OpenCloudOS-Kernel/fs/gfs2/quota.c

1616 lines
38 KiB
C
Raw Normal View History

/*
* 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.
*/
/*
* Quota change tags are associated with each transaction that allocates or
* deallocates space. Those changes are accumulated locally to each node (in a
* per-node file) and then are periodically synced to the quota file. This
* avoids the bottleneck of constantly touching the quota file, but introduces
* fuzziness in the current usage value of IDs that are being used on different
* nodes in the cluster simultaneously. So, it is possible for a user on
* multiple nodes to overrun their quota, but that overrun is controlable.
* Since quota tags are part of transactions, there is no need for a quota check
* program to be run on node crashes or anything like that.
*
* There are couple of knobs that let the administrator manage the quota
* fuzziness. "quota_quantum" sets the maximum time a quota change can be
* sitting on one node before being synced to the quota file. (The default is
* 60 seconds.) Another knob, "quota_scale" controls how quickly the frequency
* of quota file syncs increases as the user moves closer to their limit. The
* more frequent the syncs, the more accurate the quota enforcement, but that
* means that there is more contention between the nodes for the quota file.
* The default value is one. This sets the maximum theoretical quota overrun
* (with infinite node with infinite bandwidth) to twice the user's limit. (In
* practice, the maximum overrun you see should be much less.) A "quota_scale"
* number greater than one makes quota syncs more frequent and reduces the
* maximum overrun. Numbers less than one (but greater than zero) make quota
* syncs less frequent.
*
* GFS quotas also use per-ID Lock Value Blocks (LVBs) to cache the contents of
* the quota file, so it is not being constantly read.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/sort.h>
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
#include <linux/fs.h>
#include <linux/bio.h>
#include <linux/gfs2_ondisk.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/quota.h>
#include <linux/dqblk_xfs.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "glops.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
#include "inode.h"
#include "util.h"
struct gfs2_quota_change_host {
u64 qc_change;
u32 qc_flags; /* GFS2_QCF_... */
struct kqid qc_id;
};
static LIST_HEAD(qd_lru_list);
static atomic_t qd_lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(qd_lru_lock);
int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
int nr_to_scan = sc->nr_to_scan;
if (nr_to_scan == 0)
goto out;
if (!(sc->gfp_mask & __GFP_FS))
return -1;
spin_lock(&qd_lru_lock);
while (nr_to_scan && !list_empty(&qd_lru_list)) {
qd = list_entry(qd_lru_list.next,
struct gfs2_quota_data, qd_reclaim);
sdp = qd->qd_gl->gl_sbd;
/* Free from the filesystem-specific list */
list_del(&qd->qd_list);
gfs2_assert_warn(sdp, !qd->qd_change);
gfs2_assert_warn(sdp, !qd->qd_slot_count);
gfs2_assert_warn(sdp, !qd->qd_bh_count);
gfs2_glock_put(qd->qd_gl);
atomic_dec(&sdp->sd_quota_count);
/* Delete it from the common reclaim list */
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
spin_unlock(&qd_lru_lock);
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lru_lock);
nr_to_scan--;
}
spin_unlock(&qd_lru_lock);
out:
return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
}
static u64 qd2index(struct gfs2_quota_data *qd)
{
struct kqid qid = qd->qd_id;
return (2 * (u64)from_kqid(&init_user_ns, qid)) +
(qid.type == USRQUOTA) ? 0 : 1;
}
static u64 qd2offset(struct gfs2_quota_data *qd)
{
u64 offset;
offset = qd2index(qd);
offset *= sizeof(struct gfs2_quota);
return offset;
}
static int qd_alloc(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd;
int error;
qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS);
if (!qd)
return -ENOMEM;
atomic_set(&qd->qd_count, 1);
qd->qd_id = qid;
qd->qd_slot = -1;
INIT_LIST_HEAD(&qd->qd_reclaim);
error = gfs2_glock_get(sdp, qd2index(qd),
&gfs2_quota_glops, CREATE, &qd->qd_gl);
if (error)
goto fail;
*qdp = qd;
return 0;
fail:
kmem_cache_free(gfs2_quotad_cachep, qd);
return error;
}
static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd = NULL, *new_qd = NULL;
int error, found;
*qdp = NULL;
