);
-	}
-
-	if (!sysfs_addrm_finish(&acxt)) {
+	if (rc == 0)
+		*p_sd = sd;
+	else
 		sysfs_put(sd);
-		return -EEXIST;
-	}
 
-	*p_sd = sd;
-	return 0;
+	return rc;
 }
 
 int sysfs_create_subdir(struct kobject *kobj, const char *name,
@@ -723,24 +647,18 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name,
 /**
  *	sysfs_create_dir - create a directory for an object.
  *	@kobj:		object we're creating directory for. 
- *	@shadow_parent:	parent object.
  */
-int sysfs_create_dir(struct kobject *kobj,
-		     struct sysfs_dirent *shadow_parent_sd)
+int sysfs_create_dir(struct kobject * kobj)
 {
 	struct sysfs_dirent *parent_sd, *sd;
 	int error = 0;
 
 	BUG_ON(!kobj);
 
-	if (shadow_parent_sd)
-		parent_sd = shadow_parent_sd;
-	else if (kobj->parent)
+	if (kobj->parent)
 		parent_sd = kobj->parent->sd;
-	else if (sysfs_mount && sysfs_mount->mnt_sb)
-		parent_sd = sysfs_mount->mnt_sb->s_root->d_fsdata;
 	else
-		return -EFAULT;
+		parent_sd = &sysfs_root;
 
 	error = create_dir(kobj, parent_sd, kobject_name(kobj), &sd);
 	if (!error)
@@ -748,39 +666,20 @@ int sysfs_create_dir(struct kobject *kobj,
 	return error;
 }
 
-static int sysfs_count_nlink(struct sysfs_dirent *sd)
-{
-	struct sysfs_dirent *child;
-	int nr = 0;
-
-	for (child = sd->s_children; child; child = child->s_sibling)
-		if (sysfs_type(child) == SYSFS_DIR)
-			nr++;
-	return nr + 2;
-}
-
 static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
 				struct nameidata *nd)
 {
 	struct dentry *ret = NULL;
-	struct sysfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
-	struct sysfs_dirent * sd;
-	struct bin_attribute *bin_attr;
+	struct sysfs_dirent *parent_sd = dentry->d_parent->d_fsdata;
+	struct sysfs_dirent *sd;
 	struct inode *inode;
-	int found = 0;
 
 	mutex_lock(&sysfs_mutex);
 
-	for (sd = parent_sd->s_children; sd; sd = sd->s_sibling) {
-		if (sysfs_type(sd) &&
-		    !strcmp(sd->s_name, dentry->d_name.name)) {
-			found = 1;
-			break;
-		}
-	}
+	sd = sysfs_find_dirent(parent_sd, dentry->d_name.name);
 
 	/* no such entry */
-	if (!found)
+	if (!sd)
 		goto out_unlock;
 
 	/* attach dentry and inode */
@@ -790,33 +689,11 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
-	if (inode->i_state & I_NEW) {
-		/* initialize inode according to type */
-		switch (sysfs_type(sd)) {
-		case SYSFS_DIR:
-			inode->i_op = &sysfs_dir_inode_operations;
-			inode->i_fop = &sysfs_dir_operations;
-			inode->i_nlink = sysfs_count_nlink(sd);
-			break;
-		case SYSFS_KOBJ_ATTR:
-			inode->i_size = PAGE_SIZE;
-			inode->i_fop = &sysfs_file_operations;
-			break;
-		case SYSFS_KOBJ_BIN_ATTR:
-			bin_attr = sd->s_elem.bin_attr.bin_attr;
-			inode->i_size = bin_attr->size;
-			inode->i_fop = &bin_fops;
-			break;
-		case SYSFS_KOBJ_LINK:
-			inode->i_op = &sysfs_symlink_inode_operations;
-			break;
-		default:
-			BUG();
-		}
-	}
-
-	sysfs_instantiate(dentry, inode);
-	sysfs_attach_dentry(sd, dentry);
+	/* instantiate and hash dentry */
+	dentry->d_op = &sysfs_dentry_ops;
+	dentry->d_fsdata = sysfs_get(sd);
+	d_instantiate(dentry, inode);
+	d_rehash(dentry);
 
  out_unlock:
 	mutex_unlock(&sysfs_mutex);
@@ -833,7 +710,6 @@ static void remove_dir(struct sysfs_dirent *sd)
 	struct sysfs_addrm_cxt acxt;
 
 	sysfs_addrm_start(&acxt, sd->s_parent);
-	sysfs_unlink_sibling(sd);
 	sysfs_remove_one(&acxt, sd);
 	sysfs_addrm_finish(&acxt);
 }
@@ -854,15 +730,13 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
 
 	pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
 	sysfs_addrm_start(&acxt, dir_sd);
-	pos = &dir_sd->s_children;
+	pos = &dir_sd->s_dir.children;
 	while (*pos) {
 		struct sysfs_dirent *sd = *pos;
 
-		if (sysfs_type(sd) && sysfs_type(sd) != SYSFS_DIR) {
-			*pos = sd->s_sibling;
-			sd->s_sibling = NULL;
+		if (sysfs_type(sd) != SYSFS_DIR)
 			sysfs_remove_one(&acxt, sd);
-		} else
+		else
 			pos = &(*pos)->s_sibling;
 	}
 	sysfs_addrm_finish(&acxt);
@@ -890,90 +764,68 @@ void sysfs_remove_dir(struct kobject * kobj)
 	__sysfs_remove_dir(sd);
 }
 
-int sysfs_rename_dir(struct kobject *kobj, struct sysfs_dirent *new_parent_sd,
-		     const char *new_name)
+int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
 {
 	struct sysfs_dirent *sd = kobj->sd;
-	struct dentry *new_parent = NULL;
+	struct dentry *parent = NULL;
 	struct dentry *old_dentry = NULL, *new_dentry = NULL;
 	const char *dup_name = NULL;
 	int error;
 
-	/* get dentries */
+	mutex_lock(&sysfs_rename_mutex);
+
+	error = 0;
+	if (strcmp(sd->s_name, new_name) == 0)
+		goto out;	/* nothing to rename */
+
+	/* get the original dentry */
 	old_dentry = sysfs_get_dentry(sd);
 	if (IS_ERR(old_dentry)) {
 		error = PTR_ERR(old_dentry);
-		goto out_dput;
-	}
-
-	new_parent = sysfs_get_dentry(new_parent_sd);
-	if (IS_ERR(new_parent)) {
-		error = PTR_ERR(new_parent);
-		goto out_dput;
+		goto out;
 	}
 
-	/* lock new_parent and get dentry for new name */
-	mutex_lock(&new_parent->d_inode->i_mutex);
+	parent = old_dentry->d_parent;
 
