int
xfs_qm_vop_rename_dqattach(
struct xfs_inode **i_tab)
{
struct xfs_mount *mp = i_tab[0]->i_mount;
int i;
if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
return 0;
for (i = 0; (i < 4 && i_tab[i]); i++) {
struct xfs_inode *ip = i_tab[i];
int error;
/*
* Watch out for duplicate entries in the table.
*/
if (i == 0 || ip != i_tab[i-1]) {
if (XFS_NOT_DQATTACHED(mp, ip)) {
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
}
}
}
return 0;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (newsize > oldsize) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
return error;
}
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
int
xfs_alloc_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len,
int alloc_type)
{
xfs_mount_t *mp = ip->i_mount;
xfs_off_t count;
xfs_filblks_t allocated_fsb;
xfs_filblks_t allocatesize_fsb;
xfs_extlen_t extsz, temp;
xfs_fileoff_t startoffset_fsb;
xfs_fsblock_t firstfsb;
int nimaps;
int quota_flag;
int rt;
xfs_trans_t *tp;
xfs_bmbt_irec_t imaps[1], *imapp;
xfs_bmap_free_t free_list;
uint qblocks, resblks, resrtextents;
int committed;
int error;
trace_xfs_alloc_file_space(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
if (len <= 0)
return XFS_ERROR(EINVAL);
rt = XFS_IS_REALTIME_INODE(ip);
extsz = xfs_get_extsz_hint(ip);
count = len;
imapp = &imaps[0];
nimaps = 1;
startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
allocatesize_fsb = XFS_B_TO_FSB(mp, count);
/*
* Allocate file space until done or until there is an error
*/
while (allocatesize_fsb && !error) {
xfs_fileoff_t s, e;
/*
* Determine space reservations for data/realtime.
*/
if (unlikely(extsz)) {
s = startoffset_fsb;
do_div(s, extsz);
s *= extsz;
e = startoffset_fsb + allocatesize_fsb;
if ((temp = do_mod(startoffset_fsb, extsz)))
e += temp;
if ((temp = do_mod(e, extsz)))
e += extsz - temp;
} else {
s = 0;
e = allocatesize_fsb;
}
/*
* The transaction reservation is limited to a 32-bit block
* count, hence we need to limit the number of blocks we are
* trying to reserve to avoid an overflow. We can't allocate
* more than @nimaps extents, and an extent is limited on disk
* to MAXEXTLEN (21 bits), so use that to enforce the limit.
*/
resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
if (unlikely(rt)) {
resrtextents = qblocks = resblks;
resrtextents /= mp->m_sb.sb_rextsize;
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
quota_flag = XFS_QMOPT_RES_RTBLKS;
} else {
resrtextents = 0;
resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
quota_flag = XFS_QMOPT_RES_REGBLKS;
}
/*
* Allocate and setup the transaction.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
resblks, resrtextents);
/*
* Check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
0, quota_flag);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
allocatesize_fsb, alloc_type, &firstfsb,
0, imapp, &nimaps, &free_list);
if (error) {
goto error0;
}
/*
* Complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error) {
break;
}
allocated_fsb = imapp->br_blockcount;
if (nimaps == 0) {
error = XFS_ERROR(ENOSPC);
break;
}
startoffset_fsb += allocated_fsb;
allocatesize_fsb -= allocated_fsb;
}
return error;
error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
xfs_bmap_cancel(&free_list);
xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
error1: /* Just cancel transaction */
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* This is called by xfs_inactive to free any blocks beyond eof
* when the link count isn't zero and by xfs_dm_punch_hole() when
* punching a hole to EOF.
*/
int
xfs_free_eofblocks(
xfs_mount_t *mp,
xfs_inode_t *ip,
bool need_iolock)
{
xfs_trans_t *tp;
int error;
xfs_fileoff_t end_fsb;
xfs_fileoff_t last_fsb;
xfs_filblks_t map_len;
int nimaps;
xfs_bmbt_irec_t imap;
/*
* Figure out if there are any blocks beyond the end
* of the file. If not, then there is nothing to do.
