Creation of Cybook 2416 (actually Gen4) repository

fs/gfs2/Kconfig

@@ -0,0 +1,46 @@
+config GFS2_FS
+	tristate "GFS2 file system support"
+	depends on EXPERIMENTAL
+	select FS_POSIX_ACL
+	select CRC32
+	help
+	  A cluster filesystem.
+
+	  Allows a cluster of computers to simultaneously use a block device
+	  that is shared between them (with FC, iSCSI, NBD, etc...).  GFS reads
+	  and writes to the block device like a local filesystem, but also uses
+	  a lock module to allow the computers coordinate their I/O so
+	  filesystem consistency is maintained.  One of the nifty features of
+	  GFS is perfect consistency -- changes made to the filesystem on one
+	  machine show up immediately on all other machines in the cluster.
+
+	  To use the GFS2 filesystem, you will need to enable one or more of
+	  the below locking modules. Documentation and utilities for GFS2 can
+	  be found here: http://sources.redhat.com/cluster
+
+config GFS2_FS_LOCKING_NOLOCK
+	tristate "GFS2 \"nolock\" locking module"
+	depends on GFS2_FS
+	help
+	  Single node locking module for GFS2.
+
+	  Use this module if you want to use GFS2 on a single node without
+	  its clustering features. You can still take advantage of the
+	  large file support, and upgrade to running a full cluster later on
+	  if required.
+
+	  If you will only be using GFS2 in cluster mode, you do not need this
+	  module.
+
+config GFS2_FS_LOCKING_DLM
+	tristate "GFS2 DLM locking module"
+	depends on GFS2_FS && SYSFS && NET && INET && (IPV6 || IPV6=n)
+	select IP_SCTP if DLM_SCTP
+	select CONFIGFS_FS
+	select DLM
+	help
+	  Multiple node locking module for GFS2
+
+	  Most users of GFS2 will require this module. It provides the locking
+	  interface between GFS2 and the DLM, which is required to use GFS2
+	  in a cluster environment.

fs/gfs2/Makefile

@@ -0,0 +1,10 @@
+obj-$(CONFIG_GFS2_FS) += gfs2.o
+gfs2-y := acl.o bmap.o daemon.o dir.o eaops.o eattr.o glock.o \
+	glops.o inode.o lm.o log.o lops.o locking.o main.o meta_io.o \
+	mount.o ondisk.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
+	ops_fstype.o ops_inode.o ops_super.o ops_vm.o quota.o \
+	recovery.o rgrp.o super.o sys.o trans.o util.o
+
+obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/
+obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += locking/dlm/
+

fs/gfs2/acl.c

@@ -0,0 +1,294 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "eaops.h"
+#include "eattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+
+#define ACL_ACCESS 1
+#define ACL_DEFAULT 0
+
+int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
+		      struct gfs2_ea_request *er,
+		      int *remove, mode_t *mode)
+{
+	struct posix_acl *acl;
+	int error;
+
+	error = gfs2_acl_validate_remove(ip, access);
+	if (error)
+		return error;
+
+	if (!er->er_data)
+		return -EINVAL;
+
+	acl = posix_acl_from_xattr(er->er_data, er->er_data_len);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl) {
+		*remove = 1;
+		return 0;
+	}
+
+	error = posix_acl_valid(acl);
+	if (error)
+		goto out;
+
+	if (access) {
+		error = posix_acl_equiv_mode(acl, mode);
+		if (!error)
+			*remove = 1;
+		else if (error > 0)
+			error = 0;
+	}
+
+out:
+	posix_acl_release(acl);
+	return error;
+}
+
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access)
+{
+	if (!GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl)
+		return -EOPNOTSUPP;
+	if (current->fsuid != ip->i_inode.i_uid && !capable(CAP_FOWNER))
+		return -EPERM;
+	if (S_ISLNK(ip->i_inode.i_mode))
+		return -EOPNOTSUPP;
+	if (!access && !S_ISDIR(ip->i_inode.i_mode))
+		return -EACCES;
+
+	return 0;
+}
+
+static int acl_get(struct gfs2_inode *ip, int access, struct posix_acl **acl,
+		   struct gfs2_ea_location *el, char **data, unsigned int *len)
+{
+	struct gfs2_ea_request er;
+	struct gfs2_ea_location el_this;
+	int error;
+
+	if (!ip->i_di.di_eattr)
+		return 0;
+
+	memset(&er, 0, sizeof(struct gfs2_ea_request));
+	if (access) {
+		er.er_name = GFS2_POSIX_ACL_ACCESS;
+		er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
+	} else {
+		er.er_name = GFS2_POSIX_ACL_DEFAULT;
+		er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
+	}
+	er.er_type = GFS2_EATYPE_SYS;
+
+	if (!el)
+		el = &el_this;
+
+	error = gfs2_ea_find(ip, &er, el);
+	if (error)
+		return error;
+	if (!el->el_ea)
+		return 0;
+	if (!GFS2_EA_DATA_LEN(el->el_ea))
+		goto out;
+
+	er.er_data_len = GFS2_EA_DATA_LEN(el->el_ea);
+	er.er_data = kmalloc(er.er_data_len, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!er.er_data)
+		goto out;
+
+	error = gfs2_ea_get_copy(ip, el, er.er_data);
+	if (error)
+		goto out_kfree;
+
+	if (acl) {
+		*acl = posix_acl_from_xattr(er.er_data, er.er_data_len);
+		if (IS_ERR(*acl))
+			error = PTR_ERR(*acl);
+	}
+
+out_kfree:
+	if (error || !data)
+		kfree(er.er_data);
+	else {
+		*data = er.er_data;
+		*len = er.er_data_len;
+	}
+out:
+	if (error || el == &el_this)
+		brelse(el->el_bh);
+	return error;
+}
+
+/**
+ * gfs2_check_acl - Check an ACL to see if we're allowed to do something
+ * @inode: the file we want to do something to
+ * @mask: what we want to do
+ *
+ * Returns: errno
+ */
+
+int gfs2_check_acl(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = NULL;
+	int error;
+
+	error = acl_get(GFS2_I(inode), ACL_ACCESS, &acl, NULL, NULL, NULL);
+	if (error)
+		return error;
+
+	if (acl) {
+		error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+static int munge_mode(struct gfs2_inode *ip, mode_t mode)
+{
+	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;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		gfs2_assert_withdraw(sdp,
+				(ip->i_inode.i_mode & S_IFMT) == (mode & S_IFMT));
+		ip->i_inode.i_mode = mode;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(ip, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+	return 0;
+}
+
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_request er;
+	mode_t mode = ip->i_inode.i_mode;
+	int error;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return 0;
+	if (S_ISLNK(ip->i_inode.i_mode))
+		return 0;
+
+	memset(&er, 0, sizeof(struct gfs2_ea_request));
+	er.er_type = GFS2_EATYPE_SYS;
+
+	error = acl_get(dip, ACL_DEFAULT, &acl, NULL,
+			&er.er_data, &er.er_data_len);
+	if (error)
+		return error;
+	if (!acl) {
+		mode &= ~current->fs->umask;
+		if (mode != ip->i_inode.i_mode)
+			error = munge_mode(ip, mode);
+		return error;
+	}
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	if (S_ISDIR(ip->i_inode.i_mode)) {
+		er.er_name = GFS2_POSIX_ACL_DEFAULT;
+		er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
+		error = gfs2_system_eaops.eo_set(ip, &er);
+		if (error)
+			goto out;
+	}
+
+	error = posix_acl_create_masq(acl, &mode);
+	if (error < 0)
+		goto out;
+	if (error > 0) {
+		er.er_name = GFS2_POSIX_ACL_ACCESS;
+		er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
+		posix_acl_to_xattr(acl, er.er_data, er.er_data_len);
+		er.er_mode = mode;
+		er.er_flags = GFS2_ERF_MODE;
+		error = gfs2_system_eaops.eo_set(ip, &er);
+		if (error)
+			goto out;
+	} else
+		munge_mode(ip, mode);
+
+out:
+	posix_acl_release(acl);
+	kfree(er.er_data);
+	return error;
+}
+
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
+{
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_location el;
+	char *data;
+	unsigned int len;
+	int error;
+
+	error = acl_get(ip, ACL_ACCESS, &acl, &el, &data, &len);
+	if (error)
+		return error;
+	if (!acl)
+		return gfs2_setattr_simple(ip, attr);
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	error = posix_acl_chmod_masq(acl, attr->ia_mode);
+	if (!error) {
+		posix_acl_to_xattr(acl, data, len);
+		error = gfs2_ea_acl_chmod(ip, &el, attr, data);
+	}
+
+out:
+	posix_acl_release(acl);
+	brelse(el.el_bh);
+	kfree(data);
+	return error;
+}
+

fs/gfs2/acl.h

@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __ACL_DOT_H__
+#define __ACL_DOT_H__
+
+#include "incore.h"
+
+#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
+#define GFS2_POSIX_ACL_ACCESS_LEN	16
+#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
+#define GFS2_POSIX_ACL_DEFAULT_LEN	17
+
+#define GFS2_ACL_IS_ACCESS(name, len) \
+         ((len) == GFS2_POSIX_ACL_ACCESS_LEN && \
+         !memcmp(GFS2_POSIX_ACL_ACCESS, (name), (len)))
+
+#define GFS2_ACL_IS_DEFAULT(name, len) \
+         ((len) == GFS2_POSIX_ACL_DEFAULT_LEN && \
+         !memcmp(GFS2_POSIX_ACL_DEFAULT, (name), (len)))
+
+struct gfs2_ea_request;
+
+int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
+			  struct gfs2_ea_request *er,
+			  int *remove, mode_t *mode);
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access);
+int gfs2_check_acl(struct inode *inode, int mask);
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip);
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+
+#endif /* __ACL_DOT_H__ */

fs/gfs2/bmap.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __BMAP_DOT_H__
+#define __BMAP_DOT_H__
+
+struct inode;
+struct gfs2_inode;
+struct page;
+
+int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+int gfs2_block_map(struct inode *inode, u64 lblock, int create, struct buffer_head *bh);
+int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen);
+
+int gfs2_truncatei(struct gfs2_inode *ip, u64 size);
+int gfs2_truncatei_resume(struct gfs2_inode *ip);
+int gfs2_file_dealloc(struct gfs2_inode *ip);
+
+void gfs2_write_calc_reserv(struct gfs2_inode *ip, unsigned int len,
+			    unsigned int *data_blocks,
+			    unsigned int *ind_blocks);
+int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+			      unsigned int len, int *alloc_required);
+
+#endif /* __BMAP_DOT_H__ */

fs/gfs2/daemon.c

@@ -0,0 +1,199 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "daemon.h"
+#include "glock.h"
+#include "log.h"
+#include "quota.h"
+#include "recovery.h"
+#include "super.h"
+#include "util.h"
+
+/* This uses schedule_timeout() instead of msleep() because it's good for
+   the daemons to wake up more often than the timeout when unmounting so
+   the user's unmount doesn't sit there forever.
+
+   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;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_glockd - Reclaim unused glock structures
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * One or more of these daemons run, reclaiming glocks on sd_reclaim_list.
+ * Number of daemons can be set by user, with num_glockd mount option.
+ */
+
+int gfs2_glockd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+
+	while (!kthread_should_stop()) {
+		while (atomic_read(&sdp->sd_reclaim_count))
+			gfs2_reclaim_glock(sdp);
+
+		wait_event_interruptible(sdp->sd_reclaim_wq,
+					 (atomic_read(&sdp->sd_reclaim_count) ||
+					 kthread_should_stop()));
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_recoverd - Recover dead machine's journals
+ * @sdp: Pointer to GFS2 superblock
+ *
+ */
+
+int gfs2_recoverd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t;
+
+	while (!kthread_should_stop()) {
+		gfs2_check_journals(sdp);
+		t = gfs2_tune_get(sdp,  gt_recoverd_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * Also, periodically check to make sure that we're using the most recent
+ * journal index.
+ */
+
+int gfs2_logd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	struct gfs2_holder ji_gh;
+	unsigned long t;
+	int need_flush;
+
+	while (!kthread_should_stop()) {
+		/* Advance the log tail */
+
+		t = sdp->sd_log_flush_time +
+		    gfs2_tune_get(sdp, gt_log_flush_secs) * HZ;
+
+		gfs2_ail1_empty(sdp, DIO_ALL);
+		gfs2_log_lock(sdp);
+		need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks);
+		gfs2_log_unlock(sdp);
+		if (need_flush || time_after_eq(jiffies, t)) {
+			gfs2_log_flush(sdp, NULL);
+			sdp->sd_log_flush_time = jiffies;
+		}
+
+		/* Check for latest journal index */
+
+		t = sdp->sd_jindex_refresh_time +
+		    gfs2_tune_get(sdp, gt_jindex_refresh_secs) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			if (!gfs2_jindex_hold(sdp, &ji_gh))
+				gfs2_glock_dq_uninit(&ji_gh);
+			sdp->sd_jindex_refresh_time = jiffies;
+		}
+
+		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_quotad - Write cached quota changes into the quota file
+ * @sdp: Pointer to GFS2 superblock
+ *
+ */
+
+int gfs2_quotad(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t;
+	int error;
+
+	while (!kthread_should_stop()) {
+		/* Update the master statfs file */
+
+		t = sdp->sd_statfs_sync_time +
+		    gfs2_tune_get(sdp, gt_statfs_quantum) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			error = gfs2_statfs_sync(sdp);
+			if (error &&
+			    error != -EROFS &&
+			    !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+				fs_err(sdp, "quotad: (1) error=%d\n", error);
+			sdp->sd_statfs_sync_time = jiffies;
+		}
+
+		/* Update quota file */
+
+		t = sdp->sd_quota_sync_time +
+		    gfs2_tune_get(sdp, gt_quota_quantum) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			error = gfs2_quota_sync(sdp);
+			if (error &&
+			    error != -EROFS &&
+			    !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+				fs_err(sdp, "quotad: (2) error=%d\n", error);
+			sdp->sd_quota_sync_time = jiffies;
+		}
+
+		gfs2_quota_scan(sdp);
+
+		t = gfs2_tune_get(sdp, gt_quotad_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+

fs/gfs2/daemon.h

@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#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);
+int gfs2_quotad(void *data);
+
+#endif /* __DAEMON_DOT_H__ */

fs/gfs2/dir.h

@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+#include <linux/dcache.h>
+
+struct inode;
+struct gfs2_inode;
+struct gfs2_inum;
+
+int gfs2_dir_search(struct inode *dir, const struct qstr *filename,
+		    struct gfs2_inum_host *inum, unsigned int *type);
+int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+		 const struct gfs2_inum_host *inum, unsigned int type);
+int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
+int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
+		  filldir_t filldir);
+int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+		   struct gfs2_inum_host *new_inum, unsigned int new_type);
+
+int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+
+int gfs2_diradd_alloc_required(struct inode *dir,
+			       const struct qstr *filename);
+int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+			    struct buffer_head **bhp);
+
+static inline u32 gfs2_disk_hash(const char *data, int len)
+{
+        return crc32_le((u32)~0, data, len) ^ (u32)~0;
+}
+
+
+static inline void gfs2_str2qstr(struct qstr *name, const char *fname)
+{
+	name->name = fname;
+	name->len = strlen(fname);
+	name->hash = gfs2_disk_hash(name->name, name->len);
+}
+
+/* N.B. This probably ought to take inum & type as args as well */
+static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_addr = cpu_to_be64(0);
+	dent->de_inum.no_formal_ino = cpu_to_be64(0);
+	dent->de_hash = cpu_to_be32(name->hash);
+	dent->de_rec_len = cpu_to_be16(reclen);
+	dent->de_name_len = cpu_to_be16(name->len);
+	dent->de_type = cpu_to_be16(0);
+	memset(dent->__pad, 0, sizeof(dent->__pad));
+	memcpy(dent + 1, name->name, name->len);
+}
+
+#endif /* __DIR_DOT_H__ */

fs/gfs2/eaops.c

@@ -0,0 +1,229 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "eaops.h"
+#include "eattr.h"
+#include "util.h"
+
+/**
+ * gfs2_ea_name2type - get the type of the ea, and truncate type from the name
+ * @namep: ea name, possibly with type appended
+ *
+ * Returns: GFS2_EATYPE_XXX
+ */
+
+unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name)
+{
+	unsigned int type;
+
+	if (strncmp(name, "system.", 7) == 0) {
+		type = GFS2_EATYPE_SYS;
+		if (truncated_name)
+			*truncated_name = name + sizeof("system.") - 1;
+	} else if (strncmp(name, "user.", 5) == 0) {
+		type = GFS2_EATYPE_USR;
+		if (truncated_name)
+			*truncated_name = name + sizeof("user.") - 1;
+	} else if (strncmp(name, "security.", 9) == 0) {
+		type = GFS2_EATYPE_SECURITY;
+		if (truncated_name)
+			*truncated_name = name + sizeof("security.") - 1;
+	} else {
+		type = GFS2_EATYPE_UNUSED;
+		if (truncated_name)
+			*truncated_name = NULL;
+	}
+
+	return type;
+}
+
+static int user_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_READ, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int user_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+
+	if (S_ISREG(inode->i_mode) ||
+	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
+		int error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			return error;
+	} else
+		return -EPERM;
+
+	return gfs2_ea_set_i(ip, er);
+}
+
+static int user_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+
+	if (S_ISREG(inode->i_mode) ||
+	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
+		int error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			return error;
+	} else
+		return -EPERM;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	if (!GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) &&
+	    !GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl == 0 &&
+	    (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) ||
+	     GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)))
+		return -EOPNOTSUPP;
+
+
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int system_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	int remove = 0;
+	int error;
+
+	if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
+		if (!(er->er_flags & GFS2_ERF_MODE)) {
+			er->er_mode = ip->i_inode.i_mode;
+			er->er_flags |= GFS2_ERF_MODE;
+		}
+		error = gfs2_acl_validate_set(ip, 1, er,
+					      &remove, &er->er_mode);
+		if (error)
+			return error;
+		error = gfs2_ea_set_i(ip, er);
+		if (error)
+			return error;
+		if (remove)
+			gfs2_ea_remove_i(ip, er);
+		return 0;
+
+	} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
+		error = gfs2_acl_validate_set(ip, 0, er,
+					      &remove, NULL);
+		if (error)
+			return error;
+		if (!remove)
+			error = gfs2_ea_set_i(ip, er);
+		else {
+			error = gfs2_ea_remove_i(ip, er);
+			if (error == -ENODATA)
+				error = 0;
+		}
+		return error;
+	}
+
+	return -EPERM;
+}
+
+static int system_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
+		int error = gfs2_acl_validate_remove(ip, 1);
+		if (error)
+			return error;
+
+	} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
+		int error = gfs2_acl_validate_remove(ip, 0);
+		if (error)
+			return error;
+
+	} else
+		return -EPERM;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static int security_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_READ, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int security_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_WRITE, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_set_i(ip, er);
+}
+
+static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_WRITE, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static 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 = {
+	.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 = {
+	.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[] = {
+	NULL,
+	&gfs2_user_eaops,
+	&gfs2_system_eaops,
+	&gfs2_security_eaops,
+};
+

fs/gfs2/eaops.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __EAOPS_DOT_H__
+#define __EAOPS_DOT_H__
+
+struct gfs2_ea_request;
+struct gfs2_inode;
+
+struct gfs2_eattr_operations {
+	int (*eo_get) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	int (*eo_set) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	int (*eo_remove) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	char *eo_name;
+};
+
+unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
+
+extern struct gfs2_eattr_operations gfs2_system_eaops;
+
+extern struct gfs2_eattr_operations *gfs2_ea_ops[];
+
+#endif /* __EAOPS_DOT_H__ */
+

fs/gfs2/eattr.h

@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __EATTR_DOT_H__
+#define __EATTR_DOT_H__
+
+struct gfs2_inode;
+struct iattr;
+
+#define GFS2_EA_REC_LEN(ea) be32_to_cpu((ea)->ea_rec_len)
+#define GFS2_EA_DATA_LEN(ea) be32_to_cpu((ea)->ea_data_len)
+
+#define GFS2_EA_SIZE(ea) \
+ALIGN(sizeof(struct gfs2_ea_header) + (ea)->ea_name_len + \
+      ((GFS2_EA_IS_STUFFED(ea)) ? GFS2_EA_DATA_LEN(ea) : \
+                                  (sizeof(__be64) * (ea)->ea_num_ptrs)), 8)
+
+#define GFS2_EA_IS_STUFFED(ea) (!(ea)->ea_num_ptrs)
+#define GFS2_EA_IS_LAST(ea) ((ea)->ea_flags & GFS2_EAFLAG_LAST)
+
+#define GFS2_EAREQ_SIZE_STUFFED(er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + (er)->er_data_len, 8)
+
+#define GFS2_EAREQ_SIZE_UNSTUFFED(sdp, er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + \
+      sizeof(__be64) * DIV_ROUND_UP((er)->er_data_len, (sdp)->sd_jbsize), 8)
+
+#define GFS2_EA2NAME(ea) ((char *)((struct gfs2_ea_header *)(ea) + 1))
+#define GFS2_EA2DATA(ea) (GFS2_EA2NAME(ea) + (ea)->ea_name_len)
+
+#define GFS2_EA2DATAPTRS(ea) \
+((__be64 *)(GFS2_EA2NAME(ea) + ALIGN((ea)->ea_name_len, 8)))
+
+#define GFS2_EA2NEXT(ea) \
+((struct gfs2_ea_header *)((char *)(ea) + GFS2_EA_REC_LEN(ea)))
+
+#define GFS2_EA_BH2FIRST(bh) \
+((struct gfs2_ea_header *)((bh)->b_data + sizeof(struct gfs2_meta_header)))
+
+#define GFS2_ERF_MODE 0x80000000
+
+struct gfs2_ea_request {
+	const char *er_name;
+	char *er_data;
+	unsigned int er_name_len;
+	unsigned int er_data_len;
+	unsigned int er_type; /* GFS2_EATYPE_... */
+	int er_flags;
+	mode_t er_mode;
+};
+
+struct gfs2_ea_location {
+	struct buffer_head *el_bh;
+	struct gfs2_ea_header *el_ea;
+	struct gfs2_ea_header *el_prev;
+};
+
+int gfs2_ea_get_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+
+int gfs2_ea_list(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_get(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_set(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+
+int gfs2_ea_dealloc(struct gfs2_inode *ip);
+
+/* Exported to acl.c */
+
+int gfs2_ea_find(struct gfs2_inode *ip,
+		 struct gfs2_ea_request *er,
+		 struct gfs2_ea_location *el);
+int gfs2_ea_get_copy(struct gfs2_inode *ip,
+		     struct gfs2_ea_location *el,
+		     char *data);
+int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el,
+		      struct iattr *attr, char *data);
+
+static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
+{
+	switch (ea->ea_type) {
+	case GFS2_EATYPE_USR:
+		return 5 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SYS:
+		return 7 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SECURITY:
+		return 9 + ea->ea_name_len + 1;
+	default:
+		return 0;
+	}
+}
+
+#endif /* __EATTR_DOT_H__ */

fs/gfs2/gfs2.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GFS2_DOT_H__
+#define __GFS2_DOT_H__
+
+enum {
+	NO_CREATE = 0,
+	CREATE = 1,
+};
+
+enum {
+	NO_WAIT = 0,
+	WAIT = 1,
+};
+
+enum {
+	NO_FORCE = 0,
+	FORCE = 1,
+};
+
+#define GFS2_FAST_NAME_SIZE 8
+
+#endif /* __GFS2_DOT_H__ */
+

fs/gfs2/glock.h

@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOCK_DOT_H__
+#define __GLOCK_DOT_H__
+
+#include "incore.h"
+
+/* Flags for lock requests; used in gfs2_holder gh_flag field.
+   From lm_interface.h:
+#define LM_FLAG_TRY		0x00000001
+#define LM_FLAG_TRY_1CB		0x00000002
+#define LM_FLAG_NOEXP		0x00000004
+#define LM_FLAG_ANY		0x00000008
+#define LM_FLAG_PRIORITY	0x00000010 */
+
+#define GL_ASYNC		0x00000040
+#define GL_EXACT		0x00000080
+#define GL_SKIP			0x00000100
+#define GL_ATIME		0x00000200
+#define GL_NOCACHE		0x00000400
+#define GL_NOCANCEL		0x00001000
+
+#define GLR_TRYFAILED		13
+#define GLR_CANCELED		14
+
+static inline int gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+	int locked = 0;
+
+	/* Look in glock's list of holders for one with current task as owner */
+	spin_lock(&gl->gl_spin);
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (gh->gh_owner == current) {
+			locked = 1;
+			break;
+		}
+	}
+	spin_unlock(&gl->gl_spin);
+
+	return locked;
+}
+
+static inline int gfs2_glock_is_held_excl(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_EXCLUSIVE;
+}
+
+static inline int gfs2_glock_is_held_dfrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_DEFERRED;
+}
+
+static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_SHARED;
+}
+
+static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
+{
+	int ret;
+	spin_lock(&gl->gl_spin);
+	ret = !list_empty(&gl->gl_waiters2) || !list_empty(&gl->gl_waiters3);
+	spin_unlock(&gl->gl_spin);
+	return ret;
+}
+
+int gfs2_glock_get(struct gfs2_sbd *sdp,
+		   u64 number, const struct gfs2_glock_operations *glops,
+		   int create, struct gfs2_glock **glp);
+void gfs2_glock_hold(struct gfs2_glock *gl);
+int gfs2_glock_put(struct gfs2_glock *gl);
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+		      struct gfs2_holder *gh);
+void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			struct gfs2_holder *gh);
+void gfs2_holder_uninit(struct gfs2_holder *gh);
+int gfs2_glock_nq(struct gfs2_holder *gh);
+int gfs2_glock_poll(struct gfs2_holder *gh);
+int gfs2_glock_wait(struct gfs2_holder *gh);
+void gfs2_glock_dq(struct gfs2_holder *gh);
+
+void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
+int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
+		      u64 number, const struct gfs2_glock_operations *glops,
+		      unsigned int state, int flags, struct gfs2_holder *gh);
+
+int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+
+/**
+ * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
+ * @gl: the glock
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Returns: 0, GLR_*, or errno
+ */
+
+static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
+				     unsigned int state, int flags,
+				     struct gfs2_holder *gh)
+{
+	int error;
+
+	gfs2_holder_init(gl, state, flags, gh);
+
+	error = gfs2_glock_nq(gh);
+	if (error)
+		gfs2_holder_uninit(gh);
+
+	return error;
+}
+
+/*  Lock Value Block functions  */
+
+int gfs2_lvb_hold(struct gfs2_glock *gl);
+void gfs2_lvb_unhold(struct gfs2_glock *gl);
+
+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);
+
+#endif /* __GLOCK_DOT_H__ */

fs/gfs2/glops.c

@@ -0,0 +1,497 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "util.h"
+#include "trans.h"
+
+/**
+ * ail_empty_gl - remove all buffers for a given lock from the AIL
+ * @gl: the glock
+ *
+ * None of the buffers should be dirty, locked, or pinned.
+ */
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int blocks;
+	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);
+	if (!blocks)
+		return;
+
+	error = gfs2_trans_begin(sdp, 0, blocks);
+	if (gfs2_assert_withdraw(sdp, !error))
+		return;
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata,
+				bd_ail_gl_list);
+		bh = bd->bd_bh;
+		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_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	gfs2_log_unlock(sdp);
+
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL);
+}
+
+/**
+ * gfs2_pte_inval - Sync and invalidate all PTEs associated with a glock
+ * @gl: the glock
+ *
+ */
+
+static void gfs2_pte_inval(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip;
+	struct inode *inode;
+
+	ip = gl->gl_object;
+	inode = &ip->i_inode;
+	if (!ip || !S_ISREG(inode->i_mode))
+		return;
+
+	if (!test_bit(GIF_PAGED, &ip->i_flags))
+		return;
+
+	unmap_shared_mapping_range(inode->i_mapping, 0, 0);
+
+	if (test_bit(GIF_SW_PAGED, &ip->i_flags))
+		set_bit(GLF_DIRTY, &gl->gl_flags);
+
+	clear_bit(GIF_SW_PAGED, &ip->i_flags);
+}
+
+/**
+ * meta_go_sync - sync out the metadata for this glock
+ * @gl: the glock
+ *
+ * Called when demoting or unlocking an EX glock.  We must flush
+ * to disk all dirty buffers/pages relating to this glock, and must not
+ * not return to caller to demote/unlock the glock until I/O is complete.
+ */
+
+static void meta_go_sync(struct gfs2_glock *gl)
+{
+	if (gl->gl_state != LM_ST_EXCLUSIVE)
+		return;
+
+	if (test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) {
+		gfs2_log_flush(gl->gl_sbd, gl);
+		gfs2_meta_sync(gl);
+		gfs2_ail_empty_gl(gl);
+	}
+}
+
+/**
+ * meta_go_inval - invalidate the metadata for this glock
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void meta_go_inval(struct gfs2_glock *gl, int flags)
+{
+	if (!(flags & DIO_METADATA))
+		return;
+
+	gfs2_meta_inval(gl);
+	gl->gl_vn++;
+}
+
+/**
+ * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * @gl: the glock protecting the inode
+ *
+ */
+
+static void inode_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+
+	if (ip && !S_ISREG(ip->i_inode.i_mode))
+		ip = NULL;
+
+	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
+		gfs2_log_flush(gl->gl_sbd, gl);
+		if (ip)
+			filemap_fdatawrite(ip->i_inode.i_mapping);
+		gfs2_meta_sync(gl);
+		if (ip) {
+			struct address_space *mapping = ip->i_inode.i_mapping;
+			int error = filemap_fdatawait(mapping);
+			if (error == -ENOSPC)
+				set_bit(AS_ENOSPC, &mapping->flags);
+			else if (error)
+				set_bit(AS_EIO, &mapping->flags);
+		}
+		clear_bit(GLF_DIRTY, &gl->gl_flags);
+		gfs2_ail_empty_gl(gl);
+	}
+}
+
+/**
+ * inode_go_xmote_th - promote/demote a glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void inode_go_xmote_th(struct gfs2_glock *gl)
+{
+	if (gl->gl_state != LM_ST_UNLOCKED)
+		gfs2_pte_inval(gl);
+	if (gl->gl_state == LM_ST_EXCLUSIVE)
+		inode_go_sync(gl);
+}
+
+/**
+ * inode_go_xmote_bh - After promoting/demoting a glock
+ * @gl: the glock
+ *
+ */
+
+static void inode_go_xmote_bh(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh = gl->gl_req_gh;
+	struct buffer_head *bh;
+	int error;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    (!gh || !(gh->gh_flags & GL_SKIP))) {
+		error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
+		if (!error)
+			brelse(bh);
+	}
+}
+
+/**
+ * inode_go_drop_th - unlock a glock
+ * @gl: the glock
+ *
+ * Invoked from rq_demote().
+ * Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long)
+ * is being purged from our node's glock cache; we're dropping lock.
+ */
+
+static void inode_go_drop_th(struct gfs2_glock *gl)
+{
+	gfs2_pte_inval(gl);
+	if (gl->gl_state == LM_ST_EXCLUSIVE)
+		inode_go_sync(gl);
+}
+
+/**
+ * inode_go_inval - prepare a inode glock to be released
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void inode_go_inval(struct gfs2_glock *gl, int flags)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	int meta = (flags & DIO_METADATA);
+
+	if (meta) {
+		gfs2_meta_inval(gl);
+		if (ip)
+			set_bit(GIF_INVALID, &ip->i_flags);
+	}
+
+	if (ip && S_ISREG(ip->i_inode.i_mode)) {
+		truncate_inode_pages(ip->i_inode.i_mapping, 0);
+		clear_bit(GIF_PAGED, &ip->i_flags);
+	}
+}
+
+/**
+ * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int inode_go_demote_ok(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	int demote = 0;
+
+	if (!gl->gl_object && !gl->gl_aspace->i_mapping->nrpages)
+		demote = 1;
+	else if (!sdp->sd_args.ar_localcaching &&
+		 time_after_eq(jiffies, gl->gl_stamp +
+			       gfs2_tune_get(sdp, gt_demote_secs) * HZ))
+		demote = 1;
+
+	return demote;
+}
+
+/**
+ * inode_go_lock - operation done after an inode lock is locked by a process
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int inode_go_lock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_inode *ip = gl->gl_object;
+	int error = 0;
+
+	if (!ip)
+		return 0;
+
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			return error;
+	}
+
+	if ((ip->i_di.di_flags & GFS2_DIF_TRUNC_IN_PROG) &&
+	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
+	    (gh->gh_state == LM_ST_EXCLUSIVE))
+		error = gfs2_truncatei_resume(ip);
+
+	return error;
+}
+
+/**
+ * inode_go_unlock - operation done before an inode lock is unlocked by a
+ *		     process
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void inode_go_unlock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_inode *ip = gl->gl_object;
+
+	if (ip)
+		gfs2_meta_cache_flush(ip);
+}
+
+/**
+ * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int rgrp_go_demote_ok(struct gfs2_glock *gl)
+{
+	return !gl->gl_aspace->i_mapping->nrpages;
+}
+
+/**
+ * rgrp_go_lock - operation done after an rgrp lock is locked by
+ *    a first holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int rgrp_go_lock(struct gfs2_holder *gh)
+{
+	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
+}
+
+/**
+ * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
+ *    a last holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void rgrp_go_unlock(struct gfs2_holder *gh)
+{
+	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
+}
+
+/**
+ * trans_go_xmote_th - promote/demote the transaction glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void trans_go_xmote_th(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_syncfs(sdp);
+		gfs2_log_shutdown(sdp);
+	}
+}
+
+/**
+ * trans_go_xmote_bh - After promoting/demoting the transaction glock
+ * @gl: the glock
+ *
+ */
+
+static void trans_go_xmote_bh(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_log_header_host head;
+	int error;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode));
+		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+
+		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+		if (error)
+			gfs2_consist(sdp);
+		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
+			gfs2_consist(sdp);
+
+		/*  Initialize some head of the log stuff  */
+		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+			sdp->sd_log_sequence = head.lh_sequence + 1;
+			gfs2_log_pointers_init(sdp, head.lh_blkno);
+		}
+	}
+}
+
+/**
+ * trans_go_drop_th - unlock the transaction glock
+ * @gl: the glock
+ *
+ * We want to sync the device even with localcaching.  Remember
+ * that localcaching journal replay only marks buffers dirty.
+ */
+
+static void trans_go_drop_th(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_syncfs(sdp);
+		gfs2_log_shutdown(sdp);
+	}
+}
+
+/**
+ * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int quota_go_demote_ok(struct gfs2_glock *gl)
+{
+	return !atomic_read(&gl->gl_lvb_count);
+}
+
+const struct gfs2_glock_operations gfs2_meta_glops = {
+	.go_xmote_th = meta_go_sync,
+	.go_drop_th = meta_go_sync,
+	.go_type = LM_TYPE_META,
+};
+
+const struct gfs2_glock_operations gfs2_inode_glops = {
+	.go_xmote_th = inode_go_xmote_th,
+	.go_xmote_bh = inode_go_xmote_bh,
+	.go_drop_th = inode_go_drop_th,
+	.go_inval = inode_go_inval,
+	.go_demote_ok = inode_go_demote_ok,
+	.go_lock = inode_go_lock,
+	.go_unlock = inode_go_unlock,
+	.go_type = LM_TYPE_INODE,
+};
+
+const struct gfs2_glock_operations gfs2_rgrp_glops = {
+	.go_xmote_th = meta_go_sync,
+	.go_drop_th = meta_go_sync,
+	.go_inval = meta_go_inval,
+	.go_demote_ok = rgrp_go_demote_ok,
+	.go_lock = rgrp_go_lock,
+	.go_unlock = rgrp_go_unlock,
+	.go_type = LM_TYPE_RGRP,
+};
+
+const struct gfs2_glock_operations gfs2_trans_glops = {
+	.go_xmote_th = trans_go_xmote_th,
+	.go_xmote_bh = trans_go_xmote_bh,
+	.go_drop_th = trans_go_drop_th,
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_iopen_glops = {
+	.go_type = LM_TYPE_IOPEN,
+};
+
+const struct gfs2_glock_operations gfs2_flock_glops = {
+	.go_type = LM_TYPE_FLOCK,
+};
+
+const struct gfs2_glock_operations gfs2_nondisk_glops = {
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_quota_glops = {
+	.go_demote_ok = quota_go_demote_ok,
+	.go_type = LM_TYPE_QUOTA,
+};
+
+const struct gfs2_glock_operations gfs2_journal_glops = {
+	.go_type = LM_TYPE_JOURNAL,
+};
+

fs/gfs2/glops.h

@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOPS_DOT_H__
+#define __GLOPS_DOT_H__
+
+#include "incore.h"
+
+extern const struct gfs2_glock_operations gfs2_meta_glops;
+extern const struct gfs2_glock_operations gfs2_inode_glops;
+extern const struct gfs2_glock_operations gfs2_rgrp_glops;
+extern const struct gfs2_glock_operations gfs2_trans_glops;
+extern const struct gfs2_glock_operations gfs2_iopen_glops;
+extern const struct gfs2_glock_operations gfs2_flock_glops;
+extern const struct gfs2_glock_operations gfs2_nondisk_glops;
+extern const struct gfs2_glock_operations gfs2_quota_glops;
+extern const struct gfs2_glock_operations gfs2_journal_glops;
+
+#endif /* __GLOPS_DOT_H__ */

