int copy_extent_to_buffer(xfs_mount_t *mp, xfs_bmbt_irec_t rec, void *buffer, off_t offset, size_t len) {
xfs_buf_t *block_buffer;
int64_t copylen, copy_start;
xfs_daddr_t block, start, end;
char *src;
off_t cofs = offset;
xfs_off_t block_start;
xfs_daddr_t block_size = XFS_FSB_TO_B(mp, 1);
//xfs_daddr_t extent_size = XFS_FSB_TO_B(mp, rec.br_blockcount);
xfs_daddr_t extent_start = XFS_FSB_TO_B(mp, rec.br_startoff);
/* compute a block to start reading from */
if (offset >= extent_start) {
start = XFS_B_TO_FSBT(mp, offset - extent_start);
} else {
buffer = buffer + extent_start - offset;
cofs += extent_start - offset;
start = 0;
}
end = min(rec.br_blockcount, XFS_B_TO_FSBT(mp, offset + len - extent_start - 1) + 1);
for (block=start; block<end; block++) {
block_start = XFS_FSB_TO_B(mp, (rec.br_startoff + block));
block_buffer = libxfs_readbuf(mp->m_dev, XFS_FSB_TO_DADDR(mp, (rec.br_startblock + block)),
XFS_FSB_TO_BB(mp, 1), 0);
if (block_buffer == NULL) {
printf("Buffer error\n");
return XFS_ERROR(EIO);
}
src = block_buffer->b_addr;
copy_start = block_start;
copylen = block_size;
if (block_start < offset) {
copylen = block_size + block_start - offset;
copy_start = (block_size - copylen) + block_start;
src = block_buffer->b_addr + (block_size - copylen);
}
if ((block_start + block_size) > (offset + len)) {
copylen = offset + len - copy_start;
}
if (copylen > 0) {
memcpy(buffer, src, copylen);
buffer += copylen;
cofs += copylen;
}
libxfs_putbuf(block_buffer);
}
return 0;
}
int
xfs_ioc_trim(
struct xfs_mount *mp,
struct fstrim_range __user *urange)
{
struct request_queue *q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
unsigned int granularity = q->limits.discard_granularity;
struct fstrim_range range;
xfs_fsblock_t start, len, minlen;
xfs_agnumber_t start_agno, end_agno, agno;
__uint64_t blocks_trimmed = 0;
int error, last_error = 0;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (!blk_queue_discard(q))
return -XFS_ERROR(EOPNOTSUPP);
if (copy_from_user(&range, urange, sizeof(range)))
return -XFS_ERROR(EFAULT);
/*
* Truncating down the len isn't actually quite correct, but using
* XFS_B_TO_FSB would mean we trivially get overflows for values
* of ULLONG_MAX or slightly lower. And ULLONG_MAX is the default
* used by the fstrim application. In the end it really doesn't
* matter as trimming blocks is an advisory interface.
*/
start = XFS_B_TO_FSBT(mp, range.start);
len = XFS_B_TO_FSBT(mp, range.len);
minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
start_agno = XFS_FSB_TO_AGNO(mp, start);
if (start_agno >= mp->m_sb.sb_agcount)
return -XFS_ERROR(EINVAL);
end_agno = XFS_FSB_TO_AGNO(mp, start + len);
if (end_agno >= mp->m_sb.sb_agcount)
end_agno = mp->m_sb.sb_agcount - 1;
for (agno = start_agno; agno <= end_agno; agno++) {
error = -xfs_trim_extents(mp, agno, start, len, minlen,
&blocks_trimmed);
if (error)
last_error = error;
}
if (last_error)
return last_error;
range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
if (copy_to_user(urange, &range, sizeof(range)))
return -XFS_ERROR(EFAULT);
return 0;
}
/* Convert all of the unwritten CoW extents in a file's range to real ones. */
int
xfs_reflink_convert_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_filblks_t count_fsb = end_fsb - offset_fsb;
struct xfs_bmbt_irec imap;
struct xfs_defer_ops dfops;
xfs_fsblock_t first_block = NULLFSBLOCK;
int nimaps = 1, error = 0;
ASSERT(count != 0);
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap, &nimaps,
&dfops);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* 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 to read the
* garbage on the disk.
