/*
* Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
* into account.
* If XFS_QMOPT_DQALLOC, the dquot(s) will be allocated if needed.
* Inode may get unlocked and relocked in here, and the caller must deal with
* the consequences.
*/
int
xfs_qm_dqattach_locked(
xfs_inode_t *ip,
uint flags)
{
xfs_mount_t *mp = ip->i_mount;
int error = 0;
if (!xfs_qm_need_dqattach(ip))
return 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
flags & XFS_QMOPT_DQALLOC,
&ip->i_udquot);
if (error)
goto done;
ASSERT(ip->i_udquot);
}
if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
flags & XFS_QMOPT_DQALLOC,
&ip->i_gdquot);
if (error)
goto done;
ASSERT(ip->i_gdquot);
}
if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
flags & XFS_QMOPT_DQALLOC,
&ip->i_pdquot);
if (error)
goto done;
ASSERT(ip->i_pdquot);
}
done:
/*
* Don't worry about the dquots that we may have attached before any
* error - they'll get detached later if it has not already been done.
*/
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
return error;
}
/*
* This is called to asynchronously write the inode associated with this
* inode log item out to disk. The inode will already have been locked by
* a successful call to xfs_inode_item_trylock().
*/
STATIC void
xfs_inode_item_push(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
ASSERT(!completion_done(&ip->i_flush));
/*
* Since we were able to lock the inode's flush lock and
* we found it on the AIL, the inode must be dirty. This
* is because the inode is removed from the AIL while still
* holding the flush lock in xfs_iflush_done(). Thus, if
* we found it in the AIL and were able to obtain the flush
* lock without sleeping, then there must not have been
* anyone in the process of flushing the inode.
*/
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) ||
iip->ili_format.ilf_fields != 0);
/*
* Push the inode to it's backing buffer. This will not remove the
* inode from the AIL - a further push will be required to trigger a
* buffer push. However, this allows all the dirty inodes to be pushed
* to the buffer before it is pushed to disk. The buffer IO completion
* will pull the inode from the AIL, mark it clean and unlock the flush
* lock.
*/
(void) xfs_iflush(ip, SYNC_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
STATIC void
xfs_inode_item_push(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
/*
*/
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || iip->ili_fields != 0);
/*
*/
(void) xfs_iflush(ip, SYNC_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
STATIC bool
xfs_inode_item_pushbuf(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
struct xfs_buf *bp;
bool ret = true;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
/*
*/
if (!xfs_isiflocked(ip) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return true;
}
bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
iip->ili_format.ilf_len, XBF_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!bp)
return true;
if (XFS_BUF_ISDELAYWRITE(bp))
xfs_buf_delwri_promote(bp);
if (xfs_buf_ispinned(bp))
ret = false;
xfs_buf_relse(bp);
return ret;
}
int
xfs_break_layouts(
struct inode *inode,
uint *iolock,
enum layout_break_reason reason)
{
bool retry;
int error;
ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
do {
retry = false;
switch (reason) {
case BREAK_UNMAP:
error = xfs_break_dax_layouts(inode, &retry);
if (error || retry)
break;
/* fall through */
case BREAK_WRITE:
error = xfs_break_leased_layouts(inode, iolock, &retry);
break;
default:
WARN_ON_ONCE(1);
error = -EINVAL;
}
} while (error == 0 && retry);
return error;
}
/*
* This gets called by xfs_trans_push_ail(), when IOP_TRYLOCK
* failed to get the inode flush lock but did get the inode locked SHARED.
* Here we're trying to see if the inode buffer is incore, and if so whether it's
* marked delayed write. If that's the case, we'll promote it and that will
* allow the caller to write the buffer by triggering the xfsbufd to run.
*/
STATIC bool
xfs_inode_item_pushbuf(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
struct xfs_buf *bp;
bool ret = true;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
/*
* If a flush is not in progress anymore, chances are that the
* inode was taken off the AIL. So, just get out.