for (;;) {
found = 0;
spin_lock(&qd_lru_lock);
list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
if (qid_eq(qd->qd_id, qid)) {
if (!atomic_read(&qd->qd_count) &&
!list_empty(&qd->qd_reclaim)) {
/* Remove it from reclaim list */
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
}
atomic_inc(&qd->qd_count);
found = 1;
break;
}
}
if (!found)
qd = NULL;
if (!qd && new_qd) {
qd = new_qd;
list_add(&qd->qd_list, &sdp->sd_quota_list);
atomic_inc(&sdp->sd_quota_count);
new_qd = NULL;
}
spin_unlock(&qd_lru_lock);
if (qd) {
if (new_qd) {
gfs2_glock_put(new_qd->qd_gl);
kmem_cache_free(gfs2_quotad_cachep, new_qd);
}
*qdp = qd;
return 0;
}
error = qd_alloc(sdp, qid, &new_qd);
if (error)
return error;
}
}
static void qd_hold(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
gfs2_assert(sdp, atomic_read(&qd->qd_count));
atomic_inc(&qd->qd_count);
}
static void qd_put(struct gfs2_quota_data *qd)
{
if (atomic_dec_and_lock(&qd->qd_count, &qd_lru_lock)) {
/* Add to the reclaim list */
list_add_tail(&qd->qd_reclaim, &qd_lru_list);
atomic_inc(&qd_lru_count);
spin_unlock(&qd_lru_lock);
}
}
static int slot_get(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
unsigned int c, o = 0, b;
unsigned char byte = 0;
spin_lock(&qd_lru_lock);
if (qd->qd_slot_count++) {
spin_unlock(&qd_lru_lock);
return 0;
}
for (c = 0; c < sdp->sd_quota_chunks; c++)
for (o = 0; o < PAGE_SIZE; o++) {
byte = sdp->sd_quota_bitmap[c][o];
if (byte != 0xFF)
goto found;
}
goto fail;
found:
for (b = 0; b < 8; b++)
if (!(byte & (1 << b)))
break;
qd->qd_slot = c * (8 * PAGE_SIZE) + o * 8 + b;
if (qd->qd_slot >= sdp->sd_quota_slots)
goto fail;
sdp->sd_quota_bitmap[c][o] |= 1 << b;
spin_unlock(&qd_lru_lock);
return 0;
fail:
qd->qd_slot_count--;
spin_unlock(&qd_lru_lock);
return -ENOSPC;
}
static void slot_hold(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
spin_lock(&qd_lru_lock);
gfs2_assert(sdp, qd->qd_slot_count);
qd->qd_slot_count++;
spin_unlock(&qd_lru_lock);
}
static void slot_put(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
spin_lock(&qd_lru_lock);
gfs2_assert(sdp, qd->qd_slot_count);
if (!--qd->qd_slot_count) {
gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, qd->qd_slot, 0);
qd->qd_slot = -1;
}
spin_unlock(&qd_lru_lock);
}
static int bh_get(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
unsigned int block, offset;
struct buffer_head *bh;
int error;
struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
mutex_lock(&sdp->sd_quota_mutex);
if (qd->qd_bh_count++) {
mutex_unlock(&sdp->sd_quota_mutex);
return 0;
}
block = qd->qd_slot / sdp->sd_qc_per_block;
offset = qd->qd_slot % sdp->sd_qc_per_block;
bh_map.b_size = 1 << ip->i_inode.i_blkbits;
error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
if (error)
goto fail;
error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
if (error)
goto fail;
error = -EIO;
if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC))
goto fail_brelse;
qd->qd_bh = bh;
qd->qd_bh_qc = (struct gfs2_quota_change *)
(bh->b_data + sizeof(struct gfs2_meta_header) +
offset * sizeof(struct gfs2_quota_change));
mutex_unlock(&sdp->sd_quota_mutex);
return 0;
fail_brelse:
brelse(bh);
fail:
qd->qd_bh_count--;
mutex_unlock(&sdp->sd_quota_mutex);
return error;
}
static void bh_put(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
mutex_lock(&sdp->sd_quota_mutex);
gfs2_assert(sdp, qd->qd_bh_count);
if (!--qd->qd_bh_count) {
brelse(qd->qd_bh);
qd->qd_bh = NULL;
qd->qd_bh_qc = NULL;
}
mutex_unlock(&sdp->sd_quota_mutex);
}
static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd = NULL;
int error;
int found = 0;
*qdp = NULL;
if (sdp->sd_vfs->s_flags & MS_RDONLY)
return 0;
spin_lock(&qd_lru_lock);
list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
!test_bit(QDF_CHANGE, &qd->qd_flags) ||
qd->qd_sync_gen >= sdp->sd_quota_sync_gen)
continue;
list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
set_bit(QDF_LOCKED, &qd->qd_flags);
gfs2_assert_warn(sdp, atomic_read(&qd->qd_count));
atomic_inc(&qd->qd_count);
qd->qd_change_sync = qd->qd_change;
gfs2_assert_warn(sdp, qd->qd_slot_count);
qd->qd_slot_count++;
found = 1;
break;
}
if (!found)
qd = NULL;
spin_unlock(&qd_lru_lock);
if (qd) {
gfs2_assert_warn(sdp, qd->qd_change_sync);
error = bh_get(qd);
if (error) {
clear_bit(QDF_LOCKED, &qd->qd_flags);