*/
STATIC int /* error (positive) */
xfs_zero_last_block(
struct xfs_inode *ip,
xfs_fsize_t offset,
xfs_fsize_t isize)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t last_fsb = XFS_B_TO_FSBT(mp, isize);
int zero_offset = XFS_B_FSB_OFFSET(mp, isize);
int zero_len;
int nimaps = 1;
int error = 0;
struct xfs_bmbt_irec imap;
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
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_len = mp->m_sb.sb_blocksize - zero_offset;
if (isize + zero_len > offset)
zero_len = offset - isize;
return xfs_iozero(ip, isize, zero_len);
}
/* Convert all of the unwritten CoW extents in a file's range to real ones. */
int
xfs_reflink_convert_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_bmbt_irec got;
struct xfs_defer_ops dfops;
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_extnum_t idx;
bool found;
int error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
/* Convert all the extents to real from unwritten. */
for (found = xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
found && got.br_startoff < end_fsb;
found = xfs_iext_get_extent(ifp, ++idx, &got)) {
error = xfs_reflink_convert_cow_extent(ip, &got, offset_fsb,
end_fsb - offset_fsb, &dfops);
if (error)
break;
}
/* Finish up. */
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* 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 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_vnode_t *vp,
xfs_iocore_t *io,
xfs_fsize_t isize,
xfs_fsize_t end_size)
{
xfs_fileoff_t last_fsb;
xfs_mount_t *mp;
int nimaps;
int zero_offset;
int zero_len;
int error = 0;
xfs_bmbt_irec_t imap;
xfs_off_t loff;
ASSERT(ismrlocked(io->io_lock, MR_UPDATE) != 0);
mp = io->io_mount;
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(mp, NULL, io, 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(mp, io, XFS_ILOCK_EXCL| XFS_EXTSIZE_RD);
loff = XFS_FSB_TO_B(mp, last_fsb);
zero_len = mp->m_sb.sb_blocksize - zero_offset;
error = xfs_iozero(vp, loff + zero_offset, zero_len, end_size);
XFS_ILOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
ASSERT(error >= 0);
return error;
}
STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t count = 1 << inode->i_blkbits;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (type == XFS_IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset + count > mp->m_super->s_maxbytes)
count = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return error;
if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
error = xfs_iomap_write_allocate(ip, offset, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return error;
}
#ifdef DEBUG
if (type == XFS_IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
}
#endif
if (nimaps)
trace_xfs_map_blocks_found(ip, offset, count, type, imap);
return 0;
}
/*
* 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;
}
/*
* Allocation group level functions.
*/
static inline int
xfs_ialloc_cluster_alignment(
xfs_alloc_arg_t *args)
{
if (xfs_sb_version_hasalign(&args->mp->m_sb) &&
args->mp->m_sb.sb_inoalignmt >=
XFS_B_TO_FSBT(args->mp, XFS_INODE_CLUSTER_SIZE(args->mp)))
return args->mp->m_sb.sb_inoalignmt;
return 1;
}
/*
* Remap parts of a file's data fork after a successful CoW.
*/
int
xfs_reflink_end_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
int error = 0;
trace_xfs_reflink_end_cow(ip, offset, count);
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/*
* Walk backwards until we're out of the I/O range. The loop function
* repeatedly cycles the ILOCK to allocate one transaction per remapped
* extent.
*
* If we're being called by writeback then the the pages will still
* have PageWriteback set, which prevents races with reflink remapping
* and truncate. Reflink remapping prevents races with writeback by
* taking the iolock and mmaplock before flushing the pages and
* remapping, which means there won't be any further writeback or page
* cache dirtying until the reflink completes.
*
* We should never have two threads issuing writeback for the same file
* region. There are also have post-eof checks in the writeback
* preparation code so that we don't bother writing out pages that are
* about to be truncated.
*
* If we're being called as part of directio write completion, the dio
* count is still elevated, which reflink and truncate will wait for.
* Reflink remapping takes the iolock and mmaplock and waits for
* pending dio to finish, which should prevent any directio until the
* remap completes. Multiple concurrent directio writes to the same
* region are handled by end_cow processing only occurring for the
* threads which succeed; the outcome of multiple overlapping direct
* writes is not well defined anyway.
*
* It's possible that a buffered write and a direct write could collide
* here (the buffered write stumbles in after the dio flushes and
* invalidates the page cache and immediately queues writeback), but we
* have never supported this 100%. If either disk write succeeds the
* blocks will be remapped.
*/
while (end_fsb > offset_fsb && !error)
error = xfs_reflink_end_cow_extent(ip, offset_fsb, &end_fsb);
if (error)
trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
return error;
}
STATIC loff_t
xfs_seek_hole(
struct file *file,
loff_t start,
u32 type)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
loff_t holeoff;
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
uint lock;
int error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
lock = xfs_ilock_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK);
if (error)
goto out_unlock;
holeoff = XFS_FSB_TO_B(mp, fsbno);
if (holeoff <= start)
offset = start;
else {
/*
* xfs_bmap_first_unused() could return a value bigger than
* isize if there are no more holes past the supplied offset.