*/
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
if (last_fsb <= end_fsb)
return 0;
map_len = last_fsb - end_fsb;
nimaps = 1;
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!error && (nimaps != 0) &&
(imap.br_startblock != HOLESTARTBLOCK ||
ip->i_delayed_blks)) {
/*
* Attach the dquots to the inode up front.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* There are blocks after the end of file.
* Free them up now by truncating the file to
* its current size.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
if (need_iolock) {
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
xfs_trans_cancel(tp, 0);
return EAGAIN;
}
}
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Do not update the on-disk file size. If we update the
* on-disk file size and then the system crashes before the
* contents of the file are flushed to disk then the files
* may be full of holes (ie NULL files bug).
*/
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
XFS_ISIZE(ip));
if (error) {
/*
* If we get an error at this point we simply don't
* bother truncating the file.
*/
xfs_trans_cancel(tp,
(XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
} else {
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES);
if (!error)
xfs_inode_clear_eofblocks_tag(ip);
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
}
return error;
}
int
xfs_free_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
int committed;
int done;
xfs_fileoff_t endoffset_fsb;
int error;
xfs_fsblock_t firstfsb;
xfs_bmap_free_t free_list;
xfs_bmbt_irec_t imap;
xfs_off_t ioffset;
xfs_extlen_t mod=0;
xfs_mount_t *mp;
int nimap;
uint resblks;
xfs_off_t rounding;
int rt;
xfs_fileoff_t startoffset_fsb;
xfs_trans_t *tp;
mp = ip->i_mount;
trace_xfs_free_file_space(ip);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
error = 0;
if (len <= 0) /* if nothing being freed */
return error;
rt = XFS_IS_REALTIME_INODE(ip);
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
/* wait for the completion of any pending DIOs */
inode_dio_wait(VFS_I(ip));
rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
ioffset = offset & ~(rounding - 1);
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ioffset, -1);
if (error)
goto out;
truncate_pagecache_range(VFS_I(ip), ioffset, -1);
/*
* Need to zero the stuff we're not freeing, on disk.
* If it's a realtime file & can't use unwritten extents then we
* actually need to zero the extent edges. Otherwise xfs_bunmapi
* will take care of it for us.
*/
if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
nimap = 1;
error = xfs_bmapi_read(ip, startoffset_fsb, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
xfs_daddr_t block;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
block = imap.br_startblock;
mod = do_div(block, mp->m_sb.sb_rextsize);
if (mod)
startoffset_fsb += mp->m_sb.sb_rextsize - mod;
}
nimap = 1;
error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
mod++;
if (mod && (mod != mp->m_sb.sb_rextsize))
endoffset_fsb -= mod;
}
}
if ((done = (endoffset_fsb <= startoffset_fsb)))
/*
* One contiguous piece to clear
*/
error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
else {
/*
* Some full blocks, possibly two pieces to clear
*/
if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
error = xfs_zero_remaining_bytes(ip, offset,
XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
if (!error &&
XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
error = xfs_zero_remaining_bytes(ip,
XFS_FSB_TO_B(mp, endoffset_fsb),
offset + len - 1);
}
/*
* free file space until done or until there is an error
*/
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
while (!error && !done) {
/*
* allocate and setup the transaction. Allow this
* transaction to dip into the reserve blocks to ensure
* the freeing of the space succeeds at ENOSPC.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
/*
* check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota(tp, mp,
ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
resblks, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
/*
* issue the bunmapi() call to free the blocks
*/
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bunmapi(tp, ip, startoffset_fsb,
endoffset_fsb - startoffset_fsb,
0, 2, &firstfsb, &free_list, &done);
if (error) {
goto error0;
}
/*
* complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
out:
return error;
error0:
xfs_bmap_cancel(&free_list);
error1:
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_buf *leaf_bp = NULL;
struct xfs_da_args args;
struct xfs_trans_res tres;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, local;
XFS_STATS_INC(mp, xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &tres, args.total, 0,
rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* If this is a synchronous mount, make sure that
* the transaction goes to disk before returning
* to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
if (error)
goto out;
/*
* Prevent the leaf buffer from being unlocked so that a
* concurrent AIL push cannot grab the half-baked leaf
* buffer and run into problems with the write verifier.