-	new_dentry = lookup_one_len(new_name, new_parent, strlen(new_name));
-	if (IS_ERR(new_dentry)) {
-		error = PTR_ERR(new_dentry);
-		goto out_unlock;
-	}
+	/* lock parent and get dentry for new name */
+	mutex_lock(&parent->d_inode->i_mutex);
+	mutex_lock(&sysfs_mutex);
 
-	/* By allowing two different directories with the same
-	 * d_parent we allow this routine to move between different
-	 * shadows of the same directory
-	 */
-	error = -EINVAL;
-	if (old_dentry->d_parent->d_inode != new_parent->d_inode ||
-	    new_dentry->d_parent->d_inode != new_parent->d_inode ||
-	    old_dentry == new_dentry)
+	error = -EEXIST;
+	if (sysfs_find_dirent(sd->s_parent, new_name))
 		goto out_unlock;
 
-	error = -EEXIST;
-	if (new_dentry->d_inode)
+	error = -ENOMEM;
+	new_dentry = d_alloc_name(parent, new_name);
+	if (!new_dentry)
 		goto out_unlock;
 
 	/* rename kobject and sysfs_dirent */
 	error = -ENOMEM;
 	new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
 	if (!new_name)
-		goto out_drop;
+		goto out_unlock;
 
 	error = kobject_set_name(kobj, "%s", new_name);
 	if (error)
-		goto out_drop;
-
-	mutex_lock(&sysfs_mutex);
+		goto out_unlock;
 
 	dup_name = sd->s_name;
 	sd->s_name = new_name;
 
-	/* move under the new parent */
+	/* rename */
 	d_add(new_dentry, NULL);
-	d_move(sd->s_dentry, new_dentry);
-
-	sysfs_unlink_sibling(sd);
-	sysfs_get(new_parent_sd);
-	sysfs_put(sd->s_parent);
-	sd->s_parent = new_parent_sd;
-	sysfs_link_sibling(sd);
-
-	mutex_unlock(&sysfs_mutex);
+	d_move(old_dentry, new_dentry);
 
 	error = 0;
-	goto out_unlock;
-
- out_drop:
-	d_drop(new_dentry);
  out_unlock:
-	mutex_unlock(&new_parent->d_inode->i_mutex);
- out_dput:
+	mutex_unlock(&sysfs_mutex);
+	mutex_unlock(&parent->d_inode->i_mutex);
 	kfree(dup_name);
-	dput(new_parent);
 	dput(old_dentry);
 	dput(new_dentry);
+ out:
+	mutex_unlock(&sysfs_rename_mutex);
 	return error;
 }
 
@@ -985,96 +837,69 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
 	struct dentry *old_dentry = NULL, *new_dentry = NULL;
 	int error;
 
+	mutex_lock(&sysfs_rename_mutex);
 	BUG_ON(!sd->s_parent);
 	new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root;
 
+	error = 0;
+	if (sd->s_parent == new_parent_sd)
+		goto out;	/* nothing to move */
+
 	/* get dentries */
 	old_dentry = sysfs_get_dentry(sd);
 	if (IS_ERR(old_dentry)) {
 		error = PTR_ERR(old_dentry);
-		goto out_dput;
+		goto out;
 	}
-	old_parent = sd->s_parent->s_dentry;
+	old_parent = old_dentry->d_parent;
 
 	new_parent = sysfs_get_dentry(new_parent_sd);
 	if (IS_ERR(new_parent)) {
 		error = PTR_ERR(new_parent);
-		goto out_dput;
+		goto out;
 	}
 
-	if (old_parent->d_inode == new_parent->d_inode) {
-		error = 0;
-		goto out_dput;	/* nothing to move */
-	}
 again:
 	mutex_lock(&old_parent->d_inode->i_mutex);
 	if (!mutex_trylock(&new_parent->d_inode->i_mutex)) {
 		mutex_unlock(&old_parent->d_inode->i_mutex);
 		goto again;
 	}
+	mutex_lock(&sysfs_mutex);
 
-	new_dentry = lookup_one_len(kobj->name, new_parent, strlen(kobj->name));
-	if (IS_ERR(new_dentry)) {
-		error = PTR_ERR(new_dentry);
+	error = -EEXIST;
+	if (sysfs_find_dirent(new_parent_sd, sd->s_name))
 		goto out_unlock;
-	} else
-		error = 0;
+
+	error = -ENOMEM;
+	new_dentry = d_alloc_name(new_parent, sd->s_name);
+	if (!new_dentry)
+		goto out_unlock;
+
+	error = 0;
 	d_add(new_dentry, NULL);
-	d_move(sd->s_dentry, new_dentry);
+	d_move(old_dentry, new_dentry);
 	dput(new_dentry);
 
 	/* Remove from old parent's list and insert into new parent's list. */
-	mutex_lock(&sysfs_mutex);
-
 	sysfs_unlink_sibling(sd);
 	sysfs_get(new_parent_sd);
 	sysfs_put(sd->s_parent);
 	sd->s_parent = new_parent_sd;
 	sysfs_link_sibling(sd);
 
-	mutex_unlock(&sysfs_mutex);
-
  out_unlock:
+	mutex_unlock(&sysfs_mutex);
 	mutex_unlock(&new_parent->d_inode->i_mutex);
 	mutex_unlock(&old_parent->d_inode->i_mutex);
- out_dput:
+ out:
 	dput(new_parent);
 	dput(old_dentry);
 	dput(new_dentry);
+	mutex_unlock(&sysfs_rename_mutex);
 	return error;
 }
 
-static int sysfs_dir_open(struct inode *inode, struct file *file)
-{
-	struct dentry * dentry = file->f_path.dentry;
-	struct sysfs_dirent * parent_sd = dentry->d_fsdata;
-	struct sysfs_dirent * sd;
-
-	sd = sysfs_new_dirent("_DIR_", 0, 0);
-	if (sd) {
-		mutex_lock(&sysfs_mutex);
-		sd->s_parent = sysfs_get(parent_sd);
-		sysfs_link_sibling(sd);
-		mutex_unlock(&sysfs_mutex);
-	}
-
-	file->private_data = sd;
-	return sd ? 0 : -ENOMEM;
-}
-
-static int sysfs_dir_close(struct inode *inode, struct file *file)
-{
-	struct sysfs_dirent * cursor = file->private_data;
-
-	mutex_lock(&sysfs_mutex);
-	sysfs_unlink_sibling(cursor);
-	mutex_unlock(&sysfs_mutex);
-
-	release_sysfs_dirent(cursor);
-
-	return 0;
-}
-
 /* Relationship between s_mode and the DT_xxx types */
 static inline unsigned char dt_type(struct sysfs_dirent *sd)
 {
@@ -1085,232 +910,51 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct sysfs_dirent * parent_sd = dentry->d_fsdata;
-	struct sysfs_dirent *cursor = filp->private_data;
-	struct sysfs_dirent **pos;
+	struct sysfs_dirent *pos;
 	ino_t ino;
-	int i = filp->f_pos;
 