slot_put(qd);
qd_put(qd);
return error;
}
}
*qdp = qd;
return 0;
}
static int qd_trylock(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
if (sdp->sd_vfs->s_flags & MS_RDONLY)
return 0;
spin_lock(&qd_lru_lock);
if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
!test_bit(QDF_CHANGE, &qd->qd_flags)) {
spin_unlock(&qd_lru_lock);
return 0;
}
list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
set_bit(QDF_LOCKED, &qd->qd_flags);
gfs2_assert_warn(sdp, atomic_read(&qd->qd_count));
atomic_inc(&qd->qd_count);
qd->qd_change_sync = qd->qd_change;
gfs2_assert_warn(sdp, qd->qd_slot_count);
qd->qd_slot_count++;
spin_unlock(&qd_lru_lock);
gfs2_assert_warn(sdp, qd->qd_change_sync);
if (bh_get(qd)) {
clear_bit(QDF_LOCKED, &qd->qd_flags);
slot_put(qd);
qd_put(qd);
return 0;
}
return 1;
}
static void qd_unlock(struct gfs2_quota_data *qd)
{
gfs2_assert_warn(qd->qd_gl->gl_sbd,
test_bit(QDF_LOCKED, &qd->qd_flags));
clear_bit(QDF_LOCKED, &qd->qd_flags);
bh_put(qd);
slot_put(qd);
qd_put(qd);
}
static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
int error;
error = qd_get(sdp, qid, qdp);
if (error)
return error;
error = slot_get(*qdp);
if (error)
goto fail;
error = bh_get(*qdp);
if (error)
goto fail_slot;
return 0;
fail_slot:
slot_put(*qdp);
fail:
qd_put(*qdp);
return error;
}
static void qdsb_put(struct gfs2_quota_data *qd)
{
bh_put(qd);
slot_put(qd);
qd_put(qd);
}
int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data **qd;
int error;
if (ip->i_res == NULL) {
error = gfs2_rs_alloc(ip);
if (error)
return error;
}
qd = ip->i_res->rs_qa_qd;
if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) ||
gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
return -EIO;
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
!uid_eq(uid, ip->i_inode.i_uid)) {
error = qdsb_get(sdp, make_kqid_uid(uid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
}
if (!gid_eq(gid, NO_GID_QUOTA_CHANGE) &&
!gid_eq(gid, ip->i_inode.i_gid)) {
error = qdsb_get(sdp, make_kqid_gid(gid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
}
out:
if (error)
gfs2_quota_unhold(ip);
return error;
}
void gfs2_quota_unhold(struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
unsigned int x;
if (ip->i_res == NULL)
return;
gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
qdsb_put(ip->i_res->rs_qa_qd[x]);
ip->i_res->rs_qa_qd[x] = NULL;
}
ip->i_res->rs_qa_qd_num = 0;
}
static int sort_qd(const void *a, const void *b)
{
const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a;
const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b;
if (qid_lt(qd_a->qd_id, qd_b->qd_id))
return -1;
if (qid_lt(qd_b->qd_id, qd_a->qd_id))
return 1;
return 0;
}
static void do_qc(struct gfs2_quota_data *qd, s64 change)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
struct gfs2_quota_change *qc = qd->qd_bh_qc;
s64 x;
mutex_lock(&sdp->sd_quota_mutex);
gfs2_trans_add_meta(ip->i_gl, qd->qd_bh);
if (!test_bit(QDF_CHANGE, &qd->qd_flags)) {
qc->qc_change = 0;
qc->qc_flags = 0;
if (qd->qd_id.type == USRQUOTA)
qc->qc_flags = cpu_to_be32(GFS2_QCF_USER);
qc->qc_id = cpu_to_be32(from_kqid(&init_user_ns, qd->qd_id));
}
x = be64_to_cpu(qc->qc_change) + change;
qc->qc_change = cpu_to_be64(x);
spin_lock(&qd_lru_lock);
qd->qd_change = x;
spin_unlock(&qd_lru_lock);
if (!x) {
gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags));
clear_bit(QDF_CHANGE, &qd->qd_flags);
qc->qc_flags = 0;
qc->qc_id = 0;
slot_put(qd);
qd_put(qd);
} else if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) {
qd_hold(qd);
slot_hold(qd);
}
mutex_unlock(&sdp->sd_quota_mutex);
}
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
/**
* gfs2_adjust_quota - adjust record of current block usage
* @ip: The quota inode
* @loc: Offset of the entry in the quota file
* @change: The amount of usage change to record
* @qd: The quota data
* @fdq: The updated limits to record
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
*
* This function was mostly borrowed from gfs2_block_truncate_page which was
* in turn mostly borrowed from ext3
*
* Returns: 0 or -ve on error
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
*/
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
s64 change, struct gfs2_quota_data *qd,
struct fs_disk_quota *fdq)
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
