kernel-ark/fs/gfs2/super.c
Steven Whitehouse f057f6cdf6 GFS2: Merge lock_dlm module into GFS2
This is the big patch that I've been working on for some time
now. There are many reasons for wanting to make this change
such as:
 o Reducing overhead by eliminating duplicated fields between structures
 o Simplifcation of the code (reduces the code size by a fair bit)
 o The locking interface is now the DLM interface itself as proposed
   some time ago.
 o Fewer lookups of glocks when processing replies from the DLM
 o Fewer memory allocations/deallocations for each glock
 o Scope to do further optimisations in the future (but this patch is
   more than big enough for now!)

Please note that (a) this patch relates to the lock_dlm module and
not the DLM itself, that is still a separate module; and (b) that
we retain the ability to build GFS2 as a standalone single node
filesystem with out requiring the DLM.

This patch needs a lot of testing, hence my keeping it I restarted
my -git tree after the last merge window. That way, this has the maximum
exposure before its merged. This is (modulo a few minor bug fixes) the
same patch that I've been posting on and off the the last three months
and its passed a number of different tests so far.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2009-03-24 11:21:14 +00:00

441 lines
9.9 KiB
C

/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* 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 "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"
/**
* 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, *head;
struct gfs2_jdesc *jd;
struct gfs2_journal_extent *jext;
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);
head = &jd->extent_list;
while (!list_empty(head)) {
jext = list_entry(head->next,
struct gfs2_journal_extent,
extent_list);
list_del(&jext->extent_list);
kfree(jext);
}
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;
}
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_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
(ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
gfs2_consist_inode(ip);
return -EIO;
}
jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
error = gfs2_write_alloc_required(ip, 0, ip->i_disksize, &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;
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;
}
static 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);
}
static 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);
}
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;
gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
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;
gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
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;
}
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;
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,
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);
}