fs/gfs2/incore.h

@@ -0,0 +1,617 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INCORE_DOT_H__
+#define __INCORE_DOT_H__
+
+#include <linux/fs.h>
+
+#define DIO_WAIT	0x00000010
+#define DIO_METADATA	0x00000020
+#define DIO_ALL		0x00000100
+
+struct gfs2_log_operations;
+struct gfs2_log_element;
+struct gfs2_holder;
+struct gfs2_glock;
+struct gfs2_quota_data;
+struct gfs2_trans;
+struct gfs2_ail;
+struct gfs2_jdesc;
+struct gfs2_sbd;
+
+typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret);
+
+/*
+ * Structure of operations that are associated with each
+ * type of element in the log.
+ */
+
+struct gfs2_log_operations {
+	void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le);
+	void (*lo_incore_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
+	void (*lo_before_commit) (struct gfs2_sbd *sdp);
+	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
+	void (*lo_before_scan) (struct gfs2_jdesc *jd,
+				struct gfs2_log_header_host *head, int pass);
+	int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start,
+				 struct gfs2_log_descriptor *ld, __be64 *ptr,
+				 int pass);
+	void (*lo_after_scan) (struct gfs2_jdesc *jd, int error, int pass);
+	const char *lo_name;
+};
+
+struct gfs2_log_element {
+	struct list_head le_list;
+	const struct gfs2_log_operations *le_ops;
+};
+
+struct gfs2_bitmap {
+	struct buffer_head *bi_bh;
+	char *bi_clone;
+	u32 bi_offset;
+	u32 bi_start;
+	u32 bi_len;
+};
+
+struct gfs2_rgrpd {
+	struct list_head rd_list;	/* Link with superblock */
+	struct list_head rd_list_mru;
+	struct list_head rd_recent;	/* Recently used rgrps */
+	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
+	struct gfs2_rindex_host rd_ri;
+	struct gfs2_rgrp_host rd_rg;
+	u64 rd_rg_vn;
+	struct gfs2_bitmap *rd_bits;
+	unsigned int rd_bh_count;
+	struct mutex rd_mutex;
+	u32 rd_free_clone;
+	struct gfs2_log_element rd_le;
+	u32 rd_last_alloc_data;
+	u32 rd_last_alloc_meta;
+	struct gfs2_sbd *rd_sbd;
+};
+
+enum gfs2_state_bits {
+	BH_Pinned = BH_PrivateStart,
+	BH_Escaped = BH_PrivateStart + 1,
+};
+
+BUFFER_FNS(Pinned, pinned)
+TAS_BUFFER_FNS(Pinned, pinned)
+BUFFER_FNS(Escaped, escaped)
+TAS_BUFFER_FNS(Escaped, escaped)
+
+struct gfs2_bufdata {
+	struct buffer_head *bd_bh;
+	struct gfs2_glock *bd_gl;
+
+	struct list_head bd_list_tr;
+	struct gfs2_log_element bd_le;
+
+	struct gfs2_ail *bd_ail;
+	struct list_head bd_ail_st_list;
+	struct list_head bd_ail_gl_list;
+};
+
+struct gfs2_glock_operations {
+	void (*go_xmote_th) (struct gfs2_glock *gl);
+	void (*go_xmote_bh) (struct gfs2_glock *gl);
+	void (*go_drop_th) (struct gfs2_glock *gl);
+	void (*go_inval) (struct gfs2_glock *gl, int flags);
+	int (*go_demote_ok) (struct gfs2_glock *gl);
+	int (*go_lock) (struct gfs2_holder *gh);
+	void (*go_unlock) (struct gfs2_holder *gh);
+	const int go_type;
+};
+
+enum {
+	/* Actions */
+	HIF_MUTEX		= 0,
+	HIF_PROMOTE		= 1,
+	HIF_DEMOTE		= 2,
+
+	/* States */
+	HIF_ALLOCED		= 4,
+	HIF_DEALLOC		= 5,
+	HIF_HOLDER		= 6,
+	HIF_FIRST		= 7,
+	HIF_ABORTED		= 9,
+	HIF_WAIT		= 10,
+};
+
+struct gfs2_holder {
+	struct list_head gh_list;
+
+	struct gfs2_glock *gh_gl;
+	struct task_struct *gh_owner;
+	unsigned int gh_state;
+	unsigned gh_flags;
+
+	int gh_error;
+	unsigned long gh_iflags;
+	unsigned long gh_ip;
+};
+
+enum {
+	GLF_LOCK		= 1,
+	GLF_STICKY		= 2,
+	GLF_DIRTY		= 5,
+	GLF_SKIP_WAITERS2	= 6,
+};
+
+struct gfs2_glock {
+	struct hlist_node gl_list;
+	unsigned long gl_flags;		/* GLF_... */
+	struct lm_lockname gl_name;
+	atomic_t gl_ref;
+
+	spinlock_t gl_spin;
+
+	unsigned int gl_state;
+	unsigned int gl_hash;
+	struct task_struct *gl_owner;
+	unsigned long gl_ip;
+	struct list_head gl_holders;
+	struct list_head gl_waiters1;	/* HIF_MUTEX */
+	struct list_head gl_waiters2;	/* HIF_DEMOTE */
+	struct list_head gl_waiters3;	/* HIF_PROMOTE */
+
+	const struct gfs2_glock_operations *gl_ops;
+
+	struct gfs2_holder *gl_req_gh;
+	gfs2_glop_bh_t gl_req_bh;
+
+	void *gl_lock;
+	char *gl_lvb;
+	atomic_t gl_lvb_count;
+
+	u64 gl_vn;
+	unsigned long gl_stamp;
+	void *gl_object;
+
+	struct list_head gl_reclaim;
+
+	struct gfs2_sbd *gl_sbd;
+
+	struct inode *gl_aspace;
+	struct gfs2_log_element gl_le;
+	struct list_head gl_ail_list;
+	atomic_t gl_ail_count;
+};
+
+struct gfs2_alloc {
+	/* Quota stuff */
+
+	struct gfs2_quota_data *al_qd[2*MAXQUOTAS];
+	struct gfs2_holder al_qd_ghs[2*MAXQUOTAS];
+	unsigned int al_qd_num;
+
+	u32 al_requested; /* Filled in by caller of gfs2_inplace_reserve() */
+	u32 al_alloced; /* Filled in by gfs2_alloc_*() */
+
+	/* Filled in by gfs2_inplace_reserve() */
+
+	unsigned int al_line;
+	char *al_file;
+	struct gfs2_holder al_ri_gh;
+	struct gfs2_holder al_rgd_gh;
+	struct gfs2_rgrpd *al_rgd;
+
+};
+
+enum {
+	GIF_INVALID		= 0,
+	GIF_QD_LOCKED		= 1,
+	GIF_PAGED		= 2,
+	GIF_SW_PAGED		= 3,
+};
+
+struct gfs2_inode {
+	struct inode i_inode;
+	struct gfs2_inum_host i_num;
+
+	unsigned long i_flags;		/* GIF_... */
+
+	struct gfs2_dinode_host i_di; /* To be replaced by ref to block */
+
+	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_holder i_iopen_gh;
+	struct gfs2_holder i_gh; /* for prepare/commit_write only */
+	struct gfs2_alloc i_alloc;
+	u64 i_last_rg_alloc;
+
+	spinlock_t i_spin;
+	struct rw_semaphore i_rw_mutex;
+	unsigned long i_last_pfault;
+
+	struct buffer_head *i_cache[GFS2_MAX_META_HEIGHT];
+};
+
+/*
+ * Since i_inode is the first element of struct gfs2_inode,
+ * this is effectively a cast.
+ */
+static inline struct gfs2_inode *GFS2_I(struct inode *inode)
+{
+	return container_of(inode, struct gfs2_inode, i_inode);
+}
+
+/* To be removed? */
+static inline struct gfs2_sbd *GFS2_SB(struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+enum {
+	GFF_DID_DIRECT_ALLOC	= 0,
+	GFF_EXLOCK = 1,
+};
+
+struct gfs2_file {
+	unsigned long f_flags;		/* GFF_... */
+	struct mutex f_fl_mutex;
+	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;
+	unsigned int rr_where;
+};
+
+enum {
+	QDF_USER		= 0,
+	QDF_CHANGE		= 1,
+	QDF_LOCKED		= 2,
+};
+
+struct gfs2_quota_lvb {
+        __be32 qb_magic;
+        u32 __pad;
+        __be64 qb_limit;      /* Hard limit of # blocks to alloc */
+        __be64 qb_warn;       /* Warn user when alloc is above this # */
+        __be64 qb_value;       /* Current # blocks allocated */
+};
+
+struct gfs2_quota_data {
+	struct list_head qd_list;
+	unsigned int qd_count;
+
+	u32 qd_id;
+	unsigned long qd_flags;		/* QDF_... */
+
+	s64 qd_change;
+	s64 qd_change_sync;
+
+	unsigned int qd_slot;
+	unsigned int qd_slot_count;
+
+	struct buffer_head *qd_bh;
+	struct gfs2_quota_change *qd_bh_qc;
+	unsigned int qd_bh_count;
+
+	struct gfs2_glock *qd_gl;
+	struct gfs2_quota_lvb qd_qb;
+
+	u64 qd_sync_gen;
+	unsigned long qd_last_warn;
+	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;
+
+	unsigned int tr_blocks;
+	unsigned int tr_revokes;
+	unsigned int tr_reserved;
+
+	struct gfs2_holder tr_t_gh;
+
+	int tr_touched;
+
+	unsigned int tr_num_buf;
+	unsigned int tr_num_buf_new;
+	unsigned int tr_num_buf_rm;
+	struct list_head tr_list_buf;
+
+	unsigned int tr_num_revoke;
+	unsigned int tr_num_revoke_rm;
+};
+
+struct gfs2_ail {
+	struct list_head ai_list;
+
+	unsigned int ai_first;
+	struct list_head ai_ail1_list;
+	struct list_head ai_ail2_list;
+
+	u64 ai_sync_gen;
+};
+
+struct gfs2_jdesc {
+	struct list_head jd_list;
+
+	struct inode *jd_inode;
+	unsigned int jd_jid;
+	int jd_dirty;
+
+	unsigned int jd_blocks;
+};
+
+#define GFS2_GLOCKD_DEFAULT	1
+#define GFS2_GLOCKD_MAX		16
+
+#define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
+#define GFS2_QUOTA_OFF		0
+#define GFS2_QUOTA_ACCOUNT	1
+#define GFS2_QUOTA_ON		2
+
+#define GFS2_DATA_DEFAULT	GFS2_DATA_ORDERED
+#define GFS2_DATA_WRITEBACK	1
+#define GFS2_DATA_ORDERED	2
+
+struct gfs2_args {
+	char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
+	char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
+	char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */
+	int ar_spectator; /* Don't get a journal because we're always RO */
+	int ar_ignore_local_fs; /* Don't optimize even if local_fs is 1 */
+	int ar_localflocks; /* Let the VFS do flock|fcntl locks for us */
+	int ar_localcaching; /* Local-style caching (dangerous on multihost) */
+	int ar_debug; /* Oops on errors instead of trying to be graceful */
+	int ar_upgrade; /* Upgrade ondisk/multihost format */
+	unsigned int ar_num_glockd; /* Number of glockd threads */
+	int ar_posix_acl; /* Enable posix acls */
+	int ar_quota; /* off/account/on */
+	int ar_suiddir; /* suiddir support */
+	int ar_data; /* ordered/writeback */
+};
+
+struct gfs2_tune {
+	spinlock_t gt_spin;
+
+	unsigned int gt_ilimit;
+	unsigned int gt_ilimit_tries;
+	unsigned int gt_ilimit_min;
+	unsigned int gt_demote_secs; /* Cache retention for unheld glock */
+	unsigned int gt_incore_log_blocks;
+	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;
+
+	unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
+	unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */
+	unsigned int gt_quota_scale_num; /* Numerator */
+	unsigned int gt_quota_scale_den; /* Denominator */
+	unsigned int gt_quota_cache_secs;
+	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
+	unsigned int gt_atime_quantum; /* Min secs between atime updates */
+	unsigned int gt_new_files_jdata;
+	unsigned int gt_new_files_directio;
+	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
+	unsigned int gt_lockdump_size;
+	unsigned int gt_stall_secs; /* Detects trouble! */
+	unsigned int gt_complain_secs;
+	unsigned int gt_reclaim_limit; /* Max num of glocks in reclaim list */
+	unsigned int gt_statfs_quantum;
+	unsigned int gt_statfs_slow;
+};
+
+enum {
+	SDF_JOURNAL_CHECKED	= 0,
+	SDF_JOURNAL_LIVE	= 1,
+	SDF_SHUTDOWN		= 2,
+	SDF_NOATIME		= 3,
+};
+
+#define GFS2_FSNAME_LEN		256
+
+struct gfs2_sbd {
+	struct super_block *sd_vfs;
+	struct super_block *sd_vfs_meta;
+	struct kobject sd_kobj;
+	unsigned long sd_flags;	/* SDF_... */
+	struct gfs2_sb_host sd_sb;
+
+	/* Constants computed on mount */
+
+	u32 sd_fsb2bb;
+	u32 sd_fsb2bb_shift;
+	u32 sd_diptrs;	/* Number of pointers in a dinode */
+	u32 sd_inptrs;	/* Number of pointers in a indirect block */
+	u32 sd_jbsize;	/* Size of a journaled data block */
+	u32 sd_hash_bsize;	/* sizeof(exhash block) */
+	u32 sd_hash_bsize_shift;
+	u32 sd_hash_ptrs;	/* Number of pointers in a hash block */
+	u32 sd_qc_per_block;
+	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
+	u32 sd_max_height;	/* Max height of a file's metadata tree */
+	u64 sd_heightsize[GFS2_MAX_META_HEIGHT];
+	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
+	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT];
+
+	struct gfs2_args sd_args;	/* Mount arguments */
+	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
+
+	/* Lock Stuff */
+
+	struct lm_lockstruct sd_lockstruct;
+	struct list_head sd_reclaim_list;
+	spinlock_t sd_reclaim_lock;
+	wait_queue_head_t sd_reclaim_wq;
+	atomic_t sd_reclaim_count;
+	struct gfs2_holder sd_live_gh;
+	struct gfs2_glock *sd_rename_gl;
+	struct gfs2_glock *sd_trans_gl;
+
+	/* Inode Stuff */
+
+	struct inode *sd_master_dir;
+	struct inode *sd_jindex;
+	struct inode *sd_inum_inode;
+	struct inode *sd_statfs_inode;
+	struct inode *sd_ir_inode;
+	struct inode *sd_sc_inode;
+	struct inode *sd_qc_inode;
+	struct inode *sd_rindex;
+	struct inode *sd_quota_inode;
+
+	/* Inum stuff */
+
+	struct mutex sd_inum_mutex;
+
+	/* StatFS stuff */
+
+	spinlock_t sd_statfs_spin;
+	struct mutex sd_statfs_mutex;
+	struct gfs2_statfs_change_host sd_statfs_master;
+	struct gfs2_statfs_change_host sd_statfs_local;
+	unsigned long sd_statfs_sync_time;
+
+	/* Resource group stuff */
+
+	u64 sd_rindex_vn;
+	spinlock_t sd_rindex_spin;
+	struct mutex sd_rindex_mutex;
+	struct list_head sd_rindex_list;
+	struct list_head sd_rindex_mru_list;
+	struct list_head sd_rindex_recent_list;
+	struct gfs2_rgrpd *sd_rindex_forward;
+	unsigned int sd_rgrps;
+
+	/* Journal index stuff */
+
+	struct list_head sd_jindex_list;
+	spinlock_t sd_jindex_spin;
+	struct mutex sd_jindex_mutex;
+	unsigned int sd_journals;
+	unsigned long sd_jindex_refresh_time;
+
+	struct gfs2_jdesc *sd_jdesc;
+	struct gfs2_holder sd_journal_gh;
+	struct gfs2_holder sd_jinode_gh;
+
+	struct gfs2_holder sd_ir_gh;
+	struct gfs2_holder sd_sc_gh;
+	struct gfs2_holder sd_qc_gh;
+
+	/* 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;
+	struct task_struct *sd_glockd_process[GFS2_GLOCKD_MAX];
+	unsigned int sd_glockd_num;
+
+	/* Quota stuff */
+
+	struct list_head sd_quota_list;
+	atomic_t sd_quota_count;
+	spinlock_t sd_quota_spin;
+	struct mutex sd_quota_mutex;
+
+	unsigned int sd_quota_slots;
+	unsigned int sd_quota_chunks;
+	unsigned char **sd_quota_bitmap;
+
+	u64 sd_quota_sync_gen;
+	unsigned long sd_quota_sync_time;
+
+	/* Log stuff */
+
+	spinlock_t sd_log_lock;
+
+	unsigned int sd_log_blks_reserved;
+	unsigned int sd_log_commited_buf;
+	unsigned int sd_log_commited_revoke;
+
+	unsigned int sd_log_num_gl;
+	unsigned int sd_log_num_buf;
+	unsigned int sd_log_num_revoke;
+	unsigned int sd_log_num_rg;
+	unsigned int sd_log_num_databuf;
+	unsigned int sd_log_num_jdata;
+	unsigned int sd_log_num_hdrs;
+
+	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;
+
+	unsigned int sd_log_blks_free;
+	struct mutex sd_log_reserve_mutex;
+
+	u64 sd_log_sequence;
+	unsigned int sd_log_head;
+	unsigned int sd_log_tail;
+	int sd_log_idle;
+
+	unsigned long sd_log_flush_time;
+	struct rw_semaphore sd_log_flush_lock;
+	struct list_head sd_log_flush_list;
+
+	unsigned int sd_log_flush_head;
+	u64 sd_log_flush_wrapped;
+
+	struct list_head sd_ail1_list;
+	struct list_head sd_ail2_list;
+	u64 sd_ail_sync_gen;
+
+	/* Replay stuff */
+
+	struct list_head sd_revoke_list;
+	unsigned int sd_replay_tail;
+
+	unsigned int sd_found_blocks;
+	unsigned int sd_found_revokes;
+	unsigned int sd_replayed_blocks;
+
+	/* For quiescing the filesystem */
+
+	struct gfs2_holder sd_freeze_gh;
+	struct mutex sd_freeze_lock;
+	unsigned int sd_freeze_count;
+
+	/* Counters */
+
+	atomic_t sd_glock_count;
+	atomic_t sd_glock_held_count;
+	atomic_t sd_inode_count;
+	atomic_t sd_reclaimed;
+
+	char sd_fsname[GFS2_FSNAME_LEN];
+	char sd_table_name[GFS2_FSNAME_LEN];
+	char sd_proto_name[GFS2_FSNAME_LEN];
+
+	/* Debugging crud */
+
+	unsigned long sd_last_warning;
+	struct vfsmount *sd_gfs2mnt;
+};
+
+#endif /* __INCORE_DOT_H__ */
+

fs/gfs2/inode.h

@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INODE_DOT_H__
+#define __INODE_DOT_H__
+
+static inline int gfs2_is_stuffed(struct gfs2_inode *ip)
+{
+	return !ip->i_di.di_height;
+}
+
+static inline int gfs2_is_jdata(struct gfs2_inode *ip)
+{
+	return ip->i_di.di_flags & GFS2_DIF_JDATA;
+}
+
+static inline int gfs2_is_dir(struct gfs2_inode *ip)
+{
+	return S_ISDIR(ip->i_inode.i_mode);
+}
+
+static inline void gfs2_set_inode_blocks(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	inode->i_blocks = ip->i_di.di_blocks <<
+		(GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT);
+}
+
+void gfs2_inode_attr_in(struct gfs2_inode *ip);
+struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum_host *inum, unsigned type);
+struct inode *gfs2_ilookup(struct super_block *sb, struct gfs2_inum_host *inum);
+
+int gfs2_inode_refresh(struct gfs2_inode *ip);
+
+int gfs2_dinode_dealloc(struct gfs2_inode *inode);
+int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
+struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+			   int is_root, struct nameidata *nd);
+struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
+			   unsigned int mode, dev_t dev);
+int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
+		struct gfs2_inode *ip);
+int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+		   struct gfs2_inode *ip);
+int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
+int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
+int gfs2_glock_nq_atime(struct gfs2_holder *gh);
+int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+
+#endif /* __INODE_DOT_H__ */
+

fs/gfs2/lm.c

@@ -0,0 +1,210 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "lm.h"
+#include "super.h"
+#include "util.h"
+
+/**
+ * gfs2_lm_mount - mount a locking protocol
+ * @sdp: the filesystem
+ * @args: mount arguements
+ * @silent: if 1, don't complain if the FS isn't a GFS2 fs
+ *
+ * Returns: errno
+ */
+
+int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
+{
+	char *proto = sdp->sd_proto_name;
+	char *table = sdp->sd_table_name;
+	int flags = 0;
+	int error;
+
+	if (sdp->sd_args.ar_spectator)
+		flags |= LM_MFLAG_SPECTATOR;
+
+	fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table);
+
+	error = gfs2_mount_lockproto(proto, table, sdp->sd_args.ar_hostdata,
+				     gfs2_glock_cb, sdp,
+				     GFS2_MIN_LVB_SIZE, flags,
+				     &sdp->sd_lockstruct, &sdp->sd_kobj);
+	if (error) {
+		fs_info(sdp, "can't mount proto=%s, table=%s, hostdata=%s\n",
+			proto, table, sdp->sd_args.ar_hostdata);
+		goto out;
+	}
+
+	if (gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lockspace) ||
+	    gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_ops) ||
+	    gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lvb_size >=
+				  GFS2_MIN_LVB_SIZE)) {
+		gfs2_unmount_lockproto(&sdp->sd_lockstruct);
+		goto out;
+	}
+
+	if (sdp->sd_args.ar_spectator)
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", table);
+	else
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table,
+			 sdp->sd_lockstruct.ls_jid);
+
+	fs_info(sdp, "Joined cluster. Now mounting FS...\n");
+
+	if ((sdp->sd_lockstruct.ls_flags & LM_LSFLAG_LOCAL) &&
+	    !sdp->sd_args.ar_ignore_local_fs) {
+		sdp->sd_args.ar_localflocks = 1;
+		sdp->sd_args.ar_localcaching = 1;
+	}
+
+out:
+	return error;
+}
+
+void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_others_may_mount(
+					sdp->sd_lockstruct.ls_lockspace);
+}
+
+void gfs2_lm_unmount(struct gfs2_sbd *sdp)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		gfs2_unmount_lockproto(&sdp->sd_lockstruct);
+}
+
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+{
+	va_list args;
+
+	if (test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return 0;
+
+	va_start(args, fmt);
+	vprintk(fmt, args);
+	va_end(args);
+
+	fs_err(sdp, "about to withdraw this file system\n");
+	BUG_ON(sdp->sd_args.ar_debug);
+
+	fs_err(sdp, "telling LM to withdraw\n");
+	gfs2_withdraw_lockproto(&sdp->sd_lockstruct);
+	fs_err(sdp, "withdrawn\n");
+	dump_stack();
+
+	return -1;
+}
+
+int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		     void **lockp)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_get_lock(
+				sdp->sd_lockstruct.ls_lockspace, name, lockp);
+	return error;
+}
+
+void gfs2_lm_put_lock(struct gfs2_sbd *sdp, void *lock)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_put_lock(lock);
+}
+
+unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+			  unsigned int cur_state, unsigned int req_state,
+			  unsigned int flags)
+{
+	int ret = 0;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
+							 req_state, flags);
+	return ret;
+}
+
+unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
+			    unsigned int cur_state)
+{
+	int ret = 0;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret =  sdp->sd_lockstruct.ls_ops->lm_unlock(lock, cur_state);
+	return ret;
+}
+
+void gfs2_lm_cancel(struct gfs2_sbd *sdp, void *lock)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_cancel(lock);
+}
+
+int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_hold_lvb(lock, lvbp);
+	return error;
+}
+
+void gfs2_lm_unhold_lvb(struct gfs2_sbd *sdp, void *lock, char *lvb)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_unhold_lvb(lock, lvb);
+}
+
+int gfs2_lm_plock_get(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		      struct file *file, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_plock_get(
+				sdp->sd_lockstruct.ls_lockspace, name, file, fl);
+	return error;
+}
+
+int gfs2_lm_plock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		  struct file *file, int cmd, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_plock(
+				sdp->sd_lockstruct.ls_lockspace, name, file, cmd, fl);
+	return error;
+}
+
+int gfs2_lm_punlock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		    struct file *file, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_punlock(
+				sdp->sd_lockstruct.ls_lockspace, name, file, fl);
+	return error;
+}
+
+void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+			   unsigned int message)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_recovery_done(
+			sdp->sd_lockstruct.ls_lockspace, jid, message);
+}
+

fs/gfs2/lm.h

@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LM_DOT_H__
+#define __LM_DOT_H__
+
+struct gfs2_sbd;
+
+#define GFS2_MIN_LVB_SIZE 32
+
+int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent);
+void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp);
+void gfs2_lm_unmount(struct gfs2_sbd *sdp);
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+				__attribute__ ((format(printf, 2, 3)));
+int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		     void **lockp);
+void gfs2_lm_put_lock(struct gfs2_sbd *sdp, void *lock);
+unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+			 unsigned int cur_state, unsigned int req_state,
+			 unsigned int flags);
+unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
+			   unsigned int cur_state);
+void gfs2_lm_cancel(struct gfs2_sbd *sdp, void *lock);
+int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp);
+void gfs2_lm_unhold_lvb(struct gfs2_sbd *sdp, void *lock, char *lvb);
+int gfs2_lm_plock_get(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		      struct file *file, struct file_lock *fl);
+int gfs2_lm_plock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		  struct file *file, int cmd, struct file_lock *fl);
+int gfs2_lm_punlock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		    struct file *file, struct file_lock *fl);
+void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+			   unsigned int message);
+
+#endif /* __LM_DOT_H__ */

fs/gfs2/locking.c

@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/lm_interface.h>
+
+struct lmh_wrapper {
+	struct list_head lw_list;
+	const struct lm_lockops *lw_ops;
+};
+
+/* List of registered low-level locking protocols.  A file system selects one
+   of them by name at mount time, e.g. lock_nolock, lock_dlm. */
+
+static LIST_HEAD(lmh_list);
+static DEFINE_MUTEX(lmh_lock);
+
+/**
+ * gfs2_register_lockproto - Register a low-level locking protocol
+ * @proto: the protocol definition
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+int gfs2_register_lockproto(const struct lm_lockops *proto)
+{
+	struct lmh_wrapper *lw;
+
+	mutex_lock(&lmh_lock);
+
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) {
+			mutex_unlock(&lmh_lock);
+			printk(KERN_INFO "GFS2: protocol %s already exists\n",
+			       proto->lm_proto_name);
+			return -EEXIST;
+		}
+	}
+
+	lw = kzalloc(sizeof(struct lmh_wrapper), GFP_KERNEL);
+	if (!lw) {
+		mutex_unlock(&lmh_lock);
+		return -ENOMEM;
+	}
+
+	lw->lw_ops = proto;
+	list_add(&lw->lw_list, &lmh_list);
+
+	mutex_unlock(&lmh_lock);
+
+	return 0;
+}
+
+/**
+ * gfs2_unregister_lockproto - Unregister a low-level locking protocol
+ * @proto: the protocol definition
+ *
+ */
+
+void gfs2_unregister_lockproto(const struct lm_lockops *proto)
+{
+	struct lmh_wrapper *lw;
+
+	mutex_lock(&lmh_lock);
+
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) {
+			list_del(&lw->lw_list);
+			mutex_unlock(&lmh_lock);
+			kfree(lw);
+			return;
+		}
+	}
+
+	mutex_unlock(&lmh_lock);
+
+	printk(KERN_WARNING "GFS2: can't unregister lock protocol %s\n",
+	       proto->lm_proto_name);
+}
+
+/**
+ * gfs2_mount_lockproto - Mount a lock protocol
+ * @proto_name - the name of the protocol
+ * @table_name - the name of the lock space
+ * @host_data - data specific to this host
+ * @cb - the callback to the code using the lock module
+ * @sdp - The GFS2 superblock
+ * @min_lvb_size - the mininum LVB size that the caller can deal with
+ * @flags - LM_MFLAG_*
+ * @lockstruct - a structure returned describing the mount
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+int gfs2_mount_lockproto(char *proto_name, char *table_name, char *host_data,
+			 lm_callback_t cb, void *cb_data,
+			 unsigned int min_lvb_size, int flags,
+			 struct lm_lockstruct *lockstruct,
+			 struct kobject *fskobj)
+{
+	struct lmh_wrapper *lw = NULL;
+	int try = 0;
+	int error, found;
+
+retry:
+	mutex_lock(&lmh_lock);
+
+	found = 0;
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto_name)) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		if (!try && capable(CAP_SYS_MODULE)) {
+			try = 1;
+			mutex_unlock(&lmh_lock);
+			request_module(proto_name);
+			goto retry;
+		}
+		printk(KERN_INFO "GFS2: can't find protocol %s\n", proto_name);
+		error = -ENOENT;
+		goto out;
+	}
+
+	if (!try_module_get(lw->lw_ops->lm_owner)) {
+		try = 0;
+		mutex_unlock(&lmh_lock);
+		msleep(1000);
+		goto retry;
+	}
+
+	error = lw->lw_ops->lm_mount(table_name, host_data, cb, cb_data,
+				     min_lvb_size, flags, lockstruct, fskobj);
+	if (error)
+		module_put(lw->lw_ops->lm_owner);
+out:
+	mutex_unlock(&lmh_lock);
+	return error;
+}
+
+void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct)
+{
+	mutex_lock(&lmh_lock);
+	lockstruct->ls_ops->lm_unmount(lockstruct->ls_lockspace);
+	if (lockstruct->ls_ops->lm_owner)
+		module_put(lockstruct->ls_ops->lm_owner);
+	mutex_unlock(&lmh_lock);
+}
+
+/**
+ * gfs2_withdraw_lockproto - abnormally unmount a lock module
+ * @lockstruct: the lockstruct passed into mount
+ *
+ */
+
+void gfs2_withdraw_lockproto(struct lm_lockstruct *lockstruct)
+{
+	mutex_lock(&lmh_lock);
+	lockstruct->ls_ops->lm_withdraw(lockstruct->ls_lockspace);
+	if (lockstruct->ls_ops->lm_owner)
+		module_put(lockstruct->ls_ops->lm_owner);
+	mutex_unlock(&lmh_lock);
+}
+
+EXPORT_SYMBOL_GPL(gfs2_register_lockproto);
+EXPORT_SYMBOL_GPL(gfs2_unregister_lockproto);
+

fs/gfs2/locking/dlm/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
+lock_dlm-y := lock.o main.o mount.o sysfs.o thread.o plock.o
+

fs/gfs2/locking/dlm/lock.c

@@ -0,0 +1,524 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+static char junk_lvb[GDLM_LVB_SIZE];
+
+static void queue_complete(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	clear_bit(LFL_ACTIVE, &lp->flags);
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->clist, &ls->complete);
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+static inline void gdlm_ast(void *astarg)
+{
+	queue_complete(astarg);
+}
+
+static inline void gdlm_bast(void *astarg, int mode)
+{
+	struct gdlm_lock *lp = astarg;
+	struct gdlm_ls *ls = lp->ls;
+
+	if (!mode) {
+		printk(KERN_INFO "lock_dlm: bast mode zero %x,%llx\n",
+			lp->lockname.ln_type,
+			(unsigned long long)lp->lockname.ln_number);
+		return;
+	}
+
+	spin_lock(&ls->async_lock);
+	if (!lp->bast_mode) {
+		list_add_tail(&lp->blist, &ls->blocking);
+		lp->bast_mode = mode;
+	} else if (lp->bast_mode < mode)
+		lp->bast_mode = mode;
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+void gdlm_queue_delayed(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->delay_list, &ls->delayed);
+	spin_unlock(&ls->async_lock);
+}
+
+/* convert gfs lock-state to dlm lock-mode */
+
+static s16 make_mode(s16 lmstate)
+{
+	switch (lmstate) {
+	case LM_ST_UNLOCKED:
+		return DLM_LOCK_NL;
+	case LM_ST_EXCLUSIVE:
+		return DLM_LOCK_EX;
+	case LM_ST_DEFERRED:
+		return DLM_LOCK_CW;
+	case LM_ST_SHARED:
+		return DLM_LOCK_PR;
+	}
+	gdlm_assert(0, "unknown LM state %d", lmstate);
+	return -1;
+}
+
+/* convert dlm lock-mode to gfs lock-state */
+
+s16 gdlm_make_lmstate(s16 dlmmode)
+{
+	switch (dlmmode) {
+	case DLM_LOCK_IV:
+	case DLM_LOCK_NL:
+		return LM_ST_UNLOCKED;
+	case DLM_LOCK_EX:
+		return LM_ST_EXCLUSIVE;
+	case DLM_LOCK_CW:
+		return LM_ST_DEFERRED;
+	case DLM_LOCK_PR:
+		return LM_ST_SHARED;
+	}
+	gdlm_assert(0, "unknown DLM mode %d", dlmmode);
+	return -1;
+}
+
+/* verify agreement with GFS on the current lock state, NB: DLM_LOCK_NL and
+   DLM_LOCK_IV are both considered LM_ST_UNLOCKED by GFS. */
+
+static void check_cur_state(struct gdlm_lock *lp, unsigned int cur_state)
+{
+	s16 cur = make_mode(cur_state);
+	if (lp->cur != DLM_LOCK_IV)
+		gdlm_assert(lp->cur == cur, "%d, %d", lp->cur, cur);
+}
+
+static inline unsigned int make_flags(struct gdlm_lock *lp,
+				      unsigned int gfs_flags,
+				      s16 cur, s16 req)
+{
+	unsigned int lkf = 0;
+
+	if (gfs_flags & LM_FLAG_TRY)
+		lkf |= DLM_LKF_NOQUEUE;
+
+	if (gfs_flags & LM_FLAG_TRY_1CB) {
+		lkf |= DLM_LKF_NOQUEUE;
+		lkf |= DLM_LKF_NOQUEUEBAST;
+	}
+
+	if (gfs_flags & LM_FLAG_PRIORITY) {
+		lkf |= DLM_LKF_NOORDER;
+		lkf |= DLM_LKF_HEADQUE;
+	}
+
+	if (gfs_flags & LM_FLAG_ANY) {
+		if (req == DLM_LOCK_PR)
+			lkf |= DLM_LKF_ALTCW;
+		else if (req == DLM_LOCK_CW)
+			lkf |= DLM_LKF_ALTPR;
+	}
+
+	if (lp->lksb.sb_lkid != 0) {
+		lkf |= DLM_LKF_CONVERT;
+
+		/* Conversion deadlock avoidance by DLM */
+
+		if (!test_bit(LFL_FORCE_PROMOTE, &lp->flags) &&
+		    !(lkf & DLM_LKF_NOQUEUE) &&
+		    cur > DLM_LOCK_NL && req > DLM_LOCK_NL && cur != req)
+			lkf |= DLM_LKF_CONVDEADLK;
+	}
+
+	if (lp->lvb)
+		lkf |= DLM_LKF_VALBLK;
+
+	return lkf;
+}
+
+/* make_strname - convert GFS lock numbers to a string */
+
+static inline void make_strname(struct lm_lockname *lockname,
+				struct gdlm_strname *str)
+{
+	sprintf(str->name, "%8x%16llx", lockname->ln_type,
+		(unsigned long long)lockname->ln_number);
+	str->namelen = GDLM_STRNAME_BYTES;
+}
+
+static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name,
+			  struct gdlm_lock **lpp)
+{
+	struct gdlm_lock *lp;
+
+	lp = kzalloc(sizeof(struct gdlm_lock), GFP_KERNEL);
+	if (!lp)
+		return -ENOMEM;
+
+	lp->lockname = *name;
+	lp->ls = ls;
+	lp->cur = DLM_LOCK_IV;
+	lp->lvb = NULL;
+	lp->hold_null = NULL;
+	init_completion(&lp->ast_wait);
+	INIT_LIST_HEAD(&lp->clist);
+	INIT_LIST_HEAD(&lp->blist);
+	INIT_LIST_HEAD(&lp->delay_list);
+
+	spin_lock(&ls->async_lock);
+	list_add(&lp->all_list, &ls->all_locks);
+	ls->all_locks_count++;
+	spin_unlock(&ls->async_lock);
+
+	*lpp = lp;
+	return 0;
+}
+
+void gdlm_delete_lp(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	if (!list_empty(&lp->clist))
+		list_del_init(&lp->clist);
+	if (!list_empty(&lp->blist))
+		list_del_init(&lp->blist);
+	if (!list_empty(&lp->delay_list))
+		list_del_init(&lp->delay_list);
+	gdlm_assert(!list_empty(&lp->all_list), "%x,%llx", lp->lockname.ln_type,
+		    (unsigned long long)lp->lockname.ln_number);
+	list_del_init(&lp->all_list);
+	ls->all_locks_count--;
+	spin_unlock(&ls->async_lock);
+
+	kfree(lp);
+}
+
+int gdlm_get_lock(void *lockspace, struct lm_lockname *name,
+		  void **lockp)
+{
+	struct gdlm_lock *lp;
+	int error;
+
+	error = gdlm_create_lp(lockspace, name, &lp);
+
+	*lockp = lp;
+	return error;
+}
+
+void gdlm_put_lock(void *lock)
+{
+	gdlm_delete_lp(lock);
+}
+
+unsigned int gdlm_do_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	struct gdlm_strname str;
+	int error, bast = 1;
+
+	/*
+	 * When recovery is in progress, delay lock requests for submission
+	 * once recovery is done.  Requests for recovery (NOEXP) and unlocks
+	 * can pass.
+	 */
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+	    !test_bit(LFL_NOBLOCK, &lp->flags) && lp->req != DLM_LOCK_NL) {
+		gdlm_queue_delayed(lp);
+		return LM_OUT_ASYNC;
+	}
+
+	/*
+	 * Submit the actual lock request.
+	 */
+
+	if (test_bit(LFL_NOBAST, &lp->flags))
+		bast = 0;
+
+	make_strname(&lp->lockname, &str);
+
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	log_debug("lk %x,%llx id %x %d,%d %x", lp->lockname.ln_type,
+		  (unsigned long long)lp->lockname.ln_number, lp->lksb.sb_lkid,
+		  lp->cur, lp->req, lp->lkf);
+
+	error = dlm_lock(ls->dlm_lockspace, lp->req, &lp->lksb, lp->lkf,
+			 str.name, str.namelen, 0, gdlm_ast, lp,
+			 bast ? gdlm_bast : NULL);
+
+	if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
+		lp->lksb.sb_status = -EAGAIN;
+		queue_complete(lp);
+		error = 0;
+	}
+
+	if (error) {
+		log_debug("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
+			  "flags=%lx", ls->fsname, lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number, error,
+			  lp->cur, lp->req, lp->lkf, lp->flags);
+		return LM_OUT_ERROR;
+	}
+	return LM_OUT_ASYNC;
+}
+
+static unsigned int gdlm_do_unlock(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	unsigned int lkf = 0;
+	int error;
+
+	set_bit(LFL_DLM_UNLOCK, &lp->flags);
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	if (lp->lvb)
+		lkf = DLM_LKF_VALBLK;
+
+	log_debug("un %x,%llx %x %d %x", lp->lockname.ln_type,
+		  (unsigned long long)lp->lockname.ln_number,
+		  lp->lksb.sb_lkid, lp->cur, lkf);
+
+	error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, lkf, NULL, lp);
+
+	if (error) {
+		log_debug("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
+			  "flags=%lx", ls->fsname, lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number, error,
+			  lp->cur, lp->req, lp->lkf, lp->flags);
+		return LM_OUT_ERROR;
+	}
+	return LM_OUT_ASYNC;
+}
+
+unsigned int gdlm_lock(void *lock, unsigned int cur_state,
+		       unsigned int req_state, unsigned int flags)
+{
+	struct gdlm_lock *lp = lock;
+
+	clear_bit(LFL_DLM_CANCEL, &lp->flags);
+	if (flags & LM_FLAG_NOEXP)
+		set_bit(LFL_NOBLOCK, &lp->flags);
+
+	check_cur_state(lp, cur_state);
+	lp->req = make_mode(req_state);
+	lp->lkf = make_flags(lp, flags, lp->cur, lp->req);
+
+	return gdlm_do_lock(lp);
+}
+
+unsigned int gdlm_unlock(void *lock, unsigned int cur_state)
+{
+	struct gdlm_lock *lp = lock;
+
+	clear_bit(LFL_DLM_CANCEL, &lp->flags);
+	if (lp->cur == DLM_LOCK_IV)
+		return 0;
+	return gdlm_do_unlock(lp);
+}
+
+void gdlm_cancel(void *lock)
+{
+	struct gdlm_lock *lp = lock;
+	struct gdlm_ls *ls = lp->ls;
+	int error, delay_list = 0;
+
+	if (test_bit(LFL_DLM_CANCEL, &lp->flags))
+		return;
+
+	log_info("gdlm_cancel %x,%llx flags %lx", lp->lockname.ln_type,
+		 (unsigned long long)lp->lockname.ln_number, lp->flags);
+
+	spin_lock(&ls->async_lock);
+	if (!list_empty(&lp->delay_list)) {
+		list_del_init(&lp->delay_list);
+		delay_list = 1;
+	}
+	spin_unlock(&ls->async_lock);
+
+	if (delay_list) {
+		set_bit(LFL_CANCEL, &lp->flags);
+		set_bit(LFL_ACTIVE, &lp->flags);
+		queue_complete(lp);
+		return;
+	}
+
+	if (!test_bit(LFL_ACTIVE, &lp->flags) ||
+	    test_bit(LFL_DLM_UNLOCK, &lp->flags)) {
+		log_info("gdlm_cancel skip %x,%llx flags %lx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number, lp->flags);
+		return;
+	}
+
+	/* the lock is blocked in the dlm */
+
+	set_bit(LFL_DLM_CANCEL, &lp->flags);
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, DLM_LKF_CANCEL,
+			   NULL, lp);
+
+	log_info("gdlm_cancel rv %d %x,%llx flags %lx", error,
+		 lp->lockname.ln_type,
+		 (unsigned long long)lp->lockname.ln_number, lp->flags);
+
+	if (error == -EBUSY)
+		clear_bit(LFL_DLM_CANCEL, &lp->flags);
+}
+
+static int gdlm_add_lvb(struct gdlm_lock *lp)
+{
+	char *lvb;
+
+	lvb = kzalloc(GDLM_LVB_SIZE, GFP_KERNEL);
+	if (!lvb)
+		return -ENOMEM;
+
+	lp->lksb.sb_lvbptr = lvb;
+	lp->lvb = lvb;
+	return 0;
+}
+
+static void gdlm_del_lvb(struct gdlm_lock *lp)
+{
+	kfree(lp->lvb);
+	lp->lvb = NULL;
+	lp->lksb.sb_lvbptr = NULL;
+}
+
+/* This can do a synchronous dlm request (requiring a lock_dlm thread to get
+   the completion) because gfs won't call hold_lvb() during a callback (from
+   the context of a lock_dlm thread). */
+
+static int hold_null_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_lock *lpn = NULL;
+	int error;
+
+	if (lp->hold_null) {
+		printk(KERN_INFO "lock_dlm: lvb already held\n");
+		return 0;
+	}
+
+	error = gdlm_create_lp(lp->ls, &lp->lockname, &lpn);
+	if (error)
+		goto out;
+
+	lpn->lksb.sb_lvbptr = junk_lvb;
+	lpn->lvb = junk_lvb;
+
+	lpn->req = DLM_LOCK_NL;
+	lpn->lkf = DLM_LKF_VALBLK | DLM_LKF_EXPEDITE;
+	set_bit(LFL_NOBAST, &lpn->flags);
+	set_bit(LFL_INLOCK, &lpn->flags);
+
+	init_completion(&lpn->ast_wait);
+	gdlm_do_lock(lpn);
+	wait_for_completion(&lpn->ast_wait);
+	error = lpn->lksb.sb_status;
+	if (error) {
+		printk(KERN_INFO "lock_dlm: hold_null_lock dlm error %d\n",
+		       error);
+		gdlm_delete_lp(lpn);
+		lpn = NULL;
+	}
+out:
+	lp->hold_null = lpn;
+	return error;
+}
+
+/* This cannot do a synchronous dlm request (requiring a lock_dlm thread to get
+   the completion) because gfs may call unhold_lvb() during a callback (from
+   the context of a lock_dlm thread) which could cause a deadlock since the
+   other lock_dlm thread could be engaged in recovery. */
+
+static void unhold_null_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_lock *lpn = lp->hold_null;
+
+	gdlm_assert(lpn, "%x,%llx", lp->lockname.ln_type,
+		    (unsigned long long)lp->lockname.ln_number);
+	lpn->lksb.sb_lvbptr = NULL;
+	lpn->lvb = NULL;
+	set_bit(LFL_UNLOCK_DELETE, &lpn->flags);
+	gdlm_do_unlock(lpn);
+	lp->hold_null = NULL;
+}
+
+/* Acquire a NL lock because gfs requires the value block to remain
+   intact on the resource while the lvb is "held" even if it's holding no locks
+   on the resource. */
+
+int gdlm_hold_lvb(void *lock, char **lvbp)
+{
+	struct gdlm_lock *lp = lock;
+	int error;
+
+	error = gdlm_add_lvb(lp);
+	if (error)
+		return error;
+
+	*lvbp = lp->lvb;
+
+	error = hold_null_lock(lp);
+	if (error)
+		gdlm_del_lvb(lp);
+
+	return error;
+}
+
+void gdlm_unhold_lvb(void *lock, char *lvb)
+{
+	struct gdlm_lock *lp = lock;
+
+	unhold_null_lock(lp);
+	gdlm_del_lvb(lp);
+}
+
+void gdlm_submit_delayed(struct gdlm_ls *ls)
+{
+	struct gdlm_lock *lp, *safe;
+
+	spin_lock(&ls->async_lock);
+	list_for_each_entry_safe(lp, safe, &ls->delayed, delay_list) {
+		list_del_init(&lp->delay_list);
+		list_add_tail(&lp->delay_list, &ls->submit);
+	}
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+int gdlm_release_all_locks(struct gdlm_ls *ls)
+{
+	struct gdlm_lock *lp, *safe;
+	int count = 0;
+
+	spin_lock(&ls->async_lock);
+	list_for_each_entry_safe(lp, safe, &ls->all_locks, all_list) {
+		list_del_init(&lp->all_list);
+
+		if (lp->lvb && lp->lvb != junk_lvb)
+			kfree(lp->lvb);
+		kfree(lp);
+		count++;
+	}
+	spin_unlock(&ls->async_lock);
+
+	return count;
+}
+