*/
xfs_trans_bhold(args.trans, leaf_bp);
error = xfs_defer_finish(&args.trans);
if (error)
goto out;
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf, which
* means that we have to hold & join the leaf buffer here too.
*/
error = xfs_trans_roll_inode(&args.trans, dp);
if (error)
goto out;
xfs_trans_bjoin(args.trans, leaf_bp);
leaf_bp = NULL;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (leaf_bp)
xfs_trans_brelse(args.trans, leaf_bp);
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Generic handler routine to remove a name from an attribute list.
* Transitions attribute list from Btree to shortform as necessary.
*/
int
xfs_attr_remove(
struct xfs_inode *dp,
const unsigned char *name,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args;
int error;
XFS_STATS_INC(mp, xs_attr_remove);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
/*
* we have no control over the attribute names that userspace passes us
* to remove, so we have to allow the name lookup prior to attribute
* removal to fail.
*/
args.op_flags = XFS_DA_OP_OKNOENT;
error = xfs_qm_dqattach(dp);
if (error)
return error;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrrm,
XFS_ATTRRM_SPACE_RES(mp), 0,
(flags & ATTR_ROOT) ? XFS_TRANS_RESERVE : 0,
&args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
/*
* No need to make quota reservations here. We expect to release some
* blocks not allocate in the common case.
*/
xfs_trans_ijoin(args.trans, dp, 0);
if (!xfs_inode_hasattr(dp)) {
error = -ENOATTR;
} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
error = xfs_attr_shortform_remove(&args);
} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
error = xfs_attr_leaf_removename(&args);
} else {
error = xfs_attr_node_removename(&args);
}
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Generic handler routine to remove a name from an attribute list.
* Transitions attribute list from Btree to shortform as necessary.
*/
int
xfs_attr_remove(
struct xfs_inode *dp,
const unsigned char *name,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args;
struct xfs_bmap_free flist;
xfs_fsblock_t firstblock;
int error;
XFS_STATS_INC(xs_attr_remove);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
if (!xfs_inode_hasattr(dp))
return -ENOATTR;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.firstblock = &firstblock;
args.flist = &flist;
/*
* we have no control over the attribute names that userspace passes us
* to remove, so we have to allow the name lookup prior to attribute
* removal to fail.
*/
args.op_flags = XFS_DA_OP_OKNOENT;
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
/*
* Start our first transaction of the day.
*
* All future transactions during this code must be "chained" off
* this one via the trans_dup() call. All transactions will contain
* the inode, and the inode will always be marked with trans_ihold().
* Since the inode will be locked in all transactions, we must log
* the inode in every transaction to let it float upward through
* the log.
*/
args.trans = xfs_trans_alloc(mp, XFS_TRANS_ATTR_RM);
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
if (flags & ATTR_ROOT)
args.trans->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(args.trans, &M_RES(mp)->tr_attrrm,
XFS_ATTRRM_SPACE_RES(mp), 0);
if (error) {
xfs_trans_cancel(args.trans);
return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
/*
* No need to make quota reservations here. We expect to release some
* blocks not allocate in the common case.
*/
xfs_trans_ijoin(args.trans, dp, 0);
if (!xfs_inode_hasattr(dp)) {
error = -ENOATTR;
} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
error = xfs_attr_shortform_remove(&args);
} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
error = xfs_attr_leaf_removename(&args);
} else {
error = xfs_attr_node_removename(&args);
}
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args;
struct xfs_bmap_free flist;
struct xfs_trans_res tres;
xfs_fsblock_t firstblock;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, committed, local;
XFS_STATS_INC(xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.firstblock = &firstblock;
args.flist = &flist;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
/*
* Start our first transaction of the day.