{
struct inode *inode = &ip->i_inode;
struct gfs2_sbd *sdp = GFS2_SB(inode);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
struct address_space *mapping = inode->i_mapping;
unsigned long index = loc >> PAGE_CACHE_SHIFT;
unsigned offset = loc & (PAGE_CACHE_SIZE - 1);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
unsigned blocksize, iblock, pos;
struct buffer_head *bh;
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
struct page *page;
void *kaddr, *ptr;
struct gfs2_quota q, *qp;
int err, nbytes;
u64 size;
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
if (gfs2_is_stuffed(ip)) {
err = gfs2_unstuff_dinode(ip, NULL);
if (err)
return err;
}
memset(&q, 0, sizeof(struct gfs2_quota));
err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q));
if (err < 0)
return err;
err = -EIO;
qp = &q;
qp->qu_value = be64_to_cpu(qp->qu_value);
qp->qu_value += change;
qp->qu_value = cpu_to_be64(qp->qu_value);
qd->qd_qb.qb_value = qp->qu_value;
if (fdq) {
if (fdq->d_fieldmask & FS_DQ_BSOFT) {
qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
qd->qd_qb.qb_warn = qp->qu_warn;
}
if (fdq->d_fieldmask & FS_DQ_BHARD) {
qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
qd->qd_qb.qb_limit = qp->qu_limit;
}
if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
qd->qd_qb.qb_value = qp->qu_value;
}
}
/* Write the quota into the quota file on disk */
ptr = qp;
nbytes = sizeof(struct gfs2_quota);
get_a_page:
page = find_or_create_page(mapping, index, GFP_NOFS);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
if (!page)
return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
bh = page_buffers(page);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
if (!buffer_mapped(bh)) {
gfs2_block_map(inode, iblock, bh, 1);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
if (!buffer_mapped(bh))
goto unlock_out;
/* If it's a newly allocated disk block for quota, zero it */
if (buffer_new(bh))
zero_user(page, pos - blocksize, bh->b_size);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
}
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
ll_rw_block(READ | REQ_META, 1, &bh);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
goto unlock_out;
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
}
gfs2_trans_add_meta(ip->i_gl, bh);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
kaddr = kmap_atomic(page);
if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE)
nbytes = PAGE_CACHE_SIZE - offset;
memcpy(kaddr + offset, ptr, nbytes);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
flush_dcache_page(page);
kunmap_atomic(kaddr);
unlock_page(page);
page_cache_release(page);
/* If quota straddles page boundary, we need to update the rest of the
* quota at the beginning of the next page */
if ((offset + sizeof(struct gfs2_quota)) > PAGE_CACHE_SIZE) {
ptr = ptr + nbytes;
nbytes = sizeof(struct gfs2_quota) - nbytes;
offset = 0;
index++;
goto get_a_page;
}
size = loc + sizeof(struct gfs2_quota);
if (size > inode->i_size)
i_size_write(inode, size);
inode->i_mtime = inode->i_atime = CURRENT_TIME;
mark_inode_dirty(inode);
return 0;
unlock_out:
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
unlock_page(page);
page_cache_release(page);
return err;
}
static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
{
struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
unsigned int data_blocks, ind_blocks;
struct gfs2_holder *ghs, i_gh;
unsigned int qx, x;
struct gfs2_quota_data *qd;
unsigned reserved;
loff_t offset;
unsigned int nalloc = 0, blocks;
int error;
error = gfs2_rs_alloc(ip);
if (error)
return error;
gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
&data_blocks, &ind_blocks);
ghs = kcalloc(num_qd, sizeof(struct gfs2_holder), GFP_NOFS);
if (!ghs)
return -ENOMEM;
sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
mutex_lock(&ip->i_inode.i_mutex);
for (qx = 0; qx < num_qd; qx++) {
error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, &ghs[qx]);
if (error)
goto out;
}
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
if (error)
goto out;
for (x = 0; x < num_qd; x++) {
offset = qd2offset(qda[x]);
if (gfs2_write_alloc_required(ip, offset,
sizeof(struct gfs2_quota)))
nalloc++;
}
/*
* 1 blk for unstuffing inode if stuffed. We add this extra