*/
if (completion_done(&ip->i_flush) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return true;
}
bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
iip->ili_format.ilf_len, XBF_TRYLOCK);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!bp)
return true;
if (XFS_BUF_ISDELAYWRITE(bp))
xfs_buf_delwri_promote(bp);
if (xfs_buf_ispinned(bp))
ret = false;
xfs_buf_relse(bp);
return ret;
}
/*
* This is called to pin the inode associated with the inode log
* item in memory so it cannot be written out. Do this by calling
* xfs_ipin() to bump the pin count in the inode while holding the
* inode pin lock.
*/
STATIC void
xfs_inode_item_pin(
xfs_inode_log_item_t *iip)
{
ASSERT(xfs_isilocked(iip->ili_inode, XFS_ILOCK_EXCL));
xfs_ipin(iip->ili_inode);
}
/*
* Actually transfer ownership, and do dquot modifications.
* These were already reserved.
*/
xfs_dquot_t *
xfs_qm_vop_chown(
xfs_trans_t *tp,
xfs_inode_t *ip,
xfs_dquot_t **IO_olddq,
xfs_dquot_t *newdq)
{
xfs_dquot_t *prevdq;
uint bfield = XFS_IS_REALTIME_INODE(ip) ?
XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(XFS_IS_QUOTA_RUNNING(ip->i_mount));
/* old dquot */
prevdq = *IO_olddq;
ASSERT(prevdq);
ASSERT(prevdq != newdq);
xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_d.di_nblocks));
xfs_trans_mod_dquot(tp, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
/* the sparkling new dquot */
xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_d.di_nblocks);
xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1);
/*
* Take an extra reference, because the inode is going to keep
* this dquot pointer even after the trans_commit.
*/
*IO_olddq = xfs_qm_dqhold(newdq);
return prevdq;
}
/*
* Lock the dquot and change the reservation if we can.
* This doesn't change the actual usage, just the reservation.
* The inode sent in is locked.
*/
int
xfs_trans_reserve_quota_nblks(
struct xfs_trans *tp,
struct xfs_inode *ip,
long nblks,
long ninos,
uint flags)
{
struct xfs_mount *mp = ip->i_mount;
if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
return 0;
if (XFS_IS_PQUOTA_ON(mp))
flags |= XFS_QMOPT_ENOSPC;
ASSERT(!xfs_is_quota_inode(&mp->m_sb, ip->i_ino));
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT((flags & ~(XFS_QMOPT_FORCE_RES | XFS_QMOPT_ENOSPC)) ==
XFS_TRANS_DQ_RES_RTBLKS ||
(flags & ~(XFS_QMOPT_FORCE_RES | XFS_QMOPT_ENOSPC)) ==
XFS_TRANS_DQ_RES_BLKS);
/*
* Reserve nblks against these dquots, with trans as the mediator.
*/
return xfs_trans_reserve_quota_bydquots(tp, mp,
ip->i_udquot, ip->i_gdquot,
ip->i_pdquot,
nblks, ninos, flags);
}
static void
xfs_setattr_time(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (iattr->ia_valid & ATTR_ATIME) {
inode->i_atime = iattr->ia_atime;
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
}
if (iattr->ia_valid & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (iattr->ia_valid & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
}
void
xfs_qm_vop_create_dqattach(
struct xfs_trans *tp,
struct xfs_inode *ip,
struct xfs_dquot *udqp,
struct xfs_dquot *gdqp)
{
struct xfs_mount *mp = tp->t_mountp;
if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
return;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
if (udqp) {
ASSERT(ip->i_udquot == NULL);
ASSERT(XFS_IS_UQUOTA_ON(mp));
ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id));
ip->i_udquot = xfs_qm_dqhold(udqp);
xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
}
if (gdqp) {
ASSERT(ip->i_gdquot == NULL);
ASSERT(XFS_IS_OQUOTA_ON(mp));
ASSERT((XFS_IS_GQUOTA_ON(mp) ?
ip->i_d.di_gid : xfs_get_projid(ip)) ==
be32_to_cpu(gdqp->q_core.d_id));
ip->i_gdquot = xfs_qm_dqhold(gdqp);
xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
}
}
/*
* 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 == 1);
ip->i_d.di_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 */
}
/*
* Transactional inode timestamp update. Requires the inode to be locked and
* joined to the transaction supplied. Relies on the transaction subsystem to
* track dirty state and update/writeback the inode accordingly.
