![Dave Chinner](/assets/img/avatar_default.png)
When an I/O error occurs during an intermediate commit on a rolling transaction, xfs_trans_commit() will free the transaction structure and the related ticket. However, the duplicate transaction that gets used as the transaction continues still contains a pointer to the ticket. Hence when the duplicate transaction is cancelled and freed, we free the ticket a second time. Add reference counting to the ticket so that we hold an extra reference to the ticket over the transaction commit. We drop the extra reference once we have checked that the transaction commit did not return an error, thus avoiding a double free on commit error. Credit to Nick Piggin for tripping over the problem. SGI-PV: 989741 Signed-off-by: Dave Chinner <david@fromorbit.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
410 lines
11 KiB
C
410 lines
11 KiB
C
/*
|
|
* Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write the Free Software Foundation,
|
|
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
#include "xfs.h"
|
|
#include "xfs_fs.h"
|
|
#include "xfs_types.h"
|
|
#include "xfs_bit.h"
|
|
#include "xfs_log.h"
|
|
#include "xfs_inum.h"
|
|
#include "xfs_trans.h"
|
|
#include "xfs_sb.h"
|
|
#include "xfs_ag.h"
|
|
#include "xfs_dir2.h"
|
|
#include "xfs_dmapi.h"
|
|
#include "xfs_mount.h"
|
|
#include "xfs_bmap_btree.h"
|
|
#include "xfs_dir2_sf.h"
|
|
#include "xfs_attr_sf.h"
|
|
#include "xfs_dinode.h"
|
|
#include "xfs_inode.h"
|
|
#include "xfs_inode_item.h"
|
|
#include "xfs_bmap.h"
|
|
#include "xfs_error.h"
|
|
#include "xfs_quota.h"
|
|
#include "xfs_rw.h"
|
|
#include "xfs_itable.h"
|
|
#include "xfs_utils.h"
|
|
|
|
|
|
/*
|
|
* Allocates a new inode from disk and return a pointer to the
|
|
* incore copy. This routine will internally commit the current
|
|
* transaction and allocate a new one if the Space Manager needed
|
|
* to do an allocation to replenish the inode free-list.
|
|
*
|
|
* This routine is designed to be called from xfs_create and
|
|
* xfs_create_dir.
|
|
*
|
|
*/
|
|
int
|
|
xfs_dir_ialloc(
|
|
xfs_trans_t **tpp, /* input: current transaction;
|
|
output: may be a new transaction. */
|
|
xfs_inode_t *dp, /* directory within whose allocate
|
|
the inode. */
|
|
mode_t mode,
|
|
xfs_nlink_t nlink,
|
|
xfs_dev_t rdev,
|
|
cred_t *credp,
|
|
prid_t prid, /* project id */
|
|
int okalloc, /* ok to allocate new space */
|
|
xfs_inode_t **ipp, /* pointer to inode; it will be
|
|
locked. */
|
|
int *committed)
|
|
|
|
{
|
|
xfs_trans_t *tp;
|
|
xfs_trans_t *ntp;
|
|
xfs_inode_t *ip;
|
|
xfs_buf_t *ialloc_context = NULL;
|
|
boolean_t call_again = B_FALSE;
|
|
int code;
|
|
uint log_res;
|
|
uint log_count;
|
|
void *dqinfo;
|
|
uint tflags;
|
|
|
|
tp = *tpp;
|
|
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
|
|
|
|
/*
|
|
* xfs_ialloc will return a pointer to an incore inode if
|
|
* the Space Manager has an available inode on the free
|
|
* list. Otherwise, it will do an allocation and replenish
|
|
* the freelist. Since we can only do one allocation per
|
|
* transaction without deadlocks, we will need to commit the
|
|
* current transaction and start a new one. We will then
|
|
* need to call xfs_ialloc again to get the inode.
|
|
*
|
|
* If xfs_ialloc did an allocation to replenish the freelist,
|
|
* it returns the bp containing the head of the freelist as
|
|
* ialloc_context. We will hold a lock on it across the
|
|
* transaction commit so that no other process can steal
|
|
* the inode(s) that we've just allocated.
|
|
*/
|
|
code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid, okalloc,
|
|
&ialloc_context, &call_again, &ip);
|
|
|
|
/*
|
|
* Return an error if we were unable to allocate a new inode.
|
|
* This should only happen if we run out of space on disk or
|
|
* encounter a disk error.
|
|
*/
|
|
if (code) {
|
|
*ipp = NULL;
|
|
return code;
|
|
}
|
|
if (!call_again && (ip == NULL)) {
|
|
*ipp = NULL;
|
|
return XFS_ERROR(ENOSPC);
|
|
}
|
|
|
|
/*
|
|
* If call_again is set, then we were unable to get an
|
|
* inode in one operation. We need to commit the current
|
|
* transaction and call xfs_ialloc() again. It is guaranteed
|
|
* to succeed the second time.
|
|
*/
|
|
if (call_again) {
|
|
|
|
/*
|
|
* Normally, xfs_trans_commit releases all the locks.