* block to the reservation unconditionally. If the inode
* doesn't need unstuffing, the block will be released to the
* rgrp since it won't be allocated during the transaction
*/
/* +3 in the end for unstuffing block, inode size update block
* and another block in case quota straddles page boundary and
* two blocks need to be updated instead of 1 */
blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3;
reserved = 1 + (nalloc * (data_blocks + ind_blocks));
error = gfs2_inplace_reserve(ip, reserved, 0);
if (error)
goto out_alloc;
if (nalloc)
blocks += gfs2_rg_blocks(ip, reserved) + nalloc * ind_blocks + RES_STATFS;
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
goto out_ipres;
for (x = 0; x < num_qd; x++) {
qd = qda[x];
offset = qd2offset(qd);
error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, qd, NULL);
[GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2006-02-08 19:50:51 +08:00
if (error)
goto out_end_trans;
do_qc(qd, -qd->qd_change_sync);
set_bit(QDF_REFRESH, &qd->qd_flags);
}
error = 0;
out_end_trans:
gfs2_trans_end(sdp);
out_ipres:
gfs2_inplace_release(ip);
out_alloc:
gfs2_glock_dq_uninit(&i_gh);
out:
while (qx--)
gfs2_glock_dq_uninit(&ghs[qx]);
mutex_unlock(&ip->i_inode.i_mutex);
kfree(ghs);
gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);
return error;
}
static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_quota q;
struct gfs2_quota_lvb *qlvb;
loff_t pos;
int error;
memset(&q, 0, sizeof(struct gfs2_quota));
pos = qd2offset(qd);
error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q));
if (error < 0)
return error;
qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC);
qlvb->__pad = 0;
qlvb->qb_limit = q.qu_limit;
qlvb->qb_warn = q.qu_warn;
qlvb->qb_value = q.qu_value;
qd->qd_qb = *qlvb;
return 0;
}
static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
struct gfs2_holder *q_gh)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_holder i_gh;
int error;
restart:
error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
if (error)
return error;
qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) {
gfs2_glock_dq_uninit(q_gh);
error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, q_gh);
if (error)
return error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
if (error)
goto fail;
error = update_qd(sdp, qd);
if (error)
goto fail_gunlock;
gfs2_glock_dq_uninit(&i_gh);
gfs2_glock_dq_uninit(q_gh);
force_refresh = 0;
goto restart;
}
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&i_gh);
fail:
gfs2_glock_dq_uninit(q_gh);
return error;
}
int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data *qd;
unsigned int x;
int error = 0;
error = gfs2_quota_hold(ip, uid, gid);
if (error)
return error;
if (capable(CAP_SYS_RESOURCE) ||
sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
return 0;
sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num,
sizeof(struct gfs2_quota_data *), sort_qd, NULL);
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
int force = NO_FORCE;
qd = ip->i_res->rs_qa_qd[x];
if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags))
force = FORCE;
error = do_glock(qd, force, &ip->i_res->rs_qa_qd_ghs[x]);
if (error)
break;
}
if (!error)
set_bit(GIF_QD_LOCKED, &ip->i_flags);
else {
while (x--)
gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
gfs2_quota_unhold(ip);
}
return error;
}
static int need_sync(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
struct gfs2_tune *gt = &sdp->sd_tune;
s64 value;
unsigned int num, den;
int do_sync = 1;
if (!qd->qd_qb.qb_limit)
return 0;
spin_lock(&qd_lru_lock);
value = qd->qd_change;
spin_unlock(&qd_lru_lock);
spin_lock(&gt->gt_spin);
num = gt->gt_quota_scale_num;
den = gt->gt_quota_scale_den;
spin_unlock(&gt->gt_spin);
if (value < 0)
do_sync = 0;
else if ((s64)be64_to_cpu(qd->qd_qb.qb_value) >=
(s64)be64_to_cpu(qd->qd_qb.qb_limit))
do_sync = 0;
else {
value *= gfs2_jindex_size(sdp) * num;
value = div_s64(value, den);
value += (s64)be64_to_cpu(qd->qd_qb.qb_value);
if (value < (s64)be64_to_cpu(qd->qd_qb.qb_limit))
do_sync = 0;
}
return do_sync;
}
void gfs2_quota_unlock(struct gfs2_inode *ip)
{
struct gfs2_quota_data *qda[4];
unsigned int count = 0;
unsigned int x;
if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
goto out;
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
struct gfs2_quota_data *qd;