*
* All future transactions during this code must be "chained" off
* this one via the trans_dup() call. All transactions will contain
* the inode, and the inode will always be marked with trans_ihold().
* Since the inode will be locked in all transactions, we must log
* the inode in every transaction to let it float upward through
* the log.
*/
args.trans = xfs_trans_alloc(mp, XFS_TRANS_ATTR_SET);
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
if (rsvd)
args.trans->t_flags |= XFS_TRANS_RESERVE;
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
if (error) {
xfs_trans_cancel(args.trans);
return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* If this is a synchronous mount, make sure that
* the transaction goes to disk before returning
* to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
xfs_bmap_init(args.flist, args.firstblock);
error = xfs_attr_shortform_to_leaf(&args);
if (!error) {
error = xfs_bmap_finish(&args.trans, args.flist,
&committed);
}
if (error) {
ASSERT(committed);
args.trans = NULL;
xfs_bmap_cancel(&flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args.trans, dp, 0);
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf.
*/
error = xfs_trans_roll(&args.trans, dp);
if (error)
goto out;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
bool did_zeroing = false;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
/*
* File data changes must be complete before we start the transaction to
* modify the inode. This needs to be done before joining the inode to
* the transaction because the inode cannot be unlocked once it is a
* part of the transaction.
*
* Start with zeroing any data beyond EOF that we may expose on file
* extension, or zeroing out the rest of the block on a downward
* truncate.
*/
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
} else {
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_iomap_ops);
}
if (error)
return error;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
(newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*/
truncate_setsize(inode, newsize);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_cancel;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
/*
* Prepare two files for range cloning. Upon a successful return both inodes
* will have the iolock and mmaplock held, the page cache of the out file will
* be truncated, and any leases on the out file will have been broken. This
* function borrows heavily from xfs_file_aio_write_checks.
*
* The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
* checked that the bytes beyond EOF physically match. Hence we cannot use the
* EOF block in the source dedupe range because it's not a complete block match,
* hence can introduce a corruption into the file that has it's block replaced.
*
* In similar fashion, the VFS file cloning also allows partial EOF blocks to be
* "block aligned" for the purposes of cloning entire files. However, if the
* source file range includes the EOF block and it lands within the existing EOF
* of the destination file, then we can expose stale data from beyond the source
* file EOF in the destination file.
*
* XFS doesn't support partial block sharing, so in both cases we have check
* these cases ourselves. For dedupe, we can simply round the length to dedupe
* down to the previous whole block and ignore the partial EOF block. While this
* means we can't dedupe the last block of a file, this is an acceptible
* tradeoff for simplicity on implementation.
*
* For cloning, we want to share the partial EOF block if it is also the new EOF
* block of the destination file. If the partial EOF block lies inside the
* existing destination EOF, then we have to abort the clone to avoid exposing
* stale data in the destination file. Hence we reject these clone attempts with
* -EINVAL in this case.
*/
int
xfs_reflink_remap_prep(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
loff_t *len,
unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
bool same_inode = (inode_in == inode_out);
ssize_t ret;
/* Lock both files against IO */
ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
if (ret)
return ret;
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
len, remap_flags);
if (ret < 0 || *len == 0)
goto out_unlock;
/* Attach dquots to dest inode before changing block map */
ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
/*
* Zero existing post-eof speculative preallocations in the destination
* file.
*/
ret = xfs_reflink_zero_posteof(dest, pos_out);
if (ret)
goto out_unlock;
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
/*
* If pos_out > EOF, we may have dirtied blocks between EOF and
* pos_out. In that case, we need to extend the flush and unmap to cover
* from EOF to the end of the copy length.
*/
if (pos_out > XFS_ISIZE(dest)) {
loff_t flen = *len + (pos_out - XFS_ISIZE(dest));
ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
} else {
ret = xfs_flush_unmap_range(dest, pos_out, *len);
}
if (ret)
goto out_unlock;
return 1;
out_unlock:
xfs_reflink_remap_unlock(file_in, file_out);
return ret;
}
/*
* Pass in a delayed allocate extent, convert it to real extents;
* return to the caller the extent we create which maps on top of
* the originating callers request.