|
|
* We call bhold to hang on to the ialloc_context across
|
|
* the commit. Holding this buffer prevents any other
|
|
* processes from doing any allocations in this
|
|
* allocation group.
|
|
*/
|
|
xfs_trans_bhold(tp, ialloc_context);
|
|
/*
|
|
* Save the log reservation so we can use
|
|
* them in the next transaction.
|
|
*/
|
|
log_res = xfs_trans_get_log_res(tp);
|
|
log_count = xfs_trans_get_log_count(tp);
|
|
|
|
/*
|
|
* We want the quota changes to be associated with the next
|
|
* transaction, NOT this one. So, detach the dqinfo from this
|
|
* and attach it to the next transaction.
|
|
*/
|
|
dqinfo = NULL;
|
|
tflags = 0;
|
|
if (tp->t_dqinfo) {
|
|
dqinfo = (void *)tp->t_dqinfo;
|
|
tp->t_dqinfo = NULL;
|
|
tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY;
|
|
tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
|
|
}
|
|
|
|
ntp = xfs_trans_dup(tp);
|
|
code = xfs_trans_commit(tp, 0);
|
|
tp = ntp;
|
|
if (committed != NULL) {
|
|
*committed = 1;
|
|
}
|
|
/*
|
|
* If we get an error during the commit processing,
|
|
* release the buffer that is still held and return
|
|
* to the caller.
|
|
*/
|
|
if (code) {
|
|
xfs_buf_relse(ialloc_context);
|
|
if (dqinfo) {
|
|
tp->t_dqinfo = dqinfo;
|
|
XFS_TRANS_FREE_DQINFO(tp->t_mountp, tp);
|
|
}
|
|
*tpp = ntp;
|
|
*ipp = NULL;
|
|
return code;
|
|
}
|
|
|
|
/*
|
|
* transaction commit worked ok so we can drop the extra ticket
|
|
* reference that we gained in xfs_trans_dup()
|
|
*/
|
|
xfs_log_ticket_put(tp->t_ticket);
|
|
code = xfs_trans_reserve(tp, 0, log_res, 0,
|
|
XFS_TRANS_PERM_LOG_RES, log_count);
|
|
/*
|
|
* Re-attach the quota info that we detached from prev trx.
|
|
*/
|
|
if (dqinfo) {
|
|
tp->t_dqinfo = dqinfo;
|
|
tp->t_flags |= tflags;
|
|
}
|
|
|
|
if (code) {
|
|
xfs_buf_relse(ialloc_context);
|
|
*tpp = ntp;
|
|
*ipp = NULL;
|
|
return code;
|
|
}
|
|
xfs_trans_bjoin(tp, ialloc_context);
|
|
|
|
/*
|
|
* Call ialloc again. Since we've locked out all
|
|
* other allocations in this allocation group,
|
|
* this call should always succeed.
|
|
*/
|
|
code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid,
|
|
okalloc, &ialloc_context, &call_again, &ip);
|
|
|
|
/*
|
|
* If we get an error at this point, return to the caller
|
|
* so that the current transaction can be aborted.
|
|
*/
|
|
if (code) {
|
|
*tpp = tp;
|
|
*ipp = NULL;
|
|
return code;
|
|
}
|
|
ASSERT ((!call_again) && (ip != NULL));
|
|
|
|
} else {
|
|
if (committed != NULL) {
|
|
*committed = 0;
|
|
}
|
|
}
|
|
|
|
*ipp = ip;
|
|
*tpp = tp;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Decrement the link count on an inode & log the change.
|
|
* If this causes the link count to go to zero, initiate the
|
|
* logging activity required to truncate a file.
|
|
*/
|
|
int /* error */
|
|
xfs_droplink(
|
|
xfs_trans_t *tp,
|
|
xfs_inode_t *ip)
|
|
{
|
|
int error;
|
|
|
|
xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
|
|
|
|
ASSERT (ip->i_d.di_nlink > 0);
|
|
ip->i_d.di_nlink--;
|
|
drop_nlink(VFS_I(ip));
|
|
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
|
|
|
|
error = 0;
|
|
if (ip->i_d.di_nlink == 0) {
|
|
/*
|
|
* We're dropping the last link to this file.
|
|
* Move the on-disk inode to the AGI unlinked list.
|
|
* From xfs_inactive() we will pull the inode from
|
|
* the list and free it.
|
|
*/
|
|
error = xfs_iunlink(tp, ip);
|
|
}
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* This gets called when the inode's version needs to be changed from 1 to 2.
|
|
* Currently this happens when the nlink field overflows the old 16-bit value
|
|
* or when chproj is called to change the project for the first time.
|
|
* As a side effect the superblock version will also get rev'd
|
|
* to contain the NLINK bit.