*/
offset = min_t(loff_t, holeoff, isize);
}
if (offset != file->f_pos)
file->f_pos = offset;
out_unlock:
xfs_iunlock_map_shared(ip, lock);
if (error)
return -error;
return offset;
}
/*
* Cancel CoW reservations for some byte range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_range(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count,
bool cancel_real)
{
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
int error;
trace_xfs_reflink_cancel_cow_range(ip, offset, count);
ASSERT(xfs_is_reflink_inode(ip));
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
if (count == NULLFILEOFF)
end_fsb = NULLFILEOFF;
else
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/* Start a rolling transaction to remove the mappings */
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
0, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* Scrape out the old CoW reservations */
error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
cancel_real);
if (error)
goto out_cancel;
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_cancel_cow_range_error(ip, error, _RET_IP_);
return error;
}
/*
* Pre-COW all shared blocks within a given byte range of a file and turn off
* the reflink flag if we unshare all of the file's blocks.
*/
int
xfs_reflink_unshare(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t fbno;
xfs_filblks_t end;
xfs_off_t isize;
int error;
if (!xfs_is_reflink_inode(ip))
return 0;
trace_xfs_reflink_unshare(ip, offset, len);
inode_dio_wait(VFS_I(ip));
/* Try to CoW the selected ranges */
xfs_ilock(ip, XFS_ILOCK_EXCL);
fbno = XFS_B_TO_FSBT(mp, offset);
isize = i_size_read(VFS_I(ip));
end = XFS_B_TO_FSB(mp, offset + len);
error = xfs_reflink_dirty_extents(ip, fbno, end, isize);
if (error)
goto out_unlock;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* Wait for the IO to finish */
error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out;
/* Turn off the reflink flag if possible. */
error = xfs_reflink_try_clear_inode_flag(ip);
if (error)
goto out;
return 0;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
return error;
}
/*
* If the caller is doing a write at the end of the file,
* then extend the allocation out to the file system's write
* iosize. We clean up any extra space left over when the
* file is closed in xfs_inactive().
*
* For sync writes, we are flushing delayed allocate space to
* try to make additional space available for allocation near
* the filesystem full boundary - preallocation hurts in that
* situation, of course.
*/
STATIC int
xfs_iomap_eof_want_preallocate(
xfs_mount_t *mp,
xfs_iocore_t *io,
xfs_fsize_t isize,
xfs_off_t offset,
size_t count,
int ioflag,
xfs_bmbt_irec_t *imap,
int nimaps,
int *prealloc)
{
xfs_fileoff_t start_fsb;
xfs_filblks_t count_fsb;
xfs_fsblock_t firstblock;
int n, error, imaps;
*prealloc = 0;
if ((ioflag & BMAPI_SYNC) || (offset + count) <= isize)
return 0;
/*
* If there are any real blocks past eof, then don't
* do any speculative allocation.
*/
start_fsb = XFS_B_TO_FSBT(mp, ((xfs_ufsize_t)(offset + count - 1)));
count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
while (count_fsb > 0) {
imaps = nimaps;
firstblock = NULLFSBLOCK;
error = XFS_BMAPI(mp, NULL, io, start_fsb, count_fsb, 0,
&firstblock, 0, imap, &imaps, NULL, NULL);
if (error)
return error;
for (n = 0; n < imaps; n++) {
if ((imap[n].br_startblock != HOLESTARTBLOCK) &&
(imap[n].br_startblock != DELAYSTARTBLOCK))
return 0;
start_fsb += imap[n].br_blockcount;
count_fsb -= imap[n].br_blockcount;
}
}
*prealloc = 1;
return 0;
}
/* Convert all of the unwritten CoW extents in a file's range to real ones. */
int
xfs_reflink_convert_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_filblks_t count_fsb = end_fsb - offset_fsb;
int error;
ASSERT(count != 0);
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
STATIC int
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) {
return 0;
}
last_fsb = XFS_B_TO_FSBT(mp, isize);
nimaps = 1;
error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
if (error)
return error;
ASSERT(nimaps > 0);
if (imap.br_startblock == HOLESTARTBLOCK) {
return 0;
}
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;
}
/*
* Add a block to the directory.
*
* This routine is for data and free blocks, not leaf/node blocks which are
* handled by xfs_da_grow_inode.