-	switch (i) {
-		case 0:
-			ino = parent_sd->s_ino;
-			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
-				break;
+	if (filp->f_pos == 0) {
+		ino = parent_sd->s_ino;
+		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
-			i++;
-			/* fallthrough */
-		case 1:
-			if (parent_sd->s_parent)
-				ino = parent_sd->s_parent->s_ino;
-			else
-				ino = parent_sd->s_ino;
-			if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
-				break;
+	}
+	if (filp->f_pos == 1) {
+		if (parent_sd->s_parent)
+			ino = parent_sd->s_parent->s_ino;
+		else
+			ino = parent_sd->s_ino;
+		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
-			i++;
-			/* fallthrough */
-		default:
-			mutex_lock(&sysfs_mutex);
-
-			pos = &parent_sd->s_children;
-			while (*pos != cursor)
-				pos = &(*pos)->s_sibling;
-
-			/* unlink cursor */
-			*pos = cursor->s_sibling;
-
-			if (filp->f_pos == 2)
-				pos = &parent_sd->s_children;
-
-			for ( ; *pos; pos = &(*pos)->s_sibling) {
-				struct sysfs_dirent *next = *pos;
-				const char * name;
-				int len;
-
-				if (!sysfs_type(next))
-					continue;
-
-				name = next->s_name;
-				len = strlen(name);
-				ino = next->s_ino;
-
-				if (filldir(dirent, name, len, filp->f_pos, ino,
-						 dt_type(next)) < 0)
-					break;
+	}
+	if ((filp->f_pos > 1) && (filp->f_pos < INT_MAX)) {
+		mutex_lock(&sysfs_mutex);
 
-				filp->f_pos++;
-			}
+		/* Skip the dentries we have already reported */
+		pos = parent_sd->s_dir.children;
+		while (pos && (filp->f_pos > pos->s_ino))
+			pos = pos->s_sibling;
 
-			/* put cursor back in */
-			cursor->s_sibling = *pos;
-			*pos = cursor;
+		for ( ; pos; pos = pos->s_sibling) {
+			const char * name;
+			int len;
 
-			mutex_unlock(&sysfs_mutex);
-	}
-	return 0;
-}
-
-static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin)
-{
-	struct dentry * dentry = file->f_path.dentry;
+			name = pos->s_name;
+			len = strlen(name);
+			filp->f_pos = ino = pos->s_ino;
 
-	switch (origin) {
-		case 1:
-			offset += file->f_pos;
-		case 0:
-			if (offset >= 0)
+			if (filldir(dirent, name, len, filp->f_pos, ino,
+					 dt_type(pos)) < 0)
 				break;
-		default:
-			return -EINVAL;
-	}
-	if (offset != file->f_pos) {
-		mutex_lock(&sysfs_mutex);
-
-		file->f_pos = offset;
-		if (file->f_pos >= 2) {
-			struct sysfs_dirent *sd = dentry->d_fsdata;
-			struct sysfs_dirent *cursor = file->private_data;
-			struct sysfs_dirent **pos;
-			loff_t n = file->f_pos - 2;
-
-			sysfs_unlink_sibling(cursor);
-
-			pos = &sd->s_children;
-			while (n && *pos) {
-				struct sysfs_dirent *next = *pos;
-				if (sysfs_type(next))
-					n--;
-				pos = &(*pos)->s_sibling;
-			}
-
-			cursor->s_sibling = *pos;
-			*pos = cursor;
 		}
-
+		if (!pos)
+			filp->f_pos = INT_MAX;
 		mutex_unlock(&sysfs_mutex);
 	}
-
-	return offset;
-}
-
-
-/**
- *	sysfs_make_shadowed_dir - Setup so a directory can be shadowed
- *	@kobj:	object we're creating shadow of.
- */
-
-int sysfs_make_shadowed_dir(struct kobject *kobj,
-	void * (*follow_link)(struct dentry *, struct nameidata *))
-{
-	struct dentry *dentry;
-	struct inode *inode;
-	struct inode_operations *i_op;
-
-	/* get dentry for @kobj->sd, dentry of a shadowed dir is pinned */
-	dentry = sysfs_get_dentry(kobj->sd);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-
-	inode = dentry->d_inode;
-	if (inode->i_op != &sysfs_dir_inode_operations) {
-		dput(dentry);
-		return -EINVAL;
-	}
-
-	i_op = kmalloc(sizeof(*i_op), GFP_KERNEL);
-	if (!i_op)
-		return -ENOMEM;
-
-	memcpy(i_op, &sysfs_dir_inode_operations, sizeof(*i_op));
-	i_op->follow_link = follow_link;
-
-	/* Locking of inode->i_op?
-	 * Since setting i_op is a single word write and they
-	 * are atomic we should be ok here.
-	 */
-	inode->i_op = i_op;
 	return 0;
 }
 
-/**
- *	sysfs_create_shadow_dir - create a shadow directory for an object.
- *	@kobj:	object we're creating directory for.
- *
- *	sysfs_make_shadowed_dir must already have been called on this
- *	directory.
- */
-
-struct sysfs_dirent *sysfs_create_shadow_dir(struct kobject *kobj)
-{
-	struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
-	struct dentry *dir, *parent, *shadow;
-	struct inode *inode;
-	struct sysfs_dirent *sd;
-	struct sysfs_addrm_cxt acxt;
-
-	dir = sysfs_get_dentry(kobj->sd);
-	if (IS_ERR(dir)) {
-		sd = (void *)dir;
-		goto out;
-	}
-	parent = dir->d_parent;
-
-	inode = dir->d_inode;
-	sd = ERR_PTR(-EINVAL);
-	if (!sysfs_is_shadowed_inode(inode))
-		goto out_dput;
-
-	shadow = d_alloc(parent, &dir->d_name);
-	if (!shadow)
-		goto nomem;
-
-	sd = sysfs_new_dirent("_SHADOW_", inode->i_mode, SYSFS_DIR);
-	if (!sd)
-		goto nomem;
-	sd->s_elem.dir.kobj = kobj;
-
-	sysfs_addrm_start(&acxt, parent_sd);
-
-	/* add but don't link into children list */
-	sysfs_add_one(&acxt, sd);
-
-	/* attach and instantiate dentry */
-	sysfs_attach_dentry(sd, shadow);
-	d_instantiate(shadow, igrab(inode));
-	inc_nlink(inode);	/* tj: synchronization? */
-
-	sysfs_addrm_finish(&acxt);
-
-	dget(shadow);		/* Extra count - pin the dentry in core */
-
-	goto out_dput;
-
- nomem:
-	dput(shadow);
-	sd = ERR_PTR(-ENOMEM);
- out_dput:
-	dput(dir);
- out:
-	return sd;
-}
-
-/**
- *	sysfs_remove_shadow_dir - remove an object's directory.
- *	@shadow_sd: sysfs_dirent of shadow directory
- *
- *	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 sysfs_rmdir() below, instead of calling separately.
- */
-
-void sysfs_remove_shadow_dir(struct sysfs_dirent *shadow_sd)
-{
-	__sysfs_remove_dir(shadow_sd);
-}
 