fs/gfs2/locking/dlm/lock_dlm.h

@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef LOCK_DLM_DOT_H
+#define LOCK_DLM_DOT_H
+
+#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>
+#include <linux/socket.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/kobject.h>
+#include <linux/fcntl.h>
+#include <linux/wait.h>
+#include <net/sock.h>
+
+#include <linux/dlm.h>
+#include <linux/lm_interface.h>
+
+/*
+ * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a
+ * prefix of lock_dlm_ gets awkward.  Externally, GFS refers to this module
+ * as "lock_dlm".
+ */
+
+#define GDLM_STRNAME_BYTES	24
+#define GDLM_LVB_SIZE		32
+#define GDLM_DROP_COUNT		200000
+#define GDLM_DROP_PERIOD	60
+#define GDLM_NAME_LEN		128
+
+/* GFS uses 12 bytes to identify a resource (32 bit type + 64 bit number).
+   We sprintf these numbers into a 24 byte string of hex values to make them
+   human-readable (to make debugging simpler.) */
+
+struct gdlm_strname {
+	unsigned char		name[GDLM_STRNAME_BYTES];
+	unsigned short		namelen;
+};
+
+enum {
+	DFL_BLOCK_LOCKS		= 0,
+	DFL_SPECTATOR		= 1,
+	DFL_WITHDRAW		= 2,
+};
+
+struct gdlm_ls {
+	u32		id;
+	int			jid;
+	int			first;
+	int			first_done;
+	unsigned long		flags;
+	struct kobject		kobj;
+	char			clustername[GDLM_NAME_LEN];
+	char			fsname[GDLM_NAME_LEN];
+	int			fsflags;
+	dlm_lockspace_t		*dlm_lockspace;
+	lm_callback_t		fscb;
+	struct gfs2_sbd		*sdp;
+	int			recover_jid;
+	int			recover_jid_done;
+	int			recover_jid_status;
+	spinlock_t		async_lock;
+	struct list_head	complete;
+	struct list_head	blocking;
+	struct list_head	delayed;
+	struct list_head	submit;
+	struct list_head	all_locks;
+	u32		all_locks_count;
+	wait_queue_head_t	wait_control;
+	struct task_struct	*thread1;
+	struct task_struct	*thread2;
+	wait_queue_head_t	thread_wait;
+	unsigned long		drop_time;
+	int			drop_locks_count;
+	int			drop_locks_period;
+};
+
+enum {
+	LFL_NOBLOCK		= 0,
+	LFL_NOCACHE		= 1,
+	LFL_DLM_UNLOCK		= 2,
+	LFL_DLM_CANCEL		= 3,
+	LFL_SYNC_LVB		= 4,
+	LFL_FORCE_PROMOTE	= 5,
+	LFL_REREQUEST		= 6,
+	LFL_ACTIVE		= 7,
+	LFL_INLOCK		= 8,
+	LFL_CANCEL		= 9,
+	LFL_NOBAST		= 10,
+	LFL_HEADQUE		= 11,
+	LFL_UNLOCK_DELETE	= 12,
+};
+
+struct gdlm_lock {
+	struct gdlm_ls		*ls;
+	struct lm_lockname	lockname;
+	char			*lvb;
+	struct dlm_lksb		lksb;
+
+	s16			cur;
+	s16			req;
+	s16			prev_req;
+	u32			lkf;		/* dlm flags DLM_LKF_ */
+	unsigned long		flags;		/* lock_dlm flags LFL_ */
+
+	int			bast_mode;	/* protected by async_lock */
+	struct completion	ast_wait;
+
+	struct list_head	clist;		/* complete */
+	struct list_head	blist;		/* blocking */
+	struct list_head	delay_list;	/* delayed */
+	struct list_head	all_list;	/* all locks for the fs */
+	struct gdlm_lock	*hold_null;	/* NL lock for hold_lvb */
+};
+
+#define gdlm_assert(assertion, fmt, args...)                                  \
+do {                                                                          \
+	if (unlikely(!(assertion))) {                                         \
+		printk(KERN_EMERG "lock_dlm: fatal assertion failed \"%s\"\n" \
+				  "lock_dlm:  " fmt "\n",                     \
+				  #assertion, ##args);                        \
+		BUG();                                                        \
+	}                                                                     \
+} while (0)
+
+#define log_print(lev, fmt, arg...) printk(lev "lock_dlm: " fmt "\n" , ## arg)
+#define log_info(fmt, arg...)  log_print(KERN_INFO , fmt , ## arg)
+#define log_error(fmt, arg...) log_print(KERN_ERR , fmt , ## arg)
+#ifdef LOCK_DLM_LOG_DEBUG
+#define log_debug(fmt, arg...) log_print(KERN_DEBUG , fmt , ## arg)
+#else
+#define log_debug(fmt, arg...)
+#endif
+
+/* sysfs.c */
+
+int gdlm_sysfs_init(void);
+void gdlm_sysfs_exit(void);
+int gdlm_kobject_setup(struct gdlm_ls *, struct kobject *);
+void gdlm_kobject_release(struct gdlm_ls *);
+
+/* thread.c */
+
+int gdlm_init_threads(struct gdlm_ls *);
+void gdlm_release_threads(struct gdlm_ls *);
+
+/* lock.c */
+
+s16 gdlm_make_lmstate(s16);
+void gdlm_queue_delayed(struct gdlm_lock *);
+void gdlm_submit_delayed(struct gdlm_ls *);
+int gdlm_release_all_locks(struct gdlm_ls *);
+void gdlm_delete_lp(struct gdlm_lock *);
+unsigned int gdlm_do_lock(struct gdlm_lock *);
+
+int gdlm_get_lock(void *, struct lm_lockname *, void **);
+void gdlm_put_lock(void *);
+unsigned int gdlm_lock(void *, unsigned int, unsigned int, unsigned int);
+unsigned int gdlm_unlock(void *, unsigned int);
+void gdlm_cancel(void *);
+int gdlm_hold_lvb(void *, char **);
+void gdlm_unhold_lvb(void *, char *);
+
+/* plock.c */
+
+int gdlm_plock_init(void);
+void gdlm_plock_exit(void);
+int gdlm_plock(void *, struct lm_lockname *, struct file *, int,
+		struct file_lock *);
+int gdlm_plock_get(void *, struct lm_lockname *, struct file *,
+		struct file_lock *);
+int gdlm_punlock(void *, struct lm_lockname *, struct file *,
+		struct file_lock *);
+#endif
+

fs/gfs2/locking/dlm/main.c

@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/init.h>
+
+#include "lock_dlm.h"
+
+extern struct lm_lockops gdlm_ops;
+
+static int __init init_lock_dlm(void)
+{
+	int error;
+
+	error = gfs2_register_lockproto(&gdlm_ops);
+	if (error) {
+		printk(KERN_WARNING "lock_dlm:  can't register protocol: %d\n",
+		       error);
+		return error;
+	}
+
+	error = gdlm_sysfs_init();
+	if (error) {
+		gfs2_unregister_lockproto(&gdlm_ops);
+		return error;
+	}
+
+	error = gdlm_plock_init();
+	if (error) {
+		gdlm_sysfs_exit();
+		gfs2_unregister_lockproto(&gdlm_ops);
+		return error;
+	}
+
+	printk(KERN_INFO
+	       "Lock_DLM (built %s %s) installed\n", __DATE__, __TIME__);
+	return 0;
+}
+
+static void __exit exit_lock_dlm(void)
+{
+	gdlm_plock_exit();
+	gdlm_sysfs_exit();
+	gfs2_unregister_lockproto(&gdlm_ops);
+}
+
+module_init(init_lock_dlm);
+module_exit(exit_lock_dlm);
+
+MODULE_DESCRIPTION("GFS DLM Locking Module");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+

fs/gfs2/locking/dlm/mount.c

@@ -0,0 +1,253 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+const struct lm_lockops gdlm_ops;
+
+
+static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp,
+				 int flags, char *table_name)
+{
+	struct gdlm_ls *ls;
+	char buf[256], *p;
+
+	ls = kzalloc(sizeof(struct gdlm_ls), GFP_KERNEL);
+	if (!ls)
+		return NULL;
+
+	ls->drop_locks_count = GDLM_DROP_COUNT;
+	ls->drop_locks_period = GDLM_DROP_PERIOD;
+	ls->fscb = cb;
+	ls->sdp = sdp;
+	ls->fsflags = flags;
+	spin_lock_init(&ls->async_lock);
+	INIT_LIST_HEAD(&ls->complete);
+	INIT_LIST_HEAD(&ls->blocking);
+	INIT_LIST_HEAD(&ls->delayed);
+	INIT_LIST_HEAD(&ls->submit);
+	INIT_LIST_HEAD(&ls->all_locks);
+	init_waitqueue_head(&ls->thread_wait);
+	init_waitqueue_head(&ls->wait_control);
+	ls->thread1 = NULL;
+	ls->thread2 = NULL;
+	ls->drop_time = jiffies;
+	ls->jid = -1;
+
+	strncpy(buf, table_name, 256);
+	buf[255] = '\0';
+
+	p = strchr(buf, ':');
+	if (!p) {
+		log_info("invalid table_name \"%s\"", table_name);
+		kfree(ls);
+		return NULL;
+	}
+	*p = '\0';
+	p++;
+
+	strncpy(ls->clustername, buf, GDLM_NAME_LEN);
+	strncpy(ls->fsname, p, GDLM_NAME_LEN);
+
+	return ls;
+}
+
+static int make_args(struct gdlm_ls *ls, char *data_arg, int *nodir)
+{
+	char data[256];
+	char *options, *x, *y;
+	int error = 0;
+
+	memset(data, 0, 256);
+	strncpy(data, data_arg, 255);
+
+	for (options = data; (x = strsep(&options, ":")); ) {
+		if (!*x)
+			continue;
+
+		y = strchr(x, '=');
+		if (y)
+			*y++ = 0;
+
+		if (!strcmp(x, "jid")) {
+			if (!y) {
+				log_error("need argument to jid");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->jid);
+
+		} else if (!strcmp(x, "first")) {
+			if (!y) {
+				log_error("need argument to first");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->first);
+
+		} else if (!strcmp(x, "id")) {
+			if (!y) {
+				log_error("need argument to id");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->id);
+
+		} else if (!strcmp(x, "nodir")) {
+			if (!y) {
+				log_error("need argument to nodir");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", nodir);
+
+		} else {
+			log_error("unkonwn option: %s", x);
+			error = -EINVAL;
+			break;
+		}
+	}
+
+	return error;
+}
+
+static int gdlm_mount(char *table_name, char *host_data,
+			lm_callback_t cb, void *cb_data,
+			unsigned int min_lvb_size, int flags,
+			struct lm_lockstruct *lockstruct,
+			struct kobject *fskobj)
+{
+	struct gdlm_ls *ls;
+	int error = -ENOMEM, nodir = 0;
+
+	if (min_lvb_size > GDLM_LVB_SIZE)
+		goto out;
+
+	ls = init_gdlm(cb, cb_data, flags, table_name);
+	if (!ls)
+		goto out;
+
+	error = make_args(ls, host_data, &nodir);
+	if (error)
+		goto out;
+
+	error = gdlm_init_threads(ls);
+	if (error)
+		goto out_free;
+
+	error = gdlm_kobject_setup(ls, fskobj);
+	if (error)
+		goto out_thread;
+
+	error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname),
+				  &ls->dlm_lockspace,
+				  nodir ? DLM_LSFL_NODIR : 0,
+				  GDLM_LVB_SIZE);
+	if (error) {
+		log_error("dlm_new_lockspace error %d", error);
+		goto out_kobj;
+	}
+
+	lockstruct->ls_jid = ls->jid;
+	lockstruct->ls_first = ls->first;
+	lockstruct->ls_lockspace = ls;
+	lockstruct->ls_ops = &gdlm_ops;
+	lockstruct->ls_flags = 0;
+	lockstruct->ls_lvb_size = GDLM_LVB_SIZE;
+	return 0;
+
+out_kobj:
+	gdlm_kobject_release(ls);
+out_thread:
+	gdlm_release_threads(ls);
+out_free:
+	kfree(ls);
+out:
+	return error;
+}
+
+static void gdlm_unmount(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+	int rv;
+
+	log_debug("unmount flags %lx", ls->flags);
+
+	/* FIXME: serialize unmount and withdraw in case they
+	   happen at once.  Also, if unmount follows withdraw,
+	   wait for withdraw to finish. */
+
+	if (test_bit(DFL_WITHDRAW, &ls->flags))
+		goto out;
+
+	gdlm_kobject_release(ls);
+	dlm_release_lockspace(ls->dlm_lockspace, 2);
+	gdlm_release_threads(ls);
+	rv = gdlm_release_all_locks(ls);
+	if (rv)
+		log_info("gdlm_unmount: %d stray locks freed", rv);
+out:
+	kfree(ls);
+}
+
+static void gdlm_recovery_done(void *lockspace, unsigned int jid,
+                               unsigned int message)
+{
+	struct gdlm_ls *ls = lockspace;
+	ls->recover_jid_done = jid;
+	ls->recover_jid_status = message;
+	kobject_uevent(&ls->kobj, KOBJ_CHANGE);
+}
+
+static void gdlm_others_may_mount(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+	ls->first_done = 1;
+	kobject_uevent(&ls->kobj, KOBJ_CHANGE);
+}
+
+/* Userspace gets the offline uevent, blocks new gfs locks on
+   other mounters, and lets us know (sets WITHDRAW flag).  Then,
+   userspace leaves the mount group while we leave the lockspace. */
+
+static void gdlm_withdraw(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+
+	kobject_uevent(&ls->kobj, KOBJ_OFFLINE);
+
+	wait_event_interruptible(ls->wait_control,
+				 test_bit(DFL_WITHDRAW, &ls->flags));
+
+	dlm_release_lockspace(ls->dlm_lockspace, 2);
+	gdlm_release_threads(ls);
+	gdlm_release_all_locks(ls);
+	gdlm_kobject_release(ls);
+}
+
+const struct lm_lockops gdlm_ops = {
+	.lm_proto_name = "lock_dlm",
+	.lm_mount = gdlm_mount,
+	.lm_others_may_mount = gdlm_others_may_mount,
+	.lm_unmount = gdlm_unmount,
+	.lm_withdraw = gdlm_withdraw,
+	.lm_get_lock = gdlm_get_lock,
+	.lm_put_lock = gdlm_put_lock,
+	.lm_lock = gdlm_lock,
+	.lm_unlock = gdlm_unlock,
+	.lm_plock = gdlm_plock,
+	.lm_punlock = gdlm_punlock,
+	.lm_plock_get = gdlm_plock_get,
+	.lm_cancel = gdlm_cancel,
+	.lm_hold_lvb = gdlm_hold_lvb,
+	.lm_unhold_lvb = gdlm_unhold_lvb,
+	.lm_recovery_done = gdlm_recovery_done,
+	.lm_owner = THIS_MODULE,
+};
+

fs/gfs2/locking/dlm/plock.c

@@ -0,0 +1,302 @@
+/*
+ * Copyright (C) 2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/lock_dlm_plock.h>
+#include <linux/poll.h>
+
+#include "lock_dlm.h"
+
+
+static spinlock_t ops_lock;
+static struct list_head send_list;
+static struct list_head recv_list;
+static wait_queue_head_t send_wq;
+static wait_queue_head_t recv_wq;
+
+struct plock_op {
+	struct list_head list;
+	int done;
+	struct gdlm_plock_info info;
+};
+
+static inline void set_version(struct gdlm_plock_info *info)
+{
+	info->version[0] = GDLM_PLOCK_VERSION_MAJOR;
+	info->version[1] = GDLM_PLOCK_VERSION_MINOR;
+	info->version[2] = GDLM_PLOCK_VERSION_PATCH;
+}
+
+static int check_version(struct gdlm_plock_info *info)
+{
+	if ((GDLM_PLOCK_VERSION_MAJOR != info->version[0]) ||
+	    (GDLM_PLOCK_VERSION_MINOR < info->version[1])) {
+		log_error("plock device version mismatch: "
+			  "kernel (%u.%u.%u), user (%u.%u.%u)",
+			  GDLM_PLOCK_VERSION_MAJOR,
+			  GDLM_PLOCK_VERSION_MINOR,
+			  GDLM_PLOCK_VERSION_PATCH,
+			  info->version[0],
+			  info->version[1],
+			  info->version[2]);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void send_op(struct plock_op *op)
+{
+	set_version(&op->info);
+	INIT_LIST_HEAD(&op->list);
+	spin_lock(&ops_lock);
+	list_add_tail(&op->list, &send_list);
+	spin_unlock(&ops_lock);
+	wake_up(&send_wq);
+}
+
+int gdlm_plock(void *lockspace, struct lm_lockname *name,
+	       struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	op->info.optype		= GDLM_PLOCK_OP_LOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.wait		= IS_SETLKW(cmd);
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	op->info.owner		= (__u64)(long) fl->fl_owner;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "plock op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (!rv) {
+		if (posix_lock_file_wait(file, fl) < 0)
+			log_error("gdlm_plock: vfs lock error %x,%llx",
+				  name->ln_type,
+				  (unsigned long long)name->ln_number);
+	}
+
+	kfree(op);
+	return rv;
+}
+
+int gdlm_punlock(void *lockspace, struct lm_lockname *name,
+		 struct file *file, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	if (posix_lock_file_wait(file, fl) < 0)
+		log_error("gdlm_punlock: vfs unlock error %x,%llx",
+			  name->ln_type, (unsigned long long)name->ln_number);
+
+	op->info.optype		= GDLM_PLOCK_OP_UNLOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	op->info.owner		= (__u64)(long) fl->fl_owner;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "punlock op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	kfree(op);
+	return rv;
+}
+
+int gdlm_plock_get(void *lockspace, struct lm_lockname *name,
+		   struct file *file, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	op->info.optype		= GDLM_PLOCK_OP_GET;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "plock_get op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (rv == 0)
+		fl->fl_type = F_UNLCK;
+	else if (rv > 0) {
+		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+		fl->fl_pid = op->info.pid;
+		fl->fl_start = op->info.start;
+		fl->fl_end = op->info.end;
+	}
+
+	kfree(op);
+	return rv;
+}
+
+/* a read copies out one plock request from the send list */
+static ssize_t dev_read(struct file *file, char __user *u, size_t count,
+			loff_t *ppos)
+{
+	struct gdlm_plock_info info;
+	struct plock_op *op = NULL;
+
+	if (count < sizeof(info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list)) {
+		op = list_entry(send_list.next, struct plock_op, list);
+		list_move(&op->list, &recv_list);
+		memcpy(&info, &op->info, sizeof(info));
+	}
+	spin_unlock(&ops_lock);
+
+	if (!op)
+		return -EAGAIN;
+
+	if (copy_to_user(u, &info, sizeof(info)))
+		return -EFAULT;
+	return sizeof(info);
+}
+
+/* a write copies in one plock result that should match a plock_op
+   on the recv list */
+static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
+			 loff_t *ppos)
+{
+	struct gdlm_plock_info info;
+	struct plock_op *op;
+	int found = 0;
+
+	if (count != sizeof(info))
+		return -EINVAL;
+
+	if (copy_from_user(&info, u, sizeof(info)))
+		return -EFAULT;
+
+	if (check_version(&info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	list_for_each_entry(op, &recv_list, list) {
+		if (op->info.fsid == info.fsid && op->info.number == info.number &&
+		    op->info.owner == info.owner) {
+			list_del_init(&op->list);
+			found = 1;
+			op->done = 1;
+			memcpy(&op->info, &info, sizeof(info));
+			break;
+		}
+	}
+	spin_unlock(&ops_lock);
+
+	if (found)
+		wake_up(&recv_wq);
+	else
+		printk(KERN_INFO "gdlm dev_write no op %x %llx\n", info.fsid,
+			(unsigned long long)info.number);
+	return count;
+}
+
+static unsigned int dev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &send_wq, wait);
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list)) {
+		spin_unlock(&ops_lock);
+		return POLLIN | POLLRDNORM;
+	}
+	spin_unlock(&ops_lock);
+	return 0;
+}
+
+static const struct file_operations dev_fops = {
+	.read    = dev_read,
+	.write   = dev_write,
+	.poll    = dev_poll,
+	.owner   = THIS_MODULE
+};
+
+static struct miscdevice plock_dev_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = GDLM_PLOCK_MISC_NAME,
+	.fops = &dev_fops
+};
+
+int gdlm_plock_init(void)
+{
+	int rv;
+
+	spin_lock_init(&ops_lock);
+	INIT_LIST_HEAD(&send_list);
+	INIT_LIST_HEAD(&recv_list);
+	init_waitqueue_head(&send_wq);
+	init_waitqueue_head(&recv_wq);
+
+	rv = misc_register(&plock_dev_misc);
+	if (rv)
+		printk(KERN_INFO "gdlm_plock_init: misc_register failed %d",
+		       rv);
+	return rv;
+}
+
+void gdlm_plock_exit(void)
+{
+	if (misc_deregister(&plock_dev_misc) < 0)
+		printk(KERN_INFO "gdlm_plock_exit: misc_deregister failed");
+}
+

fs/gfs2/locking/dlm/sysfs.c

@@ -0,0 +1,239 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/ctype.h>
+#include <linux/stat.h>
+
+#include "lock_dlm.h"
+
+extern struct lm_lockops gdlm_ops;
+
+static ssize_t proto_name_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%s\n", gdlm_ops.lm_proto_name);
+}
+
+static ssize_t block_show(struct gdlm_ls *ls, char *buf)
+{
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t block_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_BLOCK_LOCKS, &ls->flags);
+	else if (val == 0) {
+		clear_bit(DFL_BLOCK_LOCKS, &ls->flags);
+		gdlm_submit_delayed(ls);
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t withdraw_show(struct gdlm_ls *ls, char *buf)
+{
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_WITHDRAW, &ls->flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t withdraw_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_WITHDRAW, &ls->flags);
+	else
+		ret = -EINVAL;
+	wake_up(&ls->wait_control);
+	return ret;
+}
+
+static ssize_t id_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%u\n", ls->id);
+}
+
+static ssize_t jid_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->jid);
+}
+
+static ssize_t first_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->first);
+}
+
+static ssize_t first_done_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->first_done);
+}
+
+static ssize_t recover_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid);
+}
+
+static ssize_t recover_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ls->recover_jid = simple_strtol(buf, NULL, 0);
+	ls->fscb(ls->sdp, LM_CB_NEED_RECOVERY, &ls->recover_jid);
+	return len;
+}
+
+static ssize_t recover_done_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid_done);
+}
+
+static ssize_t recover_status_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid_status);
+}
+
+static ssize_t drop_count_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->drop_locks_count);
+}
+
+static ssize_t drop_count_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ls->drop_locks_count = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+struct gdlm_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gdlm_ls *, char *);
+	ssize_t (*store)(struct gdlm_ls *, const char *, size_t);
+};
+
+#define GDLM_ATTR(_name,_mode,_show,_store) \
+static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
+
+GDLM_ATTR(proto_name,     0444, proto_name_show,     NULL);
+GDLM_ATTR(block,          0644, block_show,          block_store);
+GDLM_ATTR(withdraw,       0644, withdraw_show,       withdraw_store);
+GDLM_ATTR(id,             0444, id_show,             NULL);
+GDLM_ATTR(jid,            0444, jid_show,            NULL);
+GDLM_ATTR(first,          0444, first_show,          NULL);
+GDLM_ATTR(first_done,     0444, first_done_show,     NULL);
+GDLM_ATTR(recover,        0644, recover_show,        recover_store);
+GDLM_ATTR(recover_done,   0444, recover_done_show,   NULL);
+GDLM_ATTR(recover_status, 0444, recover_status_show, NULL);
+GDLM_ATTR(drop_count,     0644, drop_count_show,     drop_count_store);
+
+static struct attribute *gdlm_attrs[] = {
+	&gdlm_attr_proto_name.attr,
+	&gdlm_attr_block.attr,
+	&gdlm_attr_withdraw.attr,
+	&gdlm_attr_id.attr,
+	&gdlm_attr_jid.attr,
+	&gdlm_attr_first.attr,
+	&gdlm_attr_first_done.attr,
+	&gdlm_attr_recover.attr,
+	&gdlm_attr_recover_done.attr,
+	&gdlm_attr_recover_status.attr,
+	&gdlm_attr_drop_count.attr,
+	NULL,
+};
+
+static ssize_t gdlm_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj);
+	struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr);
+	return a->show ? a->show(ls, buf) : 0;
+}
+
+static ssize_t gdlm_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj);
+	struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr);
+	return a->store ? a->store(ls, buf, len) : len;
+}
+
+static struct sysfs_ops gdlm_attr_ops = {
+	.show  = gdlm_attr_show,
+	.store = gdlm_attr_store,
+};
+
+static struct kobj_type gdlm_ktype = {
+	.default_attrs = gdlm_attrs,
+	.sysfs_ops     = &gdlm_attr_ops,
+};
+
+static struct kset gdlm_kset = {
+	.subsys = &kernel_subsys,
+	.kobj   = {.name = "lock_dlm",},
+	.ktype  = &gdlm_ktype,
+};
+
+int gdlm_kobject_setup(struct gdlm_ls *ls, struct kobject *fskobj)
+{
+	int error;
+
+	error = kobject_set_name(&ls->kobj, "%s", "lock_module");
+	if (error) {
+		log_error("can't set kobj name %d", error);
+		return error;
+	}
+
+	ls->kobj.kset = &gdlm_kset;
+	ls->kobj.ktype = &gdlm_ktype;
+	ls->kobj.parent = fskobj;
+
+	error = kobject_register(&ls->kobj);
+	if (error)
+		log_error("can't register kobj %d", error);
+
+	return error;
+}
+
+void gdlm_kobject_release(struct gdlm_ls *ls)
+{
+	kobject_unregister(&ls->kobj);
+}
+
+int gdlm_sysfs_init(void)
+{
+	int error;
+
+	error = kset_register(&gdlm_kset);
+	if (error)
+		printk("lock_dlm: cannot register kset %d\n", error);
+
+	return error;
+}
+
+void gdlm_sysfs_exit(void)
+{
+	kset_unregister(&gdlm_kset);
+}
+

fs/gfs2/locking/dlm/thread.c

@@ -0,0 +1,359 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+/* A lock placed on this queue is re-submitted to DLM as soon as the lock_dlm
+   thread gets to it. */
+
+static void queue_submit(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->delay_list, &ls->submit);
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+static void process_blocking(struct gdlm_lock *lp, int bast_mode)
+{
+	struct gdlm_ls *ls = lp->ls;
+	unsigned int cb = 0;
+
+	switch (gdlm_make_lmstate(bast_mode)) {
+	case LM_ST_EXCLUSIVE:
+		cb = LM_CB_NEED_E;
+		break;
+	case LM_ST_DEFERRED:
+		cb = LM_CB_NEED_D;
+		break;
+	case LM_ST_SHARED:
+		cb = LM_CB_NEED_S;
+		break;
+	default:
+		gdlm_assert(0, "unknown bast mode %u", lp->bast_mode);
+	}
+
+	ls->fscb(ls->sdp, cb, &lp->lockname);
+}
+
+static void process_complete(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	struct lm_async_cb acb;
+	s16 prev_mode = lp->cur;
+
+	memset(&acb, 0, sizeof(acb));
+
+	if (lp->lksb.sb_status == -DLM_ECANCEL) {
+		log_info("complete dlm cancel %x,%llx flags %lx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number,
+			 lp->flags);
+
+		lp->req = lp->cur;
+		acb.lc_ret |= LM_OUT_CANCELED;
+		if (lp->cur == DLM_LOCK_IV)
+			lp->lksb.sb_lkid = 0;
+		goto out;
+	}
+
+	if (test_and_clear_bit(LFL_DLM_UNLOCK, &lp->flags)) {
+		if (lp->lksb.sb_status != -DLM_EUNLOCK) {
+			log_info("unlock sb_status %d %x,%llx flags %lx",
+				 lp->lksb.sb_status, lp->lockname.ln_type,
+				 (unsigned long long)lp->lockname.ln_number,
+				 lp->flags);
+			return;
+		}
+
+		lp->cur = DLM_LOCK_IV;
+		lp->req = DLM_LOCK_IV;
+		lp->lksb.sb_lkid = 0;
+
+		if (test_and_clear_bit(LFL_UNLOCK_DELETE, &lp->flags)) {
+			gdlm_delete_lp(lp);
+			return;
+		}
+		goto out;
+	}
+
+	if (lp->lksb.sb_flags & DLM_SBF_VALNOTVALID)
+		memset(lp->lksb.sb_lvbptr, 0, GDLM_LVB_SIZE);
+
+	if (lp->lksb.sb_flags & DLM_SBF_ALTMODE) {
+		if (lp->req == DLM_LOCK_PR)
+			lp->req = DLM_LOCK_CW;
+		else if (lp->req == DLM_LOCK_CW)
+			lp->req = DLM_LOCK_PR;
+	}
+
+	/*
+	 * A canceled lock request.  The lock was just taken off the delayed
+	 * list and was never even submitted to dlm.
+	 */
+
+	if (test_and_clear_bit(LFL_CANCEL, &lp->flags)) {
+		log_info("complete internal cancel %x,%llx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number);
+		lp->req = lp->cur;
+		acb.lc_ret |= LM_OUT_CANCELED;
+		goto out;
+	}
+
+	/*
+	 * An error occured.
+	 */
+
+	if (lp->lksb.sb_status) {
+		/* a "normal" error */
+		if ((lp->lksb.sb_status == -EAGAIN) &&
+		    (lp->lkf & DLM_LKF_NOQUEUE)) {
+			lp->req = lp->cur;
+			if (lp->cur == DLM_LOCK_IV)
+				lp->lksb.sb_lkid = 0;
+			goto out;
+		}
+
+		/* this could only happen with cancels I think */
+		log_info("ast sb_status %d %x,%llx flags %lx",
+			 lp->lksb.sb_status, lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number,
+			 lp->flags);
+		return;
+	}
+
+	/*
+	 * This is an AST for an EX->EX conversion for sync_lvb from GFS.
+	 */
+
+	if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) {
+		complete(&lp->ast_wait);
+		return;
+	}
+
+	/*
+	 * A lock has been demoted to NL because it initially completed during
+	 * BLOCK_LOCKS.  Now it must be requested in the originally requested
+	 * mode.
+	 */
+
+	if (test_and_clear_bit(LFL_REREQUEST, &lp->flags)) {
+		gdlm_assert(lp->req == DLM_LOCK_NL, "%x,%llx",
+			    lp->lockname.ln_type,
+			    (unsigned long long)lp->lockname.ln_number);
+		gdlm_assert(lp->prev_req > DLM_LOCK_NL, "%x,%llx",
+			    lp->lockname.ln_type,
+			    (unsigned long long)lp->lockname.ln_number);
+
+		lp->cur = DLM_LOCK_NL;
+		lp->req = lp->prev_req;
+		lp->prev_req = DLM_LOCK_IV;
+		lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+		set_bit(LFL_NOCACHE, &lp->flags);
+
+		if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+		    !test_bit(LFL_NOBLOCK, &lp->flags))
+			gdlm_queue_delayed(lp);
+		else
+			queue_submit(lp);
+		return;
+	}
+
+	/*
+	 * A request is granted during dlm recovery.  It may be granted
+	 * because the locks of a failed node were cleared.  In that case,
+	 * there may be inconsistent data beneath this lock and we must wait
+	 * for recovery to complete to use it.  When gfs recovery is done this
+	 * granted lock will be converted to NL and then reacquired in this
+	 * granted state.
+	 */
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+	    !test_bit(LFL_NOBLOCK, &lp->flags) &&
+	    lp->req != DLM_LOCK_NL) {
+
+		lp->cur = lp->req;
+		lp->prev_req = lp->req;
+		lp->req = DLM_LOCK_NL;
+		lp->lkf |= DLM_LKF_CONVERT;
+		lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+		log_debug("rereq %x,%llx id %x %d,%d",
+			  lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number,
+			  lp->lksb.sb_lkid, lp->cur, lp->req);
+
+		set_bit(LFL_REREQUEST, &lp->flags);
+		queue_submit(lp);
+		return;
+	}
+
+	/*
+	 * DLM demoted the lock to NL before it was granted so GFS must be
+	 * told it cannot cache data for this lock.
+	 */
+
+	if (lp->lksb.sb_flags & DLM_SBF_DEMOTED)
+		set_bit(LFL_NOCACHE, &lp->flags);
+
+out:
+	/*
+	 * This is an internal lock_dlm lock
+	 */
+
+	if (test_bit(LFL_INLOCK, &lp->flags)) {
+		clear_bit(LFL_NOBLOCK, &lp->flags);
+		lp->cur = lp->req;
+		complete(&lp->ast_wait);
+		return;
+	}
+
+	/*
+	 * Normal completion of a lock request.  Tell GFS it now has the lock.
+	 */
+
+	clear_bit(LFL_NOBLOCK, &lp->flags);
+	lp->cur = lp->req;
+
+	acb.lc_name = lp->lockname;
+	acb.lc_ret |= gdlm_make_lmstate(lp->cur);
+
+	if (!test_and_clear_bit(LFL_NOCACHE, &lp->flags) &&
+	    (lp->cur > DLM_LOCK_NL) && (prev_mode > DLM_LOCK_NL))
+		acb.lc_ret |= LM_OUT_CACHEABLE;
+
+	ls->fscb(ls->sdp, LM_CB_ASYNC, &acb);
+}
+
+static inline int no_work(struct gdlm_ls *ls, int blocking)
+{
+	int ret;
+
+	spin_lock(&ls->async_lock);
+	ret = list_empty(&ls->complete) && list_empty(&ls->submit);
+	if (ret && blocking)
+		ret = list_empty(&ls->blocking);
+	spin_unlock(&ls->async_lock);
+
+	return ret;
+}
+
+static inline int check_drop(struct gdlm_ls *ls)
+{
+	if (!ls->drop_locks_count)
+		return 0;
+
+	if (time_after(jiffies, ls->drop_time + ls->drop_locks_period * HZ)) {
+		ls->drop_time = jiffies;
+		if (ls->all_locks_count >= ls->drop_locks_count)
+			return 1;
+	}
+	return 0;
+}
+
+static int gdlm_thread(void *data)
+{
+	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);
+		if (no_work(ls, blist))
+			schedule();
+		remove_wait_queue(&ls->thread_wait, &wait);
+		set_current_state(TASK_RUNNING);
+
+		complete = blocking = submit = drop = 0;
+
+		spin_lock(&ls->async_lock);
+
+		if (blist && !list_empty(&ls->blocking)) {
+			lp = list_entry(ls->blocking.next, struct gdlm_lock,
+					blist);
+			list_del_init(&lp->blist);
+			blocking = lp->bast_mode;
+			lp->bast_mode = 0;
+		} else if (!list_empty(&ls->complete)) {
+			lp = list_entry(ls->complete.next, struct gdlm_lock,
+					clist);
+			list_del_init(&lp->clist);
+			complete = 1;
+		} else if (!list_empty(&ls->submit)) {
+			lp = list_entry(ls->submit.next, struct gdlm_lock,
+					delay_list);
+			list_del_init(&lp->delay_list);
+			submit = 1;
+		}
+
+		drop = check_drop(ls);
+		spin_unlock(&ls->async_lock);
+
+		if (complete)
+			process_complete(lp);
+
+		else if (blocking)
+			process_blocking(lp, blocking);
+
+		else if (submit)
+			gdlm_do_lock(lp);
+
+		if (drop)
+			ls->fscb(ls->sdp, LM_CB_DROPLOCKS, NULL);
+
+		schedule();
+	}
+
+	return 0;
+}
+
+int gdlm_init_threads(struct gdlm_ls *ls)
+{
+	struct task_struct *p;
+	int error;
+
+	p = kthread_run(gdlm_thread, ls, "lock_dlm1");
+	error = IS_ERR(p);
+	if (error) {
+		log_error("can't start lock_dlm1 thread %d", error);
+		return error;
+	}
+	ls->thread1 = p;
+
+	p = kthread_run(gdlm_thread, ls, "lock_dlm2");
+	error = IS_ERR(p);
+	if (error) {
+		log_error("can't start lock_dlm2 thread %d", error);
+		kthread_stop(ls->thread1);
+		return error;
+	}
+	ls->thread2 = p;
+
+	return 0;
+}
+
+void gdlm_release_threads(struct gdlm_ls *ls)
+{
+	kthread_stop(ls->thread1);
+	kthread_stop(ls->thread2);
+}
+

