iomapp->iomap_bsize = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomapp->iomap_flags = flags;
- if (ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
+ if (XFS_IS_REALTIME_INODE(ip)) {
iomapp->iomap_flags |= IOMAP_REALTIME;
iomapp->iomap_target = mp->m_rtdev_targp;
} else {
break;
case BMAPI_WRITE:
xfs_iomap_enter_trace(XFS_IOMAP_WRITE_ENTER, ip, offset, count);
- lockmode = XFS_ILOCK_EXCL|XFS_EXTSIZE_WR;
+ lockmode = XFS_ILOCK_EXCL;
if (flags & BMAPI_IGNSTATE)
bmapi_flags |= XFS_BMAPI_IGSTATE|XFS_BMAPI_ENTIRE;
xfs_ilock(ip, lockmode);
break;
case BMAPI_ALLOCATE:
xfs_iomap_enter_trace(XFS_IOMAP_ALLOC_ENTER, ip, offset, count);
- lockmode = XFS_ILOCK_SHARED|XFS_EXTSIZE_RD;
+ lockmode = XFS_ILOCK_SHARED;
bmapi_flags = XFS_BMAPI_ENTIRE;
/* Attempt non-blocking lock */
xfs_extlen_t align;
int eof, error;
- if (ip->i_d.di_flags & XFS_DIFLAG_REALTIME)
+ if (XFS_IS_REALTIME_INODE(ip))
;
/*
* If mounted with the "-o swalloc" option, roundup the allocation
goto error_out;
}
- if (unlikely(!imap.br_startblock &&
- !(ip->i_d.di_flags & XFS_DIFLAG_REALTIME))) {
+ if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip))) {
error = xfs_cmn_err_fsblock_zero(ip, &imap);
goto error_out;
}
int prealloc, fsynced = 0;
int error;
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
/*
* Make sure that the dquots are there. This doesn't hold
goto retry;
}
- if (unlikely(!imap[0].br_startblock &&
- !(ip->i_d.di_flags & XFS_DIFLAG_REALTIME)))
+ if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))
return xfs_cmn_err_fsblock_zero(ip, &imap[0]);
*ret_imap = imap[0];
* 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_fsblock_t first_block;
xfs_bmap_free_t free_list;
xfs_filblks_t count_fsb;
- xfs_bmbt_irec_t imap[XFS_STRAT_WRITE_IMAPS];
+ xfs_bmbt_irec_t imap;
xfs_trans_t *tp;
- int i, nimaps, committed;
+ int nimaps, committed;
int error = 0;
int nres;
XFS_BMAP_INIT(&free_list, &first_block);
- nimaps = XFS_STRAT_WRITE_IMAPS;
/*
- * Ensure we don't go beyond eof - it is possible
- * the extents changed since we did the read call,
- * we dropped the ilock in the interim.
+ * 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);
- xfs_bmap_last_offset(NULL, ip, &last_block,
- XFS_DATA_FORK);
+ 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;
/* 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);
+ &imap, &nimaps, &free_list, NULL);
if (error)
goto trans_cancel;
* See if we were able to allocate an extent that
* covers at least part of the callers request
*/
- for (i = 0; i < nimaps; i++) {
- if (unlikely(!imap[i].br_startblock &&
- !(ip->i_d.di_flags & XFS_DIFLAG_REALTIME)))
- return xfs_cmn_err_fsblock_zero(ip, &imap[i]);
- if ((offset_fsb >= imap[i].br_startoff) &&
- (offset_fsb < (imap[i].br_startoff +
- imap[i].br_blockcount))) {
- *map = imap[i];
- *retmap = 1;
- XFS_STATS_INC(xs_xstrat_quick);
- return 0;
- }
- count_fsb -= imap[i].br_blockcount;
+ 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
+ /*
+ * So far we have not mapped the requested part of the
* file, just surrounding data, try again.
*/
- nimaps--;
- map_start_fsb = imap[nimaps].br_startoff +
- imap[nimaps].br_blockcount;
+ count_fsb -= imap.br_blockcount;
+ map_start_fsb = imap.br_startoff + imap.br_blockcount;
}
trans_cancel:
count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);
+ /*
+ * Reserve enough blocks in this transaction for two complete extent
+ * btree splits. We may be converting the middle part of an unwritten
+ * extent and in this case we will insert two new extents in the btree
+ * each of which could cause a full split.
+ *
+ * This reservation amount will be used in the first call to
+ * xfs_bmbt_split() to select an AG with enough space to satisfy the
+ * rest of the operation.
+ */
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
do {
if (error)
return XFS_ERROR(error);
- if (unlikely(!imap.br_startblock &&
- !(ip->i_d.di_flags & XFS_DIFLAG_REALTIME)))
+ if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip)))
return xfs_cmn_err_fsblock_zero(ip, &imap);
if ((numblks_fsb = imap.br_blockcount) == 0) {