 const struct file_operations sysfs_dir_operations = {
-	.open		= sysfs_dir_open,
-	.release	= sysfs_dir_close,
-	.llseek		= sysfs_dir_lseek,
 	.read		= generic_read_dir,
 	.readdir	= sysfs_readdir,
 };
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 3e1cc062a740..d3be1e7fb48b 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -1,15 +1,22 @@
 /*
- * file.c - operations for regular (text) files.
+ * fs/sysfs/file.c - sysfs regular (text) file implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
  */
 
 #include <linux/module.h>
-#include <linux/fsnotify.h>
 #include <linux/kobject.h>
 #include <linux/namei.h>
 #include <linux/poll.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
-#include <asm/semaphore.h>
 
 #include "sysfs.h"
 
@@ -50,14 +57,33 @@ static struct sysfs_ops subsys_sysfs_ops = {
 	.store	= subsys_attr_store,
 };
 
+/*
+ * There's one sysfs_buffer for each open file and one
+ * sysfs_open_dirent for each sysfs_dirent with one or more open
+ * files.
+ *
+ * filp->private_data points to sysfs_buffer and
+ * sysfs_dirent->s_attr.open points to sysfs_open_dirent.  s_attr.open
+ * is protected by sysfs_open_dirent_lock.
+ */
+static spinlock_t sysfs_open_dirent_lock = SPIN_LOCK_UNLOCKED;
+
+struct sysfs_open_dirent {
+	atomic_t		refcnt;
+	atomic_t		event;
+	wait_queue_head_t	poll;
+	struct list_head	buffers; /* goes through sysfs_buffer.list */
+};
+
 struct sysfs_buffer {
 	size_t			count;
 	loff_t			pos;
 	char			* page;
 	struct sysfs_ops	* ops;
-	struct semaphore	sem;
+	struct mutex		mutex;
 	int			needs_read_fill;
 	int			event;
+	struct list_head	list;
 };
 
 /**
@@ -74,7 +100,7 @@ struct sysfs_buffer {
 static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer)
 {
 	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	struct sysfs_ops * ops = buffer->ops;
 	int ret = 0;
 	ssize_t count;
@@ -88,8 +114,8 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer
 	if (!sysfs_get_active_two(attr_sd))
 		return -ENODEV;
 
-	buffer->event = atomic_read(&attr_sd->s_event);
-	count = ops->show(kobj, attr_sd->s_elem.attr.attr, buffer->page);
+	buffer->event = atomic_read(&attr_sd->s_attr.open->event);
+	count = ops->show(kobj, attr_sd->s_attr.attr, buffer->page);
 
 	sysfs_put_active_two(attr_sd);
 
@@ -128,7 +154,7 @@ sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	struct sysfs_buffer * buffer = file->private_data;
 	ssize_t retval = 0;
 
-	down(&buffer->sem);
+	mutex_lock(&buffer->mutex);
 	if (buffer->needs_read_fill) {
 		retval = fill_read_buffer(file->f_path.dentry,buffer);
 		if (retval)
@@ -139,7 +165,7 @@ sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
 					 buffer->count);
 out:
-	up(&buffer->sem);
+	mutex_unlock(&buffer->mutex);
 	return retval;
 }
 
@@ -189,7 +215,7 @@ static int
 flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t count)
 {
 	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	struct sysfs_ops * ops = buffer->ops;
 	int rc;
 
@@ -197,7 +223,7 @@ flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t
 	if (!sysfs_get_active_two(attr_sd))
 		return -ENODEV;
 
-	rc = ops->store(kobj, attr_sd->s_elem.attr.attr, buffer->page, count);
+	rc = ops->store(kobj, attr_sd->s_attr.attr, buffer->page, count);
 
 	sysfs_put_active_two(attr_sd);
 
@@ -228,20 +254,102 @@ sysfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t
 	struct sysfs_buffer * buffer = file->private_data;
 	ssize_t len;
 
-	down(&buffer->sem);
+	mutex_lock(&buffer->mutex);
 	len = fill_write_buffer(buffer, buf, count);
 	if (len > 0)
 		len = flush_write_buffer(file->f_path.dentry, buffer, len);
 	if (len > 0)
 		*ppos += len;
-	up(&buffer->sem);
+	mutex_unlock(&buffer->mutex);
 	return len;
 }
 
+/**
+ *	sysfs_get_open_dirent - get or create sysfs_open_dirent
+ *	@sd: target sysfs_dirent
+ *	@buffer: sysfs_buffer for this instance of open
+ *
+ *	If @sd->s_attr.open exists, increment its reference count;
+ *	otherwise, create one.  @buffer is chained to the buffers
+ *	list.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno on failure.
+ */
+static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
+				 struct sysfs_buffer *buffer)
+{
+	struct sysfs_open_dirent *od, *new_od = NULL;
+
+ retry:
+	spin_lock(&sysfs_open_dirent_lock);
+
+	if (!sd->s_attr.open && new_od) {
+		sd->s_attr.open = new_od;
+		new_od = NULL;
+	}
+
+	od = sd->s_attr.open;
+	if (od) {
+		atomic_inc(&od->refcnt);
+		list_add_tail(&buffer->list, &od->buffers);
+	}
+
+	spin_unlock(&sysfs_open_dirent_lock);
+
+	if (od) {
+		kfree(new_od);
+		return 0;
+	}
+
+	/* not there, initialize a new one and retry */
+	new_od = kmalloc(sizeof(*new_od), GFP_KERNEL);
+	if (!new_od)
+		return -ENOMEM;
+
+	atomic_set(&new_od->refcnt, 0);
+	atomic_set(&new_od->event, 1);
+	init_waitqueue_head(&new_od->poll);
+	INIT_LIST_HEAD(&new_od->buffers);
+	goto retry;
+}
+
+/**
+ *	sysfs_put_open_dirent - put sysfs_open_dirent
+ *	@sd: target sysfs_dirent
+ *	@buffer: associated sysfs_buffer
+ *
+ *	Put @sd->s_attr.open and unlink @buffer from the buffers list.
+ *	If reference count reaches zero, disassociate and free it.
+ *
+ *	LOCKING:
+ *	None.
+ */
+static void sysfs_put_open_dirent(struct sysfs_dirent *sd,
+				  struct sysfs_buffer *buffer)
+{
+	struct sysfs_open_dirent *od = sd->s_attr.open;
+
+	spin_lock(&sysfs_open_dirent_lock);
+
+	list_del(&buffer->list);
+	if (atomic_dec_and_test(&od->refcnt))
+		sd->s_attr.open = NULL;
+	else
+		od = NULL;
+
+	spin_unlock(&sysfs_open_dirent_lock);
+
+	kfree(od);
+}
+
 static int sysfs_open_file(struct inode *inode, struct file *file)
 {
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	struct sysfs_buffer * buffer;
 	struct sysfs_ops * ops = NULL;
 	int error;
@@ -294,33 +402,38 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	if (!buffer)
 		goto err_out;
 