*/
int
xfs_dir2_grow_inode(
struct xfs_da_args *args,
int space, /* v2 dir's space XFS_DIR2_xxx_SPACE */
xfs_dir2_db_t *dbp) /* out: block number added */
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
xfs_fileoff_t bno; /* directory offset of new block */
int count; /* count of filesystem blocks */
int error;
trace_xfs_dir2_grow_inode(args, space);
/*
* Set lowest possible block in the space requested.
*/
bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
count = args->geo->fsbcount;
error = xfs_da_grow_inode_int(args, &bno, count);
if (error)
return error;
*dbp = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)bno);
/*
* Update file's size if this is the data space and it grew.
*/
if (space == XFS_DIR2_DATA_SPACE) {
xfs_fsize_t size; /* directory file (data) size */
size = XFS_FSB_TO_B(mp, bno + count);
if (size > dp->i_d.di_size) {
dp->i_d.di_size = size;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
}
}
return 0;
}
/*
* Ensure the size update falls into a valid allocated block.
*/
static int
xfs_pnfs_validate_isize(
struct xfs_inode *ip,
xfs_off_t isize)
{
struct xfs_bmbt_irec imap;
int nimaps = 1;
int error = 0;
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1,
&imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return error;
if (imap.br_startblock == HOLESTARTBLOCK ||
imap.br_startblock == DELAYSTARTBLOCK ||
imap.br_state == XFS_EXT_UNWRITTEN)
return -EIO;
return 0;
}
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_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;
}
int /* error (positive) */
xfs_zero_eof(
vnode_t *vp,
xfs_iocore_t *io,
xfs_off_t offset, /* starting I/O offset */
xfs_fsize_t isize, /* current inode size */
xfs_fsize_t end_size) /* terminal inode size */
{
struct inode *ip = LINVFS_GET_IP(vp);
xfs_fileoff_t start_zero_fsb;
xfs_fileoff_t end_zero_fsb;
xfs_fileoff_t prev_zero_fsb;
xfs_fileoff_t zero_count_fsb;
xfs_fileoff_t last_fsb;
xfs_extlen_t buf_len_fsb;
xfs_extlen_t prev_zero_count;
xfs_mount_t *mp;
int nimaps;
int error = 0;
xfs_bmbt_irec_t imap;
loff_t loff;
size_t lsize;
ASSERT(ismrlocked(io->io_lock, MR_UPDATE));
ASSERT(ismrlocked(io->io_iolock, MR_UPDATE));
mp = io->io_mount;
/*
* First handle zeroing the block on which isize resides.
* We only zero a part of that block so it is handled specially.
*/
error = xfs_zero_last_block(ip, io, offset, isize, end_size);
if (error) {
ASSERT(ismrlocked(io->io_lock, MR_UPDATE));
ASSERT(ismrlocked(io->io_iolock, MR_UPDATE));
return error;
}
/*
* Calculate the range between the new size and the old
* where blocks needing to be zeroed may exist. To get the
* block where the last byte in the file currently resides,
* we need to subtract one from the size and truncate back
* to a block boundary. We subtract 1 in case the size is
* exactly on a block boundary.
*/
last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
if (last_fsb == end_zero_fsb) {
/*
* The size was only incremented on its last block.
* We took care of that above, so just return.
*/
return 0;
}
ASSERT(start_zero_fsb <= end_zero_fsb);
prev_zero_fsb = NULLFILEOFF;
prev_zero_count = 0;
while (start_zero_fsb <= end_zero_fsb) {
nimaps = 1;
zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
error = XFS_BMAPI(mp, NULL, io, start_zero_fsb, zero_count_fsb,
0, NULL, 0, &imap, &nimaps, NULL);
if (error) {
ASSERT(ismrlocked(io->io_lock, MR_UPDATE));
ASSERT(ismrlocked(io->io_iolock, MR_UPDATE));
return error;
}
ASSERT(nimaps > 0);
if (imap.br_state == XFS_EXT_UNWRITTEN ||
imap.br_startblock == HOLESTARTBLOCK) {
/*
* This loop handles initializing pages that were
* partially initialized by the code below this
* loop. It basically zeroes the part of the page
* that sits on a hole and sets the page as P_HOLE
* and calls remapf if it is a mapped file.
*/
prev_zero_fsb = NULLFILEOFF;
prev_zero_count = 0;
start_zero_fsb = imap.br_startoff +
imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
continue;
}
/*
* There are blocks in the range requested.
* Zero them a single write at a time. We actually
* don't zero the entire range returned if it is
* too big and simply loop around to get the rest.