*/
void
xfs_trans_ichgtime(
struct xfs_trans *tp,
struct xfs_inode *ip,
int flags)
{
struct inode *inode = VFS_I(ip);
timespec_t tv;
ASSERT(tp);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
tv = current_fs_time(inode->i_sb);
if ((flags & XFS_ICHGTIME_MOD) &&
!timespec_equal(&inode->i_mtime, &tv)) {
inode->i_mtime = tv;
ip->i_d.di_mtime.t_sec = tv.tv_sec;
ip->i_d.di_mtime.t_nsec = tv.tv_nsec;
}
if ((flags & XFS_ICHGTIME_CHG) &&
!timespec_equal(&inode->i_ctime, &tv)) {
inode->i_ctime = tv;
ip->i_d.di_ctime.t_sec = tv.tv_sec;
ip->i_d.di_ctime.t_nsec = tv.tv_nsec;
}
}
/*
* Find the CoW reservation for a given byte offset of a file.
*/
bool
xfs_reflink_find_cow_mapping(
struct xfs_inode *ip,
xfs_off_t offset,
struct xfs_bmbt_irec *imap)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_fileoff_t offset_fsb;
struct xfs_bmbt_irec got;
xfs_extnum_t idx;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
ASSERT(xfs_is_reflink_inode(ip));
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return false;
if (got.br_startoff > offset_fsb)
return false;
trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
&got);
*imap = got;
return true;
}
/*
* This is called to mark the fields indicated in fieldmask as needing
* to be logged when the transaction is committed. The inode must
* already be associated with the given transaction.
*
* The values for fieldmask are defined in xfs_inode_item.h. We always
* log all of the core inode if any of it has changed, and we always log
* all of the inline data/extents/b-tree root if any of them has changed.
*/
void
xfs_trans_log_inode(
xfs_trans_t *tp,
xfs_inode_t *ip,
uint flags)
{
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
/*
* First time we log the inode in a transaction, bump the inode change
* counter if it is configured for this to occur.
*/
if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
IS_I_VERSION(VFS_I(ip))) {
inode_inc_iversion(VFS_I(ip));
ip->i_d.di_changecount = VFS_I(ip)->i_version;
flags |= XFS_ILOG_CORE;
}
tp->t_flags |= XFS_TRANS_DIRTY;
ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
/*
* Always OR in the bits from the ili_last_fields field.
* This is to coordinate with the xfs_iflush() and xfs_iflush_done()
* routines in the eventual clearing of the ili_fields bits.
* See the big comment in xfs_iflush() for an explanation of
* this coordination mechanism.
*/
flags |= ip->i_itemp->ili_last_fields;
ip->i_itemp->ili_fields |= flags;
}
/*
* This is called to asynchronously write the inode associated with this
* inode log item out to disk. The inode will already have been locked by
* a successful call to xfs_inode_item_trylock().
*/
STATIC void
xfs_inode_item_push(
xfs_inode_log_item_t *iip)
{
xfs_inode_t *ip;
ip = iip->ili_inode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
ASSERT(!completion_done(&ip->i_flush));
/*
* Since we were able to lock the inode's flush lock and
* we found it on the AIL, the inode must be dirty. This
* is because the inode is removed from the AIL while still
* holding the flush lock in xfs_iflush_done(). Thus, if
* we found it in the AIL and were able to obtain the flush
* lock without sleeping, then there must not have been
* anyone in the process of flushing the inode.
*/
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) ||
iip->ili_format.ilf_fields != 0);
/*
* Write out the inode. The completion routine ('iflush_done') will
* pull it from the AIL, mark it clean, unlock the flush lock.
*/
(void) xfs_iflush(ip, XFS_IFLUSH_ASYNC);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return;
}
/*
* Add a locked inode to the transaction.
*
* The inode must be locked, and it cannot be associated with any transaction.
*/
void
xfs_trans_ijoin(
struct xfs_trans *tp,
struct xfs_inode *ip)
{
xfs_inode_log_item_t *iip;
ASSERT(ip->i_transp == NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (ip->i_itemp == NULL)
xfs_inode_item_init(ip, ip->i_mount);
iip = ip->i_itemp;
ASSERT(iip->ili_lock_flags == 0);
/*
* Get a log_item_desc to point at the new item.