int sync;
qd = ip->i_res->rs_qa_qd[x];
sync = need_sync(qd);
gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
if (sync && qd_trylock(qd))
qda[count++] = qd;
}
if (count) {
do_sync(count, qda);
for (x = 0; x < count; x++)
qd_unlock(qda[x]);
}
out:
gfs2_quota_unhold(ip);
}
#define MAX_LINE 256
static int print_message(struct gfs2_quota_data *qd, char *type)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\n",
sdp->sd_fsname, type,
(qd->qd_id.type == USRQUOTA) ? "user" : "group",
from_kqid(&init_user_ns, qd->qd_id));
return 0;
}
int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data *qd;
s64 value;
unsigned int x;
int error = 0;
if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
return 0;
if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
return 0;
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
qd = ip->i_res->rs_qa_qd[x];
if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
qid_eq(qd->qd_id, make_kqid_gid(gid))))
continue;
value = (s64)be64_to_cpu(qd->qd_qb.qb_value);
spin_lock(&qd_lru_lock);
value += qd->qd_change;
spin_unlock(&qd_lru_lock);
if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) {
print_message(qd, "exceeded");
quota_send_warning(qd->qd_id,
sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN);
error = -EDQUOT;
break;
} else if (be64_to_cpu(qd->qd_qb.qb_warn) &&
(s64)be64_to_cpu(qd->qd_qb.qb_warn) < value &&
time_after_eq(jiffies, qd->qd_last_warn +
gfs2_tune_get(sdp,
gt_quota_warn_period) * HZ)) {
quota_send_warning(qd->qd_id,
sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN);
error = print_message(qd, "warning");
qd->qd_last_warn = jiffies;
}
}
return error;
}
void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
kuid_t uid, kgid_t gid)
{
struct gfs2_quota_data *qd;
unsigned int x;
if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
return;
if (ip->i_diskflags & GFS2_DIF_SYSTEM)
return;
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
qd = ip->i_res->rs_qa_qd[x];
if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
qid_eq(qd->qd_id, make_kqid_gid(gid))) {
do_qc(qd, change);
}
}
}
int gfs2_quota_sync(struct super_block *sb, int type)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_quota_data **qda;
unsigned int max_qd = gfs2_tune_get(sdp, gt_quota_simul_sync);
unsigned int num_qd;
unsigned int x;
int error = 0;
sdp->sd_quota_sync_gen++;
qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL);
if (!qda)
return -ENOMEM;
do {
num_qd = 0;
for (;;) {
error = qd_fish(sdp, qda + num_qd);
if (error || !qda[num_qd])
break;
if (++num_qd == max_qd)
break;
}
if (num_qd) {
if (!error)
error = do_sync(num_qd, qda);
if (!error)
for (x = 0; x < num_qd; x++)
qda[x]->qd_sync_gen =
sdp->sd_quota_sync_gen;
for (x = 0; x < num_qd; x++)
qd_unlock(qda[x]);
}
} while (!error && num_qd == max_qd);
kfree(qda);
return error;
}
static int gfs2_quota_sync_timeo(struct super_block *sb, int type)
{
return gfs2_quota_sync(sb, type);
}
int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid)
{
struct gfs2_quota_data *qd;
struct gfs2_holder q_gh;
int error;
error = qd_get(sdp, qid, &qd);
if (error)
return error;
error = do_glock(qd, FORCE, &q_gh);
if (!error)
gfs2_glock_dq_uninit(&q_gh);
qd_put(qd);
return error;
}
static 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 = make_kqid(&init_user_ns,
(qc->qc_flags & GFS2_QCF_USER)?USRQUOTA:GRPQUOTA,
be32_to_cpu(str->qc_id));
}
int gfs2_quota_init(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
u64 size = i_size_read(sdp->sd_qc_inode);
unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift;
unsigned int x, slot = 0;
unsigned int found = 0;
u64 dblock;
u32 extlen = 0;
int error;
if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20))
return -EIO;
sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block;
sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE);
error = -ENOMEM;
sdp->sd_quota_bitmap = kcalloc(sdp->sd_quota_chunks,
sizeof(unsigned char *), GFP_NOFS);
if (!sdp->sd_quota_bitmap)
return error;
for (x = 0; x < sdp->sd_quota_chunks; x++) {
sdp->sd_quota_bitmap[x] = kzalloc(PAGE_SIZE, GFP_NOFS);
if (!sdp->sd_quota_bitmap[x])
goto fail;
}
for (x = 0; x < blocks; x++) {
struct buffer_head *bh;
unsigned int y;
if (!extlen) {
int new = 0;
error = gfs2_extent_map(&ip->i_inode, x, &new, &dblock, &extlen);