fs/gfs2/locking/nolock/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += lock_nolock.o
+lock_nolock-y := main.o
+

fs/gfs2/locking/nolock/main.c

@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/lm_interface.h>
+
+struct nolock_lockspace {
+	unsigned int nl_lvb_size;
+};
+
+static const struct lm_lockops nolock_ops;
+
+static int nolock_mount(char *table_name, char *host_data,
+			lm_callback_t cb, void *cb_data,
+			unsigned int min_lvb_size, int flags,
+			struct lm_lockstruct *lockstruct,
+			struct kobject *fskobj)
+{
+	char *c;
+	unsigned int jid;
+	struct nolock_lockspace *nl;
+
+	c = strstr(host_data, "jid=");
+	if (!c)
+		jid = 0;
+	else {
+		c += 4;
+		sscanf(c, "%u", &jid);
+	}
+
+	nl = kzalloc(sizeof(struct nolock_lockspace), GFP_KERNEL);
+	if (!nl)
+		return -ENOMEM;
+
+	nl->nl_lvb_size = min_lvb_size;
+
+	lockstruct->ls_jid = jid;
+	lockstruct->ls_first = 1;
+	lockstruct->ls_lvb_size = min_lvb_size;
+	lockstruct->ls_lockspace = nl;
+	lockstruct->ls_ops = &nolock_ops;
+	lockstruct->ls_flags = LM_LSFLAG_LOCAL;
+
+	return 0;
+}
+
+static void nolock_others_may_mount(void *lockspace)
+{
+}
+
+static void nolock_unmount(void *lockspace)
+{
+	struct nolock_lockspace *nl = lockspace;
+	kfree(nl);
+}
+
+static void nolock_withdraw(void *lockspace)
+{
+}
+
+/**
+ * nolock_get_lock - get a lm_lock_t given a descripton of the lock
+ * @lockspace: the lockspace the lock lives in
+ * @name: the name of the lock
+ * @lockp: return the lm_lock_t here
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+static int nolock_get_lock(void *lockspace, struct lm_lockname *name,
+			   void **lockp)
+{
+	*lockp = lockspace;
+	return 0;
+}
+
+/**
+ * nolock_put_lock - get rid of a lock structure
+ * @lock: the lock to throw away
+ *
+ */
+
+static void nolock_put_lock(void *lock)
+{
+}
+
+/**
+ * nolock_lock - acquire a lock
+ * @lock: the lock to manipulate
+ * @cur_state: the current state
+ * @req_state: the requested state
+ * @flags: modifier flags
+ *
+ * Returns: A bitmap of LM_OUT_*
+ */
+
+static unsigned int nolock_lock(void *lock, unsigned int cur_state,
+				unsigned int req_state, unsigned int flags)
+{
+	return req_state | LM_OUT_CACHEABLE;
+}
+
+/**
+ * nolock_unlock - unlock a lock
+ * @lock: the lock to manipulate
+ * @cur_state: the current state
+ *
+ * Returns: 0
+ */
+
+static unsigned int nolock_unlock(void *lock, unsigned int cur_state)
+{
+	return 0;
+}
+
+static void nolock_cancel(void *lock)
+{
+}
+
+/**
+ * nolock_hold_lvb - hold on to a lock value block
+ * @lock: the lock the LVB is associated with
+ * @lvbp: return the lm_lvb_t here
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+static int nolock_hold_lvb(void *lock, char **lvbp)
+{
+	struct nolock_lockspace *nl = lock;
+	int error = 0;
+
+	*lvbp = kzalloc(nl->nl_lvb_size, GFP_KERNEL);
+	if (!*lvbp)
+		error = -ENOMEM;
+
+	return error;
+}
+
+/**
+ * nolock_unhold_lvb - release a LVB
+ * @lock: the lock the LVB is associated with
+ * @lvb: the lock value block
+ *
+ */
+
+static void nolock_unhold_lvb(void *lock, char *lvb)
+{
+	kfree(lvb);
+}
+
+static int nolock_plock_get(void *lockspace, struct lm_lockname *name,
+			    struct file *file, struct file_lock *fl)
+{
+	struct file_lock tmp;
+	int ret;
+
+	ret = posix_test_lock(file, fl, &tmp);
+	fl->fl_type = F_UNLCK;
+	if (ret)
+		memcpy(fl, &tmp, sizeof(struct file_lock));
+
+	return 0;
+}
+
+static int nolock_plock(void *lockspace, struct lm_lockname *name,
+			struct file *file, int cmd, struct file_lock *fl)
+{
+	int error;
+	error = posix_lock_file_wait(file, fl);
+	return error;
+}
+
+static int nolock_punlock(void *lockspace, struct lm_lockname *name,
+			  struct file *file, struct file_lock *fl)
+{
+	int error;
+	error = posix_lock_file_wait(file, fl);
+	return error;
+}
+
+static void nolock_recovery_done(void *lockspace, unsigned int jid,
+				 unsigned int message)
+{
+}
+
+static const struct lm_lockops nolock_ops = {
+	.lm_proto_name = "lock_nolock",
+	.lm_mount = nolock_mount,
+	.lm_others_may_mount = nolock_others_may_mount,
+	.lm_unmount = nolock_unmount,
+	.lm_withdraw = nolock_withdraw,
+	.lm_get_lock = nolock_get_lock,
+	.lm_put_lock = nolock_put_lock,
+	.lm_lock = nolock_lock,
+	.lm_unlock = nolock_unlock,
+	.lm_cancel = nolock_cancel,
+	.lm_hold_lvb = nolock_hold_lvb,
+	.lm_unhold_lvb = nolock_unhold_lvb,
+	.lm_plock_get = nolock_plock_get,
+	.lm_plock = nolock_plock,
+	.lm_punlock = nolock_punlock,
+	.lm_recovery_done = nolock_recovery_done,
+	.lm_owner = THIS_MODULE,
+};
+
+static int __init init_nolock(void)
+{
+	int error;
+
+	error = gfs2_register_lockproto(&nolock_ops);
+	if (error) {
+		printk(KERN_WARNING
+		       "lock_nolock: can't register protocol: %d\n", error);
+		return error;
+	}
+
+	printk(KERN_INFO
+	       "Lock_Nolock (built %s %s) installed\n", __DATE__, __TIME__);
+	return 0;
+}
+
+static void __exit exit_nolock(void)
+{
+	gfs2_unregister_lockproto(&nolock_ops);
+}
+
+module_init(init_nolock);
+module_exit(exit_nolock);
+
+MODULE_DESCRIPTION("GFS Nolock Locking Module");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+

fs/gfs2/log.c

@@ -0,0 +1,711 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+#include <linux/delay.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "util.h"
+#include "dir.h"
+
+#define PULL 1
+
+/**
+ * gfs2_struct2blk - compute stuff
+ * @sdp: the filesystem
+ * @nstruct: the number of structures
+ * @ssize: the size of the structures
+ *
+ * Compute the number of log descriptor blocks needed to hold a certain number
+ * of structures of a certain size.
+ *
+ * Returns: the number of blocks needed (minimum is always 1)
+ */
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			     unsigned int ssize)
+{
+	unsigned int blks;
+	unsigned int first, second;
+
+	blks = 1;
+	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+
+	if (nstruct > first) {
+		second = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / ssize;
+		blks += DIV_ROUND_UP(nstruct - first, second);
+	}
+
+	return blks;
+}
+
+/**
+ * gfs2_ail1_start_one - Start I/O on a part of the AIL
+ * @sdp: the filesystem
+ * @tr: the part of the AIL
+ *
+ */
+
+static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+	int retry;
+
+	BUG_ON(!spin_is_locked(&sdp->sd_log_lock));
+
+	do {
+		retry = 0;
+
+		list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+						 bd_ail_st_list) {
+			bh = bd->bd_bh;
+
+			gfs2_assert(sdp, bd->bd_ail == ai);
+
+			if (!buffer_busy(bh)) {
+				if (!buffer_uptodate(bh)) {
+					gfs2_log_unlock(sdp);
+					gfs2_io_error_bh(sdp, bh);
+					gfs2_log_lock(sdp);
+				}
+				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+				continue;
+			}
+
+			if (!buffer_dirty(bh))
+				continue;
+
+			list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+
+			gfs2_log_unlock(sdp);
+			wait_on_buffer(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			gfs2_log_lock(sdp);
+
+			retry = 1;
+			break;
+		}
+	} while (retry);
+}
+
+/**
+ * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+					 bd_ail_st_list) {
+		bh = bd->bd_bh;
+
+		gfs2_assert(sdp, bd->bd_ail == ai);
+
+		if (buffer_busy(bh)) {
+			if (flags & DIO_ALL)
+				continue;
+			else
+				break;
+		}
+
+		if (!buffer_uptodate(bh))
+			gfs2_io_error_bh(sdp, bh);
+
+		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+	}
+
+	return list_empty(&ai->ai_ail1_list);
+}
+
+static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
+{
+	struct list_head *head = &sdp->sd_ail1_list;
+	u64 sync_gen;
+	struct list_head *first;
+	struct gfs2_ail *first_ai, *ai, *tmp;
+	int done = 0;
+
+	gfs2_log_lock(sdp);
+	if (list_empty(head)) {
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	sync_gen = sdp->sd_ail_sync_gen++;
+
+	first = head->prev;
+	first_ai = list_entry(first, struct gfs2_ail, ai_list);
+	first_ai->ai_sync_gen = sync_gen;
+	gfs2_ail1_start_one(sdp, first_ai); /* This may drop log lock */
+
+	if (flags & DIO_ALL)
+		first = NULL;
+
+	while(!done) {
+		if (first && (head->prev != first ||
+			      gfs2_ail1_empty_one(sdp, first_ai, 0)))
+			break;
+
+		done = 1;
+		list_for_each_entry_safe_reverse(ai, tmp, head, ai_list) {
+			if (ai->ai_sync_gen >= sync_gen)
+				continue;
+			ai->ai_sync_gen = sync_gen;
+			gfs2_ail1_start_one(sdp, ai); /* This may drop log lock */
+			done = 0;
+			break;
+		}
+	}
+
+	gfs2_log_unlock(sdp);
+}
+
+int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
+{
+	struct gfs2_ail *ai, *s;
+	int ret;
+
+	gfs2_log_lock(sdp);
+
+	list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
+		if (gfs2_ail1_empty_one(sdp, ai, flags))
+			list_move(&ai->ai_list, &sdp->sd_ail2_list);
+		else if (!(flags & DIO_ALL))
+			break;
+	}
+
+	ret = list_empty(&sdp->sd_ail1_list);
+
+	gfs2_log_unlock(sdp);
+
+	return ret;
+}
+
+
+/**
+ * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &ai->ai_ail2_list;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		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);
+	}
+}
+
+static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	struct gfs2_ail *ai, *safe;
+	unsigned int old_tail = sdp->sd_log_tail;
+	int wrap = (new_tail < old_tail);
+	int a, b, rm;
+
+	gfs2_log_lock(sdp);
+
+	list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
+		a = (old_tail <= ai->ai_first);
+		b = (ai->ai_first < new_tail);
+		rm = (wrap) ? (a || b) : (a && b);
+		if (!rm)
+			continue;
+
+		gfs2_ail2_empty_one(sdp, ai);
+		list_del(&ai->ai_list);
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
+		kfree(ai);
+	}
+
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_reserve - Make a log reservation
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks to reserve
+ *
+ * Note that we never give out the last 6 blocks of the journal. Thats
+ * due to the fact that there is are a small number of header blocks
+ * associated with each log flush. The exact number can't be known until
+ * flush time, so we ensure that we have just enough free blocks at all
+ * times to avoid running out during a log flush.
+ *
+ * Returns: errno
+ */
+
+int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
+{
+	unsigned int try = 0;
+
+	if (gfs2_assert_warn(sdp, blks) ||
+	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
+		return -EINVAL;
+
+	mutex_lock(&sdp->sd_log_reserve_mutex);
+	gfs2_log_lock(sdp);
+	while(sdp->sd_log_blks_free <= (blks + 6)) {
+		gfs2_log_unlock(sdp);
+		gfs2_ail1_empty(sdp, 0);
+		gfs2_log_flush(sdp, NULL);
+
+		if (try++)
+			gfs2_ail1_start(sdp, 0);
+		gfs2_log_lock(sdp);
+	}
+	sdp->sd_log_blks_free -= blks;
+	gfs2_log_unlock(sdp);
+	mutex_unlock(&sdp->sd_log_reserve_mutex);
+
+	down_read(&sdp->sd_log_flush_lock);
+
+	return 0;
+}
+
+/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_blks_free += blks;
+	gfs2_assert_withdraw(sdp,
+			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+	gfs2_log_unlock(sdp);
+	up_read(&sdp->sd_log_flush_lock);
+}
+
+static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+{
+	struct inode *inode = sdp->sd_jdesc->jd_inode;
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	bh_map.b_size = 1 << inode->i_blkbits;
+	error = gfs2_block_map(inode, lbn, 0, &bh_map);
+	if (error || !bh_map.b_blocknr)
+		printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error,
+		       (unsigned long long)bh_map.b_blocknr, lbn);
+	gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr);
+
+	return bh_map.b_blocknr;
+}
+
+/**
+ * log_distance - Compute distance between two journal blocks
+ * @sdp: The GFS2 superblock
+ * @newer: The most recent journal block of the pair
+ * @older: The older journal block of the pair
+ *
+ *   Compute the distance (in the journal direction) between two
+ *   blocks in the journal
+ *
+ * Returns: the distance in blocks
+ */
+
+static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
+					unsigned int older)
+{
+	int dist;
+
+	dist = newer - older;
+	if (dist < 0)
+		dist += sdp->sd_jdesc->jd_blocks;
+
+	return dist;
+}
+
+static unsigned int current_tail(struct gfs2_sbd *sdp)
+{
+	struct gfs2_ail *ai;
+	unsigned int tail;
+
+	gfs2_log_lock(sdp);
+
+	if (list_empty(&sdp->sd_ail1_list)) {
+		tail = sdp->sd_log_head;
+	} else {
+		ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
+		tail = ai->ai_first;
+	}
+
+	gfs2_log_unlock(sdp);
+
+	return tail;
+}
+
+static inline void 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);
+
+	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
+		sdp->sd_log_flush_head = 0;
+		sdp->sd_log_flush_wrapped = 1;
+	}
+}
+
+/**
+ * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the buffer_head
+ */
+
+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);
+	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);
+
+	return bh;
+}
+
+/**
+ * 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
+ *
+ * Returns: the log buffer descriptor
+ */
+
+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);
+	atomic_set(&bh->b_count, 1);
+	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate);
+	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;
+
+	log_incr_head(sdp);
+
+	return bh;
+}
+
+static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail, int pull)
+{
+	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+
+	ail2_empty(sdp, new_tail);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_blks_free += dist - (pull ? 1 : 0);
+	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+	gfs2_log_unlock(sdp);
+
+	sdp->sd_log_tail = new_tail;
+}
+
+/**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+	struct gfs2_log_header *lh;
+	unsigned int tail;
+	u32 hash;
+
+	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);
+
+	gfs2_ail1_empty(sdp, 0);
+	tail = current_tail(sdp);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
+	lh->lh_flags = cpu_to_be32(flags);
+	lh->lh_tail = cpu_to_be32(tail);
+	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	set_buffer_dirty(bh);
+	if (sync_dirty_buffer(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	if (sdp->sd_log_tail != tail)
+		log_pull_tail(sdp, tail, pull);
+	else
+		gfs2_assert_withdraw(sdp, !pull);
+
+	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+	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;
+
+	while (!list_empty(head)) {
+		lb = list_entry(head->next, struct gfs2_log_buf, lb_list);
+		list_del(&lb->lb_list);
+		bh = lb->lb_bh;
+
+		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
+			brelse(bh);
+		kfree(lb);
+	}
+
+	log_write_header(sdp, 0, 0);
+}
+
+/**
+ * gfs2_log_flush - flush incore transaction(s)
+ * @sdp: the filesystem
+ * @gl: The glock structure to flush.  If NULL, flush the whole incore log
+ *
+ */
+
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+{
+	struct gfs2_ail *ai;
+
+	down_write(&sdp->sd_log_flush_lock);
+
+	if (gl) {
+		gfs2_log_lock(sdp);
+		if (list_empty(&gl->gl_le.le_list)) {
+			gfs2_log_unlock(sdp);
+			up_write(&sdp->sd_log_flush_lock);
+			return;
+		}
+		gfs2_log_unlock(sdp);
+	}
+
+	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
+	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_commited_buf);
+	gfs2_assert_withdraw(sdp,
+			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+	ai->ai_first = sdp->sd_log_flush_head;
+
+	lops_before_commit(sdp);
+	if (!list_empty(&sdp->sd_log_flush_list))
+		log_flush_commit(sdp);
+	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle)
+		log_write_header(sdp, 0, PULL);
+	lops_after_commit(sdp, ai);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_blks_free -= sdp->sd_log_num_hdrs;
+	sdp->sd_log_blks_reserved = 0;
+	sdp->sd_log_commited_buf = 0;
+	sdp->sd_log_num_hdrs = 0;
+	sdp->sd_log_commited_revoke = 0;
+
+	if (!list_empty(&ai->ai_ail1_list)) {
+		list_add(&ai->ai_list, &sdp->sd_ail1_list);
+		ai = NULL;
+	}
+	gfs2_log_unlock(sdp);
+
+	sdp->sd_vfs->s_dirt = 0;
+	up_write(&sdp->sd_log_flush_lock);
+
+	kfree(ai);
+}
+
+static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int reserved = 0;
+	unsigned int old;
+
+	gfs2_log_lock(sdp);
+
+	sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
+	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_buf) >= 0);
+	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0);
+
+	if (sdp->sd_log_commited_buf)
+		reserved += sdp->sd_log_commited_buf;
+	if (sdp->sd_log_commited_revoke)
+		reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+					    sizeof(u64));
+	if (reserved)
+		reserved++;
+
+	old = sdp->sd_log_blks_free;
+	sdp->sd_log_blks_free += tr->tr_reserved -
+				 (reserved - sdp->sd_log_blks_reserved);
+
+	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old);
+	gfs2_assert_withdraw(sdp,
+			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks +
+			     sdp->sd_log_num_hdrs);
+
+	sdp->sd_log_blks_reserved = reserved;
+
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_commit - Commit a transaction to the log
+ * @sdp: the filesystem
+ * @tr: the transaction
+ *
+ * Returns: errno
+ */
+
+void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	log_refund(sdp, tr);
+	lops_incore_commit(sdp, tr);
+
+	sdp->sd_vfs->s_dirt = 1;
+	up_read(&sdp->sd_log_flush_lock);
+
+	gfs2_log_lock(sdp);
+	if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks))
+		wake_up_process(sdp->sd_logd_process);
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_shutdown - write a shutdown header into a journal
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+{
+	down_write(&sdp->sd_log_flush_lock);
+
+	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);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_hdrs);
+	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+
+	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, 0);
+
+	gfs2_assert_warn(sdp, sdp->sd_log_blks_free == sdp->sd_jdesc->jd_blocks);
+	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
+	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
+
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_tail = sdp->sd_log_head;
+
+	up_write(&sdp->sd_log_flush_lock);
+}
+
+
+/**
+ * gfs2_meta_syncfs - sync all the buffers in a filesystem
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
+{
+	gfs2_log_flush(sdp, NULL);
+	for (;;) {
+		gfs2_ail1_start(sdp, DIO_ALL);
+		if (gfs2_ail1_empty(sdp, DIO_ALL))
+			break;
+		msleep(10);
+	}
+}
+

fs/gfs2/log.h

@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOG_DOT_H__
+#define __LOG_DOT_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include "incore.h"
+
+/**
+ * gfs2_log_lock - acquire the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_lock(struct gfs2_sbd *sdp)
+{
+	spin_lock(&sdp->sd_log_lock);
+}
+
+/**
+ * gfs2_log_unlock - release the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_unlock(struct gfs2_sbd *sdp)
+{
+	spin_unlock(&sdp->sd_log_lock);
+}
+
+static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
+					  unsigned int value)
+{
+	if (++value == sdp->sd_jdesc->jd_blocks) {
+		value = 0;
+	}
+	sdp->sd_log_head = sdp->sd_log_tail = value;
+}
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			    unsigned int ssize);
+
+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);
+
+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_log_shutdown(struct gfs2_sbd *sdp);
+void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
+
+#endif /* __LOG_DOT_H__ */

fs/gfs2/lops.c

@@ -0,0 +1,823 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+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;
+
+	tr->tr_touched = 1;
+
+	if (!list_empty(&le->le_list))
+		return;
+
+	gl = container_of(le, struct gfs2_glock, gl_le);
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
+		return;
+	gfs2_glock_hold(gl);
+	set_bit(GLF_DIRTY, &gl->gl_flags);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_num_gl++;
+	list_add(&le->le_list, &sdp->sd_log_le_gl);
+	gfs2_log_unlock(sdp);
+}
+
+static void glock_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_gl;
+	struct gfs2_glock *gl;
+
+	while (!list_empty(head)) {
+		gl = list_entry(head->next, struct gfs2_glock, gl_le.le_list);
+		list_del_init(&gl->gl_le.le_list);
+		sdp->sd_log_num_gl--;
+
+		gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl));
+		gfs2_glock_put(gl);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_gl);
+}
+
+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;
+
+	gfs2_log_lock(sdp);
+	if (!list_empty(&bd->bd_list_tr)) {
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	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);
+
+	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++;
+}
+
+static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head = &tr->tr_list_buf;
+	struct gfs2_bufdata *bd;
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr);
+		list_del_init(&bd->bd_list_tr);
+		tr->tr_num_buf--;
+	}
+	gfs2_log_unlock(sdp);
+	gfs2_assert_warn(sdp, !tr->tr_num_buf);
+}
+
+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 = sizeof(struct gfs2_log_descriptor);
+	unsigned int limit;
+	unsigned int num;
+	unsigned n;
+	__be64 *ptr;
+
+	offset += sizeof(__be64) - 1;
+	offset &= ~(sizeof(__be64) - 1);
+	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+	/* for 4k blocks, limit = 503 */
+
+	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);
+		sdp->sd_log_num_hdrs++;
+		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);
+		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,
+					     bd_le.le_list) {
+			*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
+			if (++n >= num)
+				break;
+		}
+
+		set_buffer_dirty(bh);
+		ll_rw_block(WRITE, 1, &bh);
+
+		n = 0;
+		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
+					     bd_le.le_list) {
+			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			if (++n >= num)
+				break;
+		}
+
+		total -= num;
+	}
+}
+
+static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_buf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
+		sdp->sd_log_num_buf--;
+
+		gfs2_unpin(sdp, bd->bd_bh, ai);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_buf);
+}
+
+static void buf_lo_before_scan(struct gfs2_jdesc *jd,
+			       struct gfs2_log_header_host *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_blocks = 0;
+	sdp->sd_replayed_blocks = 0;
+}
+
+static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				struct gfs2_log_descriptor *ld, __be64 *ptr,
+				int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		if (gfs2_meta_check(sdp, bh_ip))
+			error = -EIO;
+		else
+			mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
+	        jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_trans *tr;
+
+	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)
+{
+	struct gfs2_log_descriptor *ld;
+	struct gfs2_meta_header *mh;
+	struct buffer_head *bh;
+	unsigned int offset;
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_revoke *rv;
+
+	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);
+	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);
+		sdp->sd_log_num_revoke--;
+
+		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+
+			bh = gfs2_log_get_buf(sdp);
+			mh = (struct gfs2_meta_header *)bh->b_data;
+			mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+			mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
+			mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
+			offset = sizeof(struct gfs2_meta_header);
+		}
+
+		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno);
+		kfree(rv);
+
+		offset += sizeof(u64);
+	}
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+
+	set_buffer_dirty(bh);
+	ll_rw_block(WRITE, 1, &bh);
+}
+
+static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
+				  struct gfs2_log_header_host *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_revokes = 0;
+	sdp->sd_replay_tail = head->lh_tail;
+}
+
+static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				   struct gfs2_log_descriptor *ld, __be64 *ptr,
+				   int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int blks = be32_to_cpu(ld->ld_length);
+	unsigned int revokes = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh;
+	unsigned int offset;
+	u64 blkno;
+	int first = 1;
+	int error;
+
+	if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
+		return 0;
+
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+
+		if (!first)
+			gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);
+
+		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
+			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
+
+			error = gfs2_revoke_add(sdp, blkno, start);
+			if (error < 0)
+				return error;
+			else if (error)
+				sdp->sd_found_revokes++;
+
+			if (!--revokes)
+				break;
+			offset += sizeof(u64);
+		}
+
+		brelse(bh);
+		offset = sizeof(struct gfs2_meta_header);
+		first = 0;
+	}
+
+	return 0;
+}
+
+static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_revoke_clean(sdp);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
+	        jd->jd_jid, sdp->sd_found_revokes);
+
+	gfs2_revoke_clean(sdp);
+}
+
+static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_trans *tr = current->journal_info;
+
+	tr->tr_touched = 1;
+
+	if (!list_empty(&le->le_list))
+		return;
+
+	rgd = container_of(le, struct gfs2_rgrpd, rd_le);
+	gfs2_rgrp_bh_hold(rgd);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_num_rg++;
+	list_add(&le->le_list, &sdp->sd_log_le_rg);
+	gfs2_log_unlock(sdp);
+}
+
+static void rg_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_rg;
+	struct gfs2_rgrpd *rgd;
+
+	while (!list_empty(head)) {
+		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_le.le_list);
+		list_del_init(&rgd->rd_le.le_list);
+		sdp->sd_log_num_rg--;
+
+		gfs2_rgrp_repolish_clones(rgd);
+		gfs2_rgrp_bh_put(rgd);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_rg);
+}
+
+/**
+ * databuf_lo_add - Add a databuf to the transaction.
+ *
+ * This is used in two distinct cases:
+ * i) In ordered write mode
+ *    We put the data buffer on a list so that we can ensure that its
+ *    synced to disk at the right time
+ * ii) In journaled data mode
+ *    We need to journal the data block in the same way as metadata in
+ *    the functions above. The difference is that here we have a tag
+ *    which is two __be64's being the block number (as per meta data)
+ *    and a flag which says whether the data block needs escaping or
+ *    not. This means we need a new log entry for each 251 or so data
+ *    blocks, which isn't an enormous overhead but twice as much as
+ *    for normal metadata blocks.
+ */
+static void databuf_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 = current->journal_info;
+	struct address_space *mapping = bd->bd_bh->b_page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+
+	gfs2_log_lock(sdp);
+	tr->tr_touched = 1;
+	if (list_empty(&bd->bd_list_tr) &&
+	    (ip->i_di.di_flags & GFS2_DIF_JDATA)) {
+		tr->tr_num_buf++;
+		list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+		gfs2_log_unlock(sdp);
+		gfs2_pin(sdp, bd->bd_bh);
+		tr->tr_num_buf_new++;
+	} else {
+		gfs2_log_unlock(sdp);
+	}
+	gfs2_trans_add_gl(bd->bd_gl);
+	gfs2_log_lock(sdp);
+	if (list_empty(&le->le_list)) {
+		if (ip->i_di.di_flags & GFS2_DIF_JDATA)
+			sdp->sd_log_num_jdata++;
+		sdp->sd_log_num_databuf++;
+		list_add(&le->le_list, &sdp->sd_log_le_databuf);
+	}
+	gfs2_log_unlock(sdp);
+}
+
+static int 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);
+	ptr = kaddr + bh_offset(bh);
+	if (*ptr == cpu_to_be32(GFS2_MAGIC))
+		rv = 1;
+	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)
+{
+	LIST_HEAD(started);
+	struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt;
+	struct buffer_head *bh = NULL,*bh1 = NULL;
+	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	struct gfs2_log_descriptor *ld;
+	unsigned int limit;
+	unsigned int total_dbuf = sdp->sd_log_num_databuf;
+	unsigned int total_jdata = sdp->sd_log_num_jdata;
+	unsigned int num, n;
+	__be64 *ptr = NULL;
+
+	offset += 2*sizeof(__be64) - 1;
+	offset &= ~(2*sizeof(__be64) - 1);
+	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+
+	/*
+	 * Start writing ordered buffers, write journaled buffers
+	 * into the log along with a header
+	 */
+	gfs2_log_lock(sdp);
+	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);
+					sdp->sd_log_num_hdrs++;
+					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_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);
+			}
+		}
+		gfs2_log_unlock(sdp);
+		if (bh) {
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			bh = NULL;
+		}
+		n = 0;
+		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;
+		total_dbuf -= num;
+		total_jdata -= num;
+	}
+	gfs2_log_unlock(sdp);
+
+	/* 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);
+
+		kmem_cache_free(gfs2_bufdata_cachep, bd1);
+	}
+
+	/* 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);
+}
+
+static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				    struct gfs2_log_descriptor *ld,
+				    __be64 *ptr, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	u64 esc;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+		esc = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		/* Unescape */
+		if (esc) {
+			__be32 *eptr = (__be32 *)bh_ip->b_data;
+			*eptr = cpu_to_be32(GFS2_MAGIC);
+		}
+		mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+/* FIXME: sort out accounting for log blocks etc. */
+
+static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	/* data sync? */
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
+		jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_databuf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		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);
+}
+
+
+const struct gfs2_log_operations gfs2_glock_lops = {
+	.lo_add = glock_lo_add,
+	.lo_after_commit = glock_lo_after_commit,
+	.lo_name = "glock",
+};
+
+const struct gfs2_log_operations gfs2_buf_lops = {
+	.lo_add = buf_lo_add,
+	.lo_incore_commit = buf_lo_incore_commit,
+	.lo_before_commit = buf_lo_before_commit,
+	.lo_after_commit = buf_lo_after_commit,
+	.lo_before_scan = buf_lo_before_scan,
+	.lo_scan_elements = buf_lo_scan_elements,
+	.lo_after_scan = buf_lo_after_scan,
+	.lo_name = "buf",
+};
+
+const struct gfs2_log_operations gfs2_revoke_lops = {
+	.lo_add = revoke_lo_add,
+	.lo_before_commit = revoke_lo_before_commit,
+	.lo_before_scan = revoke_lo_before_scan,
+	.lo_scan_elements = revoke_lo_scan_elements,
+	.lo_after_scan = revoke_lo_after_scan,
+	.lo_name = "revoke",
+};
+
+const struct gfs2_log_operations gfs2_rg_lops = {
+	.lo_add = rg_lo_add,
+	.lo_after_commit = rg_lo_after_commit,
+	.lo_name = "rg",
+};
+
+const struct gfs2_log_operations gfs2_databuf_lops = {
+	.lo_add = databuf_lo_add,
+	.lo_incore_commit = buf_lo_incore_commit,
+	.lo_before_commit = databuf_lo_before_commit,
+	.lo_after_commit = databuf_lo_after_commit,
+	.lo_scan_elements = databuf_lo_scan_elements,
+	.lo_after_scan = databuf_lo_after_scan,
+	.lo_name = "databuf",
+};
+
+const struct gfs2_log_operations *gfs2_log_ops[] = {
+	&gfs2_glock_lops,
+	&gfs2_buf_lops,
+	&gfs2_revoke_lops,
+	&gfs2_rg_lops,
+	&gfs2_databuf_lops,
+	NULL,
+};
+

fs/gfs2/lops.h

@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOPS_DOT_H__
+#define __LOPS_DOT_H__
+
+#include <linux/list.h>
+#include "incore.h"
+
+extern const struct gfs2_log_operations gfs2_glock_lops;
+extern const struct gfs2_log_operations gfs2_buf_lops;
+extern const struct gfs2_log_operations gfs2_revoke_lops;
+extern const struct gfs2_log_operations gfs2_rg_lops;
+extern const struct gfs2_log_operations gfs2_databuf_lops;
+
+extern const struct gfs2_log_operations *gfs2_log_ops[];
+
+static inline void lops_init_le(struct gfs2_log_element *le,
+				const struct gfs2_log_operations *lops)
+{
+	INIT_LIST_HEAD(&le->le_list);
+	le->le_ops = lops;
+}
+
+static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	if (le->le_ops->lo_add)
+		le->le_ops->lo_add(sdp, le);
+}
+
+static inline void lops_incore_commit(struct gfs2_sbd *sdp,
+				      struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_incore_commit)
+			gfs2_log_ops[x]->lo_incore_commit(sdp, tr);
+}
+
+static inline void lops_before_commit(struct gfs2_sbd *sdp)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_commit)
+			gfs2_log_ops[x]->lo_before_commit(sdp);
+}
+
+static inline void lops_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_after_commit)
+			gfs2_log_ops[x]->lo_after_commit(sdp, ai);
+}
+
+static inline void lops_before_scan(struct gfs2_jdesc *jd,
+				    struct gfs2_log_header_host *head,
+				    unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
+}
+
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				     struct gfs2_log_descriptor *ld,
+				     __be64 *ptr,
+				     unsigned int pass)
+{
+	int x, error;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_scan_elements) {
+			error = gfs2_log_ops[x]->lo_scan_elements(jd, start,
+								  ld, ptr, pass);
+			if (error)
+				return error;
+		}
+
+	return 0;
+}
+
+static inline void lops_after_scan(struct gfs2_jdesc *jd, int error,
+				   unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_after_scan(jd, error, pass);
+}
+
+#endif /* __LOPS_DOT_H__ */
+

fs/gfs2/main.c

@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/atomic.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "ops_fstype.h"
+#include "sys.h"
+#include "util.h"
+#include "glock.h"
+
+static void gfs2_init_inode_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
+{
+	struct gfs2_inode *ip = foo;
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR) {
+		inode_init_once(&ip->i_inode);
+		spin_lock_init(&ip->i_spin);
+		init_rwsem(&ip->i_rw_mutex);
+		memset(ip->i_cache, 0, sizeof(ip->i_cache));
+	}
+}
+
+static void gfs2_init_glock_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
+{
+	struct gfs2_glock *gl = foo;
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR) {
+		INIT_HLIST_NODE(&gl->gl_list);
+		spin_lock_init(&gl->gl_spin);
+		INIT_LIST_HEAD(&gl->gl_holders);
+		INIT_LIST_HEAD(&gl->gl_waiters1);
+		INIT_LIST_HEAD(&gl->gl_waiters2);
+		INIT_LIST_HEAD(&gl->gl_waiters3);
+		gl->gl_lvb = NULL;
+		atomic_set(&gl->gl_lvb_count, 0);
+		INIT_LIST_HEAD(&gl->gl_reclaim);
+		INIT_LIST_HEAD(&gl->gl_ail_list);
+		atomic_set(&gl->gl_ail_count, 0);
+	}
+}
+
+/**
+ * init_gfs2_fs - Register GFS2 as a filesystem
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int __init init_gfs2_fs(void)
+{
+	int error;
+
+	error = gfs2_sys_init();
+	if (error)
+		return error;
+
+	error = gfs2_glock_init();
+	if (error)
+		goto fail;
+
+	error = -ENOMEM;
+	gfs2_glock_cachep = kmem_cache_create("gfs2_glock",
+					      sizeof(struct gfs2_glock),
+					      0, 0,
+					      gfs2_init_glock_once, NULL);
+	if (!gfs2_glock_cachep)
+		goto fail;
+
+	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
+					      sizeof(struct gfs2_inode),
+					      0,  SLAB_RECLAIM_ACCOUNT|
+					          SLAB_MEM_SPREAD,
+					      gfs2_init_inode_once, NULL);
+	if (!gfs2_inode_cachep)
+		goto fail;
+
+	gfs2_bufdata_cachep = kmem_cache_create("gfs2_bufdata",
+						sizeof(struct gfs2_bufdata),
+					        0, 0, NULL, NULL);
+	if (!gfs2_bufdata_cachep)
+		goto fail;
+
+	error = register_filesystem(&gfs2_fs_type);
+	if (error)
+		goto fail;
+
+	error = register_filesystem(&gfs2meta_fs_type);
+	if (error)
+		goto fail_unregister;
+
+	printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
+
+	return 0;
+
+fail_unregister:
+	unregister_filesystem(&gfs2_fs_type);
+fail:
+	if (gfs2_bufdata_cachep)
+		kmem_cache_destroy(gfs2_bufdata_cachep);
+
+	if (gfs2_inode_cachep)
+		kmem_cache_destroy(gfs2_inode_cachep);
+
+	if (gfs2_glock_cachep)
+		kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+	return error;
+}
+
+/**
+ * exit_gfs2_fs - Unregister the file system
+ *
+ */
+
+static void __exit exit_gfs2_fs(void)
+{
+	unregister_filesystem(&gfs2_fs_type);
+	unregister_filesystem(&gfs2meta_fs_type);
+
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+	kmem_cache_destroy(gfs2_inode_cachep);
+	kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+}
+
+MODULE_DESCRIPTION("Global File System");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+module_init(init_gfs2_fs);
+module_exit(exit_gfs2_fs);
+