*/
xfs_trans_add_item(tp, &iip->ili_item);
xfs_trans_inode_broot_debug(ip);
/*
* Initialize i_transp so we can find it with xfs_inode_incore()
* in xfs_trans_iget() above.
*/
ip->i_transp = tp;
}
/*
* This is called to mark the fields indicated in fieldmask as needing
* to be logged when the transaction is committed. The inode must
* already be associated with the given transaction.
*
* The values for fieldmask are defined in xfs_inode_item.h. We always
* log all of the core inode if any of it has changed, and we always log
* all of the inline data/extents/b-tree root if any of them has changed.
*/
void
xfs_trans_log_inode(
xfs_trans_t *tp,
xfs_inode_t *ip,
uint flags)
{
struct inode *inode = VFS_I(ip);
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
/*
* Don't bother with i_lock for the I_DIRTY_TIME check here, as races
* don't matter - we either will need an extra transaction in 24 hours
* to log the timestamps, or will clear already cleared fields in the
* worst case.
*/
if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) {
spin_lock(&inode->i_lock);
inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
spin_unlock(&inode->i_lock);
}
/*
* Record the specific change for fdatasync optimisation. This
* allows fdatasync to skip log forces for inodes that are only
* timestamp dirty. We do this before the change count so that
* the core being logged in this case does not impact on fdatasync
* behaviour.
*/
ip->i_itemp->ili_fsync_fields |= flags;
/*
* First time we log the inode in a transaction, bump the inode change
* counter if it is configured for this to occur. While we have the
* inode locked exclusively for metadata modification, we can usually
* avoid setting XFS_ILOG_CORE if no one has queried the value since
* the last time it was incremented. If we have XFS_ILOG_CORE already
* set however, then go ahead and bump the i_version counter
* unconditionally.
*/
if (!test_and_set_bit(XFS_LI_DIRTY, &ip->i_itemp->ili_item.li_flags) &&
IS_I_VERSION(VFS_I(ip))) {
if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
flags |= XFS_ILOG_CORE;
}
tp->t_flags |= XFS_TRANS_DIRTY;
/*
* Always OR in the bits from the ili_last_fields field.
* This is to coordinate with the xfs_iflush() and xfs_iflush_done()
* routines in the eventual clearing of the ili_fields bits.
* See the big comment in xfs_iflush() for an explanation of
* this coordination mechanism.
*/
flags |= ip->i_itemp->ili_last_fields;
ip->i_itemp->ili_fields |= flags;
}
/*
* This routine is called to handle zeroing any space in the last
* block of the file that is beyond the EOF. We do this since the
* size is being increased without writing anything to that block
* and we don't want anyone to read the garbage on the disk.
*/
STATIC int /* error (positive) */
xfs_zero_last_block(
xfs_inode_t *ip,
xfs_fsize_t offset,
xfs_fsize_t isize)
{
xfs_fileoff_t last_fsb;
xfs_mount_t *mp = ip->i_mount;
int nimaps;
int zero_offset;
int zero_len;
int error = 0;
xfs_bmbt_irec_t imap;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
zero_offset = XFS_B_FSB_OFFSET(mp, isize);
if (zero_offset == 0) {
/*
* There are no extra bytes in the last block on disk to
* zero, so return.
*/
return 0;
}
last_fsb = XFS_B_TO_FSBT(mp, isize);
nimaps = 1;
error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
&nimaps, NULL, NULL);
if (error) {
return error;
}
ASSERT(nimaps > 0);
/*
* If the block underlying isize is just a hole, then there
* is nothing to zero.
*/
if (imap.br_startblock == HOLESTARTBLOCK) {
return 0;
}
/*
* Zero the part of the last block beyond the EOF, and write it
* out sync. We need to drop the ilock while we do this so we
* don't deadlock when the buffer cache calls back to us.
*/
xfs_iunlock(ip, XFS_ILOCK_EXCL);
zero_len = mp->m_sb.sb_blocksize - zero_offset;
if (isize + zero_len > offset)
zero_len = offset - isize;
error = xfs_iozero(ip, isize, zero_len);
xfs_ilock(ip, XFS_ILOCK_EXCL);
ASSERT(error >= 0);
return error;
}
/*
* This is called to pin the inode associated with the inode log
* item in memory so it cannot be written out.