-	init_MUTEX(&buffer->sem);
+	mutex_init(&buffer->mutex);
 	buffer->needs_read_fill = 1;
 	buffer->ops = ops;
 	file->private_data = buffer;
 
-	/* open succeeded, put active references and pin attr_sd */
+	/* make sure we have open dirent struct */
+	error = sysfs_get_open_dirent(attr_sd, buffer);
+	if (error)
+		goto err_free;
+
+	/* open succeeded, put active references */
 	sysfs_put_active_two(attr_sd);
-	sysfs_get(attr_sd);
 	return 0;
 
+ err_free:
+	kfree(buffer);
  err_out:
 	sysfs_put_active_two(attr_sd);
 	return error;
 }
 
-static int sysfs_release(struct inode * inode, struct file * filp)
+static int sysfs_release(struct inode *inode, struct file *filp)
 {
-	struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
+	struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata;
 	struct sysfs_buffer *buffer = filp->private_data;
 
-	sysfs_put(attr_sd);
+	sysfs_put_open_dirent(sd, buffer);
+
+	if (buffer->page)
+		free_page((unsigned long)buffer->page);
+	kfree(buffer);
 
-	if (buffer) {
-		if (buffer->page)
-			free_page((unsigned long)buffer->page);
-		kfree(buffer);
-	}
 	return 0;
 }
 
@@ -335,24 +448,24 @@ static int sysfs_release(struct inode * inode, struct file * filp)
  * again will not get new data, or reset the state of 'poll'.
  * Reminder: this only works for attributes which actively support
  * it, and it is not possible to test an attribute from userspace
- * to see if it supports poll (Nether 'poll' or 'select' return
+ * to see if it supports poll (Neither 'poll' nor 'select' return
  * an appropriate error code).  When in doubt, set a suitable timeout value.
  */
 static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
 {
 	struct sysfs_buffer * buffer = filp->private_data;
 	struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj;
+	struct sysfs_open_dirent *od = attr_sd->s_attr.open;
 
 	/* need parent for the kobj, grab both */
 	if (!sysfs_get_active_two(attr_sd))
 		goto trigger;
 
-	poll_wait(filp, &kobj->poll, wait);
+	poll_wait(filp, &od->poll, wait);
 
 	sysfs_put_active_two(attr_sd);
 
-	if (buffer->event != atomic_read(&attr_sd->s_event))
+	if (buffer->event != atomic_read(&od->event))
 		goto trigger;
 
 	return 0;
@@ -373,8 +486,17 @@ void sysfs_notify(struct kobject *k, char *dir, char *attr)
 	if (sd && attr)
 		sd = sysfs_find_dirent(sd, attr);
 	if (sd) {
-		atomic_inc(&sd->s_event);
-		wake_up_interruptible(&k->poll);
+		struct sysfs_open_dirent *od;
+
+		spin_lock(&sysfs_open_dirent_lock);
+
+		od = sd->s_attr.open;
+		if (od) {
+			atomic_inc(&od->event);
+			wake_up_interruptible(&od->poll);
+		}
+
+		spin_unlock(&sysfs_open_dirent_lock);
 	}
 
 	mutex_unlock(&sysfs_mutex);
@@ -397,25 +519,21 @@ int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
 	umode_t mode = (attr->mode & S_IALLUGO) | S_IFREG;
 	struct sysfs_addrm_cxt acxt;
 	struct sysfs_dirent *sd;
+	int rc;
 
 	sd = sysfs_new_dirent(attr->name, mode, type);
 	if (!sd)
 		return -ENOMEM;
-	sd->s_elem.attr.attr = (void *)attr;
+	sd->s_attr.attr = (void *)attr;
 
 	sysfs_addrm_start(&acxt, dir_sd);
+	rc = sysfs_add_one(&acxt, sd);
+	sysfs_addrm_finish(&acxt);
 
-	if (!sysfs_find_dirent(dir_sd, attr->name)) {
-		sysfs_add_one(&acxt, sd);
-		sysfs_link_sibling(sd);
-	}
-
-	if (!sysfs_addrm_finish(&acxt)) {
+	if (rc)
 		sysfs_put(sd);
-		return -EEXIST;
-	}
 
-	return 0;
+	return rc;
 }
 
 
@@ -457,42 +575,6 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 }
 EXPORT_SYMBOL_GPL(sysfs_add_file_to_group);
 
-
-/**
- * sysfs_update_file - update the modified timestamp on an object attribute.
- * @kobj: object we're acting for.
- * @attr: attribute descriptor.
- */
-int sysfs_update_file(struct kobject * kobj, const struct attribute * attr)
-{
-	struct sysfs_dirent *victim_sd = NULL;
-	struct dentry *victim = NULL;
-	int rc;
-
-	rc = -ENOENT;
-	victim_sd = sysfs_get_dirent(kobj->sd, attr->name);
-	if (!victim_sd)
-		goto out;
-
-	victim = sysfs_get_dentry(victim_sd);
-	if (IS_ERR(victim)) {
-		rc = PTR_ERR(victim);
-		victim = NULL;
-		goto out;
-	}
-
-	mutex_lock(&victim->d_inode->i_mutex);
-	victim->d_inode->i_mtime = CURRENT_TIME;
-	fsnotify_modify(victim);
-	mutex_unlock(&victim->d_inode->i_mutex);
-	rc = 0;
- out:
-	dput(victim);
-	sysfs_put(victim_sd);
-	return rc;
-}
-
-
 /**
  * sysfs_chmod_file - update the modified mode value on an object attribute.
  * @kobj: object we're acting for.
@@ -513,7 +595,9 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode)
 	if (!victim_sd)
 		goto out;
 