*
* Called without a lock on the inode.
*
* We no longer bother to look at the incoming map - all we have to
* guarantee is that whatever we allocate fills the required range.
*/
int
xfs_iomap_write_allocate(
xfs_inode_t *ip,
xfs_off_t offset,
size_t count,
xfs_bmbt_irec_t *map,
int *retmap)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb, last_block;
xfs_fileoff_t end_fsb, map_start_fsb;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
xfs_filblks_t count_fsb;
xfs_bmbt_irec_t imap;
xfs_trans_t *tp;
int nimaps, committed;
int error = 0;
int nres;
*retmap = 0;
/*
* Make sure that the dquots are there.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return XFS_ERROR(error);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
count_fsb = map->br_blockcount;
map_start_fsb = map->br_startoff;
XFS_STATS_ADD(xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));
while (count_fsb != 0) {
/*
* Set up a transaction with which to allocate the
* backing store for the file. Do allocations in a
* loop until we get some space in the range we are
* interested in. The other space that might be allocated
* is in the delayed allocation extent on which we sit
* but before our buffer starts.
*/
nimaps = 0;
while (nimaps == 0) {
tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
tp->t_flags |= XFS_TRANS_RESERVE;
nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
error = xfs_trans_reserve(tp, nres,
XFS_WRITE_LOG_RES(mp),
0, XFS_TRANS_PERM_LOG_RES,
XFS_WRITE_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
return XFS_ERROR(error);
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_bmap_init(&free_list, &first_block);
/*
* it is possible that the extents have changed since
* we did the read call as we dropped the ilock for a
* while. We have to be careful about truncates or hole
* punchs here - we are not allowed to allocate
* non-delalloc blocks here.
*
* The only protection against truncation is the pages
* for the range we are being asked to convert are
* locked and hence a truncate will block on them
* first.
*
* As a result, if we go beyond the range we really
* need and hit an delalloc extent boundary followed by
* a hole while we have excess blocks in the map, we
* will fill the hole incorrectly and overrun the
* transaction reservation.
*
* Using a single map prevents this as we are forced to
* check each map we look for overlap with the desired
* range and abort as soon as we find it. Also, given
* that we only return a single map, having one beyond
* what we can return is probably a bit silly.
*
* We also need to check that we don't go beyond EOF;
* this is a truncate optimisation as a truncate sets
* the new file size before block on the pages we
* currently have locked under writeback. Because they
* are about to be tossed, we don't need to write them
* back....
*/
nimaps = 1;
end_fsb = XFS_B_TO_FSB(mp, ip->i_size);
error = xfs_bmap_last_offset(NULL, ip, &last_block,
XFS_DATA_FORK);
if (error)
goto trans_cancel;
last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
if ((map_start_fsb + count_fsb) > last_block) {
count_fsb = last_block - map_start_fsb;
if (count_fsb == 0) {
error = EAGAIN;
goto trans_cancel;
}
}
/* Go get the actual blocks */
error = xfs_bmapi(tp, ip, map_start_fsb, count_fsb,
XFS_BMAPI_WRITE, &first_block, 1,
&imap, &nimaps, &free_list, NULL);
if (error)
goto trans_cancel;
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error)
goto trans_cancel;
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto error0;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
/*
* See if we were able to allocate an extent that
* covers at least part of the callers request
*/
if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip)))
return xfs_cmn_err_fsblock_zero(ip, &imap);
if ((offset_fsb >= imap.br_startoff) &&
(offset_fsb < (imap.br_startoff +
imap.br_blockcount))) {
*map = imap;
*retmap = 1;
XFS_STATS_INC(xs_xstrat_quick);
return 0;
}
/*
* So far we have not mapped the requested part of the
* file, just surrounding data, try again.
*/
count_fsb -= imap.br_blockcount;
map_start_fsb = imap.br_startoff + imap.br_blockcount;
}
trans_cancel:
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
error0:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return XFS_ERROR(error);
}