fs/gfs2/meta_io.c

@@ -0,0 +1,573 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/delay.h>
+#include <linux/bio.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "ops_address.h"
+
+static int aspace_get_block(struct inode *inode, sector_t lblock,
+			    struct buffer_head *bh_result, int create)
+{
+	gfs2_assert_warn(inode->i_sb->s_fs_info, 0);
+	return -EOPNOTSUPP;
+}
+
+static int gfs2_aspace_writepage(struct page *page,
+				 struct writeback_control *wbc)
+{
+	return block_write_full_page(page, aspace_get_block, wbc);
+}
+
+static const struct address_space_operations aspace_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
+/**
+ * gfs2_aspace_get - Create and initialize a struct inode structure
+ * @sdp: the filesystem the aspace is in
+ *
+ * Right now a struct inode is just a struct inode.  Maybe Linux
+ * will supply a more lightweight address space construct (that works)
+ * in the future.
+ *
+ * Make sure pages/buffers in this aspace aren't in high memory.
+ *
+ * Returns: the aspace
+ */
+
+struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp)
+{
+	struct inode *aspace;
+
+	aspace = new_inode(sdp->sd_vfs);
+	if (aspace) {
+		mapping_set_gfp_mask(aspace->i_mapping, GFP_NOFS);
+		aspace->i_mapping->a_ops = &aspace_aops;
+		aspace->i_size = ~0ULL;
+		aspace->i_private = NULL;
+		insert_inode_hash(aspace);
+	}
+	return aspace;
+}
+
+void gfs2_aspace_put(struct inode *aspace)
+{
+	remove_inode_hash(aspace);
+	iput(aspace);
+}
+
+/**
+ * gfs2_meta_inval - Invalidate all buffers associated with a glock
+ * @gl: the glock
+ *
+ */
+
+void gfs2_meta_inval(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct inode *aspace = gl->gl_aspace;
+	struct address_space *mapping = gl->gl_aspace->i_mapping;
+
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+
+	atomic_inc(&aspace->i_writecount);
+	truncate_inode_pages(mapping, 0);
+	atomic_dec(&aspace->i_writecount);
+
+	gfs2_assert_withdraw(sdp, !mapping->nrpages);
+}
+
+/**
+ * gfs2_meta_sync - Sync all buffers associated with a glock
+ * @gl: The glock
+ *
+ */
+
+void gfs2_meta_sync(struct gfs2_glock *gl)
+{
+	struct address_space *mapping = gl->gl_aspace->i_mapping;
+	int error;
+
+	filemap_fdatawrite(mapping);
+	error = filemap_fdatawait(mapping);
+
+	if (error)
+		gfs2_io_error(gl->gl_sbd);
+}
+
+/**
+ * getbuf - Get a buffer with a given address space
+ * @gl: the glock
+ * @blkno: the block number (filesystem scope)
+ * @create: 1 if the buffer should be created
+ *
+ * Returns: the buffer
+ */
+
+static struct buffer_head *getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+{
+	struct address_space *mapping = gl->gl_aspace->i_mapping;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct page *page;
+	struct buffer_head *bh;
+	unsigned int shift;
+	unsigned long index;
+	unsigned int bufnum;
+
+	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
+	index = blkno >> shift;             /* convert block to page */
+	bufnum = blkno - (index << shift);  /* block buf index within page */
+
+	if (create) {
+		for (;;) {
+			page = grab_cache_page(mapping, index);
+			if (page)
+				break;
+			yield();
+		}
+	} else {
+		page = find_lock_page(mapping, index);
+		if (!page)
+			return NULL;
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
+
+	/* Locate header for our buffer within our page */
+	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
+		/* Do nothing */;
+	get_bh(bh);
+
+	if (!buffer_mapped(bh))
+		map_bh(bh, sdp->sd_vfs, blkno);
+
+	unlock_page(page);
+	mark_page_accessed(page);
+	page_cache_release(page);
+
+	return bh;
+}
+
+static void meta_prep_new(struct buffer_head *bh)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+}
+
+/**
+ * gfs2_meta_new - Get a block
+ * @gl: The glock associated with this block
+ * @blkno: The block number
+ *
+ * Returns: The buffer
+ */
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
+{
+	struct buffer_head *bh;
+	bh = getbuf(gl, blkno, CREATE);
+	meta_prep_new(bh);
+	return bh;
+}
+
+/**
+ * gfs2_meta_read - Read a block from disk
+ * @gl: The glock covering the block
+ * @blkno: The block number
+ * @flags: flags
+ * @bhp: the place where the buffer is returned (NULL on failure)
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
+		   struct buffer_head **bhp)
+{
+	*bhp = getbuf(gl, blkno, CREATE);
+	if (!buffer_uptodate(*bhp))
+		ll_rw_block(READ_META, 1, bhp);
+	if (flags & DIO_WAIT) {
+		int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
+		if (error) {
+			brelse(*bhp);
+			return error;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_meta_wait - Reread a block from disk
+ * @sdp: the filesystem
+ * @bh: The block to wait for
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh)) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		return -EIO;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer
+ * @gl: the glock the buffer belongs to
+ * @bh: The buffer to be attached to
+ * @meta: Flag to indicate whether its metadata or not
+ */
+
+void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
+			 int meta)
+{
+	struct gfs2_bufdata *bd;
+
+	if (meta)
+		lock_page(bh->b_page);
+
+	if (bh->b_private) {
+		if (meta)
+			unlock_page(bh->b_page);
+		return;
+	}
+
+	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL),
+	bd->bd_bh = bh;
+	bd->bd_gl = gl;
+
+	INIT_LIST_HEAD(&bd->bd_list_tr);
+	if (meta)
+		lops_init_le(&bd->bd_le, &gfs2_buf_lops);
+	else
+		lops_init_le(&bd->bd_le, &gfs2_databuf_lops);
+	bh->b_private = bd;
+
+	if (meta)
+		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)
+{
+	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);
+		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);
+}
+
+/**
+ * gfs2_meta_wipe - make inode's buffers so they aren't dirty/pinned anymore
+ * @ip: the inode who owns the buffers
+ * @bstart: the first buffer in the run
+ * @blen: the number of buffers in the run
+ *
+ */
+
+void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh;
+
+	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;
+				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);
+				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);
+			unlock_buffer(bh);
+
+			brelse(bh);
+		}
+
+		bstart++;
+		blen--;
+	}
+}
+
+/**
+ * gfs2_meta_cache_flush - get rid of any references on buffers for this inode
+ * @ip: The GFS2 inode
+ *
+ * This releases buffers that are in the most-recently-used array of
+ * blocks used for indirect block addressing for this inode.
+ */
+
+void gfs2_meta_cache_flush(struct gfs2_inode *ip)
+{
+	struct buffer_head **bh_slot;
+	unsigned int x;
+
+	spin_lock(&ip->i_spin);
+
+	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;
+	}
+
+	spin_unlock(&ip->i_spin);
+}
+
+/**
+ * gfs2_meta_indirect_buffer - Get a metadata buffer
+ * @ip: The GFS2 inode
+ * @height: The level of this buf in the metadata (indir addr) tree (if any)
+ * @num: The block number (device relative) of the buffer
+ * @new: Non-zero if we may create a new buffer
+ * @bhp: the buffer is returned here
+ *
+ * Try to use the gfs2_inode's MRU metadata tree cache.
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	struct buffer_head *bh = NULL, **bh_slot = ip->i_cache + height;
+	int in_cache = 0;
+
+	BUG_ON(!gl);
+	BUG_ON(!sdp);
+
+	spin_lock(&ip->i_spin);
+	if (*bh_slot && (*bh_slot)->b_blocknr == num) {
+		bh = *bh_slot;
+		get_bh(bh);
+		in_cache = 1;
+	}
+	spin_unlock(&ip->i_spin);
+
+	if (!bh)
+		bh = getbuf(gl, num, CREATE);
+
+	if (!bh)
+		return -ENOBUFS;
+
+	if (new) {
+		if (gfs2_assert_warn(sdp, height))
+			goto err;
+		meta_prep_new(bh);
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
+		gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+	} else {
+		u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+		if (!buffer_uptodate(bh)) {
+			ll_rw_block(READ_META, 1, &bh);
+			if (gfs2_meta_wait(sdp, bh))
+				goto err;
+		}
+		if (gfs2_metatype_check(sdp, bh, mtype))
+			goto err;
+	}
+
+	if (!in_cache) {
+		spin_lock(&ip->i_spin);
+		if (*bh_slot)
+			brelse(*bh_slot);
+		*bh_slot = bh;
+		get_bh(bh);
+		spin_unlock(&ip->i_spin);
+	}
+
+	*bhp = bh;
+	return 0;
+err:
+	brelse(bh);
+	return -EIO;
+}
+
+/**
+ * gfs2_meta_ra - start readahead on an extent of a file
+ * @gl: the glock the blocks belong to
+ * @dblock: the starting disk block
+ * @extlen: the number of blocks in the extent
+ *
+ * returns: the first buffer in the extent
+ */
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *first_bh, *bh;
+	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
+			  sdp->sd_sb.sb_bsize_shift;
+
+	BUG_ON(!extlen);
+
+	if (max_ra < 1)
+		max_ra = 1;
+	if (extlen > max_ra)
+		extlen = max_ra;
+
+	first_bh = getbuf(gl, dblock, CREATE);
+
+	if (buffer_uptodate(first_bh))
+		goto out;
+	if (!buffer_locked(first_bh))
+		ll_rw_block(READ_META, 1, &first_bh);
+
+	dblock++;
+	extlen--;
+
+	while (extlen) {
+		bh = getbuf(gl, dblock, CREATE);
+
+		if (!buffer_uptodate(bh) && !buffer_locked(bh))
+			ll_rw_block(READA, 1, &bh);
+		brelse(bh);
+		dblock++;
+		extlen--;
+		if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
+			goto out;
+	}
+
+	wait_on_buffer(first_bh);
+out:
+	return first_bh;
+}
+

fs/gfs2/meta_io.h

@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIO_DOT_H__
+#define __DIO_DOT_H__
+
+#include <linux/buffer_head.h>
+#include <linux/string.h>
+#include "incore.h"
+
+static inline void gfs2_buffer_clear(struct buffer_head *bh)
+{
+	memset(bh->b_data, 0, bh->b_size);
+}
+
+static inline void gfs2_buffer_clear_tail(struct buffer_head *bh, int head)
+{
+	BUG_ON(head > bh->b_size);
+	memset(bh->b_data + head, 0, bh->b_size - head);
+}
+
+static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
+					 int to_head,
+					 struct buffer_head *from_bh,
+					 int from_head)
+{
+	BUG_ON(from_head < to_head);
+	memcpy(to_bh->b_data + to_head, from_bh->b_data + from_head,
+	       from_bh->b_size - from_head);
+	memset(to_bh->b_data + to_bh->b_size + to_head - from_head,
+	       0, from_head - to_head);
+}
+
+struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp);
+void gfs2_aspace_put(struct inode *aspace);
+
+void gfs2_meta_inval(struct gfs2_glock *gl);
+void gfs2_meta_sync(struct gfs2_glock *gl);
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
+		   int flags, struct buffer_head **bhp);
+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_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
+
+void gfs2_meta_cache_flush(struct gfs2_inode *ip);
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp);
+
+static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip,
+					 struct buffer_head **bhp)
+{
+	return gfs2_meta_indirect_buffer(ip, 0, ip->i_num.no_addr, 0, bhp);
+}
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
+
+#define buffer_busy(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
+#define buffer_in_io(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock)))
+
+#endif /* __DIO_DOT_H__ */
+

fs/gfs2/mount.c

@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "mount.h"
+#include "sys.h"
+#include "util.h"
+
+/**
+ * gfs2_mount_args - Parse mount options
+ * @sdp:
+ * @data:
+ *
+ * Return: errno
+ */
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
+{
+	struct gfs2_args *args = &sdp->sd_args;
+	char *data = data_arg;
+	char *options, *o, *v;
+	int error = 0;
+
+	if (!remount) {
+		/*  If someone preloaded options, use those instead  */
+		spin_lock(&gfs2_sys_margs_lock);
+		if (gfs2_sys_margs) {
+			data = gfs2_sys_margs;
+			gfs2_sys_margs = NULL;
+		}
+		spin_unlock(&gfs2_sys_margs_lock);
+
+		/*  Set some defaults  */
+		args->ar_num_glockd = GFS2_GLOCKD_DEFAULT;
+		args->ar_quota = GFS2_QUOTA_DEFAULT;
+		args->ar_data = GFS2_DATA_DEFAULT;
+	}
+
+	/* Split the options into tokens with the "," character and
+	   process them */
+
+	for (options = data; (o = strsep(&options, ",")); ) {
+		if (!*o)
+			continue;
+
+		v = strchr(o, '=');
+		if (v)
+			*v++ = 0;
+
+		if (!strcmp(o, "lockproto")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_lockproto))
+				goto cant_remount;
+			strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN);
+			args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "locktable")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_locktable))
+				goto cant_remount;
+			strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN);
+			args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "hostdata")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_hostdata))
+				goto cant_remount;
+			strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
+			args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "spectator")) {
+			if (remount && !args->ar_spectator)
+				goto cant_remount;
+			args->ar_spectator = 1;
+			sdp->sd_vfs->s_flags |= MS_RDONLY;
+		}
+
+		else if (!strcmp(o, "ignore_local_fs")) {
+			if (remount && !args->ar_ignore_local_fs)
+				goto cant_remount;
+			args->ar_ignore_local_fs = 1;
+		}
+
+		else if (!strcmp(o, "localflocks")) {
+			if (remount && !args->ar_localflocks)
+				goto cant_remount;
+			args->ar_localflocks = 1;
+		}
+
+		else if (!strcmp(o, "localcaching")) {
+			if (remount && !args->ar_localcaching)
+				goto cant_remount;
+			args->ar_localcaching = 1;
+		}
+
+		else if (!strcmp(o, "debug"))
+			args->ar_debug = 1;
+
+		else if (!strcmp(o, "nodebug"))
+			args->ar_debug = 0;
+
+		else if (!strcmp(o, "upgrade")) {
+			if (remount && !args->ar_upgrade)
+				goto cant_remount;
+			args->ar_upgrade = 1;
+		}
+
+		else if (!strcmp(o, "num_glockd")) {
+			unsigned int x;
+			if (!v)
+				goto need_value;
+			sscanf(v, "%u", &x);
+			if (remount && x != args->ar_num_glockd)
+				goto cant_remount;
+			if (!x || x > GFS2_GLOCKD_MAX) {
+				fs_info(sdp, "0 < num_glockd <= %u  (not %u)\n",
+				        GFS2_GLOCKD_MAX, x);
+				error = -EINVAL;
+				break;
+			}
+			args->ar_num_glockd = x;
+		}
+
+		else if (!strcmp(o, "acl")) {
+			args->ar_posix_acl = 1;
+			sdp->sd_vfs->s_flags |= MS_POSIXACL;
+		}
+
+		else if (!strcmp(o, "noacl")) {
+			args->ar_posix_acl = 0;
+			sdp->sd_vfs->s_flags &= ~MS_POSIXACL;
+		}
+
+		else if (!strcmp(o, "quota")) {
+			if (!v)
+				goto need_value;
+			if (!strcmp(v, "off"))
+				args->ar_quota = GFS2_QUOTA_OFF;
+			else if (!strcmp(v, "account"))
+				args->ar_quota = GFS2_QUOTA_ACCOUNT;
+			else if (!strcmp(v, "on"))
+				args->ar_quota = GFS2_QUOTA_ON;
+			else {
+				fs_info(sdp, "invalid value for quota\n");
+				error = -EINVAL;
+				break;
+			}
+		}
+
+		else if (!strcmp(o, "suiddir"))
+			args->ar_suiddir = 1;
+
+		else if (!strcmp(o, "nosuiddir"))
+			args->ar_suiddir = 0;
+
+		else if (!strcmp(o, "data")) {
+			if (!v)
+				goto need_value;
+			if (!strcmp(v, "writeback"))
+				args->ar_data = GFS2_DATA_WRITEBACK;
+			else if (!strcmp(v, "ordered"))
+				args->ar_data = GFS2_DATA_ORDERED;
+			else {
+				fs_info(sdp, "invalid value for data\n");
+				error = -EINVAL;
+				break;
+			}
+		}
+
+		else {
+			fs_info(sdp, "unknown option: %s\n", o);
+			error = -EINVAL;
+			break;
+		}
+	}
+
+	if (error)
+		fs_info(sdp, "invalid mount option(s)\n");
+
+	if (data != data_arg)
+		kfree(data);
+
+	return error;
+
+need_value:
+	fs_info(sdp, "need value for option %s\n", o);
+	return -EINVAL;
+
+cant_remount:
+	fs_info(sdp, "can't remount with option %s\n", o);
+	return -EINVAL;
+}
+

fs/gfs2/mount.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __MOUNT_DOT_H__
+#define __MOUNT_DOT_H__
+
+struct gfs2_sbd;
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount);
+
+#endif /* __MOUNT_DOT_H__ */

fs/gfs2/ondisk.c

@@ -0,0 +1,251 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+
+#include "gfs2.h"
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include "incore.h"
+
+#define pv(struct, member, fmt) printk(KERN_INFO "  "#member" = "fmt"\n", \
+				       struct->member);
+
+/*
+ * gfs2_xxx_in - read in an xxx struct
+ * first arg: the cpu-order structure
+ * buf: the disk-order buffer
+ *
+ * gfs2_xxx_out - write out an xxx struct
+ * first arg: the cpu-order structure
+ * buf: the disk-order buffer
+ *
+ * gfs2_xxx_print - print out an xxx struct
+ * first arg: the cpu-order structure
+ */
+
+void gfs2_inum_in(struct gfs2_inum_host *no, const void *buf)
+{
+	const struct gfs2_inum *str = buf;
+
+	no->no_formal_ino = be64_to_cpu(str->no_formal_ino);
+	no->no_addr = be64_to_cpu(str->no_addr);
+}
+
+void gfs2_inum_out(const struct gfs2_inum_host *no, void *buf)
+{
+	struct gfs2_inum *str = buf;
+
+	str->no_formal_ino = cpu_to_be64(no->no_formal_ino);
+	str->no_addr = cpu_to_be64(no->no_addr);
+}
+
+static void gfs2_inum_print(const struct gfs2_inum_host *no)
+{
+	printk(KERN_INFO "  no_formal_ino = %llu\n", (unsigned long long)no->no_formal_ino);
+	printk(KERN_INFO "  no_addr = %llu\n", (unsigned long long)no->no_addr);
+}
+
+static void gfs2_meta_header_in(struct gfs2_meta_header_host *mh, const void *buf)
+{
+	const struct gfs2_meta_header *str = buf;
+
+	mh->mh_magic = be32_to_cpu(str->mh_magic);
+	mh->mh_type = be32_to_cpu(str->mh_type);
+	mh->mh_format = be32_to_cpu(str->mh_format);
+}
+
+void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
+{
+	const struct gfs2_sb *str = buf;
+
+	gfs2_meta_header_in(&sb->sb_header, buf);
+
+	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+
+	gfs2_inum_in(&sb->sb_master_dir, (char *)&str->sb_master_dir);
+	gfs2_inum_in(&sb->sb_root_dir, (char *)&str->sb_root_dir);
+
+	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+}
+
+void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf)
+{
+	const struct gfs2_rindex *str = buf;
+
+	ri->ri_addr = be64_to_cpu(str->ri_addr);
+	ri->ri_length = be32_to_cpu(str->ri_length);
+	ri->ri_data0 = be64_to_cpu(str->ri_data0);
+	ri->ri_data = be32_to_cpu(str->ri_data);
+	ri->ri_bitbytes = be32_to_cpu(str->ri_bitbytes);
+
+}
+
+void gfs2_rindex_print(const struct gfs2_rindex_host *ri)
+{
+	printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)ri->ri_addr);
+	pv(ri, ri_length, "%u");
+
+	printk(KERN_INFO "  ri_data0 = %llu\n", (unsigned long long)ri->ri_data0);
+	pv(ri, ri_data, "%u");
+
+	pv(ri, ri_bitbytes, "%u");
+}
+
+void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf)
+{
+	const struct gfs2_rgrp *str = buf;
+
+	rg->rg_flags = be32_to_cpu(str->rg_flags);
+	rg->rg_free = be32_to_cpu(str->rg_free);
+	rg->rg_dinodes = be32_to_cpu(str->rg_dinodes);
+	rg->rg_igeneration = be64_to_cpu(str->rg_igeneration);
+}
+
+void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf)
+{
+	struct gfs2_rgrp *str = buf;
+
+	str->rg_flags = cpu_to_be32(rg->rg_flags);
+	str->rg_free = cpu_to_be32(rg->rg_free);
+	str->rg_dinodes = cpu_to_be32(rg->rg_dinodes);
+	str->__pad = cpu_to_be32(0);
+	str->rg_igeneration = cpu_to_be64(rg->rg_igeneration);
+	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
+}
+
+void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf)
+{
+	const struct gfs2_quota *str = 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);
+}
+
+void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
+{
+	const struct gfs2_dinode_host *di = &ip->i_di;
+	struct gfs2_dinode *str = buf;
+
+	str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
+	str->di_header.__pad0 = 0;
+	str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
+	str->di_header.__pad1 = 0;
+
+	gfs2_inum_out(&ip->i_num, &str->di_num);
+
+	str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
+	str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
+	str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+	str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
+	str->di_size = cpu_to_be64(di->di_size);
+	str->di_blocks = cpu_to_be64(di->di_blocks);
+	str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
+	str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
+	str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
+
+	str->di_goal_meta = cpu_to_be64(di->di_goal_meta);
+	str->di_goal_data = cpu_to_be64(di->di_goal_data);
+	str->di_generation = cpu_to_be64(di->di_generation);
+
+	str->di_flags = cpu_to_be32(di->di_flags);
+	str->di_height = cpu_to_be16(di->di_height);
+	str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
+					     !(ip->i_di.di_flags & GFS2_DIF_EXHASH) ?
+					     GFS2_FORMAT_DE : 0);
+	str->di_depth = cpu_to_be16(di->di_depth);
+	str->di_entries = cpu_to_be32(di->di_entries);
+
+	str->di_eattr = cpu_to_be64(di->di_eattr);
+}
+
+void gfs2_dinode_print(const struct gfs2_inode *ip)
+{
+	const struct gfs2_dinode_host *di = &ip->i_di;
+
+	gfs2_inum_print(&ip->i_num);
+
+	printk(KERN_INFO "  di_size = %llu\n", (unsigned long long)di->di_size);
+	printk(KERN_INFO "  di_blocks = %llu\n", (unsigned long long)di->di_blocks);
+	printk(KERN_INFO "  di_goal_meta = %llu\n", (unsigned long long)di->di_goal_meta);
+	printk(KERN_INFO "  di_goal_data = %llu\n", (unsigned long long)di->di_goal_data);
+
+	pv(di, di_flags, "0x%.8X");
+	pv(di, di_height, "%u");
+
+	pv(di, di_depth, "%u");
+	pv(di, di_entries, "%u");
+
+	printk(KERN_INFO "  di_eattr = %llu\n", (unsigned long long)di->di_eattr);
+}
+
+void gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf)
+{
+	const struct gfs2_log_header *str = buf;
+
+	gfs2_meta_header_in(&lh->lh_header, buf);
+	lh->lh_sequence = be64_to_cpu(str->lh_sequence);
+	lh->lh_flags = be32_to_cpu(str->lh_flags);
+	lh->lh_tail = be32_to_cpu(str->lh_tail);
+	lh->lh_blkno = be32_to_cpu(str->lh_blkno);
+	lh->lh_hash = be32_to_cpu(str->lh_hash);
+}
+
+void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf)
+{
+	const struct gfs2_inum_range *str = buf;
+
+	ir->ir_start = be64_to_cpu(str->ir_start);
+	ir->ir_length = be64_to_cpu(str->ir_length);
+}
+
+void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf)
+{
+	struct gfs2_inum_range *str = buf;
+
+	str->ir_start = cpu_to_be64(ir->ir_start);
+	str->ir_length = cpu_to_be64(ir->ir_length);
+}
+
+void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
+{
+	const struct gfs2_statfs_change *str = buf;
+
+	sc->sc_total = be64_to_cpu(str->sc_total);
+	sc->sc_free = be64_to_cpu(str->sc_free);
+	sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
+}
+
+void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
+{
+	struct gfs2_statfs_change *str = buf;
+
+	str->sc_total = cpu_to_be64(sc->sc_total);
+	str->sc_free = cpu_to_be64(sc->sc_free);
+	str->sc_dinodes = cpu_to_be64(sc->sc_dinodes);
+}
+
+void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf)
+{
+	const struct gfs2_quota_change *str = buf;
+
+	qc->qc_change = be64_to_cpu(str->qc_change);
+	qc->qc_flags = be32_to_cpu(str->qc_flags);
+	qc->qc_id = be32_to_cpu(str->qc_id);
+}
+

fs/gfs2/ops_address.c

@@ -0,0 +1,803 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/fs.h>
+#include <linux/writeback.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "ops_address.h"
+#include "quota.h"
+#include "trans.h"
+#include "rgrp.h"
+#include "ops_file.h"
+#include "util.h"
+#include "glops.h"
+
+
+static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to)
+{
+	struct buffer_head *head = page_buffers(page);
+	unsigned int bsize = head->b_size;
+	struct buffer_head *bh;
+	unsigned int start, end;
+
+	for (bh = head, start = 0; bh != head || !start;
+	     bh = bh->b_this_page, start = end) {
+		end = start + bsize;
+		if (end <= from || start >= to)
+			continue;
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+	}
+}
+
+/**
+ * gfs2_get_block - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+int gfs2_get_block(struct inode *inode, sector_t lblock,
+	           struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, create, bh_result);
+}
+
+/**
+ * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
+				  struct buffer_head *bh_result, int create)
+{
+	int error;
+
+	error = gfs2_block_map(inode, lblock, 0, bh_result);
+	if (error)
+		return error;
+	if (bh_result->b_blocknr == 0)
+		return -EIO;
+	return 0;
+}
+
+static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
+				 struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, 0, bh_result);
+}
+
+/**
+ * gfs2_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ * Some of this is copied from block_write_full_page() although we still
+ * call it to do most of the work.
+ */
+
+static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset;
+	int error;
+	int done_trans = 0;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) {
+		unlock_page(page);
+		return -EIO;
+	}
+	if (current->journal_info)
+		goto out_ignore;
+
+	/* Is the page fully outside i_size? (truncate in progress) */
+        offset = i_size & (PAGE_CACHE_SIZE-1);
+	if (page->index > end_index || (page->index == end_index && !offset)) {
+		page->mapping->a_ops->invalidatepage(page, 0);
+		unlock_page(page);
+		return 0; /* don't care */
+	}
+
+	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) {
+		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+		if (error)
+			goto out_ignore;
+		if (!page_has_buffers(page)) {
+			create_empty_buffers(page, inode->i_sb->s_blocksize,
+					     (1 << BH_Dirty)|(1 << BH_Uptodate));
+		}
+		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
+		done_trans = 1;
+	}
+	error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	if (done_trans)
+		gfs2_trans_end(sdp);
+	gfs2_meta_cache_flush(ip);
+	return error;
+
+out_ignore:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: Write-back control
+ *
+ * For journaled files and/or ordered writes this just falls back to the
+ * kernel's default writepages path for now. We will probably want to change
+ * that eventually (i.e. when we look at allocate on flush).
+ *
+ * For the data=writeback case though we can already ignore buffer heads
+ * and write whole extents at once. This is a big reduction in the
+ * number of I/O requests we send and the bmap calls we make in this case.
+ */
+static int gfs2_writepages(struct address_space *mapping,
+			   struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip))
+		return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+
+	return generic_writepages(mapping, wbc);
+}
+
+/**
+ * stuffed_readpage - Fill in a Linux page with stuffed file data
+ * @ip: the inode
+ * @page: the page
+ *
+ * Returns: errno
+ */
+
+static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+{
+	struct buffer_head *dibh;
+	void *kaddr;
+	int error;
+
+	BUG_ON(page->index);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
+	       ip->i_di.di_size);
+	memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
+	kunmap_atomic(kaddr, KM_USER0);
+
+	brelse(dibh);
+
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+
+/**
+ * gfs2_readpage - readpage with locking
+ * @file: The file to read a page for. N.B. This may be NULL if we are
+ * reading an internal file.
+ * @page: The page to read
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	struct gfs2_file *gf = NULL;
+	struct gfs2_holder gh;
+	int error;
+	int do_unlock = 0;
+
+	if (likely(file != &gfs2_internal_file_sentinel)) {
+		if (file) {
+			gf = file->private_data;
+			if (test_bit(GFF_EXLOCK, &gf->f_flags))
+				/* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
+				goto skip_lock;
+		}
+		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
+		do_unlock = 1;
+		error = gfs2_glock_nq_atime(&gh);
+		if (unlikely(error))
+			goto out_unlock;
+	}
+
+skip_lock:
+	if (gfs2_is_stuffed(ip)) {
+		error = stuffed_readpage(ip, page);
+		unlock_page(page);
+	} else
+		error = mpage_readpage(page, gfs2_get_block);
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = -EIO;
+
+	if (do_unlock) {
+		gfs2_glock_dq_m(1, &gh);
+		gfs2_holder_uninit(&gh);
+	}
+out:
+	return error;
+out_unlock:
+	unlock_page(page);
+	if (error == GLR_TRYFAILED) {
+		error = AOP_TRUNCATED_PAGE;
+		yield();
+	}
+	if (do_unlock)
+		gfs2_holder_uninit(&gh);
+	goto out;
+}
+
+/**
+ * gfs2_readpages - Read a bunch of pages at once
+ *
+ * Some notes:
+ * 1. This is only for readahead, so we can simply ignore any things
+ *    which are slightly inconvenient (such as locking conflicts between
+ *    the page lock and the glock) and return having done no I/O. Its
+ *    obviously not something we'd want to do on too regular a basis.
+ *    Any I/O we ignore at this time will be done via readpage later.
+ * 2. We don't handle stuffed files here we let readpage do the honours.
+ * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
+ * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
+ *    well as read-ahead.
+ */
+static int gfs2_readpages(struct file *file, struct address_space *mapping,
+			  struct list_head *pages, unsigned nr_pages)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	int ret = 0;
+	int do_unlock = 0;
+
+	if (likely(file != &gfs2_internal_file_sentinel)) {
+		if (file) {
+			struct gfs2_file *gf = file->private_data;
+			if (test_bit(GFF_EXLOCK, &gf->f_flags))
+				goto skip_lock;
+		}
+		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
+				 LM_FLAG_TRY_1CB|GL_ATIME, &gh);
+		do_unlock = 1;
+		ret = gfs2_glock_nq_atime(&gh);
+		if (ret == GLR_TRYFAILED)
+			goto out_noerror;
+		if (unlikely(ret))
+			goto out_unlock;
+	}
+skip_lock:
+	if (!gfs2_is_stuffed(ip))
+		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);
+
+	if (do_unlock) {
+		gfs2_glock_dq_m(1, &gh);
+		gfs2_holder_uninit(&gh);
+	}
+out:
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = -EIO;
+	return ret;
+out_noerror:
+	ret = 0;
+out_unlock:
+	if (do_unlock)
+		gfs2_holder_uninit(&gh);
+	goto out;
+}
+
+/**
+ * gfs2_prepare_write - Prepare to write a page to a file
+ * @file: The file to write to
+ * @page: The page which is to be prepared for writing
+ * @from: From (byte range within page)
+ * @to: To (byte range within page)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_prepare_write(struct file *file, struct page *page,
+			      unsigned from, unsigned to)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	unsigned int data_blocks, ind_blocks, rblocks;
+	int alloc_required;
+	int error = 0;
+	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
+	loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	struct gfs2_alloc *al;
+	unsigned int write_len = to - from;
+
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|LM_FLAG_TRY_1CB, &ip->i_gh);
+	error = gfs2_glock_nq_atime(&ip->i_gh);
+	if (unlikely(error)) {
+		if (error == GLR_TRYFAILED) {
+			unlock_page(page);
+			error = AOP_TRUNCATED_PAGE;
+			yield();
+		}
+		goto out_uninit;
+	}
+
+	gfs2_write_calc_reserv(ip, write_len, &data_blocks, &ind_blocks);
+
+	error = gfs2_write_alloc_required(ip, pos, write_len, &alloc_required);
+	if (error)
+		goto out_unlock;
+
+
+	ip->i_alloc.al_requested = 0;
+	if (alloc_required) {
+		al = gfs2_alloc_get(ip);
+
+		error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+		if (error)
+			goto out_alloc_put;
+
+		error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+		if (error)
+			goto out_qunlock;
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto out_qunlock;
+	}
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+
+	error = gfs2_trans_begin(sdp, rblocks, 0);
+	if (error)
+		goto out;
+
+	if (gfs2_is_stuffed(ip)) {
+		if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
+			error = gfs2_unstuff_dinode(ip, page);
+			if (error == 0)
+				goto prepare_write;
+		} else if (!PageUptodate(page))
+			error = stuffed_readpage(ip, page);
+		goto out;
+	}
+
+prepare_write:
+	error = block_prepare_write(page, from, to, gfs2_get_block);
+
+out:
+	if (error) {
+		gfs2_trans_end(sdp);
+		if (alloc_required) {
+			gfs2_inplace_release(ip);
+out_qunlock:
+			gfs2_quota_unlock(ip);
+out_alloc_put:
+			gfs2_alloc_put(ip);
+		}
+out_unlock:
+		gfs2_glock_dq_m(1, &ip->i_gh);
+out_uninit:
+		gfs2_holder_uninit(&ip->i_gh);
+	}
+
+	return error;
+}
+
+/**
+ * gfs2_commit_write - Commit write to a file
+ * @file: The file to write to
+ * @page: The page containing the data
+ * @from: From (byte range within page)
+ * @to: To (byte range within page)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_commit_write(struct file *file, struct page *page,
+			     unsigned from, unsigned to)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int error = -EOPNOTSUPP;
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_dinode *di;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
+                goto fail_nounlock;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto fail_endtrans;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	di = (struct gfs2_dinode *)dibh->b_data;
+
+	if (gfs2_is_stuffed(ip)) {
+		u64 file_size;
+		void *kaddr;
+
+		file_size = ((u64)page->index << PAGE_CACHE_SHIFT) + to;
+
+		kaddr = kmap_atomic(page, KM_USER0);
+		memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
+		       kaddr + from, to - from);
+		kunmap_atomic(kaddr, KM_USER0);
+
+		SetPageUptodate(page);
+
+		if (inode->i_size < file_size) {
+			i_size_write(inode, file_size);
+			mark_inode_dirty(inode);
+		}
+	} else {
+		if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED ||
+		    gfs2_is_jdata(ip))
+			gfs2_page_add_databufs(ip, page, from, to);
+		error = generic_commit_write(file, page, from, to);
+		if (error)
+			goto fail;
+	}
+
+	if (ip->i_di.di_size < inode->i_size) {
+		ip->i_di.di_size = inode->i_size;
+		di->di_size = cpu_to_be64(inode->i_size);
+	}
+
+	brelse(dibh);
+	gfs2_trans_end(sdp);
+	if (al->al_requested) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	gfs2_glock_dq_m(1, &ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return 0;
+
+fail:
+	brelse(dibh);
+fail_endtrans:
+	gfs2_trans_end(sdp);
+	if (al->al_requested) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	gfs2_glock_dq_m(1, &ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+fail_nounlock:
+	ClearPageUptodate(page);
+	return error;
+}
+
+/**
+ * gfs2_bmap - Block map function
+ * @mapping: Address space info
+ * @lblock: The block to map
+ *
+ * Returns: The disk address for the block or 0 on hole or error
+ */
+
+static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder i_gh;
+	sector_t dblock = 0;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return 0;
+
+	if (!gfs2_is_stuffed(ip))
+		dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return dblock;
+}
+
+static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	gfs2_log_lock(sdp);
+	bd = bh->b_private;
+	if (bd) {
+		bd->bd_bh = NULL;
+		bh->b_private = NULL;
+	}
+	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);
+	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;
+
+	BUG_ON(!PageLocked(page));
+	if (!page_has_buffers(page))
+		return;
+
+	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;
+	} while (bh != head);
+
+	if (!offset)
+		try_to_release_page(page, 0);
+
+	return;
+}
+
+/**
+ * gfs2_ok_for_dio - check that dio is valid on this file
+ * @ip: The inode
+ * @rw: READ or WRITE
+ * @offset: The offset at which we are reading or writing
+ *
+ * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
+ *          1 (to accept the i/o request)
+ */
+static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
+{
+	/*
+	 * Should we return an error here? I can't see that O_DIRECT for
+	 * a journaled file makes any sense. For now we'll silently fall
+	 * back to buffered I/O, likewise we do the same for stuffed
+	 * files since they are (a) small and (b) unaligned.
+	 */
+	if (gfs2_is_jdata(ip))
+		return 0;
+
+	if (gfs2_is_stuffed(ip))
+		return 0;
+
+	if (offset > i_size_read(&ip->i_inode))
+		return 0;
+	return 1;
+}
+
+
+
+static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int rv;
+
+	/*
+	 * Deferred lock, even if its a write, since we do no allocation
+	 * on this path. All we need change is atime, and this lock mode
+	 * ensures that other nodes have flushed their buffered read caches
+	 * (i.e. their page cache entries for this inode). We do not,
+	 * unfortunately have the option of only flushing a range like
+	 * the VFS does.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
+	rv = gfs2_glock_nq_atime(&gh);
+	if (rv)
+		return rv;
+	rv = gfs2_ok_for_dio(ip, rw, offset);
+	if (rv != 1)
+		goto out; /* dio not valid, fall back to buffered i/o */
+
+	rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
+					   iov, offset, nr_segs,
+					   gfs2_get_block_direct, NULL);
+out:
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	return rv;
+}
+
+/**
+ * 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_num.no_formal_ino,
+			(unsigned long long)ip->i_num.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
+ *
+ * Call try_to_free_buffers() if the buffers in this page can be
+ * released.
+ *
+ * Returns: 0
+ */
+
+int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	struct inode *aspace = page->mapping->host;
+	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;
+
+	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();
+		}
+
+		gfs2_assert_warn(sdp, !buffer_pinned(bh));
+		gfs2_assert_warn(sdp, !buffer_dirty(bh));
+
+		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;
+			bh->b_private = NULL;
+		}
+		gfs2_log_unlock(sdp);
+		if (bd)
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+out:
+	return try_to_free_buffers(page);
+}
+
+const struct address_space_operations gfs2_file_aops = {
+	.writepage = gfs2_writepage,
+	.writepages = gfs2_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.prepare_write = gfs2_prepare_write,
+	.commit_write = gfs2_commit_write,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+};
+

fs/gfs2/ops_address.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_ADDRESS_DOT_H__
+#define __OPS_ADDRESS_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+
+extern const struct address_space_operations gfs2_file_aops;
+extern int gfs2_get_block(struct inode *inode, sector_t lblock,
+			  struct buffer_head *bh_result, int create);
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+
+#endif /* __OPS_ADDRESS_DOT_H__ */

fs/gfs2/ops_dentry.c

@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/smp_lock.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "ops_dentry.h"
+#include "util.h"
+
+/**
+ * gfs2_drevalidate - Check directory lookup consistency
+ * @dentry: the mapping to check
+ * @nd:
+ *
+ * Check to make sure the lookup necessary to arrive at this inode from its
+ * parent is still good.
+ *
+ * Returns: 1 if the dentry is ok, 0 if it isn't
+ */
+
+static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *parent = dget_parent(dentry);
+	struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
+	struct gfs2_inode *dip = GFS2_I(parent->d_inode);
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_holder d_gh;
+	struct gfs2_inode *ip;
+	struct gfs2_inum_host inum;
+	unsigned int type;
+	int error;
+	int had_lock=0;
+
+	if (inode && is_bad_inode(inode))
+		goto invalid;
+
+	if (sdp->sd_args.ar_localcaching)
+		goto valid;
+
+	had_lock = gfs2_glock_is_locked_by_me(dip->i_gl);
+	if (!had_lock) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		if (error)
+			goto fail;
+	} 
+
+	error = gfs2_dir_search(parent->d_inode, &dentry->d_name, &inum, &type);
+	switch (error) {
+	case 0:
+		if (!inode)
+			goto invalid_gunlock;
+		break;
+	case -ENOENT:
+		if (!inode)
+			goto valid_gunlock;
+		goto invalid_gunlock;
+	default:
+		goto fail_gunlock;
+	}
+
+	ip = GFS2_I(inode);
+
+	if (!gfs2_inum_equal(&ip->i_num, &inum))
+		goto invalid_gunlock;
+
+	if (IF2DT(ip->i_inode.i_mode) != type) {
+		gfs2_consist_inode(dip);
+		goto fail_gunlock;
+	}
+
+valid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+valid:
+	dput(parent);
+	return 1;
+
+invalid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+invalid:
+	if (inode && S_ISDIR(inode->i_mode)) {
+		if (have_submounts(dentry))
+			goto valid;
+		shrink_dcache_parent(dentry);
+	}
+	d_drop(dentry);
+	dput(parent);
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+fail:
+	dput(parent);
+	return 0;
+}
+
+static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
+{
+	str->hash = gfs2_disk_hash(str->name, str->len);
+	return 0;
+}
+
+struct dentry_operations gfs2_dops = {
+	.d_revalidate = gfs2_drevalidate,
+	.d_hash = gfs2_dhash,
+};
+

fs/gfs2/ops_dentry.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_DENTRY_DOT_H__
+#define __OPS_DENTRY_DOT_H__
+
+#include <linux/dcache.h>
+
+extern struct dentry_operations gfs2_dops;
+
+#endif /* __OPS_DENTRY_DOT_H__ */