+	mutex_lock(&sysfs_rename_mutex);
 	victim = sysfs_get_dentry(victim_sd);
+	mutex_unlock(&sysfs_rename_mutex);
 	if (IS_ERR(victim)) {
 		rc = PTR_ERR(victim);
 		victim = NULL;
@@ -521,10 +605,19 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode)
 	}
 
 	inode = victim->d_inode;
+
 	mutex_lock(&inode->i_mutex);
+
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
 	rc = notify_change(victim, &newattrs);
+
+	if (rc == 0) {
+		mutex_lock(&sysfs_mutex);
+		victim_sd->s_mode = newattrs.ia_mode;
+		mutex_unlock(&sysfs_mutex);
+	}
+
 	mutex_unlock(&inode->i_mutex);
  out:
 	dput(victim);
@@ -632,4 +725,3 @@ EXPORT_SYMBOL_GPL(sysfs_schedule_callback);
 
 EXPORT_SYMBOL_GPL(sysfs_create_file);
 EXPORT_SYMBOL_GPL(sysfs_remove_file);
-EXPORT_SYMBOL_GPL(sysfs_update_file);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index f318b73c790c..d1972374655a 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -13,8 +13,6 @@
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/err.h>
-#include <linux/fs.h>
-#include <asm/semaphore.h>
 #include "sysfs.h"
 
 
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 10d1b52899f1..9236635111f4 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -1,7 +1,11 @@
 /*
- * inode.c - basic inode and dentry operations.
+ * fs/sysfs/inode.c - basic sysfs inode and dentry operations
  *
- * sysfs is Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
  *
  * Please see Documentation/filesystems/sysfs.txt for more information.
  */
@@ -14,7 +18,6 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
-#include <asm/semaphore.h>
 #include "sysfs.h"
 
 extern struct super_block * sysfs_sb;
@@ -34,16 +37,6 @@ static const struct inode_operations sysfs_inode_operations ={
 	.setattr	= sysfs_setattr,
 };
 
-void sysfs_delete_inode(struct inode *inode)
-{
-	/* Free the shadowed directory inode operations */
-	if (sysfs_is_shadowed_inode(inode)) {
-		kfree(inode->i_op);
-		inode->i_op = NULL;
-	}
-	return generic_delete_inode(inode);
-}
-
 int sysfs_setattr(struct dentry * dentry, struct iattr * iattr)
 {
 	struct inode * inode = dentry->d_inode;
@@ -133,8 +126,22 @@ static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
  */
 static struct lock_class_key sysfs_inode_imutex_key;
 
+static int sysfs_count_nlink(struct sysfs_dirent *sd)
+{
+	struct sysfs_dirent *child;
+	int nr = 0;
+
+	for (child = sd->s_dir.children; child; child = child->s_sibling)
+		if (sysfs_type(child) == SYSFS_DIR)
+			nr++;
+
+	return nr + 2;
+}
+
 static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
 {
+	struct bin_attribute *bin_attr;
+
 	inode->i_blocks = 0;
 	inode->i_mapping->a_ops = &sysfs_aops;
 	inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info;
@@ -150,6 +157,32 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
 		set_inode_attr(inode, sd->s_iattr);
 	} else
 		set_default_inode_attr(inode, sd->s_mode);
+
+
+	/* initialize inode according to type */
+	switch (sysfs_type(sd)) {
+	case SYSFS_DIR:
+		inode->i_op = &sysfs_dir_inode_operations;
+		inode->i_fop = &sysfs_dir_operations;
+		inode->i_nlink = sysfs_count_nlink(sd);
+		break;
+	case SYSFS_KOBJ_ATTR:
+		inode->i_size = PAGE_SIZE;
+		inode->i_fop = &sysfs_file_operations;
+		break;
+	case SYSFS_KOBJ_BIN_ATTR:
+		bin_attr = sd->s_bin_attr.bin_attr;
+		inode->i_size = bin_attr->size;
+		inode->i_fop = &bin_fops;
+		break;
+	case SYSFS_KOBJ_LINK:
+		inode->i_op = &sysfs_symlink_inode_operations;
+		break;
+	default:
+		BUG();
+	}
+
+	unlock_new_inode(inode);
 }
 
 /**
@@ -177,50 +210,24 @@ struct inode * sysfs_get_inode(struct sysfs_dirent *sd)
 	return inode;
 }
 
-/**
- *	sysfs_instantiate - instantiate dentry
- *	@dentry: dentry to be instantiated
- *	@inode: inode associated with @sd
- *
- *	Unlock @inode if locked and instantiate @dentry with @inode.
- *
- *	LOCKING:
- *	None.
- */
-void sysfs_instantiate(struct dentry *dentry, struct inode *inode)
-{
-	BUG_ON(!dentry || dentry->d_inode);
-
-	if (inode->i_state & I_NEW)
-		unlock_new_inode(inode);
-
-	d_instantiate(dentry, inode);
-}
-
 int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name)
 {
 	struct sysfs_addrm_cxt acxt;
-	struct sysfs_dirent **pos, *sd;
+	struct sysfs_dirent *sd;
 
 	if (!dir_sd)
 		return -ENOENT;
 
 	sysfs_addrm_start(&acxt, dir_sd);
 
-	for (pos = &dir_sd->s_children; *pos; pos = &(*pos)->s_sibling) {
-		sd = *pos;
-
-		if (!sysfs_type(sd))
-			continue;
-		if (!strcmp(sd->s_name, name)) {
-			*pos = sd->s_sibling;
-			sd->s_sibling = NULL;
-			sysfs_remove_one(&acxt, sd);
-			break;
-		}
-	}
+	sd = sysfs_find_dirent(dir_sd, name);
+	if (sd)
+		sysfs_remove_one(&acxt, sd);
+
+	sysfs_addrm_finish(&acxt);
 
-	if (sysfs_addrm_finish(&acxt))
+	if (sd)
 		return 0;
-	return -ENOENT;
+	else
+		return -ENOENT;
 }
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index fbc7b65fe262..c76c540be3c8 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -1,5 +1,13 @@
 /*
- * mount.c - operations for initializing and mounting sysfs.
+ * fs/sysfs/symlink.c - operations for initializing and mounting sysfs
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
  */
 
 #define DEBUG 
@@ -8,25 +16,25 @@
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
-#include <asm/semaphore.h>
 
 #include "sysfs.h"
 