* That is not the most efficient thing to do, but it
* is simple and this path should not be exercised often.
*/
buf_len_fsb = XFS_FILBLKS_MIN(imap.br_blockcount,
mp->m_writeio_blocks << 8);
/*
* Drop the inode lock while we're doing the I/O.
* We'll still have the iolock to protect us.
*/
XFS_IUNLOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
loff = XFS_FSB_TO_B(mp, start_zero_fsb);
lsize = XFS_FSB_TO_B(mp, buf_len_fsb);
error = xfs_iozero(ip, loff, lsize, end_size);
if (error) {
goto out_lock;
}
prev_zero_fsb = start_zero_fsb;
prev_zero_count = buf_len_fsb;
start_zero_fsb = imap.br_startoff + buf_len_fsb;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
XFS_ILOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
}
return 0;
out_lock:
XFS_ILOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
ASSERT(error >= 0);
return error;
}
/*
* Zero file bytes between startoff and endoff inclusive.
* The iolock is held exclusive and no blocks are buffered.
*
* This function is used by xfs_free_file_space() to zero
* partial blocks when the range to free is not block aligned.
* When unreserving space with boundaries that are not block
* aligned we round up the start and round down the end
* boundaries and then use this function to zero the parts of
* the blocks that got dropped during the rounding.
*/
STATIC int
xfs_zero_remaining_bytes(
xfs_inode_t *ip,
xfs_off_t startoff,
xfs_off_t endoff)
{
xfs_bmbt_irec_t imap;
xfs_fileoff_t offset_fsb;
xfs_off_t lastoffset;
xfs_off_t offset;
xfs_buf_t *bp;
xfs_mount_t *mp = ip->i_mount;
int nimap;
int error = 0;
/*
* Avoid doing I/O beyond eof - it's not necessary
* since nothing can read beyond eof. The space will
* be zeroed when the file is extended anyway.
*/
if (startoff >= XFS_ISIZE(ip))
return 0;
if (endoff > XFS_ISIZE(ip))
endoff = XFS_ISIZE(ip);
bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp,
BTOBB(mp->m_sb.sb_blocksize), 0);
if (!bp)
return XFS_ERROR(ENOMEM);
xfs_buf_unlock(bp);
for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
uint lock_mode;
offset_fsb = XFS_B_TO_FSBT(mp, offset);
nimap = 1;
lock_mode = xfs_ilock_data_map_shared(ip);
error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
xfs_iunlock(ip, lock_mode);
if (error || nimap < 1)
break;
ASSERT(imap.br_blockcount >= 1);
ASSERT(imap.br_startoff == offset_fsb);
lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
if (lastoffset > endoff)
lastoffset = endoff;
if (imap.br_startblock == HOLESTARTBLOCK)
continue;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (imap.br_state == XFS_EXT_UNWRITTEN)
continue;
XFS_BUF_UNDONE(bp);
XFS_BUF_UNWRITE(bp);
XFS_BUF_READ(bp);
XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(read)");
break;
}
memset(bp->b_addr +
(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
0, lastoffset - offset + 1);
XFS_BUF_UNDONE(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_WRITE(bp);
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(write)");
break;
}
}
xfs_buf_free(bp);
return error;
}
int
xfs_ioctl(
bhv_desc_t *bdp,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
unsigned long arg)
{
int error;
vnode_t *vp;
xfs_inode_t *ip;
xfs_mount_t *mp;
vp = LINVFS_GET_VP(inode);
vn_trace_entry(vp, "xfs_ioctl", (inst_t *)__return_address);
ip = XFS_BHVTOI(bdp);
mp = ip->i_mount;
switch (cmd) {
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!XFS_SB_VERSION_HASEXTFLGBIT(&mp->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
return xfs_ioc_space(bdp, vp, filp, ioflags, cmd, arg);
case XFS_IOC_DIOINFO: {
struct dioattr da;
da.d_miniosz = mp->m_sb.sb_blocksize;
da.d_mem = mp->m_sb.sb_blocksize;
/*
* this only really needs to be BBSIZE.
* it is set to the file system block size to
* avoid having to do block zeroing on short writes.