*/
STATIC void
xfs_inode_item_pin(
struct xfs_log_item *lip)
{
struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
trace_xfs_inode_pin(ip, _RET_IP_);
atomic_inc(&ip->i_pincount);
}
static void
xfs_setattr_mode(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
umode_t mode = iattr->ia_mode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
* This handles the normal case of zeroing the remainder of the last block in
* the file and the unusual case of zeroing blocks out beyond the size of the
* file. This second case only happens with fixed size extents and when the
* system crashes before the inode size was updated but after blocks were
* allocated.
*
* Expects the iolock to be held exclusive, and will take the ilock internally.
*/
int /* error (positive) */
xfs_zero_eof(
struct xfs_inode *ip,
xfs_off_t offset, /* starting I/O offset */
xfs_fsize_t isize, /* current inode size */
bool *did_zeroing)
{
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
trace_xfs_zero_eof(ip, isize, offset - isize);
return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
}
/*
* Unlock the inode associated with the inode log item.
* Clear the fields of the inode and inode log item that
* are specific to the current transaction. If the
* hold flags is set, do not unlock the inode.
*/
STATIC void
xfs_inode_item_unlock(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
unsigned short lock_flags;
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
lock_flags = iip->ili_lock_flags;
iip->ili_lock_flags = 0;
if (lock_flags)
xfs_iunlock(ip, lock_flags);
}
void
xfs_setattr_time(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (iattr->ia_valid & ATTR_ATIME)
inode->i_atime = iattr->ia_atime;
if (iattr->ia_valid & ATTR_CTIME)
inode->i_ctime = iattr->ia_ctime;
if (iattr->ia_valid & ATTR_MTIME)
inode->i_mtime = iattr->ia_mtime;
}
/* Retrieve an extended attribute and its value. Must have ilock. */
int
xfs_attr_get_ilocked(
struct xfs_inode *ip,
struct xfs_da_args *args)
{
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
if (!xfs_inode_hasattr(ip))
return -ENOATTR;
else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_getvalue(args);
else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
return xfs_attr_leaf_get(args);
else
return xfs_attr_node_get(args);
}
STATIC int
xfs_qm_dqattach_one(
xfs_inode_t *ip,
xfs_dqid_t id,
uint type,
uint doalloc,
xfs_dquot_t **IO_idqpp)
{
xfs_dquot_t *dqp;
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
error = 0;
/*
* See if we already have it in the inode itself. IO_idqpp is &i_udquot
* or &i_gdquot. This made the code look weird, but made the logic a lot
* simpler.
*/
dqp = *IO_idqpp;
if (dqp) {
trace_xfs_dqattach_found(dqp);
return 0;
}
/*
* Find the dquot from somewhere. This bumps the reference count of
* dquot and returns it locked. This can return ENOENT if dquot didn't
* exist on disk and we didn't ask it to allocate; ESRCH if quotas got
* turned off suddenly.
*/
error = xfs_qm_dqget(ip->i_mount, ip, id, type,
doalloc | XFS_QMOPT_DOWARN, &dqp);
if (error)
return error;
trace_xfs_dqattach_get(dqp);
/*
* dqget may have dropped and re-acquired the ilock, but it guarantees
* that the dquot returned is the one that should go in the inode.
*/
*IO_idqpp = dqp;
xfs_dqunlock(dqp);
return 0;
}
static int
xfs_break_dax_layouts(
struct inode *inode,
bool *retry)
{
struct page *page;
ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
page = dax_layout_busy_page(inode->i_mapping);
if (!page)
return 0;
*retry = true;
return ___wait_var_event(&page->_refcount,
atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
0, 0, xfs_wait_dax_page(inode));
}
/*
* Run eofblocks scans on the quotas applicable to the inode. For inodes with
* multiple quotas, we don't know exactly which quota caused an allocation
* failure. We make a best effort by including each quota under low free space
* conditions (less than 1% free space) in the scan.