fs/gfs2/ops_export.c

@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "ops_dentry.h"
+#include "ops_export.h"
+#include "rgrp.h"
+#include "util.h"
+
+static struct dentry *gfs2_decode_fh(struct super_block *sb,
+				     __u32 *p,
+				     int fh_len,
+				     int fh_type,
+				     int (*acceptable)(void *context,
+						       struct dentry *dentry),
+				     void *context)
+{
+	__be32 *fh = (__force __be32 *)p;
+	struct gfs2_fh_obj fh_obj;
+	struct gfs2_inum_host *this, parent;
+
+	this 		= &fh_obj.this;
+	fh_obj.imode 	= DT_UNKNOWN;
+	memset(&parent, 0, sizeof(struct gfs2_inum));
+
+	switch (fh_len) {
+	case GFS2_LARGE_FH_SIZE:
+		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
+		parent.no_formal_ino |= be32_to_cpu(fh[5]);
+		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
+		parent.no_addr |= be32_to_cpu(fh[7]);
+		fh_obj.imode = be32_to_cpu(fh[8]);
+	case GFS2_SMALL_FH_SIZE:
+		this->no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
+		this->no_formal_ino |= be32_to_cpu(fh[1]);
+		this->no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
+		this->no_addr |= be32_to_cpu(fh[3]);
+		break;
+	default:
+		return NULL;
+	}
+
+	return gfs2_export_ops.find_exported_dentry(sb, &fh_obj, &parent,
+						    acceptable, context);
+}
+
+static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
+			  int connectable)
+{
+	__be32 *fh = (__force __be32 *)p;
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (*len < GFS2_SMALL_FH_SIZE ||
+	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+		return 255;
+
+	fh[0] = cpu_to_be32(ip->i_num.no_formal_ino >> 32);
+	fh[1] = cpu_to_be32(ip->i_num.no_formal_ino & 0xFFFFFFFF);
+	fh[2] = cpu_to_be32(ip->i_num.no_addr >> 32);
+	fh[3] = cpu_to_be32(ip->i_num.no_addr & 0xFFFFFFFF);
+	*len = GFS2_SMALL_FH_SIZE;
+
+	if (!connectable || inode == sb->s_root->d_inode)
+		return *len;
+
+	spin_lock(&dentry->d_lock);
+	inode = dentry->d_parent->d_inode;
+	ip = GFS2_I(inode);
+	igrab(inode);
+	spin_unlock(&dentry->d_lock);
+
+	fh[4] = cpu_to_be32(ip->i_num.no_formal_ino >> 32);
+	fh[5] = cpu_to_be32(ip->i_num.no_formal_ino & 0xFFFFFFFF);
+	fh[6] = cpu_to_be32(ip->i_num.no_addr >> 32);
+	fh[7] = cpu_to_be32(ip->i_num.no_addr & 0xFFFFFFFF);
+
+	fh[8]  = cpu_to_be32(inode->i_mode);
+	fh[9]  = 0;	/* pad to double word */
+	*len = GFS2_LARGE_FH_SIZE;
+
+	iput(inode);
+
+	return *len;
+}
+
+struct get_name_filldir {
+	struct gfs2_inum_host inum;
+	char *name;
+};
+
+static int get_name_filldir(void *opaque, const char *name, int length,
+			    loff_t offset, u64 inum, unsigned int type)
+{
+	struct get_name_filldir *gnfd = opaque;
+
+	if (inum != gnfd->inum.no_addr)
+		return 0;
+
+	memcpy(gnfd->name, name, length);
+	gnfd->name[length] = 0;
+
+	return 1;
+}
+
+static int gfs2_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct inode *dir = parent->d_inode;
+	struct inode *inode = child->d_inode;
+	struct gfs2_inode *dip, *ip;
+	struct get_name_filldir gnfd;
+	struct gfs2_holder gh;
+	u64 offset = 0;
+	int error;
+
+	if (!dir)
+		return -EINVAL;
+
+	if (!S_ISDIR(dir->i_mode) || !inode)
+		return -EINVAL;
+
+	dip = GFS2_I(dir);
+	ip = GFS2_I(inode);
+
+	*name = 0;
+	gnfd.inum = ip->i_num;
+	gnfd.name = name;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (error)
+		return error;
+
+	error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
+
+	gfs2_glock_dq_uninit(&gh);
+
+	if (!error && !*name)
+		error = -ENOENT;
+
+	return error;
+}
+
+static struct dentry *gfs2_get_parent(struct dentry *child)
+{
+	struct qstr dotdot;
+	struct inode *inode;
+	struct dentry *dentry;
+
+	gfs2_str2qstr(&dotdot, "..");
+	inode = gfs2_lookupi(child->d_inode, &dotdot, 1, NULL);
+
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+	/*
+	 * In case of an error, @inode carries the error value, and we
+	 * have to return that as a(n invalid) pointer to dentry.
+	 */
+	if (IS_ERR(inode))
+		return ERR_PTR(PTR_ERR(inode));
+
+	dentry = d_alloc_anon(inode);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dentry->d_op = &gfs2_dops;
+	return dentry;
+}
+
+static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_fh_obj *fh_obj = (struct gfs2_fh_obj *)inum_obj;
+	struct gfs2_inum_host *inum = &fh_obj->this;
+	struct gfs2_holder i_gh, ri_gh, rgd_gh;
+	struct gfs2_rgrpd *rgd;
+	struct inode *inode;
+	struct dentry *dentry;
+	int error;
+
+	/* System files? */
+
+	inode = gfs2_ilookup(sb, inum);
+	if (inode) {
+		if (GFS2_I(inode)->i_num.no_formal_ino != inum->no_formal_ino) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		goto out_inode;
+	}
+
+	error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
+				  LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return ERR_PTR(error);
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto fail;
+
+	error = -EINVAL;
+	rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
+	if (!rgd)
+		goto fail_rindex;
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
+	if (error)
+		goto fail_rindex;
+
+	error = -ESTALE;
+	if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
+		goto fail_rgd;
+
+	gfs2_glock_dq_uninit(&rgd_gh);
+	gfs2_glock_dq_uninit(&ri_gh);
+
+	inode = gfs2_inode_lookup(sb, inum, fh_obj->imode);
+	if (!inode)
+		goto fail;
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		goto fail;
+	}
+
+	error = gfs2_inode_refresh(GFS2_I(inode));
+	if (error) {
+		iput(inode);
+		goto fail;
+	}
+
+	error = -EIO;
+	if (GFS2_I(inode)->i_di.di_flags & GFS2_DIF_SYSTEM) {
+		iput(inode);
+		goto fail;
+	}
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+out_inode:
+	dentry = d_alloc_anon(inode);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dentry->d_op = &gfs2_dops;
+	return dentry;
+
+fail_rgd:
+	gfs2_glock_dq_uninit(&rgd_gh);
+
+fail_rindex:
+	gfs2_glock_dq_uninit(&ri_gh);
+
+fail:
+	gfs2_glock_dq_uninit(&i_gh);
+	return ERR_PTR(error);
+}
+
+struct export_operations gfs2_export_ops = {
+	.decode_fh = gfs2_decode_fh,
+	.encode_fh = gfs2_encode_fh,
+	.get_name = gfs2_get_name,
+	.get_parent = gfs2_get_parent,
+	.get_dentry = gfs2_get_dentry,
+};
+

fs/gfs2/ops_export.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_EXPORT_DOT_H__
+#define __OPS_EXPORT_DOT_H__
+
+#define GFS2_SMALL_FH_SIZE 4
+#define GFS2_LARGE_FH_SIZE 10
+
+extern struct export_operations gfs2_export_ops;
+struct gfs2_fh_obj {
+	struct gfs2_inum_host this;
+	__u32            imode;
+};
+
+#endif /* __OPS_EXPORT_DOT_H__ */

fs/gfs2/ops_file.c

@@ -0,0 +1,654 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/smp_lock.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/ext2_fs.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+#include <linux/writeback.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "lm.h"
+#include "log.h"
+#include "meta_io.h"
+#include "ops_file.h"
+#include "ops_vm.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "eaops.h"
+
+/*
+ * Most fields left uninitialised to catch anybody who tries to
+ * use them. f_flags set to prevent file_accessed() from touching
+ * any other part of this. Its use is purely as a flag so that we
+ * know (in readpage()) whether or not do to locking.
+ */
+struct file gfs2_internal_file_sentinel = {
+	.f_flags = O_NOATIME|O_RDONLY,
+};
+
+static int gfs2_read_actor(read_descriptor_t *desc, struct page *page,
+			   unsigned long offset, unsigned long size)
+{
+	char *kaddr;
+	unsigned long count = desc->count;
+
+	if (size > count)
+		size = count;
+
+	kaddr = kmap(page);
+	memcpy(desc->arg.data, kaddr + offset, size);
+	kunmap(page);
+
+	desc->count = count - size;
+	desc->written += size;
+	desc->arg.buf += size;
+	return size;
+}
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+		       char *buf, loff_t *pos, unsigned size)
+{
+	struct inode *inode = &ip->i_inode;
+	read_descriptor_t desc;
+	desc.written = 0;
+	desc.arg.data = buf;
+	desc.count = size;
+	desc.error = 0;
+	do_generic_mapping_read(inode->i_mapping, ra_state,
+				&gfs2_internal_file_sentinel, pos, &desc,
+				gfs2_read_actor);
+	return desc.written ? desc.written : desc.error;
+}
+
+/**
+ * gfs2_llseek - seek to a location in a file
+ * @file: the file
+ * @offset: the offset
+ * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
+ *
+ * SEEK_END requires the glock for the file because it references the
+ * file's size.
+ *
+ * Returns: The new offset, or errno
+ */
+
+static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	loff_t error;
+
+	if (origin == 2) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (!error) {
+			error = remote_llseek(file, offset, origin);
+			gfs2_glock_dq_uninit(&i_gh);
+		}
+	} else
+		error = remote_llseek(file, offset, origin);
+
+	return error;
+}
+
+/**
+ * gfs2_readdir - Read directory entries from a directory
+ * @file: The directory to read from
+ * @dirent: Buffer for dirents
+ * @filldir: Function used to do the copying
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct inode *dir = file->f_mapping->host;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct gfs2_holder d_gh;
+	u64 offset = file->f_pos;
+	int error;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
+	error = gfs2_glock_nq_atime(&d_gh);
+	if (error) {
+		gfs2_holder_uninit(&d_gh);
+		return error;
+	}
+
+	error = gfs2_dir_read(dir, &offset, dirent, filldir);
+
+	gfs2_glock_dq_uninit(&d_gh);
+
+	file->f_pos = offset;
+
+	return error;
+}
+
+/**
+ * fsflags_cvt
+ * @table: A table of 32 u32 flags
+ * @val: a 32 bit value to convert
+ *
+ * This function can be used to convert between fsflags values and
+ * GFS2's own flags values.
+ *
+ * Returns: the converted flags
+ */
+static u32 fsflags_cvt(const u32 *table, u32 val)
+{
+	u32 res = 0;
+	while(val) {
+		if (val & 1)
+			res |= *table;
+		table++;
+		val >>= 1;
+	}
+	return res;
+}
+
+static const u32 fsflags_to_gfs2[32] = {
+	[3] = GFS2_DIF_SYNC,
+	[4] = GFS2_DIF_IMMUTABLE,
+	[5] = GFS2_DIF_APPENDONLY,
+	[7] = GFS2_DIF_NOATIME,
+	[12] = GFS2_DIF_EXHASH,
+	[14] = GFS2_DIF_JDATA,
+	[20] = GFS2_DIF_DIRECTIO,
+};
+
+static const u32 gfs2_to_fsflags[32] = {
+	[gfs2fl_Sync] = FS_SYNC_FL,
+	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
+	[gfs2fl_AppendOnly] = FS_APPEND_FL,
+	[gfs2fl_NoAtime] = FS_NOATIME_FL,
+	[gfs2fl_ExHash] = FS_INDEX_FL,
+	[gfs2fl_Jdata] = FS_JOURNAL_DATA_FL,
+	[gfs2fl_Directio] = FS_DIRECTIO_FL,
+	[gfs2fl_InheritDirectio] = FS_DIRECTIO_FL,
+	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
+};
+
+static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+	u32 fsflags;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+	error = gfs2_glock_nq_atime(&gh);
+	if (error)
+		return error;
+
+	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_di.di_flags);
+	if (put_user(fsflags, ptr))
+		error = -EFAULT;
+
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	return error;
+}
+
+void gfs2_set_inode_flags(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_dinode_host *di = &ip->i_di;
+	unsigned int flags = inode->i_flags;
+
+	flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	if (di->di_flags & GFS2_DIF_IMMUTABLE)
+		flags |= S_IMMUTABLE;
+	if (di->di_flags & GFS2_DIF_APPENDONLY)
+		flags |= S_APPEND;
+	if (di->di_flags & GFS2_DIF_NOATIME)
+		flags |= S_NOATIME;
+	if (di->di_flags & GFS2_DIF_SYNC)
+		flags |= S_SYNC;
+	inode->i_flags = flags;
+}
+
+/* Flags that can be set by user space */
+#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
+			     GFS2_DIF_DIRECTIO|			\
+			     GFS2_DIF_IMMUTABLE|		\
+			     GFS2_DIF_APPENDONLY|		\
+			     GFS2_DIF_NOATIME|			\
+			     GFS2_DIF_SYNC|			\
+			     GFS2_DIF_SYSTEM|			\
+			     GFS2_DIF_INHERIT_DIRECTIO|		\
+			     GFS2_DIF_INHERIT_JDATA)
+
+/**
+ * gfs2_set_flags - set flags on an inode
+ * @inode: The inode
+ * @flags: The flags to set
+ * @mask: Indicates which flags are valid
+ *
+ */
+static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder gh;
+	int error;
+	u32 new_flags, flags;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (error)
+		return error;
+
+	flags = ip->i_di.di_flags;
+	new_flags = (flags & ~mask) | (reqflags & mask);
+	if ((new_flags ^ flags) == 0)
+		goto out;
+
+	if (S_ISDIR(inode->i_mode)) {
+		if ((new_flags ^ flags) & GFS2_DIF_JDATA)
+			new_flags ^= (GFS2_DIF_JDATA|GFS2_DIF_INHERIT_JDATA);
+		if ((new_flags ^ flags) & GFS2_DIF_DIRECTIO)
+			new_flags ^= (GFS2_DIF_DIRECTIO|GFS2_DIF_INHERIT_DIRECTIO);
+	}
+
+	error = -EINVAL;
+	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
+		goto out;
+
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
+		goto out;
+	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
+		goto out;
+	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		goto out;
+	if (!IS_IMMUTABLE(inode)) {
+		error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			goto out;
+	}
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		goto out;
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		goto out_trans_end;
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	ip->i_di.di_flags = new_flags;
+	gfs2_dinode_out(ip, bh->b_data);
+	brelse(bh);
+	gfs2_set_inode_flags(inode);
+out_trans_end:
+	gfs2_trans_end(sdp);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return error;
+}
+
+static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
+{
+	u32 fsflags, gfsflags;
+	if (get_user(fsflags, ptr))
+		return -EFAULT;
+	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
+	return do_gfs2_set_flags(filp, gfsflags, ~0);
+}
+
+static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch(cmd) {
+	case FS_IOC_GETFLAGS:
+		return gfs2_get_flags(filp, (u32 __user *)arg);
+	case FS_IOC_SETFLAGS:
+		return gfs2_set_flags(filp, (u32 __user *)arg);
+	}
+	return -ENOTTY;
+}
+
+
+/**
+ * gfs2_mmap -
+ * @file: The file to map
+ * @vma: The VMA which described the mapping
+ *
+ * Returns: 0 or error code
+ */
+
+static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
+	error = gfs2_glock_nq_atime(&i_gh);
+	if (error) {
+		gfs2_holder_uninit(&i_gh);
+		return error;
+	}
+
+	/* This is VM_MAYWRITE instead of VM_WRITE because a call
+	   to mprotect() can turn on VM_WRITE later. */
+
+	if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) ==
+	    (VM_MAYSHARE | VM_MAYWRITE))
+		vma->vm_ops = &gfs2_vm_ops_sharewrite;
+	else
+		vma->vm_ops = &gfs2_vm_ops_private;
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return error;
+}
+
+/**
+ * gfs2_open - open a file
+ * @inode: the inode to open
+ * @file: the struct file for this opening
+ *
+ * Returns: errno
+ */
+
+static int gfs2_open(struct inode *inode, struct file *file)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	struct gfs2_file *fp;
+	int error;
+
+	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	mutex_init(&fp->f_fl_mutex);
+
+	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
+	file->private_data = fp;
+
+	if (S_ISREG(ip->i_inode.i_mode)) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (error)
+			goto fail;
+
+		if (!(file->f_flags & O_LARGEFILE) &&
+		    ip->i_di.di_size > MAX_NON_LFS) {
+			error = -EFBIG;
+			goto fail_gunlock;
+		}
+
+		/* Listen to the Direct I/O flag */
+
+		if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
+			file->f_flags |= O_DIRECT;
+
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+fail:
+	file->private_data = NULL;
+	kfree(fp);
+	return error;
+}
+
+/**
+ * gfs2_close - called to close a struct file
+ * @inode: the inode the struct file belongs to
+ * @file: the struct file being closed
+ *
+ * Returns: errno
+ */
+
+static int gfs2_close(struct inode *inode, struct file *file)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_file *fp;
+
+	fp = file->private_data;
+	file->private_data = NULL;
+
+	if (gfs2_assert_warn(sdp, fp))
+		return -EIO;
+
+	kfree(fp);
+
+	return 0;
+}
+
+/**
+ * gfs2_fsync - sync the dirty data for a file (across the cluster)
+ * @file: the file that points to the dentry (we ignore this)
+ * @dentry: the dentry that points to the inode to sync
+ *
+ * The VFS will flush "normal" data for us. We only need to worry
+ * about metadata here. For journaled data, we just do a log flush
+ * as we can't avoid it. Otherwise we can just bale out if datasync
+ * is set. For stuffed inodes we must flush the log in order to
+ * ensure that all data is on disk.
+ *
+ * The call to write_inode_now() is there to write back metadata and
+ * the inode itself. It does also try and write the data, but thats
+ * (hopefully) a no-op due to the VFS having already called filemap_fdatawrite()
+ * for us.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
+	int ret = 0;
+
+	if (gfs2_is_jdata(GFS2_I(inode))) {
+		gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
+		return 0;
+	}
+
+	if (sync_state != 0) {
+		if (!datasync)
+			ret = write_inode_now(inode, 0);
+
+		if (gfs2_is_stuffed(GFS2_I(inode)))
+			gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
+	}
+
+	return ret;
+}
+
+/**
+ * gfs2_lock - acquire/release a posix lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+	struct lm_lockname name =
+		{ .ln_number = ip->i_num.no_addr,
+		  .ln_type = LM_TYPE_PLOCK };
+
+	if (!(fl->fl_flags & FL_POSIX))
+		return -ENOLCK;
+	if ((ip->i_inode.i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+		return -ENOLCK;
+
+	if (sdp->sd_args.ar_localflocks) {
+		if (IS_GETLK(cmd)) {
+			struct file_lock tmp;
+			int ret;
+			ret = posix_test_lock(file, fl, &tmp);
+			fl->fl_type = F_UNLCK;
+			if (ret)
+				memcpy(fl, &tmp, sizeof(struct file_lock));
+			return 0;
+		} else {
+			return posix_lock_file_wait(file, fl);
+		}
+	}
+
+	if (IS_GETLK(cmd))
+		return gfs2_lm_plock_get(sdp, &name, file, fl);
+	else if (fl->fl_type == F_UNLCK)
+		return gfs2_lm_punlock(sdp, &name, file, fl);
+	else
+		return gfs2_lm_plock(sdp, &name, file, cmd, fl);
+}
+
+static int do_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+	struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
+	struct gfs2_glock *gl;
+	unsigned int state;
+	int flags;
+	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;
+
+	mutex_lock(&fp->f_fl_mutex);
+
+	gl = fl_gh->gh_gl;
+	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);
+	} else {
+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
+				      ip->i_num.no_addr, &gfs2_flock_glops,
+				      CREATE, &gl);
+		if (error)
+			goto out;
+	}
+
+	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);
+		if (error == GLR_TRYFAILED)
+			error = -EAGAIN;
+	} else {
+		error = flock_lock_file_wait(file, fl);
+		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
+	}
+
+out:
+	mutex_unlock(&fp->f_fl_mutex);
+	return error;
+}
+
+static void do_unflock(struct file *file, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+
+	mutex_lock(&fp->f_fl_mutex);
+	flock_lock_file_wait(file, fl);
+	if (fl_gh->gh_gl)
+		gfs2_glock_dq_uninit(fl_gh);
+	mutex_unlock(&fp->f_fl_mutex);
+}
+
+/**
+ * gfs2_flock - acquire/release a flock lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		return -ENOLCK;
+	if ((ip->i_inode.i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+		return -ENOLCK;
+
+	if (sdp->sd_args.ar_localflocks)
+		return flock_lock_file_wait(file, fl);
+
+	if (fl->fl_type == F_UNLCK) {
+		do_unflock(file, fl);
+		return 0;
+	} else {
+		return do_flock(file, cmd, fl);
+	}
+}
+
+const struct file_operations gfs2_file_fops = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.sendfile	= generic_file_sendfile,
+	.flock		= gfs2_flock,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+};
+
+const struct file_operations gfs2_dir_fops = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+};
+

fs/gfs2/ops_file.h

@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_FILE_DOT_H__
+#define __OPS_FILE_DOT_H__
+
+#include <linux/fs.h>
+struct gfs2_inode;
+
+extern struct file gfs2_internal_file_sentinel;
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_set_inode_flags(struct inode *inode);
+extern const struct file_operations gfs2_file_fops;
+extern const struct file_operations gfs2_dir_fops;
+
+#endif /* __OPS_FILE_DOT_H__ */

fs/gfs2/ops_fstype.c

@@ -0,0 +1,925 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/kthread.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "daemon.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "lm.h"
+#include "mount.h"
+#include "ops_export.h"
+#include "ops_fstype.h"
+#include "ops_super.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "sys.h"
+#include "util.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;
+
+	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
+	if (!sdp)
+		return NULL;
+
+	sb->s_fs_info = sdp;
+	sdp->sd_vfs = sb;
+
+	gfs2_tune_init(&sdp->sd_tune);
+
+	INIT_LIST_HEAD(&sdp->sd_reclaim_list);
+	spin_lock_init(&sdp->sd_reclaim_lock);
+	init_waitqueue_head(&sdp->sd_reclaim_wq);
+
+	mutex_init(&sdp->sd_inum_mutex);
+	spin_lock_init(&sdp->sd_statfs_spin);
+	mutex_init(&sdp->sd_statfs_mutex);
+
+	spin_lock_init(&sdp->sd_rindex_spin);
+	mutex_init(&sdp->sd_rindex_mutex);
+	INIT_LIST_HEAD(&sdp->sd_rindex_list);
+	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
+	INIT_LIST_HEAD(&sdp->sd_rindex_recent_list);
+
+	INIT_LIST_HEAD(&sdp->sd_jindex_list);
+	spin_lock_init(&sdp->sd_jindex_spin);
+	mutex_init(&sdp->sd_jindex_mutex);
+
+	INIT_LIST_HEAD(&sdp->sd_quota_list);
+	spin_lock_init(&sdp->sd_quota_spin);
+	mutex_init(&sdp->sd_quota_mutex);
+
+	spin_lock_init(&sdp->sd_log_lock);
+
+	INIT_LIST_HEAD(&sdp->sd_log_le_gl);
+	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
+	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
+	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+
+	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);
+
+	INIT_LIST_HEAD(&sdp->sd_revoke_list);
+
+	mutex_init(&sdp->sd_freeze_lock);
+
+	return sdp;
+}
+
+static void init_vfs(struct super_block *sb, unsigned noatime)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	sb->s_magic = GFS2_MAGIC;
+	sb->s_op = &gfs2_super_ops;
+	sb->s_export_op = &gfs2_export_ops;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
+	if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
+		set_bit(noatime, &sdp->sd_flags);
+
+	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
+	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+}
+
+static int init_names(struct gfs2_sbd *sdp, int silent)
+{
+	struct page *page;
+	char *proto, *table;
+	int error = 0;
+
+	proto = sdp->sd_args.ar_lockproto;
+	table = sdp->sd_args.ar_locktable;
+
+	/*  Try to autodetect  */
+
+	if (!proto[0] || !table[0]) {
+		struct gfs2_sb *sb;
+		page = gfs2_read_super(sdp->sd_vfs, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+		if (!page)
+			return -ENOBUFS;
+		sb = kmap(page);
+		gfs2_sb_in(&sdp->sd_sb, sb);
+		kunmap(page);
+		__free_page(page);
+
+		error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+		if (error)
+			goto out;
+
+		if (!proto[0])
+			proto = sdp->sd_sb.sb_lockproto;
+		if (!table[0])
+			table = sdp->sd_sb.sb_locktable;
+	}
+
+	if (!table[0])
+		table = sdp->sd_vfs->s_id;
+
+	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
+	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
+
+out:
+	return error;
+}
+
+static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
+			int undo)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	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++) {
+		p = kthread_run(gfs2_glockd, sdp, "gfs2_glockd");
+		error = IS_ERR(p);
+		if (error) {
+			fs_err(sdp, "can't start glockd thread: %d\n", error);
+			goto fail;
+		}
+		sdp->sd_glockd_process[sdp->sd_glockd_num] = p;
+	}
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
+				  mount_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire mount glock: %d\n", error);
+		goto fail;
+	}
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_SHARED,
+				  LM_FLAG_NOEXP | GL_EXACT,
+				  &sdp->sd_live_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire live glock: %d\n", error);
+		goto fail_mount;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
+			       CREATE, &sdp->sd_rename_gl);
+	if (error) {
+		fs_err(sdp, "can't create rename glock: %d\n", error);
+		goto fail_live;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
+			       CREATE, &sdp->sd_trans_gl);
+	if (error) {
+		fs_err(sdp, "can't create transaction glock: %d\n", error);
+		goto fail_rename;
+	}
+	set_bit(GLF_STICKY, &sdp->sd_trans_gl->gl_flags);
+
+	return 0;
+
+fail_trans:
+	gfs2_glock_put(sdp->sd_trans_gl);
+fail_rename:
+	gfs2_glock_put(sdp->sd_rename_gl);
+fail_live:
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+fail_mount:
+	gfs2_glock_dq_uninit(mount_gh);
+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 struct inode *gfs2_lookup_root(struct super_block *sb,
+				      struct gfs2_inum_host *inum)
+{
+	return gfs2_inode_lookup(sb, inum, DT_DIR);
+}
+
+static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_holder sb_gh;
+	struct gfs2_inum_host *inum;
+	struct inode *inode;
+	int error = 0;
+
+	if (undo) {
+		if (sb->s_root) {
+			dput(sb->s_root);
+			sb->s_root = NULL;
+		}
+		return 0;
+	}
+
+	error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+				 LM_ST_SHARED, 0, &sb_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire superblock glock: %d\n", error);
+		return error;
+	}
+
+	error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
+	if (error) {
+		fs_err(sdp, "can't read superblock: %d\n", error);
+		goto out;
+	}
+
+	/* Set up the buffer cache and SB for real */
+	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
+		error = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too small for device "
+		       "block size (%u)\n",
+		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
+		goto out;
+	}
+	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
+		error = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too big for machine "
+		       "page size (%u)\n",
+		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
+		goto out;
+	}
+	sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);
+
+	/* Get the root inode */
+	inum = &sdp->sd_sb.sb_root_dir;
+	if (sb->s_type == &gfs2meta_fs_type)
+		inum = &sdp->sd_sb.sb_master_dir;
+	inode = gfs2_lookup_root(sb, inum);
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		fs_err(sdp, "can't read in root inode: %d\n", error);
+		goto out;
+	}
+
+	sb->s_root = d_alloc_root(inode);
+	if (!sb->s_root) {
+		fs_err(sdp, "can't get root dentry\n");
+		error = -ENOMEM;
+		iput(inode);
+	}
+	sb->s_root->d_op = &gfs2_dops;
+out:
+	gfs2_glock_dq_uninit(&sb_gh);
+	return error;
+}
+
+static int init_journal(struct gfs2_sbd *sdp, int undo)
+{
+	struct gfs2_holder ji_gh;
+	struct task_struct *p;
+	struct gfs2_inode *ip;
+	int jindex = 1;
+	int error = 0;
+
+	if (undo) {
+		jindex = 0;
+		goto fail_recoverd;
+	}
+
+	sdp->sd_jindex = gfs2_lookup_simple(sdp->sd_master_dir, "jindex");
+	if (IS_ERR(sdp->sd_jindex)) {
+		fs_err(sdp, "can't lookup journal index: %d\n", error);
+		return PTR_ERR(sdp->sd_jindex);
+	}
+	ip = GFS2_I(sdp->sd_jindex);
+	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
+
+	/* Load in the journal index special file */
+
+	error = gfs2_jindex_hold(sdp, &ji_gh);
+	if (error) {
+		fs_err(sdp, "can't read journal index: %d\n", error);
+		goto fail;
+	}
+
+	error = -EINVAL;
+	if (!gfs2_jindex_size(sdp)) {
+		fs_err(sdp, "no journals!\n");
+		goto fail_jindex;
+	}
+
+	if (sdp->sd_args.ar_spectator) {
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
+		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+	} else {
+		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
+			fs_err(sdp, "can't mount journal #%u\n",
+			       sdp->sd_lockstruct.ls_jid);
+			fs_err(sdp, "there are only %u journals (0 - %u)\n",
+			       gfs2_jindex_size(sdp),
+			       gfs2_jindex_size(sdp) - 1);
+			goto fail_jindex;
+		}
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);
+
+		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
+					  &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
+					  &sdp->sd_journal_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal glock: %d\n", error);
+			goto fail_jindex;
+		}
+
+		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_EXACT,
+					   &sdp->sd_jinode_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal inode glock: %d\n",
+			       error);
+			goto fail_journal_gh;
+		}
+
+		error = gfs2_jdesc_check(sdp->sd_jdesc);
+		if (error) {
+			fs_err(sdp, "my journal (%u) is bad: %d\n",
+			       sdp->sd_jdesc->jd_jid, error);
+			goto fail_jinode_gh;
+		}
+		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+	}
+
+	if (sdp->sd_lockstruct.ls_first) {
+		unsigned int x;
+		for (x = 0; x < sdp->sd_journals; x++) {
+			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
+			if (error) {
+				fs_err(sdp, "error recovering journal %u: %d\n",
+				       x, error);
+				goto fail_jinode_gh;
+			}
+		}
+
+		gfs2_lm_others_may_mount(sdp);
+	} else if (!sdp->sd_args.ar_spectator) {
+		error = gfs2_recover_journal(sdp->sd_jdesc);
+		if (error) {
+			fs_err(sdp, "error recovering my journal: %d\n", error);
+			goto fail_jinode_gh;
+		}
+	}
+
+	set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
+	gfs2_glock_dq_uninit(&ji_gh);
+	jindex = 0;
+
+	p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start recoverd thread: %d\n", error);
+		goto fail_jinode_gh;
+	}
+	sdp->sd_recoverd_process = p;
+
+	return 0;
+
+fail_recoverd:
+	kthread_stop(sdp->sd_recoverd_process);
+fail_jinode_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+fail_journal_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+fail_jindex:
+	gfs2_jindex_free(sdp);
+	if (jindex)
+		gfs2_glock_dq_uninit(&ji_gh);
+fail:
+	iput(sdp->sd_jindex);
+	return error;
+}
+
+
+static int init_inodes(struct gfs2_sbd *sdp, int undo)
+{
+	int error = 0;
+	struct gfs2_inode *ip;
+	struct inode *inode;
+
+	if (undo)
+		goto fail_qinode;
+
+	inode = gfs2_lookup_root(sdp->sd_vfs, &sdp->sd_sb.sb_master_dir);
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		fs_err(sdp, "can't read in master directory: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_master_dir = inode;
+
+	error = init_journal(sdp, undo);
+	if (error)
+		goto fail_master;
+
+	/* Read in the master inode number inode */
+	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
+	if (IS_ERR(sdp->sd_inum_inode)) {
+		error = PTR_ERR(sdp->sd_inum_inode);
+		fs_err(sdp, "can't read in inum inode: %d\n", error);
+		goto fail_journal;
+	}
+
+
+	/* Read in the master statfs inode */
+	sdp->sd_statfs_inode = gfs2_lookup_simple(sdp->sd_master_dir, "statfs");
+	if (IS_ERR(sdp->sd_statfs_inode)) {
+		error = PTR_ERR(sdp->sd_statfs_inode);
+		fs_err(sdp, "can't read in statfs inode: %d\n", error);
+		goto fail_inum;
+	}
+
+	/* Read in the resource index inode */
+	sdp->sd_rindex = gfs2_lookup_simple(sdp->sd_master_dir, "rindex");
+	if (IS_ERR(sdp->sd_rindex)) {
+		error = PTR_ERR(sdp->sd_rindex);
+		fs_err(sdp, "can't get resource index inode: %d\n", error);
+		goto fail_statfs;
+	}
+	ip = GFS2_I(sdp->sd_rindex);
+	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
+	sdp->sd_rindex_vn = ip->i_gl->gl_vn - 1;
+
+	/* Read in the quota inode */
+	sdp->sd_quota_inode = gfs2_lookup_simple(sdp->sd_master_dir, "quota");
+	if (IS_ERR(sdp->sd_quota_inode)) {
+		error = PTR_ERR(sdp->sd_quota_inode);
+		fs_err(sdp, "can't get quota file inode: %d\n", error);
+		goto fail_rindex;
+	}
+	return 0;
+
+fail_qinode:
+	iput(sdp->sd_quota_inode);
+fail_rindex:
+	gfs2_clear_rgrpd(sdp);
+	iput(sdp->sd_rindex);
+fail_statfs:
+	iput(sdp->sd_statfs_inode);
+fail_inum:
+	iput(sdp->sd_inum_inode);
+fail_journal:
+	init_journal(sdp, UNDO);
+fail_master:
+	iput(sdp->sd_master_dir);
+fail:
+	return error;
+}
+
+static int init_per_node(struct gfs2_sbd *sdp, int undo)
+{
+	struct inode *pn = NULL;
+	char buf[30];
+	int error = 0;
+	struct gfs2_inode *ip;
+
+	if (sdp->sd_args.ar_spectator)
+		return 0;
+
+	if (undo)
+		goto fail_qc_gh;
+
+	pn = gfs2_lookup_simple(sdp->sd_master_dir, "per_node");
+	if (IS_ERR(pn)) {
+		error = PTR_ERR(pn);
+		fs_err(sdp, "can't find per_node directory: %d\n", error);
+		return error;
+	}
+
+	sprintf(buf, "inum_range%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_ir_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_ir_inode)) {
+		error = PTR_ERR(sdp->sd_ir_inode);
+		fs_err(sdp, "can't find local \"ir\" file: %d\n", error);
+		goto fail;
+	}
+
+	sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_sc_inode)) {
+		error = PTR_ERR(sdp->sd_sc_inode);
+		fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
+		goto fail_ir_i;
+	}
+
+	sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_qc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_qc_inode)) {
+		error = PTR_ERR(sdp->sd_qc_inode);
+		fs_err(sdp, "can't find local \"qc\" file: %d\n", error);
+		goto fail_ut_i;
+	}
+
+	iput(pn);
+	pn = NULL;
+
+	ip = GFS2_I(sdp->sd_ir_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_ir_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"ir\" file: %d\n", error);
+		goto fail_qc_i;
+	}
+
+	ip = GFS2_I(sdp->sd_sc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_sc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
+		goto fail_ir_gh;
+	}
+
+	ip = GFS2_I(sdp->sd_qc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_qc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
+		goto fail_ut_gh;
+	}
+
+	return 0;
+
+fail_qc_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+fail_ut_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+fail_ir_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+fail_qc_i:
+	iput(sdp->sd_qc_inode);
+fail_ut_i:
+	iput(sdp->sd_sc_inode);
+fail_ir_i:
+	iput(sdp->sd_ir_inode);
+fail:
+	if (pn)
+		iput(pn);
+	return error;
+}
+
+static int init_threads(struct gfs2_sbd *sdp, int undo)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	if (undo)
+		goto fail_quotad;
+
+	sdp->sd_log_flush_time = jiffies;
+	sdp->sd_jindex_refresh_time = jiffies;
+
+	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start logd thread: %d\n", error);
+		return error;
+	}
+	sdp->sd_logd_process = p;
+
+	sdp->sd_statfs_sync_time = jiffies;
+	sdp->sd_quota_sync_time = jiffies;
+
+	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_quotad_process = p;
+
+	return 0;
+
+
+fail_quotad:
+	kthread_stop(sdp->sd_quotad_process);
+fail:
+	kthread_stop(sdp->sd_logd_process);
+	return error;
+}
+
+/**
+ * fill_super - Read in superblock
+ * @sb: The VFS superblock
+ * @data: Mount options
+ * @silent: Don't complain if it's not a GFS2 filesystem
+ *
+ * Returns: errno
+ */
+
+static int fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct gfs2_sbd *sdp;
+	struct gfs2_holder mount_gh;
+	int error;
+
+	sdp = init_sbd(sb);
+	if (!sdp) {
+		printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
+		return -ENOMEM;
+	}
+
+	error = gfs2_mount_args(sdp, (char *)data, 0);
+	if (error) {
+		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
+		goto fail;
+	}
+
+	init_vfs(sb, SDF_NOATIME);
+
+	/* Set up the buffer cache and fill in some fake block size values
+	   to allow us to read-in the on-disk superblock. */
+	sdp->sd_sb.sb_bsize = sb_min_blocksize(sb, GFS2_BASIC_BLOCK);
+	sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits;
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+                               GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+
+	error = init_names(sdp, silent);
+	if (error)
+		goto fail;
+
+	error = gfs2_sys_fs_add(sdp);
+	if (error)
+		goto fail;
+
+	error = gfs2_lm_mount(sdp, silent);
+	if (error)
+		goto fail_sys;
+
+	error = init_locking(sdp, &mount_gh, DO);
+	if (error)
+		goto fail_lm;
+
+	error = init_sb(sdp, silent, DO);
+	if (error)
+		goto fail_locking;
+
+	error = init_inodes(sdp, DO);
+	if (error)
+		goto fail_sb;
+
+	error = init_per_node(sdp, DO);
+	if (error)
+		goto fail_inodes;
+
+	error = gfs2_statfs_init(sdp);
+	if (error) {
+		fs_err(sdp, "can't initialize statfs subsystem: %d\n", error);
+		goto fail_per_node;
+	}
+
+	error = init_threads(sdp, DO);
+	if (error)
+		goto fail_per_node;
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_rw(sdp);
+		if (error) {
+			fs_err(sdp, "can't make FS RW: %d\n", error);
+			goto fail_threads;
+		}
+	}
+
+	gfs2_glock_dq_uninit(&mount_gh);
+
+	return 0;
+
+fail_threads:
+	init_threads(sdp, UNDO);
+fail_per_node:
+	init_per_node(sdp, UNDO);
+fail_inodes:
+	init_inodes(sdp, UNDO);
+fail_sb:
+	init_sb(sdp, 0, UNDO);
+fail_locking:
+	init_locking(sdp, &mount_gh, UNDO);
+fail_lm:
+	gfs2_gl_hash_clear(sdp, WAIT);
+	gfs2_lm_unmount(sdp);
+	while (invalidate_inodes(sb))
+		yield();
+fail_sys:
+	gfs2_sys_fs_del(sdp);
+fail:
+	kfree(sdp);
+	sb->s_fs_info = NULL;
+	return error;
+}
+
+static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
+		const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	struct super_block *sb;
+	struct gfs2_sbd *sdp;
+	int error = get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
+	if (error)
+		goto out;
+	sb = mnt->mnt_sb;
+	sdp = sb->s_fs_info;
+	sdp->sd_gfs2mnt = mnt;
+out:
+	return error;
+}
+
+static int fill_super_meta(struct super_block *sb, struct super_block *new,
+			   void *data, int silent)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct inode *inode;
+	int error = 0;
+
+	new->s_fs_info = sdp;
+	sdp->sd_vfs_meta = sb;
+
+	init_vfs(new, SDF_NOATIME);
+
+        /* Get the master inode */
+	inode = igrab(sdp->sd_master_dir);
+
+	new->s_root = d_alloc_root(inode);
+	if (!new->s_root) {
+		fs_err(sdp, "can't get root dentry\n");
+		error = -ENOMEM;
+		iput(inode);
+	} else
+		new->s_root->d_op = &gfs2_dops;
+
+	return error;
+}
+
+static int set_bdev_super(struct super_block *s, void *data)
+{
+	s->s_bdev = data;
+	s->s_dev = s->s_bdev->bd_dev;
+	return 0;
+}
+
+static int test_bdev_super(struct super_block *s, void *data)
+{
+	return s->s_bdev == data;
+}
+
+static struct super_block* get_gfs2_sb(const char *dev_name)
+{
+	struct kstat stat;
+	struct 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);
+	if (error) {
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
+		       dev_name);
+		goto out;
+	}
+	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);
+		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
+		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
+			sb = s;
+			goto free_nd;
+		}
+	}
+
+	printk(KERN_WARNING "GFS2: Unrecognized block device or "
+	       "mount point %s\n", dev_name);
+
+free_nd:
+	path_release(&nd);
+out:
+	return sb;
+}
+
+static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
+			    const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	int error = 0;
+	struct super_block *sb = NULL, *new;
+	struct gfs2_sbd *sdp;
+
+	sb = get_gfs2_sb(dev_name);
+	if (!sb) {
+		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
+		error = -ENOENT;
+		goto error;
+	}
+	sdp = (struct gfs2_sbd*) sb->s_fs_info;
+	if (sdp->sd_vfs_meta) {
+		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
+		error = -EBUSY;
+		goto error;
+	}
+	down(&sb->s_bdev->bd_mount_sem);
+	new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
+	up(&sb->s_bdev->bd_mount_sem);
+	if (IS_ERR(new)) {
+		error = PTR_ERR(new);
+		goto error;
+	}
+	module_put(fs_type->owner);
+	new->s_flags = flags;
+	strlcpy(new->s_id, sb->s_id, sizeof(new->s_id));
+	sb_set_blocksize(new, sb->s_blocksize);
+	error = fill_super_meta(sb, new, data, flags & MS_SILENT ? 1 : 0);
+	if (error) {
+		up_write(&new->s_umount);
+		deactivate_super(new);
+		goto error;
+	}
+
+	new->s_flags |= MS_ACTIVE;
+
+	/* Grab a reference to the gfs2 mount point */
+	atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
+	return simple_set_mnt(mnt, new);
+error:
+	return error;
+}
+
+static void gfs2_kill_sb(struct super_block *sb)
+{
+	kill_block_super(sb);
+}
+
+static void gfs2_kill_sb_meta(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	generic_shutdown_super(sb);
+	sdp->sd_vfs_meta = NULL;
+	atomic_dec(&sdp->sd_gfs2mnt->mnt_count);
+}
+
+struct file_system_type gfs2_fs_type = {
+	.name = "gfs2",
+	.fs_flags = FS_REQUIRES_DEV,
+	.get_sb = gfs2_get_sb,
+	.kill_sb = gfs2_kill_sb,
+	.owner = THIS_MODULE,
+};
+
+struct file_system_type gfs2meta_fs_type = {
+	.name = "gfs2meta",
+	.fs_flags = FS_REQUIRES_DEV,
+	.get_sb = gfs2_get_sb_meta,
+	.kill_sb = gfs2_kill_sb_meta,
+	.owner = THIS_MODULE,
+};
+