*/
da.d_maxiosz = XFS_FSB_TO_B(mp,
XFS_B_TO_FSBT(mp, KIO_MAX_ATOMIC_IO << 10));
if (copy_to_user((struct dioattr *)arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
case XFS_IOC_GETXFLAGS:
case XFS_IOC_SETXFLAGS:
case XFS_IOC_FSGETXATTR:
case XFS_IOC_FSSETXATTR:
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_xattr(vp, ip, filp, cmd, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, (struct fsdmidata *)arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = xfs_set_dmattrs(bdp, dmi.fsd_dmevmask, dmi.fsd_dmstate,
NULL);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(bdp, filp, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(bdp, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE:
return xfs_find_handle(cmd, arg);
case XFS_IOC_OPEN_BY_HANDLE:
return xfs_open_by_handle(mp, arg, filp, inode);
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(mp, arg, filp, inode);
case XFS_IOC_READLINK_BY_HANDLE:
return xfs_readlink_by_handle(mp, arg, filp, inode);
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(mp, arg, filp, inode);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(mp, arg, filp, inode);
case XFS_IOC_SWAPEXT: {
error = xfs_swapext((struct xfs_swapext *)arg);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user((char *)arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&inout, (char *)arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
if (error)
return -error;
if (copy_to_user((char *)arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user((char *)arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_data(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_log(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_rt(mp, &in);
return -error;
}
case XFS_IOC_FREEZE:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (vp->v_vfsp->vfs_frozen == SB_UNFROZEN) {
freeze_bdev(mp->m_ddev_targp->pbr_bdev);
if (mp->m_rtdev_targp)
freeze_bdev(mp->m_rtdev_targp->pbr_bdev);
}
return 0;
case XFS_IOC_THAW:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (vp->v_vfsp->vfs_frozen != SB_UNFROZEN) {
thaw_bdev(mp->m_ddev_targp->pbr_bdev, inode->i_sb);
if (mp->m_rtdev_targp)
thaw_bdev(mp->m_ddev_targp->pbr_bdev, NULL);
}
return 0;
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp);
return -error;
default:
return -ENOTTY;
}
}
/*
* Add a block to the directory.
* This routine is for data and free blocks, not leaf/node blocks
* which are handled by xfs_da_grow_inode.
*/
int
xfs_dir2_grow_inode(
xfs_da_args_t *args,
int space, /* v2 dir's space XFS_DIR2_xxx_SPACE */
xfs_dir2_db_t *dbp) /* out: block number added */
{
xfs_fileoff_t bno; /* directory offset of new block */
int count; /* count of filesystem blocks */
xfs_inode_t *dp; /* incore directory inode */
int error;
int got; /* blocks actually mapped */
int i;
xfs_bmbt_irec_t map; /* single structure for bmap */
int mapi; /* mapping index */
xfs_bmbt_irec_t *mapp; /* bmap mapping structure(s) */
xfs_mount_t *mp;
int nmap; /* number of bmap entries */
xfs_trans_t *tp;
xfs_drfsbno_t nblks;
trace_xfs_dir2_grow_inode(args, space);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
nblks = dp->i_d.di_nblocks;
/*
* Set lowest possible block in the space requested.
*/
bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
count = mp->m_dirblkfsbs;
/*
* Find the first hole for our block.
*/
if ((error = xfs_bmap_first_unused(tp, dp, count, &bno, XFS_DATA_FORK)))
return error;
nmap = 1;
ASSERT(args->firstblock != NULL);
/*
* Try mapping the new block contiguously (one extent).
*/
if ((error = xfs_bmapi(tp, dp, bno, count,
XFS_BMAPI_WRITE|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
args->firstblock, args->total, &map, &nmap,
args->flist)))
return error;
ASSERT(nmap <= 1);
if (nmap == 1) {
mapp = ↦
mapi = 1;
}
/*
* Didn't work and this is a multiple-fsb directory block.
* Try again with contiguous flag turned on.
*/
else if (nmap == 0 && count > 1) {
xfs_fileoff_t b; /* current file offset */
/*
* Space for maximum number of mappings.
*/
mapp = kmem_alloc(sizeof(*mapp) * count, KM_SLEEP);
/*
* Iterate until we get to the end of our block.
*/
for (b = bno, mapi = 0; b < bno + count; ) {
int c; /* current fsb count */
/*
* Can't map more than MAX_NMAP at once.
*/
nmap = MIN(XFS_BMAP_MAX_NMAP, count);
c = (int)(bno + count - b);
if ((error = xfs_bmapi(tp, dp, b, c,
XFS_BMAPI_WRITE|XFS_BMAPI_METADATA,
args->firstblock, args->total,
&mapp[mapi], &nmap, args->flist))) {
kmem_free(mapp);
return error;
}
if (nmap < 1)
break;
/*
* Add this bunch into our table, go to the next offset.