|
|
*/
|
|
void
|
|
xfs_bump_ino_vers2(
|
|
xfs_trans_t *tp,
|
|
xfs_inode_t *ip)
|
|
{
|
|
xfs_mount_t *mp;
|
|
|
|
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
|
|
ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1);
|
|
|
|
ip->i_d.di_version = XFS_DINODE_VERSION_2;
|
|
ip->i_d.di_onlink = 0;
|
|
memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
|
|
mp = tp->t_mountp;
|
|
if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
|
|
spin_lock(&mp->m_sb_lock);
|
|
if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
|
|
xfs_sb_version_addnlink(&mp->m_sb);
|
|
spin_unlock(&mp->m_sb_lock);
|
|
xfs_mod_sb(tp, XFS_SB_VERSIONNUM);
|
|
} else {
|
|
spin_unlock(&mp->m_sb_lock);
|
|
}
|
|
}
|
|
/* Caller must log the inode */
|
|
}
|
|
|
|
/*
|
|
* Increment the link count on an inode & log the change.
|
|
*/
|
|
int
|
|
xfs_bumplink(
|
|
xfs_trans_t *tp,
|
|
xfs_inode_t *ip)
|
|
{
|
|
if (ip->i_d.di_nlink >= XFS_MAXLINK)
|
|
return XFS_ERROR(EMLINK);
|
|
xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
|
|
|
|
ASSERT(ip->i_d.di_nlink > 0);
|
|
ip->i_d.di_nlink++;
|
|
inc_nlink(VFS_I(ip));
|
|
if ((ip->i_d.di_version == XFS_DINODE_VERSION_1) &&
|
|
(ip->i_d.di_nlink > XFS_MAXLINK_1)) {
|
|
/*
|
|
* The inode has increased its number of links beyond
|
|
* what can fit in an old format inode. It now needs
|
|
* to be converted to a version 2 inode with a 32 bit
|
|
* link count. If this is the first inode in the file
|
|
* system to do this, then we need to bump the superblock
|
|
* version number as well.
|
|
*/
|
|
xfs_bump_ino_vers2(tp, ip);
|
|
}
|
|
|
|
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Try to truncate the given file to 0 length. Currently called
|
|
* only out of xfs_remove when it has to truncate a file to free
|
|
* up space for the remove to proceed.
|
|
*/
|
|
int
|
|
xfs_truncate_file(
|
|
xfs_mount_t *mp,
|
|
xfs_inode_t *ip)
|
|
{
|
|
xfs_trans_t *tp;
|
|
int error;
|
|
|
|
#ifdef QUOTADEBUG
|
|
/*
|
|
* This is called to truncate the quotainodes too.
|
|
*/
|
|
if (XFS_IS_UQUOTA_ON(mp)) {
|
|
if (ip->i_ino != mp->m_sb.sb_uquotino)
|
|
ASSERT(ip->i_udquot);
|
|
}
|
|
if (XFS_IS_OQUOTA_ON(mp)) {
|
|
if (ip->i_ino != mp->m_sb.sb_gquotino)
|
|
ASSERT(ip->i_gdquot);
|
|
}
|
|
#endif
|
|
/*
|
|
* Make the call to xfs_itruncate_start before starting the
|
|
* transaction, because we cannot make the call while we're
|
|
* in a transaction.
|
|
*/
|
|
xfs_ilock(ip, XFS_IOLOCK_EXCL);
|
|
error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, (xfs_fsize_t)0);
|
|
if (error) {
|
|
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
|
|
return error;
|
|
}
|
|
|
|
tp = xfs_trans_alloc(mp, XFS_TRANS_TRUNCATE_FILE);
|
|
if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
|
|
XFS_TRANS_PERM_LOG_RES,
|
|
XFS_ITRUNCATE_LOG_COUNT))) {
|
|
xfs_trans_cancel(tp, 0);
|
|
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* Follow the normal truncate locking protocol. Since we
|
|
* hold the inode in the transaction, we know that it's number
|
|
* of references will stay constant.
|
|
*/
|
|
xfs_ilock(ip, XFS_ILOCK_EXCL);
|
|
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
|
|
xfs_trans_ihold(tp, ip);
|
|
/*
|
|
* Signal a sync xaction. The only case where that isn't
|
|
* the case is if we're truncating an already unlinked file
|
|
* on a wsync fs. In that case, we know the blocks can't
|
|
* reappear in the file because the links to file are
|
|
* permanently toast. Currently, we're always going to
|
|
* want a sync transaction because this code is being
|
|
* called from places where nlink is guaranteed to be 1
|
|
* but I'm leaving the tests in to protect against future
|
|
* changes -- rcc.
|
|
*/
|
|
error = xfs_itruncate_finish(&tp, ip, (xfs_fsize_t)0,
|
|
XFS_DATA_FORK,
|
|
((ip->i_d.di_nlink != 0 ||
|
|
!(mp->m_flags & XFS_MOUNT_WSYNC))
|
|
? 1 : 0));
|
|
if (error) {
|
|
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
|
|
XFS_TRANS_ABORT);
|
|
} else {
|
|
xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
|
|
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
|
|
}
|
|
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
|
|
|
|
return error;
|
|
}
|