*/
static int
__xfs_inode_free_quota_eofblocks(
struct xfs_inode *ip,
int (*execute)(struct xfs_mount *mp,
struct xfs_eofblocks *eofb))
{
int scan = 0;
struct xfs_eofblocks eofb = {0};
struct xfs_dquot *dq;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
/*
* Set the scan owner to avoid a potential livelock. Otherwise, the scan
* can repeatedly trylock on the inode we're currently processing. We
* run a sync scan to increase effectiveness and use the union filter to
* cover all applicable quotas in a single scan.
*/
eofb.eof_scan_owner = ip->i_ino;
eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
dq = xfs_inode_dquot(ip, XFS_DQ_USER);
if (dq && xfs_dquot_lowsp(dq)) {
eofb.eof_uid = VFS_I(ip)->i_uid;
eofb.eof_flags |= XFS_EOF_FLAGS_UID;
scan = 1;
}
}
if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
dq = xfs_inode_dquot(ip, XFS_DQ_GROUP);
if (dq && xfs_dquot_lowsp(dq)) {
eofb.eof_gid = VFS_I(ip)->i_gid;
eofb.eof_flags |= XFS_EOF_FLAGS_GID;
scan = 1;
}
}
if (scan)
execute(ip->i_mount, &eofb);
return scan;
}
/*
* This is called to mark the fields indicated in fieldmask as needing
* to be logged when the transaction is committed. The inode must
* already be associated with the given transaction.
*
* The values for fieldmask are defined in xfs_inode_item.h. We always
* log all of the core inode if any of it has changed, and we always log
* all of the inline data/extents/b-tree root if any of them has changed.
*/
void
xfs_trans_log_inode(
xfs_trans_t *tp,
xfs_inode_t *ip,
uint flags)
{
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
/*
* Record the specific change for fdatasync optimisation. This
* allows fdatasync to skip log forces for inodes that are only
* timestamp dirty. We do this before the change count so that
* the core being logged in this case does not impact on fdatasync
* behaviour.
*/
ip->i_itemp->ili_fsync_fields |= flags;
/*
* First time we log the inode in a transaction, bump the inode change
* counter if it is configured for this to occur. We don't use
* inode_inc_version() because there is no need for extra locking around
* i_version as we already hold the inode locked exclusively for
* metadata modification.
*/
if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
IS_I_VERSION(VFS_I(ip))) {
VFS_I(ip)->i_version++;
flags |= XFS_ILOG_CORE;
}
tp->t_flags |= XFS_TRANS_DIRTY;
ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
/*
* Always OR in the bits from the ili_last_fields field.
* This is to coordinate with the xfs_iflush() and xfs_iflush_done()
* routines in the eventual clearing of the ili_fields bits.
* See the big comment in xfs_iflush() for an explanation of
* this coordination mechanism.
*/
flags |= ip->i_itemp->ili_last_fields;
ip->i_itemp->ili_fields |= flags;
}
/*
* Unlock the inode associated with the inode log item.
* Clear the fields of the inode and inode log item that
* are specific to the current transaction. If the
* hold flags is set, do not unlock the inode.
*/
STATIC void
xfs_inode_item_unlock(
struct xfs_log_item *lip)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
unsigned short lock_flags;
ASSERT(iip->ili_inode->i_itemp != NULL);
ASSERT(xfs_isilocked(iip->ili_inode, XFS_ILOCK_EXCL));
/*
* Clear the transaction pointer in the inode.
*/
ip->i_transp = NULL;
/*
* If the inode needed a separate buffer with which to log
* its extents, then free it now.
*/
if (iip->ili_extents_buf != NULL) {
ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS);
ASSERT(ip->i_d.di_nextents > 0);
ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_DEXT);
ASSERT(ip->i_df.if_bytes > 0);
kmem_free(iip->ili_extents_buf);
iip->ili_extents_buf = NULL;
}
if (iip->ili_aextents_buf != NULL) {
ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS);
ASSERT(ip->i_d.di_anextents > 0);
ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_AEXT);
ASSERT(ip->i_afp->if_bytes > 0);
kmem_free(iip->ili_aextents_buf);
iip->ili_aextents_buf = NULL;
}
lock_flags = iip->ili_lock_flags;
iip->ili_lock_flags = 0;
if (lock_flags) {
xfs_iunlock(iip->ili_inode, lock_flags);
IRELE(iip->ili_inode);
}
}