*/
mapi += nmap;
b = mapp[mapi - 1].br_startoff +
mapp[mapi - 1].br_blockcount;
}
}
/*
* Didn't work.
*/
else {
mapi = 0;
mapp = NULL;
}
/*
* See how many fsb's we got.
*/
for (i = 0, got = 0; i < mapi; i++)
got += mapp[i].br_blockcount;
/*
* Didn't get enough fsb's, or the first/last block's are wrong.
*/
if (got != count || mapp[0].br_startoff != bno ||
mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount !=
bno + count) {
if (mapp != &map)
kmem_free(mapp);
return XFS_ERROR(ENOSPC);
}
/*
* Done with the temporary mapping table.
*/
if (mapp != &map)
kmem_free(mapp);
/* account for newly allocated blocks in reserved blocks total */
args->total -= dp->i_d.di_nblocks - nblks;
*dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno);
/*
* Update file's size if this is the data space and it grew.
*/
if (space == XFS_DIR2_DATA_SPACE) {
xfs_fsize_t size; /* directory file (data) size */
size = XFS_FSB_TO_B(mp, bno + count);
if (size > dp->i_d.di_size) {
dp->i_d.di_size = size;
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
}
}
return 0;
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start,
u32 type)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec map[2];
int nmap = 2;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
end = XFS_B_TO_FSB(mp, isize);
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/*
* Treat unwritten extent as data extent since it might
* contains dirty data in page cache.
*/
if (map[0].br_startblock != HOLESTARTBLOCK) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[0].br_startoff));
} else {
if (nmap == 1) {
error = ENXIO;
goto out_unlock;
}
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[1].br_startoff));
}
if (offset != file->f_pos)
file->f_pos = offset;
out_unlock:
xfs_iunlock_map_shared(ip, lock);
if (error)
return -error;
return offset;
}
/*
* 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 */
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t start_zero_fsb;
xfs_fileoff_t end_zero_fsb;
xfs_fileoff_t zero_count_fsb;
xfs_fileoff_t last_fsb;
xfs_fileoff_t zero_off;
xfs_fsize_t zero_len;
int nimaps;
int error = 0;
struct xfs_bmbt_irec imap;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
/*
* First handle zeroing the block on which isize resides.
*
* We only zero a part of that block so it is handled specially.
*/
if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
error = xfs_zero_last_block(ip, offset, isize);
if (error)
return error;
}
/*
* Calculate the range between the new size and the old where blocks
* needing to be zeroed may exist.
*
* To get the block where the last byte in the file currently resides,
* we need to subtract one from the size and truncate back to a block
* boundary. We subtract 1 in case the size is exactly on a block
* boundary.
*/
last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
if (last_fsb == end_zero_fsb) {
/*
* The size was only incremented on its last block.
* We took care of that above, so just return.
*/
return 0;
}
ASSERT(start_zero_fsb <= end_zero_fsb);
while (start_zero_fsb <= end_zero_fsb) {
nimaps = 1;
zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
&imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
ASSERT(nimaps > 0);
if (imap.br_state == XFS_EXT_UNWRITTEN ||
imap.br_startblock == HOLESTARTBLOCK) {
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
continue;
}
/*
* There are blocks we need to zero.
*/
zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
if ((zero_off + zero_len) > offset)
zero_len = offset - zero_off;
error = xfs_iozero(ip, zero_off, zero_len);
if (error)
return error;
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
}
return 0;
}
/*
* Link a range of blocks from one file to another.
*/
int
xfs_reflink_remap_range(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
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);
struct xfs_mount *mp = src->i_mount;
bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
xfs_extlen_t cowextsize;
ssize_t ret;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* Lock both files against IO */
lock_two_nondirectories(inode_in, inode_out);
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, 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 = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
&len, is_dedupe);
if (ret <= 0)
goto out_unlock;
trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
dfsbno = XFS_B_TO_FSBT(mp, pos_out);
sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
pos_out + len);
if (ret)
goto out_unlock;
/* Zap any page cache for the destination file's range. */
truncate_inode_pages_range(&inode_out->i_data, pos_out,
PAGE_ALIGN(pos_out + len) - 1);
/*
* Carry the cowextsize hint from src to dest if we're sharing the
* entire source file to the entire destination file, the source file
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
is_dedupe);
out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
if (!same_inode)
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
unlock_two_nondirectories(inode_in, inode_out);
if (ret)
trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
return ret;
}
/*
* Remap parts of a file's data fork after a successful CoW.