fs/gfs2/ops_fstype.h

@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_FSTYPE_DOT_H__
+#define __OPS_FSTYPE_DOT_H__
+
+#include <linux/fs.h>
+
+extern struct file_system_type gfs2_fs_type;
+extern struct file_system_type gfs2meta_fs_type;
+
+#endif /* __OPS_FSTYPE_DOT_H__ */

fs/gfs2/ops_inode.h

@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_INODE_DOT_H__
+#define __OPS_INODE_DOT_H__
+
+#include <linux/fs.h>
+
+extern const struct inode_operations gfs2_file_iops;
+extern const struct inode_operations gfs2_dir_iops;
+extern const struct inode_operations gfs2_symlink_iops;
+extern const struct inode_operations gfs2_dev_iops;
+
+#endif /* __OPS_INODE_DOT_H__ */

fs/gfs2/ops_super.c

@@ -0,0 +1,486 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "inode.h"
+#include "lm.h"
+#include "log.h"
+#include "mount.h"
+#include "ops_super.h"
+#include "quota.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "trans.h"
+#include "dir.h"
+#include "eattr.h"
+#include "bmap.h"
+
+/**
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @sync: synchronous write flag
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_inode(struct inode *inode, int sync)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	/* Check this is a "normal" inode */
+	if (inode->i_private) {
+		if (current->flags & PF_MEMALLOC)
+			return 0;
+		if (sync)
+			gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_put_super - Unmount the filesystem
+ * @sb: The VFS superblock
+ *
+ */
+
+static void gfs2_put_super(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (!sdp)
+		return;
+
+	if (!strncmp(sb->s_type->name, "gfs2meta", 8))
+		return; /* Nothing to do */
+
+	/*  Unfreeze the filesystem, if we need to  */
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	if (sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+	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);
+		if (error)
+			gfs2_io_error(sdp);
+	}
+	/*  At this point, we're through modifying the disk  */
+
+	/*  Release stuff  */
+
+	iput(sdp->sd_master_dir);
+	iput(sdp->sd_jindex);
+	iput(sdp->sd_inum_inode);
+	iput(sdp->sd_statfs_inode);
+	iput(sdp->sd_rindex);
+	iput(sdp->sd_quota_inode);
+
+	gfs2_glock_put(sdp->sd_rename_gl);
+	gfs2_glock_put(sdp->sd_trans_gl);
+
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+		iput(sdp->sd_ir_inode);
+		iput(sdp->sd_sc_inode);
+		iput(sdp->sd_qc_inode);
+	}
+
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+	gfs2_clear_rgrpd(sdp);
+	gfs2_jindex_free(sdp);
+	/*  Take apart glock structures and buffer lists  */
+	gfs2_gl_hash_clear(sdp, WAIT);
+	/*  Unmount the locking protocol  */
+	gfs2_lm_unmount(sdp);
+
+	/*  At this point, we're through participating in the lockspace  */
+	gfs2_sys_fs_del(sdp);
+	kfree(sdp);
+}
+
+/**
+ * gfs2_write_super
+ * @sb: the superblock
+ *
+ */
+
+static void gfs2_write_super(struct super_block *sb)
+{
+	sb->s_dirt = 0;
+}
+
+/**
+ * gfs2_sync_fs - sync the filesystem
+ * @sb: the superblock
+ *
+ * Flushes the log to disk.
+ */
+static int gfs2_sync_fs(struct super_block *sb, int wait)
+{
+	sb->s_dirt = 0;
+	if (wait)
+		gfs2_log_flush(sb->s_fs_info, NULL);
+	return 0;
+}
+
+/**
+ * gfs2_write_super_lockfs - prevent further writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static void gfs2_write_super_lockfs(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return;
+
+	for (;;) {
+		error = gfs2_freeze_fs(sdp);
+		if (!error)
+			break;
+
+		switch (error) {
+		case -EBUSY:
+			fs_err(sdp, "waiting for recovery before freeze\n");
+			break;
+
+		default:
+			fs_err(sdp, "error freezing FS: %d\n", error);
+			break;
+		}
+
+		fs_err(sdp, "retrying...\n");
+		msleep(1000);
+	}
+}
+
+/**
+ * gfs2_unlockfs - reallow writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static void gfs2_unlockfs(struct super_block *sb)
+{
+	gfs2_unfreeze_fs(sb->s_fs_info);
+}
+
+/**
+ * gfs2_statfs - Gather and return stats about the filesystem
+ * @sb: The superblock
+ * @statfsbuf: The buffer
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_statfs_change_host sc;
+	int error;
+
+	if (gfs2_tune_get(sdp, gt_statfs_slow))
+		error = gfs2_statfs_slow(sdp, &sc);
+	else
+		error = gfs2_statfs_i(sdp, &sc);
+
+	if (error)
+		return error;
+
+	buf->f_type = GFS2_MAGIC;
+	buf->f_bsize = sdp->sd_sb.sb_bsize;
+	buf->f_blocks = sc.sc_total;
+	buf->f_bfree = sc.sc_free;
+	buf->f_bavail = sc.sc_free;
+	buf->f_files = sc.sc_dinodes + sc.sc_free;
+	buf->f_ffree = sc.sc_free;
+	buf->f_namelen = GFS2_FNAMESIZE;
+
+	return 0;
+}
+
+/**
+ * gfs2_remount_fs - called when the FS is remounted
+ * @sb:  the filesystem
+ * @flags:  the remount flags
+ * @data:  extra data passed in (not used right now)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	error = gfs2_mount_args(sdp, data, 1);
+	if (error)
+		return error;
+
+	if (sdp->sd_args.ar_spectator)
+		*flags |= MS_RDONLY;
+	else {
+		if (*flags & MS_RDONLY) {
+			if (!(sb->s_flags & MS_RDONLY))
+				error = gfs2_make_fs_ro(sdp);
+		} else if (!(*flags & MS_RDONLY) &&
+			   (sb->s_flags & MS_RDONLY)) {
+			error = gfs2_make_fs_rw(sdp);
+		}
+	}
+
+	if (*flags & (MS_NOATIME | MS_NODIRATIME))
+		set_bit(SDF_NOATIME, &sdp->sd_flags);
+	else
+		clear_bit(SDF_NOATIME, &sdp->sd_flags);
+
+	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
+	*flags |= MS_NOATIME | MS_NODIRATIME;
+
+	return error;
+}
+
+/**
+ * gfs2_clear_inode - Deallocate an inode when VFS is done with it
+ * @inode: The VFS inode
+ *
+ */
+
+static void gfs2_clear_inode(struct inode *inode)
+{
+	/* This tells us its a "real" inode and not one which only
+	 * serves to contain an address space (see rgrp.c, meta_io.c)
+	 * which therefore doesn't have its own glocks.
+	 */
+	if (inode->i_private) {
+		struct gfs2_inode *ip = GFS2_I(inode);
+		ip->i_gl->gl_object = NULL;
+		gfs2_glock_schedule_for_reclaim(ip->i_gl);
+		gfs2_glock_put(ip->i_gl);
+		ip->i_gl = NULL;
+		if (ip->i_iopen_gh.gh_gl)
+			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	}
+}
+
+/**
+ * gfs2_show_options - Show mount options for /proc/mounts
+ * @s: seq_file structure
+ * @mnt: vfsmount
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_args *args = &sdp->sd_args;
+
+	if (args->ar_lockproto[0])
+		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
+	if (args->ar_locktable[0])
+		seq_printf(s, ",locktable=%s", args->ar_locktable);
+	if (args->ar_hostdata[0])
+		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
+	if (args->ar_spectator)
+		seq_printf(s, ",spectator");
+	if (args->ar_ignore_local_fs)
+		seq_printf(s, ",ignore_local_fs");
+	if (args->ar_localflocks)
+		seq_printf(s, ",localflocks");
+	if (args->ar_localcaching)
+		seq_printf(s, ",localcaching");
+	if (args->ar_debug)
+		seq_printf(s, ",debug");
+	if (args->ar_upgrade)
+		seq_printf(s, ",upgrade");
+	if (args->ar_num_glockd != GFS2_GLOCKD_DEFAULT)
+		seq_printf(s, ",num_glockd=%u", args->ar_num_glockd);
+	if (args->ar_posix_acl)
+		seq_printf(s, ",acl");
+	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
+		char *state;
+		switch (args->ar_quota) {
+		case GFS2_QUOTA_OFF:
+			state = "off";
+			break;
+		case GFS2_QUOTA_ACCOUNT:
+			state = "account";
+			break;
+		case GFS2_QUOTA_ON:
+			state = "on";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",quota=%s", state);
+	}
+	if (args->ar_suiddir)
+		seq_printf(s, ",suiddir");
+	if (args->ar_data != GFS2_DATA_DEFAULT) {
+		char *state;
+		switch (args->ar_data) {
+		case GFS2_DATA_WRITEBACK:
+			state = "writeback";
+			break;
+		case GFS2_DATA_ORDERED:
+			state = "ordered";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",data=%s", state);
+	}
+
+	return 0;
+}
+
+/*
+ * We have to (at the moment) hold the inodes main lock to cover
+ * the gap between unlocking the shared lock on the iopen lock and
+ * taking the exclusive lock. I'd rather do a shared -> exclusive
+ * conversion on the iopen lock, but we can change that later. This
+ * is safe, just less efficient.
+ */
+static void gfs2_delete_inode(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+
+	if (!inode->i_private)
+		goto out;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB, &gh);
+	if (unlikely(error)) {
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		goto out;
+	}
+
+	gfs2_glock_dq(&ip->i_iopen_gh);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
+	error = gfs2_glock_nq(&ip->i_iopen_gh);
+	if (error)
+		goto out_uninit;
+
+	if (S_ISDIR(inode->i_mode) &&
+	    (ip->i_di.di_flags & GFS2_DIF_EXHASH)) {
+		error = gfs2_dir_exhash_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (ip->i_di.di_eattr) {
+		error = gfs2_ea_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		error = gfs2_file_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	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.
+	 */
+	truncate_inode_pages(&inode->i_data, 0);
+
+out_unlock:
+	gfs2_glock_dq(&ip->i_iopen_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_uninit(&gh);
+	if (error)
+		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+out:
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+}
+
+
+
+static struct inode *gfs2_alloc_inode(struct super_block *sb)
+{
+	struct gfs2_inode *ip;
+
+	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
+	if (ip) {
+		ip->i_flags = 0;
+		ip->i_gl = NULL;
+		ip->i_last_pfault = jiffies;
+	}
+	return &ip->i_inode;
+}
+
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(gfs2_inode_cachep, inode);
+}
+
+const struct super_operations gfs2_super_ops = {
+	.alloc_inode		= gfs2_alloc_inode,
+	.destroy_inode		= gfs2_destroy_inode,
+	.write_inode		= gfs2_write_inode,
+	.delete_inode		= gfs2_delete_inode,
+	.put_super		= gfs2_put_super,
+	.write_super		= gfs2_write_super,
+	.sync_fs		= gfs2_sync_fs,
+	.write_super_lockfs 	= gfs2_write_super_lockfs,
+	.unlockfs		= gfs2_unlockfs,
+	.statfs			= gfs2_statfs,
+	.remount_fs		= gfs2_remount_fs,
+	.clear_inode		= gfs2_clear_inode,
+	.show_options		= gfs2_show_options,
+};
+

fs/gfs2/ops_super.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_SUPER_DOT_H__
+#define __OPS_SUPER_DOT_H__
+
+#include <linux/fs.h>
+
+extern const struct super_operations gfs2_super_ops;
+
+#endif /* __OPS_SUPER_DOT_H__ */

fs/gfs2/ops_vm.c

@@ -0,0 +1,161 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "ops_vm.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+static struct page *gfs2_private_nopage(struct vm_area_struct *area,
+					unsigned long address, int *type)
+{
+	struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
+
+	set_bit(GIF_PAGED, &ip->i_flags);
+	return filemap_nopage(area, address, type);
+}
+
+static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned long index = page->index;
+	u64 lblock = index << (PAGE_CACHE_SHIFT -
+				    sdp->sd_sb.sb_bsize_shift);
+	unsigned int blocks = PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift;
+	struct gfs2_alloc *al;
+	unsigned int data_blocks, ind_blocks;
+	unsigned int x;
+	int error;
+
+	al = gfs2_alloc_get(ip);
+
+	error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (error)
+		goto out;
+
+	error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	if (error)
+		goto out_gunlock_q;
+
+	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+
+	al->al_requested = data_blocks + ind_blocks;
+
+	error = gfs2_inplace_reserve(ip);
+	if (error)
+		goto out_gunlock_q;
+
+	error = gfs2_trans_begin(sdp, al->al_rgd->rd_ri.ri_length +
+				 ind_blocks + RES_DINODE +
+				 RES_STATFS + RES_QUOTA, 0);
+	if (error)
+		goto out_ipres;
+
+	if (gfs2_is_stuffed(ip)) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (error)
+			goto out_trans;
+	}
+
+	for (x = 0; x < blocks; ) {
+		u64 dblock;
+		unsigned int extlen;
+		int new = 1;
+
+		error = gfs2_extent_map(&ip->i_inode, lblock, &new, &dblock, &extlen);
+		if (error)
+			goto out_trans;
+
+		lblock += extlen;
+		x += extlen;
+	}
+
+	gfs2_assert_warn(sdp, al->al_alloced);
+
+out_trans:
+	gfs2_trans_end(sdp);
+out_ipres:
+	gfs2_inplace_release(ip);
+out_gunlock_q:
+	gfs2_quota_unlock(ip);
+out:
+	gfs2_alloc_put(ip);
+	return error;
+}
+
+static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
+					   unsigned long address, int *type)
+{
+	struct file *file = area->vm_file;
+	struct gfs2_file *gf = file->private_data;
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	struct page *result = NULL;
+	unsigned long index = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) +
+			      area->vm_pgoff;
+	int alloc_required;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+	if (error)
+		return NULL;
+
+	set_bit(GIF_PAGED, &ip->i_flags);
+	set_bit(GIF_SW_PAGED, &ip->i_flags);
+
+	error = gfs2_write_alloc_required(ip, (u64)index << PAGE_CACHE_SHIFT,
+					  PAGE_CACHE_SIZE, &alloc_required);
+	if (error)
+		goto out;
+
+	set_bit(GFF_EXLOCK, &gf->f_flags);
+	result = filemap_nopage(area, address, type);
+	clear_bit(GFF_EXLOCK, &gf->f_flags);
+	if (!result || result == NOPAGE_OOM)
+		goto out;
+
+	if (alloc_required) {
+		error = alloc_page_backing(ip, result);
+		if (error) {
+			page_cache_release(result);
+			result = NULL;
+			goto out;
+		}
+		set_page_dirty(result);
+	}
+
+out:
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return result;
+}
+
+struct vm_operations_struct gfs2_vm_ops_private = {
+	.nopage = gfs2_private_nopage,
+};
+
+struct vm_operations_struct gfs2_vm_ops_sharewrite = {
+	.nopage = gfs2_sharewrite_nopage,
+};
+

fs/gfs2/ops_vm.h

@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_VM_DOT_H__
+#define __OPS_VM_DOT_H__
+
+#include <linux/mm.h>
+
+extern struct vm_operations_struct gfs2_vm_ops_private;
+extern struct vm_operations_struct gfs2_vm_ops_sharewrite;
+
+#endif /* __OPS_VM_DOT_H__ */

fs/gfs2/quota.h

@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __QUOTA_DOT_H__
+#define __QUOTA_DOT_H__
+
+struct gfs2_inode;
+struct gfs2_sbd;
+
+#define NO_QUOTA_CHANGE ((u32)-1)
+
+int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid);
+void gfs2_quota_unhold(struct gfs2_inode *ip);
+
+int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid);
+void gfs2_quota_unlock(struct gfs2_inode *ip);
+
+int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid);
+void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
+		       u32 uid, u32 gid);
+
+int gfs2_quota_sync(struct gfs2_sbd *sdp);
+int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id);
+
+int gfs2_quota_init(struct gfs2_sbd *sdp);
+void gfs2_quota_scan(struct gfs2_sbd *sdp);
+void gfs2_quota_cleanup(struct gfs2_sbd *sdp);
+
+#endif /* __QUOTA_DOT_H__ */

fs/gfs2/recovery.c

@@ -0,0 +1,571 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "lm.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "super.h"
+#include "util.h"
+#include "dir.h"
+
+int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	int new = 0;
+	u64 dblock;
+	u32 extlen;
+	int error;
+
+	error = gfs2_extent_map(&ip->i_inode, blk, &new, &dblock, &extlen);
+	if (error)
+		return error;
+	if (!dblock) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	*bh = gfs2_meta_ra(gl, dblock, extlen);
+
+	return error;
+}
+
+int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+{
+	struct list_head *head = &sdp->sd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+	int found = 0;
+
+	list_for_each_entry(rr, head, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (found) {
+		rr->rr_where = where;
+		return 0;
+	}
+
+	rr = kmalloc(sizeof(struct gfs2_revoke_replay), GFP_KERNEL);
+	if (!rr)
+		return -ENOMEM;
+
+	rr->rr_blkno = blkno;
+	rr->rr_where = where;
+	list_add(&rr->rr_list, head);
+
+	return 1;
+}
+
+int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+{
+	struct gfs2_revoke_replay *rr;
+	int wrap, a, b, revoke;
+	int found = 0;
+
+	list_for_each_entry(rr, &sdp->sd_revoke_list, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return 0;
+
+	wrap = (rr->rr_where < sdp->sd_replay_tail);
+	a = (sdp->sd_replay_tail < where);
+	b = (where < rr->rr_where);
+	revoke = (wrap) ? (a || b) : (a && b);
+
+	return revoke;
+}
+
+void gfs2_revoke_clean(struct gfs2_sbd *sdp)
+{
+	struct list_head *head = &sdp->sd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+
+	while (!list_empty(head)) {
+		rr = list_entry(head->next, struct gfs2_revoke_replay, rr_list);
+		list_del(&rr->rr_list);
+		kfree(rr);
+	}
+}
+
+/**
+ * get_log_header - read the log header for a given segment
+ * @jd: the journal
+ * @blk: the block to look at
+ * @lh: the log header to return
+ *
+ * Read the log header for a given segement in a given journal.  Do a few
+ * sanity checks on it.
+ *
+ * Returns: 0 on success,
+ *          1 if the header was invalid or incomplete,
+ *          errno on error
+ */
+
+static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk,
+			  struct gfs2_log_header_host *head)
+{
+	struct buffer_head *bh;
+	struct gfs2_log_header_host lh;
+	const u32 nothing = 0;
+	u32 hash;
+	int error;
+
+	error = gfs2_replay_read_block(jd, blk, &bh);
+	if (error)
+		return error;
+
+	hash = crc32_le((u32)~0, bh->b_data, sizeof(struct gfs2_log_header) -
+					     sizeof(u32));
+	hash = crc32_le(hash, (unsigned char const *)&nothing, sizeof(nothing));
+	hash ^= (u32)~0;
+	gfs2_log_header_in(&lh, bh->b_data);
+	brelse(bh);
+
+	if (lh.lh_header.mh_magic != GFS2_MAGIC ||
+	    lh.lh_header.mh_type != GFS2_METATYPE_LH ||
+	    lh.lh_blkno != blk || lh.lh_hash != hash)
+		return 1;
+
+	*head = lh;
+
+	return 0;
+}
+
+/**
+ * find_good_lh - find a good log header
+ * @jd: the journal
+ * @blk: the segment to start searching from
+ * @lh: the log header to fill in
+ * @forward: if true search forward in the log, else search backward
+ *
+ * Call get_log_header() to get a log header for a segment, but if the
+ * segment is bad, either scan forward or backward until we find a good one.
+ *
+ * Returns: errno
+ */
+
+static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk,
+			struct gfs2_log_header_host *head)
+{
+	unsigned int orig_blk = *blk;
+	int error;
+
+	for (;;) {
+		error = get_log_header(jd, *blk, head);
+		if (error <= 0)
+			return error;
+
+		if (++*blk == jd->jd_blocks)
+			*blk = 0;
+
+		if (*blk == orig_blk) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+	}
+}
+
+/**
+ * jhead_scan - make sure we've found the head of the log
+ * @jd: the journal
+ * @head: this is filled in with the log descriptor of the head
+ *
+ * At this point, seg and lh should be either the head of the log or just
+ * before.  Scan forward until we find the head.
+ *
+ * Returns: errno
+ */
+
+static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	unsigned int blk = head->lh_blkno;
+	struct gfs2_log_header_host lh;
+	int error;
+
+	for (;;) {
+		if (++blk == jd->jd_blocks)
+			blk = 0;
+
+		error = get_log_header(jd, blk, &lh);
+		if (error < 0)
+			return error;
+		if (error == 1)
+			continue;
+
+		if (lh.lh_sequence == head->lh_sequence) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+		if (lh.lh_sequence < head->lh_sequence)
+			break;
+
+		*head = lh;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_find_jhead - find the head of a log
+ * @jd: the journal
+ * @head: the log descriptor for the head of the log is returned here
+ *
+ * Do a binary search of a journal and find the valid log entry with the
+ * highest sequence number.  (i.e. the log head)
+ *
+ * Returns: errno
+ */
+
+int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_log_header_host lh_1, lh_m;
+	u32 blk_1, blk_2, blk_m;
+	int error;
+
+	blk_1 = 0;
+	blk_2 = jd->jd_blocks - 1;
+
+	for (;;) {
+		blk_m = (blk_1 + blk_2) / 2;
+
+		error = find_good_lh(jd, &blk_1, &lh_1);
+		if (error)
+			return error;
+
+		error = find_good_lh(jd, &blk_m, &lh_m);
+		if (error)
+			return error;
+
+		if (blk_1 == blk_m || blk_m == blk_2)
+			break;
+
+		if (lh_1.lh_sequence <= lh_m.lh_sequence)
+			blk_1 = blk_m;
+		else
+			blk_2 = blk_m;
+	}
+
+	error = jhead_scan(jd, &lh_1);
+	if (error)
+		return error;
+
+	*head = lh_1;
+
+	return error;
+}
+
+/**
+ * foreach_descriptor - go through the active part of the log
+ * @jd: the journal
+ * @start: the first log header in the active region
+ * @end: the last log header (don't process the contents of this entry))
+ *
+ * Call a given function once for every log descriptor in the active
+ * portion of the log.
+ *
+ * Returns: errno
+ */
+
+static int foreach_descriptor(struct gfs2_jdesc *jd, unsigned int start,
+			      unsigned int end, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct buffer_head *bh;
+	struct gfs2_log_descriptor *ld;
+	int error = 0;
+	u32 length;
+	__be64 *ptr;
+	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	offset += sizeof(__be64) - 1;
+	offset &= ~(sizeof(__be64) - 1);
+
+	while (start != end) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+		if (gfs2_meta_check(sdp, bh)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ld = (struct gfs2_log_descriptor *)bh->b_data;
+		length = be32_to_cpu(ld->ld_length);
+
+		if (be32_to_cpu(ld->ld_header.mh_type) == GFS2_METATYPE_LH) {
+			struct gfs2_log_header_host lh;
+			error = get_log_header(jd, start, &lh);
+			if (!error) {
+				gfs2_replay_incr_blk(sdp, &start);
+				brelse(bh);
+				continue;
+			}
+			if (error == 1) {
+				gfs2_consist_inode(GFS2_I(jd->jd_inode));
+				error = -EIO;
+			}
+			brelse(bh);
+			return error;
+		} else if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LD)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ptr = (__be64 *)(bh->b_data + offset);
+		error = lops_scan_elements(jd, start, ld, ptr, pass);
+		if (error) {
+			brelse(bh);
+			return error;
+		}
+
+		while (length--)
+			gfs2_replay_incr_blk(sdp, &start);
+
+		brelse(bh);
+	}
+
+	return 0;
+}
+
+/**
+ * clean_journal - mark a dirty journal as being clean
+ * @sdp: the filesystem
+ * @jd: the journal
+ * @gl: the journal's glock
+ * @head: the head journal to start from
+ *
+ * Returns: errno
+ */
+
+static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int lblock;
+	struct gfs2_log_header *lh;
+	u32 hash;
+	struct buffer_head *bh;
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	lblock = head->lh_blkno;
+	gfs2_replay_incr_blk(sdp, &lblock);
+	bh_map.b_size = 1 << ip->i_inode.i_blkbits;
+	error = gfs2_block_map(&ip->i_inode, lblock, 0, &bh_map);
+	if (error)
+		return error;
+	if (!bh_map.b_blocknr) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	bh = sb_getblk(sdp->sd_vfs, bh_map.b_blocknr);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_sequence = cpu_to_be64(head->lh_sequence + 1);
+	lh->lh_flags = cpu_to_be32(GFS2_LOG_HEAD_UNMOUNT);
+	lh->lh_blkno = cpu_to_be32(lblock);
+	hash = gfs2_disk_hash((const char *)lh, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	set_buffer_dirty(bh);
+	if (sync_dirty_buffer(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	return error;
+}
+
+/**
+ * gfs2_recover_journal - recovery a given journal
+ * @jd: the struct gfs2_jdesc describing the journal
+ *
+ * Acquire the journal's lock, check to see if the journal is clean, and
+ * do recovery if necessary.
+ *
+ * Returns: errno
+ */
+
+int gfs2_recover_journal(struct gfs2_jdesc *jd)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_log_header_host head;
+	struct gfs2_holder j_gh, ji_gh, t_gh;
+	unsigned long t;
+	int ro = 0;
+	unsigned int pass;
+	int error;
+
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
+			jd->jd_jid);
+
+		/* Aquire the journal lock so we can do recovery */
+
+		error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE,
+					  LM_FLAG_NOEXP | LM_FLAG_TRY | GL_NOCACHE,
+					  &j_gh);
+		switch (error) {
+		case 0:
+			break;
+
+		case GLR_TRYFAILED:
+			fs_info(sdp, "jid=%u: Busy\n", jd->jd_jid);
+			error = 0;
+
+		default:
+			goto fail;
+		};
+
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP, &ji_gh);
+		if (error)
+			goto fail_gunlock_j;
+	} else {
+		fs_info(sdp, "jid=%u, already locked for use\n", jd->jd_jid);
+	}
+
+	fs_info(sdp, "jid=%u: Looking at journal...\n", jd->jd_jid);
+
+	error = gfs2_jdesc_check(jd);
+	if (error)
+		goto fail_gunlock_ji;
+
+	error = gfs2_find_jhead(jd, &head);
+	if (error)
+		goto fail_gunlock_ji;
+
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		fs_info(sdp, "jid=%u: Acquiring the transaction lock...\n",
+			jd->jd_jid);
+
+		t = jiffies;
+
+		/* Acquire a shared hold on the transaction lock */
+
+		error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
+					   GL_NOCANCEL | GL_NOCACHE, &t_gh);
+		if (error)
+			goto fail_gunlock_ji;
+
+		if (test_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags)) {
+			if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+				ro = 1;
+		} else {
+			if (sdp->sd_vfs->s_flags & MS_RDONLY)
+				ro = 1;
+		}
+
+		if (ro) {
+			fs_warn(sdp, "jid=%u: Can't replay: read-only FS\n",
+				jd->jd_jid);
+			error = -EROFS;
+			goto fail_gunlock_tr;
+		}
+
+		fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid);
+
+		for (pass = 0; pass < 2; pass++) {
+			lops_before_scan(jd, &head, pass);
+			error = foreach_descriptor(jd, head.lh_tail,
+						   head.lh_blkno, pass);
+			lops_after_scan(jd, error, pass);
+			if (error)
+				goto fail_gunlock_tr;
+		}
+
+		error = clean_journal(jd, &head);
+		if (error)
+			goto fail_gunlock_tr;
+
+		gfs2_glock_dq_uninit(&t_gh);
+		t = DIV_ROUND_UP(jiffies - t, HZ);
+		fs_info(sdp, "jid=%u: Journal replayed in %lus\n",
+			jd->jd_jid, t);
+	}
+
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
+		gfs2_glock_dq_uninit(&ji_gh);
+
+	gfs2_lm_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS);
+
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
+		gfs2_glock_dq_uninit(&j_gh);
+
+	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
+	return 0;
+
+fail_gunlock_tr:
+	gfs2_glock_dq_uninit(&t_gh);
+fail_gunlock_ji:
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+		gfs2_glock_dq_uninit(&ji_gh);
+fail_gunlock_j:
+		gfs2_glock_dq_uninit(&j_gh);
+	}
+
+	fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done");
+
+fail:
+	gfs2_lm_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
+	return error;
+}
+
+/**
+ * gfs2_check_journals - Recover any dirty journals
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_check_journals(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd;
+
+	for (;;) {
+		jd = gfs2_jdesc_find_dirty(sdp);
+		if (!jd)
+			break;
+
+		if (jd != sdp->sd_jdesc)
+			gfs2_recover_journal(jd);
+	}
+}
+

fs/gfs2/recovery.h

@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __RECOVERY_DOT_H__
+#define __RECOVERY_DOT_H__
+
+#include "incore.h"
+
+static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
+{
+	if (++*blk == sdp->sd_jdesc->jd_blocks)
+	        *blk = 0;
+}
+
+int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh);
+
+int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
+int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
+void gfs2_revoke_clean(struct gfs2_sbd *sdp);
+
+int gfs2_find_jhead(struct gfs2_jdesc *jd,
+		    struct gfs2_log_header_host *head);
+int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd);
+void gfs2_check_journals(struct gfs2_sbd *sdp);
+
+#endif /* __RECOVERY_DOT_H__ */
+

fs/gfs2/rgrp.h

@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __RGRP_DOT_H__
+#define __RGRP_DOT_H__
+
+struct gfs2_rgrpd;
+struct gfs2_sbd;
+struct gfs2_holder;
+
+void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
+
+struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
+struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
+struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
+
+void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
+int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
+
+int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
+void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
+void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
+
+void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+
+struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
+static inline void gfs2_alloc_put(struct gfs2_inode *ip)
+{
+	return; /* So we can see where ip->i_alloc is used */
+}
+
+int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
+			 char *file, unsigned int line);
+#define gfs2_inplace_reserve(ip) \
+gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
+
+void gfs2_inplace_release(struct gfs2_inode *ip);
+
+unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
+
+u64 gfs2_alloc_data(struct gfs2_inode *ip);
+u64 gfs2_alloc_meta(struct gfs2_inode *ip);
+u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
+
+void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
+void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
+void gfs2_unlink_di(struct inode *inode);
+
+struct gfs2_rgrp_list {
+	unsigned int rl_rgrps;
+	unsigned int rl_space;
+	struct gfs2_rgrpd **rl_rgd;
+	struct gfs2_holder *rl_ghs;
+};
+
+void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+		    u64 block);
+void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state,
+		      int flags);
+void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
+
+#endif /* __RGRP_DOT_H__ */