if (error)
goto fail;
}
error = -EIO;
bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
if (!bh)
goto fail;
if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) {
brelse(bh);
goto fail;
}
for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots;
y++, slot++) {
struct gfs2_quota_change_host qc;
struct gfs2_quota_data *qd;
gfs2_quota_change_in(&qc, bh->b_data +
sizeof(struct gfs2_meta_header) +
y * sizeof(struct gfs2_quota_change));
if (!qc.qc_change)
continue;
error = qd_alloc(sdp, qc.qc_id, &qd);
if (error) {
brelse(bh);
goto fail;
}
set_bit(QDF_CHANGE, &qd->qd_flags);
qd->qd_change = qc.qc_change;
qd->qd_slot = slot;
qd->qd_slot_count = 1;
spin_lock(&qd_lru_lock);
gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, slot, 1);
list_add(&qd->qd_list, &sdp->sd_quota_list);
atomic_inc(&sdp->sd_quota_count);
spin_unlock(&qd_lru_lock);
found++;
}
brelse(bh);
dblock++;
extlen--;
}
if (found)
fs_info(sdp, "found %u quota changes\n", found);
return 0;
fail:
gfs2_quota_cleanup(sdp);
return error;
}
void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
{
struct list_head *head = &sdp->sd_quota_list;
struct gfs2_quota_data *qd;
unsigned int x;
spin_lock(&qd_lru_lock);
while (!list_empty(head)) {
qd = list_entry(head->prev, struct gfs2_quota_data, qd_list);
if (atomic_read(&qd->qd_count) > 1 ||
(atomic_read(&qd->qd_count) &&
!test_bit(QDF_CHANGE, &qd->qd_flags))) {
list_move(&qd->qd_list, head);
spin_unlock(&qd_lru_lock);
schedule();
spin_lock(&qd_lru_lock);
continue;
}
list_del(&qd->qd_list);
/* Also remove if this qd exists in the reclaim list */
if (!list_empty(&qd->qd_reclaim)) {
list_del_init(&qd->qd_reclaim);
atomic_dec(&qd_lru_count);
}
atomic_dec(&sdp->sd_quota_count);
spin_unlock(&qd_lru_lock);
if (!atomic_read(&qd->qd_count)) {
gfs2_assert_warn(sdp, !qd->qd_change);
gfs2_assert_warn(sdp, !qd->qd_slot_count);
} else
gfs2_assert_warn(sdp, qd->qd_slot_count == 1);
gfs2_assert_warn(sdp, !qd->qd_bh_count);
gfs2_glock_put(qd->qd_gl);
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lru_lock);
}
spin_unlock(&qd_lru_lock);
gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));
if (sdp->sd_quota_bitmap) {
for (x = 0; x < sdp->sd_quota_chunks; x++)
kfree(sdp->sd_quota_bitmap[x]);
kfree(sdp->sd_quota_bitmap);
}
}
static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
{
if (error == 0 || error == -EROFS)
return;
if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
}
static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg,
int (*fxn)(struct super_block *sb, int type),
unsigned long t, unsigned long *timeo,
unsigned int *new_timeo)
{
if (t >= *timeo) {
int error = fxn(sdp->sd_vfs, 0);
quotad_error(sdp, msg, error);
*timeo = gfs2_tune_get_i(&sdp->sd_tune, new_timeo) * HZ;
} else {
*timeo -= t;
}
}
static void quotad_check_trunc_list(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
while(1) {
ip = NULL;
spin_lock(&sdp->sd_trunc_lock);
if (!list_empty(&sdp->sd_trunc_list)) {
ip = list_entry(sdp->sd_trunc_list.next,
struct gfs2_inode, i_trunc_list);
list_del_init(&ip->i_trunc_list);
}
spin_unlock(&sdp->sd_trunc_lock);
if (ip == NULL)
return;
gfs2_glock_finish_truncate(ip);
}
}
void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) {
if (!sdp->sd_statfs_force_sync) {
sdp->sd_statfs_force_sync = 1;
wake_up(&sdp->sd_quota_wait);
}
}
/**
* 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;
struct gfs2_tune *tune = &sdp->sd_tune;
unsigned long statfs_timeo = 0;
unsigned long quotad_timeo = 0;
unsigned long t = 0;
DEFINE_WAIT(wait);
int empty;
while (!kthread_should_stop()) {
/* Update the master statfs file */
if (sdp->sd_statfs_force_sync) {
int error = gfs2_statfs_sync(sdp->sd_vfs, 0);
quotad_error(sdp, "statfs", error);
statfs_timeo = gfs2_tune_get(sdp, gt_statfs_quantum) * HZ;
}
else
quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t,
&statfs_timeo,
&tune->gt_statfs_quantum);
/* Update quota file */
quotad_check_timeo(sdp, "sync", gfs2_quota_sync_timeo, t,
&quotad_timeo, &tune->gt_quota_quantum);
/* Check for & recover partially truncated inodes */
quotad_check_trunc_list(sdp);
try_to_freeze();
t = min(quotad_timeo, statfs_timeo);
prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE);
spin_lock(&sdp->sd_trunc_lock);
empty = list_empty(&sdp->sd_trunc_list);