*/
int
xfs_reflink_end_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error;
unsigned int resblks;
xfs_filblks_t rlen;
xfs_extnum_t idx;
trace_xfs_reflink_end_cow(ip, offset, count);
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0)
return 0;
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/*
* Start a rolling transaction to switch the mappings. We're
* unlikely ever to have to remap 16T worth of single-block
* extents, so just cap the worst case extent count to 2^32-1.
* Stick a warning in just in case, and avoid 64-bit division.
*/
BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
if (end_fsb - offset_fsb > UINT_MAX) {
error = -EFSCORRUPTED;
xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
ASSERT(0);
goto out;
}
resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
(unsigned int)(end_fsb - offset_fsb),
XFS_DATA_FORK);
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
resblks, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* If there is a hole at end_fsb - 1 go to the previous extent */
if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
got.br_startoff > end_fsb) {
/*
* In case of racing, overlapping AIO writes no COW extents
* might be left by the time I/O completes for the loser of
* the race. In that case we are done.
*/
if (idx <= 0)
goto out_cancel;
xfs_iext_get_extent(ifp, --idx, &got);
}
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/* Extent delete may have bumped idx forward */
if (!del.br_blockcount) {
idx--;
goto next_extent;
}
ASSERT(!isnullstartblock(got.br_startblock));
/*
* Don't remap unwritten extents; these are
* speculatively preallocated CoW extents that have been
* allocated but have not yet been involved in a write.
*/
if (got.br_state == XFS_EXT_UNWRITTEN) {
idx--;
goto next_extent;
}
/* Unmap the old blocks in the data fork. */
xfs_defer_init(&dfops, &firstfsb);
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/* Trim the extent to whatever got unmapped. */
if (rlen) {
xfs_trim_extent(&del, del.br_startoff + rlen,
del.br_blockcount - rlen);
}
trace_xfs_reflink_cow_remap(ip, &del);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
del.br_startblock, del.br_blockcount);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
if (error)
goto out_defer;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_defer;
next_extent:
if (!xfs_iext_get_extent(ifp, idx, &got))
break;
}
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
return 0;
out_defer:
xfs_defer_cancel(&dfops);
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
return error;
}
int /* error (positive) */
xfs_zero_eof(
xfs_inode_t *ip,
xfs_off_t offset, /* starting I/O offset */
xfs_fsize_t isize) /* current inode size */
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t start_zero_fsb;
xfs_fileoff_t end_zero_fsb;
xfs_fileoff_t zero_count_fsb;
xfs_fileoff_t last_fsb;
xfs_fileoff_t zero_off;
xfs_fsize_t zero_len;
int nimaps;
int error = 0;
xfs_bmbt_irec_t imap;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
/*
* First handle zeroing the block on which isize resides.
* We only zero a part of that block so it is handled specially.
*/
error = xfs_zero_last_block(ip, offset, isize);
if (error) {
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
return error;
}
/*
* Calculate the range between the new size and the old
* where blocks needing to be zeroed may exist. To get the
* block where the last byte in the file currently resides,
* we need to subtract one from the size and truncate back
* to a block boundary. We subtract 1 in case the size is
* exactly on a block boundary.
*/
last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
if (last_fsb == end_zero_fsb) {
/*
* The size was only incremented on its last block.
* We took care of that above, so just return.
*/
return 0;
}
ASSERT(start_zero_fsb <= end_zero_fsb);
while (start_zero_fsb <= end_zero_fsb) {
nimaps = 1;
zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
0, NULL, 0, &imap, &nimaps, NULL, NULL);
if (error) {
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
return error;
}
ASSERT(nimaps > 0);
if (imap.br_state == XFS_EXT_UNWRITTEN ||
imap.br_startblock == HOLESTARTBLOCK) {
/*
* This loop handles initializing pages that were
* partially initialized by the code below this
* loop. It basically zeroes the part of the page
* that sits on a hole and sets the page as P_HOLE
* and calls remapf if it is a mapped file.
*/
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
continue;
}
/*
* There are blocks we need to zero.
* Drop the inode lock while we're doing the I/O.
* We'll still have the iolock to protect us.
*/
xfs_iunlock(ip, XFS_ILOCK_EXCL);
zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
if ((zero_off + zero_len) > offset)
zero_len = offset - zero_off;
error = xfs_iozero(ip, zero_off, zero_len);
if (error) {
goto out_lock;
}
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
xfs_ilock(ip, XFS_ILOCK_EXCL);
}
return 0;
out_lock:
xfs_ilock(ip, XFS_ILOCK_EXCL);
ASSERT(error >= 0);
return error;
}