 /* Random magic number */
 #define SYSFS_MAGIC 0x62656572
 
-struct vfsmount *sysfs_mount;
+static struct vfsmount *sysfs_mount;
 struct super_block * sysfs_sb = NULL;
 struct kmem_cache *sysfs_dir_cachep;
 
 static const struct super_operations sysfs_ops = {
 	.statfs		= simple_statfs,
-	.drop_inode	= sysfs_delete_inode,
+	.drop_inode	= generic_delete_inode,
 };
 
 struct sysfs_dirent sysfs_root = {
+	.s_name		= "",
 	.s_count	= ATOMIC_INIT(1),
-	.s_flags	= SYSFS_ROOT,
+	.s_flags	= SYSFS_DIR,
 	.s_mode		= S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
 	.s_ino		= 1,
 };
@@ -50,11 +58,6 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	}
 
-	inode->i_op = &sysfs_dir_inode_operations;
-	inode->i_fop = &sysfs_dir_operations;
-	inc_nlink(inode); /* directory, account for "." */
-	unlock_new_inode(inode);
-
 	/* instantiate and link root dentry */
 	root = d_alloc_root(inode);
 	if (!root) {
@@ -62,7 +65,6 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent)
 		iput(inode);
 		return -ENOMEM;
 	}
-	sysfs_root.s_dentry = root;
 	root->d_fsdata = &sysfs_root;
 	sb->s_root = root;
 	return 0;
@@ -77,7 +79,7 @@ static int sysfs_get_sb(struct file_system_type *fs_type,
 static struct file_system_type sysfs_fs_type = {
 	.name		= "sysfs",
 	.get_sb		= sysfs_get_sb,
-	.kill_sb	= kill_litter_super,
+	.kill_sb	= kill_anon_super,
 };
 
 int __init sysfs_init(void)
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 4ce687f0b5d0..3eac20c63c41 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -1,5 +1,13 @@
 /*
- * symlink.c - operations for sysfs symlinks.
+ * fs/sysfs/symlink.c - sysfs symlink implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
  */
 
 #include <linux/fs.h>
@@ -7,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/kobject.h>
 #include <linux/namei.h>
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 
 #include "sysfs.h"
 
@@ -60,10 +68,9 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
 
 	BUG_ON(!name);
 
-	if (!kobj) {
-		if (sysfs_mount && sysfs_mount->mnt_sb)
-			parent_sd = sysfs_mount->mnt_sb->s_root->d_fsdata;
-	} else
+	if (!kobj)
+		parent_sd = &sysfs_root;
+	else
 		parent_sd = kobj->sd;
 
 	error = -EFAULT;
@@ -87,20 +94,15 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
 	if (!sd)
 		goto out_put;
 
-	sd->s_elem.symlink.target_sd = target_sd;
+	sd->s_symlink.target_sd = target_sd;
 	target_sd = NULL;	/* reference is now owned by the symlink */
 
 	sysfs_addrm_start(&acxt, parent_sd);
+	error = sysfs_add_one(&acxt, sd);
+	sysfs_addrm_finish(&acxt);
 
-	if (!sysfs_find_dirent(parent_sd, name)) {
-		sysfs_add_one(&acxt, sd);
-		sysfs_link_sibling(sd);
-	}
-
-	if (!sysfs_addrm_finish(&acxt)) {
-		error = -EEXIST;
+	if (error)
 		goto out_put;
-	}
 
 	return 0;
 
@@ -148,7 +150,7 @@ static int sysfs_getlink(struct dentry *dentry, char * path)
 {
 	struct sysfs_dirent *sd = dentry->d_fsdata;
 	struct sysfs_dirent *parent_sd = sd->s_parent;
-	struct sysfs_dirent *target_sd = sd->s_elem.symlink.target_sd;
+	struct sysfs_dirent *target_sd = sd->s_symlink.target_sd;
 	int error;
 
 	mutex_lock(&sysfs_mutex);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 6b8c8d76d308..f0326f281d1c 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -1,20 +1,39 @@
+/*
+ * fs/sysfs/sysfs.h - sysfs internal header file
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ */
+
+struct sysfs_open_dirent;
+
+/* type-specific structures for sysfs_dirent->s_* union members */
 struct sysfs_elem_dir {
-	struct kobject		* kobj;
+	struct kobject		*kobj;
+	/* children list starts here and goes through sd->s_sibling */
+	struct sysfs_dirent	*children;
 };
 
 struct sysfs_elem_symlink {
-	struct sysfs_dirent	* target_sd;
+	struct sysfs_dirent	*target_sd;
 };
 
 struct sysfs_elem_attr {
-	struct attribute	* attr;
+	struct attribute	*attr;
+	struct sysfs_open_dirent *open;
 };
 
 struct sysfs_elem_bin_attr {
-	struct bin_attribute	* bin_attr;
+	struct bin_attribute	*bin_attr;
 };
 
 /*
+ * sysfs_dirent - the building block of sysfs hierarchy.  Each and
+ * every sysfs node is represented by single sysfs_dirent.
+ *
  * As long as s_count reference is held, the sysfs_dirent itself is
  * accessible.  Dereferencing s_elem or any other outer entity
  * requires s_active reference.
@@ -22,28 +41,43 @@ struct sysfs_elem_bin_attr {
 struct sysfs_dirent {
 	atomic_t		s_count;
 	atomic_t		s_active;
-	struct sysfs_dirent	* s_parent;
-	struct sysfs_dirent	* s_sibling;
-	struct sysfs_dirent	* s_children;
-	const char		* s_name;
+	struct sysfs_dirent	*s_parent;
+	struct sysfs_dirent	*s_sibling;
+	const char		*s_name;
 
 	union {
-		struct sysfs_elem_dir		dir;
-		struct sysfs_elem_symlink	symlink;
-		struct sysfs_elem_attr		attr;
-		struct sysfs_elem_bin_attr	bin_attr;
-	}			s_elem;
+		struct sysfs_elem_dir		s_dir;
+		struct sysfs_elem_symlink	s_symlink;
+		struct sysfs_elem_attr		s_attr;
+		struct sysfs_elem_bin_attr	s_bin_attr;
+	};
 
 	unsigned int		s_flags;
-	umode_t			s_mode;
 	ino_t			s_ino;
-	struct dentry		* s_dentry;
-	struct iattr		* s_iattr;
-	atomic_t		s_event;
+	umode_t			s_mode;
+	struct iattr		*s_iattr;
 };
 
-#define SD_DEACTIVATED_BIAS	INT_MIN
+#define SD_DEACTIVATED_BIAS		INT_MIN
+
+#define SYSFS_TYPE_MASK			0x00ff
+#define SYSFS_DIR			0x0001
+#define SYSFS_KOBJ_ATTR			0x0002
+#define SYSFS_KOBJ_BIN_ATTR		0x0004
+#define SYSFS_KOBJ_LINK			0x0008
+#define SYSFS_COPY_NAME			(SYSFS_DIR | SYSFS_KOBJ_LINK)
+
+#define SYSFS_FLAG_MASK			~SYSFS_TYPE_MASK
+#define SYSFS_FLAG_REMOVED		0x0200
+
+static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
+{
+	return sd->s_flags & SYSFS_TYPE_MASK;
+}
 