fs/gfs2/super.c

@@ -0,0 +1,985 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/crc32.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "trans.h"
+#include "util.h"
+
+static const u32 gfs2_old_fs_formats[] = {
+        0
+};
+
+static const u32 gfs2_old_multihost_formats[] = {
+        0
+};
+
+/**
+ * gfs2_tune_init - Fill a gfs2_tune structure with default values
+ * @gt: tune
+ *
+ */
+
+void gfs2_tune_init(struct gfs2_tune *gt)
+{
+	spin_lock_init(&gt->gt_spin);
+
+	gt->gt_ilimit = 100;
+	gt->gt_ilimit_tries = 3;
+	gt->gt_ilimit_min = 1;
+	gt->gt_demote_secs = 300;
+	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;
+	gt->gt_quota_simul_sync = 64;
+	gt->gt_quota_warn_period = 10;
+	gt->gt_quota_scale_num = 1;
+	gt->gt_quota_scale_den = 1;
+	gt->gt_quota_cache_secs = 300;
+	gt->gt_quota_quantum = 60;
+	gt->gt_atime_quantum = 3600;
+	gt->gt_new_files_jdata = 0;
+	gt->gt_new_files_directio = 0;
+	gt->gt_max_readahead = 1 << 18;
+	gt->gt_lockdump_size = 131072;
+	gt->gt_stall_secs = 600;
+	gt->gt_complain_secs = 10;
+	gt->gt_reclaim_limit = 5000;
+	gt->gt_statfs_quantum = 30;
+	gt->gt_statfs_slow = 0;
+}
+
+/**
+ * gfs2_check_sb - Check superblock
+ * @sdp: the filesystem
+ * @sb: The superblock
+ * @silent: Don't print a message if the check fails
+ *
+ * Checks the version code of the FS is one that we understand how to
+ * read and that the sizes of the various on-disk structures have not
+ * changed.
+ */
+
+int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
+{
+	unsigned int x;
+
+	if (sb->sb_header.mh_magic != GFS2_MAGIC ||
+	    sb->sb_header.mh_type != GFS2_METATYPE_SB) {
+		if (!silent)
+			printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+		return -EINVAL;
+	}
+
+	/*  If format numbers match exactly, we're done.  */
+
+	if (sb->sb_fs_format == GFS2_FORMAT_FS &&
+	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
+		return 0;
+
+	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
+		for (x = 0; gfs2_old_fs_formats[x]; x++)
+			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
+				break;
+
+		if (!gfs2_old_fs_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
+		for (x = 0; gfs2_old_multihost_formats[x]; x++)
+			if (gfs2_old_multihost_formats[x] ==
+			    sb->sb_multihost_format)
+				break;
+
+		if (!gfs2_old_multihost_formats[x]) {
+			printk(KERN_WARNING
+			       "GFS2: code version (%u, %u) is incompatible "
+			       "with ondisk format (%u, %u)\n",
+			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+			       sb->sb_fs_format, sb->sb_multihost_format);
+			printk(KERN_WARNING
+			       "GFS2: I don't know how to upgrade this FS\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!sdp->sd_args.ar_upgrade) {
+		printk(KERN_WARNING
+		       "GFS2: code version (%u, %u) is incompatible "
+		       "with ondisk format (%u, %u)\n",
+		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+		       sb->sb_fs_format, sb->sb_multihost_format);
+		printk(KERN_INFO
+		       "GFS2: Use the \"upgrade\" mount option to upgrade "
+		       "the FS\n");
+		printk(KERN_INFO "GFS2: See the manual for more details\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+static int end_bio_io_page(struct bio *bio, unsigned int bytes_done, 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;
+}
+
+/**
+ * gfs2_read_super - Read the gfs2 super block from disk
+ * @sb: The VFS super block
+ * @sector: The location of the super block
+ *
+ * This uses the bio functions to read the super block from disk
+ * because we want to be 100% sure that we never read cached data.
+ * A super block is read twice only during each GFS2 mount and is
+ * never written to by the filesystem. The first time its read no
+ * locks are held, and the only details which are looked at are those
+ * relating to the locking protocol. Once locking is up and working,
+ * the sb is read again under the lock to establish the location of
+ * the master directory (contains pointers to journals etc) and the
+ * root directory.
+ *
+ * Returns: A page containing the sb or NULL
+ */
+
+struct page *gfs2_read_super(struct super_block *sb, sector_t sector)
+{
+	struct page *page;
+	struct bio *bio;
+
+	page = alloc_page(GFP_KERNEL);
+	if (unlikely(!page))
+		return NULL;
+
+	ClearPageUptodate(page);
+	ClearPageDirty(page);
+	lock_page(page);
+
+	bio = bio_alloc(GFP_KERNEL, 1);
+	if (unlikely(!bio)) {
+		__free_page(page);
+		return NULL;
+	}
+
+	bio->bi_sector = sector * (sb->s_blocksize >> 9);
+	bio->bi_bdev = sb->s_bdev;
+	bio_add_page(bio, page, PAGE_SIZE, 0);
+
+	bio->bi_end_io = end_bio_io_page;
+	bio->bi_private = page;
+	submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
+	wait_on_page_locked(page);
+	bio_put(bio);
+	if (!PageUptodate(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	return page;
+}
+
+/**
+ * gfs2_read_sb - Read super block
+ * @sdp: The GFS2 superblock
+ * @gl: the glock for the superblock (assumed to be held)
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
+{
+	u32 hash_blocks, ind_blocks, leaf_blocks;
+	u32 tmp_blocks;
+	unsigned int x;
+	int error;
+	struct page *page;
+	char *sb;
+
+	page = gfs2_read_super(sdp->sd_vfs, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+	if (!page) {
+		if (!silent)
+			fs_err(sdp, "can't read superblock\n");
+		return -EIO;
+	}
+	sb = kmap(page);
+	gfs2_sb_in(&sdp->sd_sb, sb);
+	kunmap(page);
+	__free_page(page);
+
+	error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+	if (error)
+		return error;
+
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+			       GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+	sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_dinode)) / sizeof(u64);
+	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
+	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
+	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
+	sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
+	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_meta_header)) /
+			        sizeof(struct gfs2_quota_change);
+
+	/* Compute maximum reservation required to add a entry to a directory */
+
+	hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+			     sdp->sd_jbsize);
+
+	ind_blocks = 0;
+	for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
+		tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
+		ind_blocks += tmp_blocks;
+	}
+
+	leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
+
+	sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
+
+	sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
+				sizeof(struct gfs2_dinode);
+	sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_heightsize[x - 1] || m)
+			break;
+		sdp->sd_heightsize[x] = space;
+	}
+	sdp->sd_max_height = x;
+	gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
+
+	sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
+				 sizeof(struct gfs2_dinode);
+	sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
+	for (x = 2;; x++) {
+		u64 space, d;
+		u32 m;
+
+		space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
+		d = space;
+		m = do_div(d, sdp->sd_inptrs);
+
+		if (d != sdp->sd_jheightsize[x - 1] || m)
+			break;
+		sdp->sd_jheightsize[x] = space;
+	}
+	sdp->sd_max_jheight = x;
+	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
+
+	return 0;
+}
+
+/**
+ * gfs2_jindex_hold - Grab a lock on the jindex
+ * @sdp: The GFS2 superblock
+ * @ji_gh: the holder for the jindex glock
+ *
+ * This is very similar to the gfs2_rindex_hold() function, except that
+ * in general we hold the jindex lock for longer periods of time and
+ * we grab it far less frequently (in general) then the rgrp lock.
+ *
+ * Returns: errno
+ */
+
+int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
+{
+	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
+	struct qstr name;
+	char buf[20];
+	struct gfs2_jdesc *jd;
+	int error;
+
+	name.name = buf;
+
+	mutex_lock(&sdp->sd_jindex_mutex);
+
+	for (;;) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, ji_gh);
+		if (error)
+			break;
+
+		name.len = sprintf(buf, "journal%u", sdp->sd_journals);
+		name.hash = gfs2_disk_hash(name.name, name.len);
+
+		error = gfs2_dir_search(sdp->sd_jindex, &name, NULL, NULL);
+		if (error == -ENOENT) {
+			error = 0;
+			break;
+		}
+
+		gfs2_glock_dq_uninit(ji_gh);
+
+		if (error)
+			break;
+
+		error = -ENOMEM;
+		jd = kzalloc(sizeof(struct gfs2_jdesc), GFP_KERNEL);
+		if (!jd)
+			break;
+
+		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL);
+		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
+			if (!jd->jd_inode)
+				error = -ENOENT;
+			else
+				error = PTR_ERR(jd->jd_inode);
+			kfree(jd);
+			break;
+		}
+
+		spin_lock(&sdp->sd_jindex_spin);
+		jd->jd_jid = sdp->sd_journals++;
+		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
+		spin_unlock(&sdp->sd_jindex_spin);
+	}
+
+	mutex_unlock(&sdp->sd_jindex_mutex);
+
+	return error;
+}
+
+/**
+ * gfs2_jindex_free - Clear all the journal index information
+ * @sdp: The GFS2 superblock
+ *
+ */
+
+void gfs2_jindex_free(struct gfs2_sbd *sdp)
+{
+	struct list_head list;
+	struct gfs2_jdesc *jd;
+
+	spin_lock(&sdp->sd_jindex_spin);
+	list_add(&list, &sdp->sd_jindex_list);
+	list_del_init(&sdp->sd_jindex_list);
+	sdp->sd_journals = 0;
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	while (!list_empty(&list)) {
+		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
+		list_del(&jd->jd_list);
+		iput(jd->jd_inode);
+		kfree(jd);
+	}
+}
+
+static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
+{
+	struct gfs2_jdesc *jd;
+	int found = 0;
+
+	list_for_each_entry(jd, head, jd_list) {
+		if (jd->jd_jid == jid) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		jd = NULL;
+
+	return jd;
+}
+
+struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
+{
+	struct gfs2_jdesc *jd;
+
+	spin_lock(&sdp->sd_jindex_spin);
+	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	return jd;
+}
+
+void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid)
+{
+	struct gfs2_jdesc *jd;
+
+	spin_lock(&sdp->sd_jindex_spin);
+	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
+	if (jd)
+		jd->jd_dirty = 1;
+	spin_unlock(&sdp->sd_jindex_spin);
+}
+
+struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd;
+	int found = 0;
+
+	spin_lock(&sdp->sd_jindex_spin);
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (jd->jd_dirty) {
+			jd->jd_dirty = 0;
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	if (!found)
+		jd = NULL;
+
+	return jd;
+}
+
+int gfs2_jdesc_check(struct gfs2_jdesc *jd)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	int ar;
+	int error;
+
+	if (ip->i_di.di_size < (8 << 20) || ip->i_di.di_size > (1 << 30) ||
+	    (ip->i_di.di_size & (sdp->sd_sb.sb_bsize - 1))) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+	jd->jd_blocks = ip->i_di.di_size >> sdp->sd_sb.sb_bsize_shift;
+
+	error = gfs2_write_alloc_required(ip, 0, ip->i_di.di_size, &ar);
+	if (!error && ar) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+	}
+
+	return error;
+}
+
+/**
+ * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_holder t_gh;
+	struct gfs2_log_header_host head;
+	int error;
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh);
+	if (error)
+		return error;
+
+	gfs2_meta_cache_flush(ip);
+	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+
+	error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+	if (error)
+		goto fail;
+
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		gfs2_consist(sdp);
+		error = -EIO;
+		goto fail;
+	}
+
+	/*  Initialize some head of the log stuff  */
+	sdp->sd_log_sequence = head.lh_sequence + 1;
+	gfs2_log_pointers_init(sdp, head.lh_blkno);
+
+	error = gfs2_quota_init(sdp);
+	if (error)
+		goto fail;
+
+	set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	gfs2_glock_dq_uninit(&t_gh);
+
+	return 0;
+
+fail:
+	t_gh.gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_uninit(&t_gh);
+
+	return error;
+}
+
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+	struct gfs2_holder t_gh;
+	int error;
+
+	gfs2_quota_sync(sdp);
+	gfs2_statfs_sync(sdp);
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &t_gh);
+	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return error;
+
+	gfs2_meta_syncfs(sdp);
+	gfs2_log_shutdown(sdp);
+
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	if (t_gh.gh_gl)
+		gfs2_glock_dq_uninit(&t_gh);
+
+	gfs2_quota_cleanup(sdp);
+
+	return error;
+}
+
+int gfs2_statfs_init(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct buffer_head *m_bh, *l_bh;
+	struct gfs2_holder gh;
+	int error;
+
+	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
+				   &gh);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
+	if (error)
+		goto out;
+
+	if (sdp->sd_args.ar_spectator) {
+		spin_lock(&sdp->sd_statfs_spin);
+		gfs2_statfs_change_in(m_sc, m_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		spin_unlock(&sdp->sd_statfs_spin);
+	} else {
+		error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+		if (error)
+			goto out_m_bh;
+
+		spin_lock(&sdp->sd_statfs_spin);
+		gfs2_statfs_change_in(m_sc, m_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		gfs2_statfs_change_in(l_sc, l_bh->b_data +
+				      sizeof(struct gfs2_dinode));
+		spin_unlock(&sdp->sd_statfs_spin);
+
+		brelse(l_bh);
+	}
+
+out_m_bh:
+	brelse(m_bh);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return 0;
+}
+
+void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
+			s64 dinodes)
+{
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct buffer_head *l_bh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+	if (error)
+		return;
+
+	mutex_lock(&sdp->sd_statfs_mutex);
+	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+	mutex_unlock(&sdp->sd_statfs_mutex);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	l_sc->sc_total += total;
+	l_sc->sc_free += free;
+	l_sc->sc_dinodes += dinodes;
+	gfs2_statfs_change_out(l_sc, l_bh->b_data + sizeof(struct gfs2_dinode));
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	brelse(l_bh);
+}
+
+int gfs2_statfs_sync(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct gfs2_holder gh;
+	struct buffer_head *m_bh, *l_bh;
+	int error;
+
+	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
+				   &gh);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
+	if (error)
+		goto out;
+
+	spin_lock(&sdp->sd_statfs_spin);
+	gfs2_statfs_change_in(m_sc, m_bh->b_data +
+			      sizeof(struct gfs2_dinode));
+	if (!l_sc->sc_total && !l_sc->sc_free && !l_sc->sc_dinodes) {
+		spin_unlock(&sdp->sd_statfs_spin);
+		goto out_bh;
+	}
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	error = gfs2_meta_inode_buffer(l_ip, &l_bh);
+	if (error)
+		goto out_bh;
+
+	error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
+	if (error)
+		goto out_bh2;
+
+	mutex_lock(&sdp->sd_statfs_mutex);
+	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+	mutex_unlock(&sdp->sd_statfs_mutex);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	m_sc->sc_total += l_sc->sc_total;
+	m_sc->sc_free += l_sc->sc_free;
+	m_sc->sc_dinodes += l_sc->sc_dinodes;
+	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
+	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
+	       0, sizeof(struct gfs2_statfs_change));
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
+	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+
+	gfs2_trans_end(sdp);
+
+out_bh2:
+	brelse(l_bh);
+out_bh:
+	brelse(m_bh);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return error;
+}
+
+/**
+ * gfs2_statfs_i - Do a statfs
+ * @sdp: the filesystem
+ * @sg: the sg structure
+ *
+ * Returns: errno
+ */
+
+int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	spin_lock(&sdp->sd_statfs_spin);
+
+	*sc = *m_sc;
+	sc->sc_total += l_sc->sc_total;
+	sc->sc_free += l_sc->sc_free;
+	sc->sc_dinodes += l_sc->sc_dinodes;
+
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	if (sc->sc_free < 0)
+		sc->sc_free = 0;
+	if (sc->sc_free > sc->sc_total)
+		sc->sc_free = sc->sc_total;
+	if (sc->sc_dinodes < 0)
+		sc->sc_dinodes = 0;
+
+	return 0;
+}
+
+/**
+ * statfs_fill - fill in the sg for a given RG
+ * @rgd: the RG
+ * @sc: the sc structure
+ *
+ * Returns: 0 on success, -ESTALE if the LVB is invalid
+ */
+
+static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
+			    struct gfs2_statfs_change_host *sc)
+{
+	gfs2_rgrp_verify(rgd);
+	sc->sc_total += rgd->rd_ri.ri_data;
+	sc->sc_free += rgd->rd_rg.rg_free;
+	sc->sc_dinodes += rgd->rd_rg.rg_dinodes;
+	return 0;
+}
+
+/**
+ * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
+ * @sdp: the filesystem
+ * @sc: the sc info that will be returned
+ *
+ * Any error (other than a signal) will cause this routine to fall back
+ * to the synchronous version.
+ *
+ * FIXME: This really shouldn't busy wait like this.
+ *
+ * Returns: errno
+ */
+
+int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_holder ri_gh;
+	struct gfs2_rgrpd *rgd_next;
+	struct gfs2_holder *gha, *gh;
+	unsigned int slots = 64;
+	unsigned int x;
+	int done;
+	int error = 0, err;
+
+	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
+	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
+	if (!gha)
+		return -ENOMEM;
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto out;
+
+	rgd_next = gfs2_rgrpd_get_first(sdp);
+
+	for (;;) {
+		done = 1;
+
+		for (x = 0; x < slots; x++) {
+			gh = gha + x;
+
+			if (gh->gh_gl && gfs2_glock_poll(gh)) {
+				err = gfs2_glock_wait(gh);
+				if (err) {
+					gfs2_holder_uninit(gh);
+					error = err;
+				} else {
+					if (!error)
+						error = statfs_slow_fill(
+							gh->gh_gl->gl_object, sc);
+					gfs2_glock_dq_uninit(gh);
+				}
+			}
+
+			if (gh->gh_gl)
+				done = 0;
+			else if (rgd_next && !error) {
+				error = gfs2_glock_nq_init(rgd_next->rd_gl,
+							   LM_ST_SHARED,
+							   GL_ASYNC,
+							   gh);
+				rgd_next = gfs2_rgrpd_get_next(rgd_next);
+				done = 0;
+			}
+
+			if (signal_pending(current))
+				error = -ERESTARTSYS;
+		}
+
+		if (done)
+			break;
+
+		yield();
+	}
+
+	gfs2_glock_dq_uninit(&ri_gh);
+
+out:
+	kfree(gha);
+	return error;
+}
+
+struct lfcc {
+	struct list_head list;
+	struct gfs2_holder gh;
+};
+
+/**
+ * gfs2_lock_fs_check_clean - Stop all writes to the FS and check that all
+ *                            journals are clean
+ * @sdp: the file system
+ * @state: the state to put the transaction lock into
+ * @t_gh: the hold on the transaction lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
+				    struct gfs2_holder *t_gh)
+{
+	struct gfs2_inode *ip;
+	struct gfs2_holder ji_gh;
+	struct gfs2_jdesc *jd;
+	struct lfcc *lfcc;
+	LIST_HEAD(list);
+	struct gfs2_log_header_host lh;
+	int error;
+
+	error = gfs2_jindex_hold(sdp, &ji_gh);
+	if (error)
+		return error;
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
+		if (!lfcc) {
+			error = -ENOMEM;
+			goto out;
+		}
+		ip = GFS2_I(jd->jd_inode);
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &lfcc->gh);
+		if (error) {
+			kfree(lfcc);
+			goto out;
+		}
+		list_add(&lfcc->list, &list);
+	}
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
+			       LM_FLAG_PRIORITY | GL_NOCACHE,
+			       t_gh);
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		error = gfs2_jdesc_check(jd);
+		if (error)
+			break;
+		error = gfs2_find_jhead(jd, &lh);
+		if (error)
+			break;
+		if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+			error = -EBUSY;
+			break;
+		}
+	}
+
+	if (error)
+		gfs2_glock_dq_uninit(t_gh);
+
+out:
+	while (!list_empty(&list)) {
+		lfcc = list_entry(list.next, struct lfcc, list);
+		list_del(&lfcc->list);
+		gfs2_glock_dq_uninit(&lfcc->gh);
+		kfree(lfcc);
+	}
+	gfs2_glock_dq_uninit(&ji_gh);
+	return error;
+}
+
+/**
+ * gfs2_freeze_fs - freezes the file system
+ * @sdp: the file system
+ *
+ * This function flushes data and meta data for all machines by
+ * aquiring the transaction log exclusively.  All journals are
+ * ensured to be in a clean state as well.
+ *
+ * Returns: errno
+ */
+
+int gfs2_freeze_fs(struct gfs2_sbd *sdp)
+{
+	int error = 0;
+
+	mutex_lock(&sdp->sd_freeze_lock);
+
+	if (!sdp->sd_freeze_count++) {
+		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+		if (error)
+			sdp->sd_freeze_count--;
+	}
+
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	return error;
+}
+
+/**
+ * gfs2_unfreeze_fs - unfreezes the file system
+ * @sdp: the file system
+ *
+ * This function allows the file system to proceed by unlocking
+ * the exclusively held transaction lock.  Other GFS2 nodes are
+ * now free to acquire the lock shared and go on with their lives.
+ *
+ */
+
+void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
+{
+	mutex_lock(&sdp->sd_freeze_lock);
+
+	if (sdp->sd_freeze_count && !--sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+
+	mutex_unlock(&sdp->sd_freeze_lock);
+}
+

fs/gfs2/super.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __SUPER_DOT_H__
+#define __SUPER_DOT_H__
+
+#include "incore.h"
+
+void gfs2_tune_init(struct gfs2_tune *gt);
+
+int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent);
+int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent);
+struct page *gfs2_read_super(struct super_block *sb, sector_t sector);
+
+static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
+{
+	unsigned int x;
+	spin_lock(&sdp->sd_jindex_spin);
+	x = sdp->sd_journals;
+	spin_unlock(&sdp->sd_jindex_spin);
+	return x;
+}
+
+int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh);
+void gfs2_jindex_free(struct gfs2_sbd *sdp);
+
+struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid);
+void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid);
+struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp);
+int gfs2_jdesc_check(struct gfs2_jdesc *jd);
+
+int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
+			      struct gfs2_inode **ipp);
+
+int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
+int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
+
+int gfs2_statfs_init(struct gfs2_sbd *sdp);
+void gfs2_statfs_change(struct gfs2_sbd *sdp,
+			s64 total, s64 free, s64 dinodes);
+int gfs2_statfs_sync(struct gfs2_sbd *sdp);
+int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc);
+int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc);
+
+int gfs2_freeze_fs(struct gfs2_sbd *sdp);
+void gfs2_unfreeze_fs(struct gfs2_sbd *sdp);
+
+#endif /* __SUPER_DOT_H__ */
+

fs/gfs2/sys.c

@@ -0,0 +1,565 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "lm.h"
+#include "sys.h"
+#include "super.h"
+#include "glock.h"
+#include "quota.h"
+#include "util.h"
+
+char *gfs2_sys_margs;
+spinlock_t gfs2_sys_margs_lock;
+
+static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_vfs->s_id);
+}
+
+static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
+}
+
+static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
+{
+	unsigned int count;
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	count = sdp->sd_freeze_count;
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", count);
+}
+
+static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int error = 0;
+	int n = simple_strtol(buf, NULL, 0);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	switch (n) {
+	case 0:
+		gfs2_unfreeze_fs(sdp);
+		break;
+	case 1:
+		error = gfs2_freeze_fs(sdp);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (error)
+		fs_warn(sdp, "freeze %d error %d", n, error);
+
+	return ret;
+}
+
+static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
+{
+	unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
+	return snprintf(buf, PAGE_SIZE, "%u\n", b);
+}
+
+static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: withdrawing from cluster at user's request\n",
+		sdp->sd_fsname);
+	return len;
+}
+
+static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_statfs_sync(sdp);
+	return len;
+}
+
+static ssize_t shrink_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_gl_hash_clear(sdp, NO_WAIT);
+	return len;
+}
+
+static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_quota_sync(sdp);
+	return len;
+}
+
+static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf,
+					size_t len)
+{
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	gfs2_quota_refresh(sdp, 1, id);
+	return len;
+}
+
+static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf,
+					 size_t len)
+{
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	gfs2_quota_refresh(sdp, 0, id);
+	return len;
+}
+
+struct gfs2_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+#define GFS2_ATTR(name, mode, show, store) \
+static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)
+
+GFS2_ATTR(id,                  0444, id_show,       NULL);
+GFS2_ATTR(fsname,              0444, fsname_show,   NULL);
+GFS2_ATTR(freeze,              0644, freeze_show,   freeze_store);
+GFS2_ATTR(shrink,              0200, NULL,          shrink_store);
+GFS2_ATTR(withdraw,            0644, withdraw_show, withdraw_store);
+GFS2_ATTR(statfs_sync,         0200, NULL,          statfs_sync_store);
+GFS2_ATTR(quota_sync,          0200, NULL,          quota_sync_store);
+GFS2_ATTR(quota_refresh_user,  0200, NULL,          quota_refresh_user_store);
+GFS2_ATTR(quota_refresh_group, 0200, NULL,          quota_refresh_group_store);
+
+static struct attribute *gfs2_attrs[] = {
+	&gfs2_attr_id.attr,
+	&gfs2_attr_fsname.attr,
+	&gfs2_attr_freeze.attr,
+	&gfs2_attr_shrink.attr,
+	&gfs2_attr_withdraw.attr,
+	&gfs2_attr_statfs_sync.attr,
+	&gfs2_attr_quota_sync.attr,
+	&gfs2_attr_quota_refresh_user.attr,
+	&gfs2_attr_quota_refresh_group.attr,
+	NULL,
+};
+
+static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->show ? a->show(sdp, buf) : 0;
+}
+
+static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->store ? a->store(sdp, buf, len) : len;
+}
+
+static struct sysfs_ops gfs2_attr_ops = {
+	.show  = gfs2_attr_show,
+	.store = gfs2_attr_store,
+};
+
+static struct kobj_type gfs2_ktype = {
+	.default_attrs = gfs2_attrs,
+	.sysfs_ops     = &gfs2_attr_ops,
+};
+
+static struct kset gfs2_kset = {
+	.subsys = &fs_subsys,
+	.kobj   = {.name = "gfs2"},
+	.ktype  = &gfs2_ktype,
+};
+
+/*
+ * display struct lm_lockstruct fields
+ */
+
+struct lockstruct_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+};
+
+#define LOCKSTRUCT_ATTR(name, fmt)                                          \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
+{                                                                           \
+	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \
+}                                                                           \
+static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name)
+
+LOCKSTRUCT_ATTR(jid,      "%u\n");
+LOCKSTRUCT_ATTR(first,    "%u\n");
+LOCKSTRUCT_ATTR(lvb_size, "%u\n");
+LOCKSTRUCT_ATTR(flags,    "%d\n");
+
+static struct attribute *lockstruct_attrs[] = {
+	&lockstruct_attr_jid.attr,
+	&lockstruct_attr_first.attr,
+	&lockstruct_attr_lvb_size.attr,
+	&lockstruct_attr_flags.attr,
+	NULL,
+};
+
+/*
+ * display struct gfs2_args fields
+ */
+
+struct args_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+};
+
+#define ARGS_ATTR(name, fmt)                                                \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
+{                                                                           \
+	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name);       \
+}                                                                           \
+static struct args_attr args_attr_##name = __ATTR_RO(name)
+
+ARGS_ATTR(lockproto,       "%s\n");
+ARGS_ATTR(locktable,       "%s\n");
+ARGS_ATTR(hostdata,        "%s\n");
+ARGS_ATTR(spectator,       "%d\n");
+ARGS_ATTR(ignore_local_fs, "%d\n");
+ARGS_ATTR(localcaching,    "%d\n");
+ARGS_ATTR(localflocks,     "%d\n");
+ARGS_ATTR(debug,           "%d\n");
+ARGS_ATTR(upgrade,         "%d\n");
+ARGS_ATTR(num_glockd,      "%u\n");
+ARGS_ATTR(posix_acl,       "%d\n");
+ARGS_ATTR(quota,           "%u\n");
+ARGS_ATTR(suiddir,         "%d\n");
+ARGS_ATTR(data,            "%d\n");
+
+/* one oddball doesn't fit the macro mold */
+static ssize_t noatime_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			!!test_bit(SDF_NOATIME, &sdp->sd_flags));
+}
+static struct args_attr args_attr_noatime = __ATTR_RO(noatime);
+
+static struct attribute *args_attrs[] = {
+	&args_attr_lockproto.attr,
+	&args_attr_locktable.attr,
+	&args_attr_hostdata.attr,
+	&args_attr_spectator.attr,
+	&args_attr_ignore_local_fs.attr,
+	&args_attr_localcaching.attr,
+	&args_attr_localflocks.attr,
+	&args_attr_debug.attr,
+	&args_attr_upgrade.attr,
+	&args_attr_num_glockd.attr,
+	&args_attr_posix_acl.attr,
+	&args_attr_quota.attr,
+	&args_attr_suiddir.attr,
+	&args_attr_data.attr,
+	&args_attr_noatime.attr,
+	NULL,
+};
+
+/*
+ * display counters from superblock
+ */
+
+struct counters_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+};
+
+#define COUNTERS_ATTR(name, fmt)                                            \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
+{                                                                           \
+	return snprintf(buf, PAGE_SIZE, fmt,                                \
+			(unsigned int)atomic_read(&sdp->sd_##name));        \
+}                                                                           \
+static struct counters_attr counters_attr_##name = __ATTR_RO(name)
+
+COUNTERS_ATTR(glock_count,      "%u\n");
+COUNTERS_ATTR(glock_held_count, "%u\n");
+COUNTERS_ATTR(inode_count,      "%u\n");
+COUNTERS_ATTR(reclaimed,        "%u\n");
+
+static struct attribute *counters_attrs[] = {
+	&counters_attr_glock_count.attr,
+	&counters_attr_glock_held_count.attr,
+	&counters_attr_inode_count.attr,
+	&counters_attr_reclaimed.attr,
+	NULL,
+};
+
+/*
+ * get and set struct gfs2_tune fields
+ */
+
+static ssize_t quota_scale_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u %u\n",
+			sdp->sd_tune.gt_quota_scale_num,
+			sdp->sd_tune.gt_quota_scale_den);
+}
+
+static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x, y;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (sscanf(buf, "%u %u", &x, &y) != 2 || !y)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	gt->gt_quota_scale_num = x;
+	gt->gt_quota_scale_den = y;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
+			int check_zero, const char *buf, size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	x = simple_strtoul(buf, NULL, 0);
+
+	if (check_zero && !x)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	*field = x;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+struct tune_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+#define TUNE_ATTR_3(name, show, store)                                        \
+static struct tune_attr tune_attr_##name = __ATTR(name, 0644, show, store)
+
+#define TUNE_ATTR_2(name, store)                                              \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
+{                                                                             \
+	return snprintf(buf, PAGE_SIZE, "%u\n", sdp->sd_tune.gt_##name);      \
+}                                                                             \
+TUNE_ATTR_3(name, name##_show, store)
+
+#define TUNE_ATTR(name, check_zero)                                           \
+static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
+{                                                                             \
+	return tune_set(sdp, &sdp->sd_tune.gt_##name, check_zero, buf, len);  \
+}                                                                             \
+TUNE_ATTR_2(name, name##_store)
+
+#define TUNE_ATTR_DAEMON(name, process)                                       \
+static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
+{                                                                             \
+	ssize_t r = tune_set(sdp, &sdp->sd_tune.gt_##name, 1, buf, len);      \
+	wake_up_process(sdp->sd_##process);                                   \
+	return r;                                                             \
+}                                                                             \
+TUNE_ATTR_2(name, name##_store)
+
+TUNE_ATTR(demote_secs, 0);
+TUNE_ATTR(incore_log_blocks, 0);
+TUNE_ATTR(log_flush_secs, 0);
+TUNE_ATTR(jindex_refresh_secs, 0);
+TUNE_ATTR(quota_warn_period, 0);
+TUNE_ATTR(quota_quantum, 0);
+TUNE_ATTR(atime_quantum, 0);
+TUNE_ATTR(max_readahead, 0);
+TUNE_ATTR(complain_secs, 0);
+TUNE_ATTR(reclaim_limit, 0);
+TUNE_ATTR(statfs_slow, 0);
+TUNE_ATTR(new_files_jdata, 0);
+TUNE_ATTR(new_files_directio, 0);
+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);
+TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
+
+static struct attribute *tune_attrs[] = {
+	&tune_attr_demote_secs.attr,
+	&tune_attr_incore_log_blocks.attr,
+	&tune_attr_log_flush_secs.attr,
+	&tune_attr_jindex_refresh_secs.attr,
+	&tune_attr_quota_warn_period.attr,
+	&tune_attr_quota_quantum.attr,
+	&tune_attr_atime_quantum.attr,
+	&tune_attr_max_readahead.attr,
+	&tune_attr_complain_secs.attr,
+	&tune_attr_reclaim_limit.attr,
+	&tune_attr_statfs_slow.attr,
+	&tune_attr_quota_simul_sync.attr,
+	&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,
+	&tune_attr_quota_scale.attr,
+	&tune_attr_new_files_jdata.attr,
+	&tune_attr_new_files_directio.attr,
+	NULL,
+};
+
+static struct attribute_group lockstruct_group = {
+	.name = "lockstruct",
+	.attrs = lockstruct_attrs,
+};
+
+static struct attribute_group counters_group = {
+	.name = "counters",
+	.attrs = counters_attrs,
+};
+
+static struct attribute_group args_group = {
+	.name = "args",
+	.attrs = args_attrs,
+};
+
+static struct attribute_group tune_group = {
+	.name = "tune",
+	.attrs = tune_attrs,
+};
+
+int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
+{
+	int error;
+
+	sdp->sd_kobj.kset = &gfs2_kset;
+	sdp->sd_kobj.ktype = &gfs2_ktype;
+
+	error = kobject_set_name(&sdp->sd_kobj, "%s", sdp->sd_table_name);
+	if (error)
+		goto fail;
+
+	error = kobject_register(&sdp->sd_kobj);
+	if (error)
+		goto fail;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &lockstruct_group);
+	if (error)
+		goto fail_reg;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &counters_group);
+	if (error)
+		goto fail_lockstruct;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &args_group);
+	if (error)
+		goto fail_counters;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
+	if (error)
+		goto fail_args;
+
+	return 0;
+
+fail_args:
+	sysfs_remove_group(&sdp->sd_kobj, &args_group);
+fail_counters:
+	sysfs_remove_group(&sdp->sd_kobj, &counters_group);
+fail_lockstruct:
+	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
+fail_reg:
+	kobject_unregister(&sdp->sd_kobj);
+fail:
+	fs_err(sdp, "error %d adding sysfs files", error);
+	return error;
+}
+
+void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
+{
+	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
+	sysfs_remove_group(&sdp->sd_kobj, &args_group);
+	sysfs_remove_group(&sdp->sd_kobj, &counters_group);
+	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
+	kobject_unregister(&sdp->sd_kobj);
+}
+
+int gfs2_sys_init(void)
+{
+	gfs2_sys_margs = NULL;
+	spin_lock_init(&gfs2_sys_margs_lock);
+	return kset_register(&gfs2_kset);
+}
+
+void gfs2_sys_uninit(void)
+{
+	kfree(gfs2_sys_margs);
+	kset_unregister(&gfs2_kset);
+}
+

fs/gfs2/sys.h

@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __SYS_DOT_H__
+#define __SYS_DOT_H__
+
+#include <linux/spinlock.h>
+struct gfs2_sbd;
+
+/* Allow args to be passed to GFS2 when using an initial ram disk */
+extern char *gfs2_sys_margs;
+extern spinlock_t gfs2_sys_margs_lock;
+
+int gfs2_sys_fs_add(struct gfs2_sbd *sdp);
+void gfs2_sys_fs_del(struct gfs2_sbd *sdp);
+
+int gfs2_sys_init(void);
+void gfs2_sys_uninit(void);
+
+#endif /* __SYS_DOT_H__ */
+

fs/gfs2/trans.c

@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/kallsyms.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes)
+{
+	struct gfs2_trans *tr;
+	int error;
+
+	BUG_ON(current->journal_info);
+	BUG_ON(blocks == 0 && revokes == 0);
+
+	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
+	if (!tr)
+		return -ENOMEM;
+
+	tr->tr_ip = (unsigned long)__builtin_return_address(0);
+	tr->tr_blocks = blocks;
+	tr->tr_revokes = revokes;
+	tr->tr_reserved = 1;
+	if (blocks)
+		tr->tr_reserved += 6 + blocks;
+	if (revokes)
+		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
+						   sizeof(u64));
+	INIT_LIST_HEAD(&tr->tr_list_buf);
+
+	gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
+
+	error = gfs2_glock_nq(&tr->tr_t_gh);
+	if (error)
+		goto fail_holder_uninit;
+
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		tr->tr_t_gh.gh_flags |= GL_NOCACHE;
+		error = -EROFS;
+		goto fail_gunlock;
+	}
+
+	error = gfs2_log_reserve(sdp, tr->tr_reserved);
+	if (error)
+		goto fail_gunlock;
+
+	current->journal_info = tr;
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq(&tr->tr_t_gh);
+
+fail_holder_uninit:
+	gfs2_holder_uninit(&tr->tr_t_gh);
+	kfree(tr);
+
+	return error;
+}
+
+void gfs2_trans_end(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr = current->journal_info;
+
+	BUG_ON(!tr);
+	current->journal_info = NULL;
+
+	if (!tr->tr_touched) {
+		gfs2_log_release(sdp, tr->tr_reserved);
+		gfs2_glock_dq(&tr->tr_t_gh);
+		gfs2_holder_uninit(&tr->tr_t_gh);
+		kfree(tr);
+		return;
+	}
+
+	if (gfs2_assert_withdraw(sdp, tr->tr_num_buf <= tr->tr_blocks)) {
+		fs_err(sdp, "tr_num_buf = %u, tr_blocks = %u ",
+		       tr->tr_num_buf, tr->tr_blocks);
+		print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
+	}
+	if (gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes)) {
+		fs_err(sdp, "tr_num_revoke = %u, tr_revokes = %u ",
+		       tr->tr_num_revoke, tr->tr_revokes);
+		print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
+	}
+
+	gfs2_log_commit(sdp, tr);
+        gfs2_glock_dq(&tr->tr_t_gh);
+        gfs2_holder_uninit(&tr->tr_t_gh);
+        kfree(tr);
+
+	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
+		gfs2_log_flush(sdp, NULL);
+}
+
+void gfs2_trans_add_gl(struct gfs2_glock *gl)
+{
+	lops_add(gl->gl_sbd, &gl->gl_le);
+}
+
+/**
+ * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction
+ * @gl: the glock the buffer belongs to
+ * @bh: The buffer to add
+ * @meta: True in the case of adding metadata
+ *
+ */
+
+void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_bufdata *bd;
+
+	bd = bh->b_private;
+	if (bd)
+		gfs2_assert(sdp, bd->bd_gl == gl);
+	else {
+		gfs2_attach_bufdata(gl, bh, meta);
+		bd = bh->b_private;
+	}
+	lops_add(sdp, &bd->bd_le);
+}
+
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
+{
+	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);
+}
+
+void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
+{
+	struct gfs2_revoke *rv;
+	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);
+			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
+			sdp->sd_log_num_revoke--;
+			found = 1;
+			break;
+		}
+	}
+
+	gfs2_log_unlock(sdp);
+
+	if (found) {
+		struct gfs2_trans *tr = current->journal_info;
+		kfree(rv);
+		tr->tr_num_revoke_rm++;
+	}
+}
+
+void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd)
+{
+	lops_add(rgd->rd_sbd, &rgd->rd_le);
+}
+

fs/gfs2/trans.h

@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __TRANS_DOT_H__
+#define __TRANS_DOT_H__
+
+#include <linux/buffer_head.h>
+struct gfs2_sbd;
+struct gfs2_rgrpd;
+struct gfs2_glock;
+
+#define RES_DINODE	1
+#define RES_INDIRECT	1
+#define RES_JDATA	1
+#define RES_DATA	1
+#define RES_LEAF	1
+#define RES_RG_BIT	2
+#define RES_EATTR	1
+#define RES_STATFS	1
+#define RES_QUOTA	2
+
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes);
+
+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_unrevoke(struct gfs2_sbd *sdp, u64 blkno);
+void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
+
+#endif /* __TRANS_DOT_H__ */

fs/gfs2/util.c

@@ -0,0 +1,244 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/crc32.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "lm.h"
+#include "util.h"
+
+struct kmem_cache *gfs2_glock_cachep __read_mostly;
+struct kmem_cache *gfs2_inode_cachep __read_mostly;
+struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
+
+void gfs2_assert_i(struct gfs2_sbd *sdp)
+{
+	printk(KERN_EMERG "GFS2: fsid=%s: fatal assertion failed\n",
+	       sdp->sd_fsname);
+}
+
+/**
+ * gfs2_assert_withdraw_i - Cause the machine to withdraw if @assertion is false
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: assertion \"%s\" failed\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname, assertion,
+		sdp->sd_fsname, function, file, line);
+	dump_stack();
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_assert_warn_i - Print a message to the console if @assertion is false
+ * Returns: -1 if we printed something
+ *          -2 if we didn't
+ */
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line)
+{
+	if (time_before(jiffies,
+			sdp->sd_last_warning +
+			gfs2_tune_get(sdp, gt_complain_secs) * HZ))
+		return -2;
+
+	printk(KERN_WARNING
+	       "GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
+	       "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+	       sdp->sd_fsname, assertion,
+	       sdp->sd_fsname, function, file, line);
+
+	if (sdp->sd_args.ar_debug)
+		BUG();
+	else
+		dump_stack();
+
+	sdp->sd_last_warning = jiffies;
+
+	return -1;
+}
+
+/**
+ * gfs2_consist_i - Flag a filesystem consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide, const char *function,
+		   char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_inode_i - Flag an inode consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   inode = %llu %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)ip->i_num.no_formal_ino,
+		(unsigned long long)ip->i_num.no_addr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_rgrpd_i - Flag a RG consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: filesystem consistency error\n"
+		"GFS2: fsid=%s:   RG = %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)rgd->rd_ri.ri_addr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_meta_check_ii - Flag a magic number consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function, char *file,
+		       unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: invalid metadata block\n"
+		"GFS2: fsid=%s:   bh = %llu (%s)\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type,
+		sdp->sd_fsname, function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_metatype_check_ii - Flag a metadata type consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t, const char *function,
+			   char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: invalid metadata block\n"
+		"GFS2: fsid=%s:   bh = %llu (type: exp=%u, found=%u)\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type, t,
+		sdp->sd_fsname, function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_io_error_i - Flag an I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
+		    unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: I/O error\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_io_error_bh_i - Flag a buffer I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+		"GFS2: fsid=%s: fatal: I/O error\n"
+		"GFS2: fsid=%s:   block = %llu\n"
+		"GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
+		sdp->sd_fsname,
+		sdp->sd_fsname, (unsigned long long)bh->b_blocknr,
+		sdp->sd_fsname, function, file, line);
+	return rv;
+}
+
+void gfs2_icbit_munge(struct gfs2_sbd *sdp, unsigned char **bitmap,
+		      unsigned int bit, int new_value)
+{
+	unsigned int c, o, b = bit;
+	int old_value;
+
+	c = b / (8 * PAGE_SIZE);
+	b %= 8 * PAGE_SIZE;
+	o = b / 8;
+	b %= 8;
+
+	old_value = (bitmap[c][o] & (1 << b));
+	gfs2_assert_withdraw(sdp, !old_value != !new_value);
+
+	if (new_value)
+		bitmap[c][o] |= 1 << b;
+	else
+		bitmap[c][o] &= ~(1 << b);
+}
+

fs/gfs2/util.h

@@ -0,0 +1,168 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 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
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __UTIL_DOT_H__
+#define __UTIL_DOT_H__
+
+#include "incore.h"
+
+#define fs_printk(level, fs, fmt, arg...) \
+	printk(level "GFS2: fsid=%s: " fmt , (fs)->sd_fsname , ## arg)
+
+#define fs_info(fs, fmt, arg...) \
+	fs_printk(KERN_INFO , fs , fmt , ## arg)
+
+#define fs_warn(fs, fmt, arg...) \
+	fs_printk(KERN_WARNING , fs , fmt , ## arg)
+
+#define fs_err(fs, fmt, arg...) \
+	fs_printk(KERN_ERR, fs , fmt , ## arg)
+
+
+void gfs2_assert_i(struct gfs2_sbd *sdp);
+
+#define gfs2_assert(sdp, assertion) \
+do { \
+	if (unlikely(!(assertion))) { \
+		gfs2_assert_i(sdp); \
+		BUG(); \
+        } \
+} while (0)
+
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_withdraw(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_withdraw_i((sdp), #assertion, \
+					__FUNCTION__, __FILE__, __LINE__))
+
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_warn(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_warn_i((sdp), #assertion, \
+					__FUNCTION__, __FILE__, __LINE__))
+
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide,
+		   const char *function, char *file, unsigned int line);
+
+#define gfs2_consist(sdp) \
+gfs2_consist_i((sdp), 0, __FUNCTION__, __FILE__, __LINE__)
+
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_inode(ip) \
+gfs2_consist_inode_i((ip), 0, __FUNCTION__, __FILE__, __LINE__)
+
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_rgrpd(rgd) \
+gfs2_consist_rgrpd_i((rgd), 0, __FUNCTION__, __FILE__, __LINE__)
+
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function,
+		       char *file, unsigned int line);
+
+static inline int gfs2_meta_check_i(struct gfs2_sbd *sdp,
+				    struct buffer_head *bh,
+				    const char *function,
+				    char *file, unsigned int line)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	if (unlikely(magic != GFS2_MAGIC))
+		return gfs2_meta_check_ii(sdp, bh, "magic number", function,
+					  file, line);
+	return 0;
+}
+
+#define gfs2_meta_check(sdp, bh) \
+gfs2_meta_check_i((sdp), (bh), __FUNCTION__, __FILE__, __LINE__)
+
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t,
+			   const char *function,
+			   char *file, unsigned int line);
+
+static inline int gfs2_metatype_check_i(struct gfs2_sbd *sdp,
+					struct buffer_head *bh,
+					u16 type,
+					const char *function,
+					char *file, unsigned int line)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	u16 t = be32_to_cpu(mh->mh_type);
+	if (unlikely(magic != GFS2_MAGIC))
+		return gfs2_meta_check_ii(sdp, bh, "magic number", function,
+					  file, line);
+        if (unlikely(t != type))
+		return gfs2_metatype_check_ii(sdp, bh, type, t, function,
+					      file, line);
+	return 0;
+}
+
+#define gfs2_metatype_check(sdp, bh, type) \
+gfs2_metatype_check_i((sdp), (bh), (type), __FUNCTION__, __FILE__, __LINE__)
+
+static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type,
+				     u16 format)
+{
+	struct gfs2_meta_header *mh;
+	mh = (struct gfs2_meta_header *)bh->b_data;
+	mh->mh_type = cpu_to_be32(type);
+	mh->mh_format = cpu_to_be32(format);
+}
+
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
+		    char *file, unsigned int line);
+
+#define gfs2_io_error(sdp) \
+gfs2_io_error_i((sdp), __FUNCTION__, __FILE__, __LINE__);
+
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_io_error_bh(sdp, bh) \
+gfs2_io_error_bh_i((sdp), (bh), __FUNCTION__, __FILE__, __LINE__);
+
+
+extern struct kmem_cache *gfs2_glock_cachep;
+extern struct kmem_cache *gfs2_inode_cachep;
+extern struct kmem_cache *gfs2_bufdata_cachep;
+
+static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
+					   unsigned int *p)
+{
+	unsigned int x;
+	spin_lock(&gt->gt_spin);
+	x = *p;
+	spin_unlock(&gt->gt_spin);
+	return x;
+}
+
+#define gfs2_tune_get(sdp, field) \
+gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
+
+void gfs2_icbit_munge(struct gfs2_sbd *sdp, unsigned char **bitmap,
+		      unsigned int bit, int new_value);
+
+#endif /* __UTIL_DOT_H__ */
+