spin_unlock(&sdp->sd_trunc_lock);
if (empty && !sdp->sd_statfs_force_sync)
t -= schedule_timeout(t);
else
t = 0;
finish_wait(&sdp->sd_quota_wait, &wait);
}
return 0;
}
static int gfs2_quota_get_xstate(struct super_block *sb,
struct fs_quota_stat *fqs)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
memset(fqs, 0, sizeof(struct fs_quota_stat));
fqs->qs_version = FS_QSTAT_VERSION;
switch (sdp->sd_args.ar_quota) {
case GFS2_QUOTA_ON:
fqs->qs_flags |= (FS_QUOTA_UDQ_ENFD | FS_QUOTA_GDQ_ENFD);
/*FALLTHRU*/
case GFS2_QUOTA_ACCOUNT:
fqs->qs_flags |= (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT);
break;
case GFS2_QUOTA_OFF:
break;
}
if (sdp->sd_quota_inode) {
fqs->qs_uquota.qfs_ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr;
fqs->qs_uquota.qfs_nblks = sdp->sd_quota_inode->i_blocks;
}
fqs->qs_uquota.qfs_nextents = 1; /* unsupported */
fqs->qs_gquota = fqs->qs_uquota; /* its the same inode in both cases */
fqs->qs_incoredqs = atomic_read(&qd_lru_count);
return 0;
}
static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
struct fs_disk_quota *fdq)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_quota_lvb *qlvb;
struct gfs2_quota_data *qd;
struct gfs2_holder q_gh;
int error;
memset(fdq, 0, sizeof(struct fs_disk_quota));
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return -ESRCH; /* Crazy XFS error code */
if ((qid.type != USRQUOTA) &&
(qid.type != GRPQUOTA))
return -EINVAL;
error = qd_get(sdp, qid, &qd);
if (error)
return error;
error = do_glock(qd, FORCE, &q_gh);
if (error)
goto out;
qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
fdq->d_version = FS_DQUOT_VERSION;
fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
fdq->d_id = from_kqid_munged(current_user_ns(), qid);
fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
gfs2_glock_dq_uninit(&q_gh);
out:
qd_put(qd);
return error;
}
/* GFS2 only supports a subset of the XFS fields */
#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
struct fs_disk_quota *fdq)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_quota_data *qd;
struct gfs2_holder q_gh, i_gh;
unsigned int data_blocks, ind_blocks;
unsigned int blocks = 0;
int alloc_required;
loff_t offset;
int error;
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return -ESRCH; /* Crazy XFS error code */
if ((qid.type != USRQUOTA) &&
(qid.type != GRPQUOTA))
return -EINVAL;
if (fdq->d_fieldmask & ~GFS2_FIELDMASK)
return -EINVAL;
error = qd_get(sdp, qid, &qd);
if (error)
return error;
error = gfs2_rs_alloc(ip);
if (error)
goto out_put;
mutex_lock(&ip->i_inode.i_mutex);
error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh);
if (error)
goto out_unlockput;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
if (error)
goto out_q;
/* Check for existing entry, if none then alloc new blocks */
error = update_qd(sdp, qd);
if (error)
goto out_i;
/* If nothing has changed, this is a no-op */
if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
fdq->d_fieldmask ^= FS_DQ_BSOFT;
if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
fdq->d_fieldmask ^= FS_DQ_BHARD;
if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
fdq->d_fieldmask ^= FS_DQ_BCOUNT;
if (fdq->d_fieldmask == 0)
goto out_i;
offset = qd2offset(qd);
alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota));
if (gfs2_is_stuffed(ip))
alloc_required = 1;
if (alloc_required) {
gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
&data_blocks, &ind_blocks);
blocks = 1 + data_blocks + ind_blocks;
error = gfs2_inplace_reserve(ip, blocks, 0);
if (error)
goto out_i;
blocks += gfs2_rg_blocks(ip, blocks);
}
/* Some quotas span block boundaries and can update two blocks,
adding an extra block to the transaction to handle such quotas */
error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 2, 0);
if (error)
goto out_release;
/* Apply changes */
error = gfs2_adjust_quota(ip, offset, 0, qd, fdq);
gfs2_trans_end(sdp);
out_release:
if (alloc_required)
gfs2_inplace_release(ip);
out_i:
gfs2_glock_dq_uninit(&i_gh);
out_q:
gfs2_glock_dq_uninit(&q_gh);
out_unlockput:
mutex_unlock(&ip->i_inode.i_mutex);
out_put:
qd_put(qd);
return error;
}
const struct quotactl_ops gfs2_quotactl_ops = {
.quota_sync = gfs2_quota_sync,
.get_xstate = gfs2_quota_get_xstate,
.get_dqblk = gfs2_get_dqblk,
.set_dqblk = gfs2_set_dqblk,
};