+/*
+ * Context structure to be used while adding/removing nodes.
+ */
 struct sysfs_addrm_cxt {
 	struct sysfs_dirent	*parent_sd;
 	struct inode		*parent_inode;
@@ -51,63 +85,47 @@ struct sysfs_addrm_cxt {
 	int			cnt;
 };
 
-extern struct vfsmount * sysfs_mount;
+/*
+ * mount.c
+ */
 extern struct sysfs_dirent sysfs_root;
+extern struct super_block *sysfs_sb;
 extern struct kmem_cache *sysfs_dir_cachep;
 
-extern struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd);
-extern void sysfs_link_sibling(struct sysfs_dirent *sd);
-extern void sysfs_unlink_sibling(struct sysfs_dirent *sd);
-extern struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd);
-extern void sysfs_put_active(struct sysfs_dirent *sd);
-extern struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd);
-extern void sysfs_put_active_two(struct sysfs_dirent *sd);
-extern void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
-			      struct sysfs_dirent *parent_sd);
-extern void sysfs_add_one(struct sysfs_addrm_cxt *acxt,
-			  struct sysfs_dirent *sd);
-extern void sysfs_remove_one(struct sysfs_addrm_cxt *acxt,
-			     struct sysfs_dirent *sd);
-extern int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
-
-extern void sysfs_delete_inode(struct inode *inode);
-extern struct inode * sysfs_get_inode(struct sysfs_dirent *sd);
-extern void sysfs_instantiate(struct dentry *dentry, struct inode *inode);
-
-extern void release_sysfs_dirent(struct sysfs_dirent * sd);
-extern struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
-					      const unsigned char *name);
-extern struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-					     const unsigned char *name);
-extern struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode,
-					     int type);
-
-extern int sysfs_add_file(struct sysfs_dirent *dir_sd,
-			  const struct attribute *attr, int type);
-extern int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name);
-extern struct sysfs_dirent *sysfs_find(struct sysfs_dirent *dir, const char * name);
-
-extern int sysfs_create_subdir(struct kobject *kobj, const char *name,
-			       struct sysfs_dirent **p_sd);
-extern void sysfs_remove_subdir(struct sysfs_dirent *sd);
-
-extern int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
-
-extern spinlock_t sysfs_assoc_lock;
+/*
+ * dir.c
+ */
 extern struct mutex sysfs_mutex;
-extern struct super_block * sysfs_sb;
+extern struct mutex sysfs_rename_mutex;
+extern spinlock_t sysfs_assoc_lock;
+
 extern const struct file_operations sysfs_dir_operations;
-extern const struct file_operations sysfs_file_operations;
-extern const struct file_operations bin_fops;
 extern const struct inode_operations sysfs_dir_inode_operations;
-extern const struct inode_operations sysfs_symlink_inode_operations;
-
-static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
-{
-	return sd->s_flags & SYSFS_TYPE_MASK;
-}
 
-static inline struct sysfs_dirent * sysfs_get(struct sysfs_dirent * sd)
+struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd);
+struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd);
+void sysfs_put_active(struct sysfs_dirent *sd);
+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);
+void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
+void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
+
+struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
+				       const unsigned char *name);
+struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
+				      const unsigned char *name);
+struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type);
+
+void release_sysfs_dirent(struct sysfs_dirent *sd);
+
+int sysfs_create_subdir(struct kobject *kobj, const char *name,
+			struct sysfs_dirent **p_sd);
+void sysfs_remove_subdir(struct sysfs_dirent *sd);
+
+static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
 {
 	if (sd) {
 		WARN_ON(!atomic_read(&sd->s_count));
@@ -116,13 +134,33 @@ static inline struct sysfs_dirent * sysfs_get(struct sysfs_dirent * sd)
 	return sd;
 }
 
-static inline void sysfs_put(struct sysfs_dirent * sd)
+static inline void sysfs_put(struct sysfs_dirent *sd)
 {
 	if (sd && atomic_dec_and_test(&sd->s_count))
 		release_sysfs_dirent(sd);
 }
 
-static inline int sysfs_is_shadowed_inode(struct inode *inode)
-{
-	return S_ISDIR(inode->i_mode) && inode->i_op->follow_link;
-}
+/*
+ * inode.c
+ */
+struct inode *sysfs_get_inode(struct sysfs_dirent *sd);
+int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
+int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name);
+
+/*
+ * file.c
+ */
+extern const struct file_operations sysfs_file_operations;
+
+int sysfs_add_file(struct sysfs_dirent *dir_sd,
+		   const struct attribute *attr, int type);
+
+/*
+ * bin.c
+ */
+extern const struct file_operations bin_fops;
+
+/*
+ * symlink.c
+ */
+extern const struct inode_operations sysfs_symlink_inode_operations;
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 5f152f60d74d..6f4c29e9c3d9 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -323,17 +323,13 @@ xfs_iomap_valid(
 /*
  * BIO completion handler for buffered IO.
  */
-STATIC int
+STATIC void
 xfs_end_bio(
 	struct bio		*bio,
-	unsigned int		bytes_done,
 	int			error)
 {
 	xfs_ioend_t		*ioend = bio->bi_private;
 
-	if (bio->bi_size)
-		return 1;
-
 	ASSERT(atomic_read(&bio->bi_cnt) >= 1);
 	ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error;
 
@@ -343,7 +339,6 @@ xfs_end_bio(
 	bio_put(bio);
 
 	xfs_finish_ioend(ioend, 0);
-	return 0;
 }
 
 STATIC void
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index b0f0e58866de..39f44ee572e8 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1103,19 +1103,15 @@ _xfs_buf_ioend(
 	}
 }
 
-STATIC int
+STATIC void
 xfs_buf_bio_end_io(
 	struct bio		*bio,
-	unsigned int		bytes_done,
 	int			error)
 {
 	xfs_buf_t		*bp = (xfs_buf_t *)bio->bi_private;
 	unsigned int		blocksize = bp->b_target->bt_bsize;
 	struct bio_vec		*bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
 
-	if (bio->bi_size)
-		return 1;
-
 	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		bp->b_error = EIO;
 
@@ -1143,7 +1139,6 @@ xfs_buf_bio_end_io(
 
 	_xfs_buf_ioend(bp, 1);
 	bio_put(bio);
-	return 0;
 }
 
 STATIC void