/* * Fast and loose check if this write could update the on-disk inode size.
*/ staticinlinebool xfs_ioend_is_append(struct iomap_ioend *ioend)
{ return ioend->io_offset + ioend->io_size >
XFS_I(ioend->io_inode)->i_disk_size;
}
/* * Update on-disk file size now that data has been written to disk.
*/ int
xfs_setfilesize( struct xfs_inode *ip,
xfs_off_t offset,
size_t size)
{ struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp;
xfs_fsize_t isize; int error;
/* * Put the open zone for all ioends merged into this one (if any).
*/
list_for_each_entry(tmp, &ioend->io_list, io_list)
xfs_open_zone_put(tmp->io_private);
/* * The main ioend might not have an open zone if the submission failed * before xfs_zone_alloc_and_submit got called.
*/ if (ioend->io_private)
xfs_open_zone_put(ioend->io_private);
}
/* * We can allocate memory here while doing writeback on behalf of * memory reclaim. To avoid memory allocation deadlocks set the * task-wide nofs context for the following operations.
*/
nofs_flag = memalloc_nofs_save();
/* * Just clean up the in-memory structures if the fs has been shut down.
*/ if (xfs_is_shutdown(mp)) {
error = -EIO; goto done;
}
/* * Clean up all COW blocks and underlying data fork delalloc blocks on * I/O error. The delalloc punch is required because this ioend was * mapped to blocks in the COW fork and the associated pages are no * longer dirty. If we don't remove delalloc blocks here, they become * stale and can corrupt free space accounting on unmount.
*/
error = blk_status_to_errno(ioend->io_bio.bi_status); if (unlikely(error)) { if (ioend->io_flags & IOMAP_IOEND_SHARED) {
ASSERT(!is_zoned);
xfs_reflink_cancel_cow_range(ip, offset, size, true);
xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset,
offset + size, NULL);
} goto done;
}
/* * Finish all pending IO completions that require transactional modifications. * * We try to merge physical and logically contiguous ioends before completion to * minimise the number of transactions we need to perform during IO completion. * Both unwritten extent conversion and COW remapping need to iterate and modify * one physical extent at a time, so we gain nothing by merging physically * discontiguous extents here. * * The ioend chain length that we can be processing here is largely unbound in * length and we may have to perform significant amounts of work on each ioend * to complete it. Hence we have to be careful about holding the CPU for too * long in this loop.
*/ void
xfs_end_io( struct work_struct *work)
{ struct xfs_inode *ip =
container_of(work, struct xfs_inode, i_ioend_work); struct iomap_ioend *ioend; struct list_head tmp; unsignedlong flags;
/* * For Appends record the actually written block number and set the * boundary flag if needed.
*/ if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) {
ioend->io_sector = bio->bi_iter.bi_sector;
xfs_mark_rtg_boundary(ioend);
}
/* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the * error state of the pages under writeback appropriately. * * If the folio has delalloc blocks on it, the caller is asking us to punch them * out. If we don't, we can leave a stale delalloc mapping covered by a clean * page that needs to be dirtied again before the delalloc mapping can be * converted. This stale delalloc mapping can trip up a later direct I/O read * operation on the same region. * * We prevent this by truncating away the delalloc regions on the folio. Because * they are delalloc, we can do this without needing a transaction. Indeed - if * we get ENOSPC errors, we have to be able to do this truncation without a * transaction as there is no space left for block reservation (typically why * we see a ENOSPC in writeback).
*/ staticvoid
xfs_discard_folio( struct folio *folio,
loff_t pos)
{ struct xfs_inode *ip = XFS_I(folio->mapping->host); struct xfs_mount *mp = ip->i_mount;
/* * The end of the punch range is always the offset of the first * byte of the next folio. Hence the end offset is only dependent on the * folio itself and not the start offset that is passed in.
*/
xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
folio_pos(folio) + folio_size(folio), NULL);
}
/* * Fast revalidation of the cached writeback mapping. Return true if the current * mapping is valid, false otherwise.
*/ staticbool
xfs_imap_valid( struct iomap_writepage_ctx *wpc, struct xfs_inode *ip,
loff_t offset)
{ if (offset < wpc->iomap.offset ||
offset >= wpc->iomap.offset + wpc->iomap.length) returnfalse; /* * If this is a COW mapping, it is sufficient to check that the mapping * covers the offset. Be careful to check this first because the caller * can revalidate a COW mapping without updating the data seqno.
*/ if (wpc->iomap.flags & IOMAP_F_SHARED) returntrue;
/* * This is not a COW mapping. Check the sequence number of the data fork * because concurrent changes could have invalidated the extent. Check * the COW fork because concurrent changes since the last time we * checked (and found nothing at this offset) could have added * overlapping blocks.
*/ if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) {
trace_xfs_wb_data_iomap_invalid(ip, &wpc->iomap,
XFS_WPC(wpc)->data_seq, XFS_DATA_FORK); returnfalse;
} if (xfs_inode_has_cow_data(ip) &&
XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) {
trace_xfs_wb_cow_iomap_invalid(ip, &wpc->iomap,
XFS_WPC(wpc)->cow_seq, XFS_COW_FORK); returnfalse;
} returntrue;
}
/* * COW fork blocks can overlap data fork blocks even if the blocks * aren't shared. COW I/O always takes precedent, so we must always * check for overlap on reflink inodes unless the mapping is already a * COW one, or the COW fork hasn't changed from the last time we looked * at it. * * It's safe to check the COW fork if_seq here without the ILOCK because * we've indirectly protected against concurrent updates: writeback has * the page locked, which prevents concurrent invalidations by reflink * and directio and prevents concurrent buffered writes to the same * page. Changes to if_seq always happen under i_lock, which protects * against concurrent updates and provides a memory barrier on the way * out that ensures that we always see the current value.
*/ if (xfs_imap_valid(wpc, ip, offset)) return 0;
/* * If we don't have a valid map, now it's time to get a new one for this * offset. This will convert delayed allocations (including COW ones) * into real extents. If we return without a valid map, it means we * landed in a hole and we skip the block.
*/
retry:
cow_fsb = NULLFILEOFF;
whichfork = XFS_DATA_FORK;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(!xfs_need_iread_extents(&ip->i_df));
/* * Check if this is offset is covered by a COW extents, and if yes use * it directly instead of looking up anything in the data fork.
*/ if (xfs_inode_has_cow_data(ip) &&
xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
cow_fsb = imap.br_startoff; if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
whichfork = XFS_COW_FORK; goto allocate_blocks;
}
/* * No COW extent overlap. Revalidate now that we may have updated * ->cow_seq. If the data mapping is still valid, we're done.
*/ if (xfs_imap_valid(wpc, ip, offset)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED); return 0;
}
/* * If we don't have a valid map, now it's time to get a new one for this * offset. This will convert delayed allocations (including COW ones) * into real extents.
*/ if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
imap.br_startoff = end_fsb; /* fake a hole past EOF */
XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
/* landed in a hole or beyond EOF? */ if (imap.br_startoff > offset_fsb) {
imap.br_blockcount = imap.br_startoff - offset_fsb;
imap.br_startoff = offset_fsb;
imap.br_startblock = HOLESTARTBLOCK;
imap.br_state = XFS_EXT_NORM;
}
/* * Truncate to the next COW extent if there is one. This is the only * opportunity to do this because we can skip COW fork lookups for the * subsequent blocks in the mapping; however, the requirement to treat * the COW range separately remains.
*/ if (cow_fsb != NULLFILEOFF &&
cow_fsb < imap.br_startoff + imap.br_blockcount)
imap.br_blockcount = cow_fsb - imap.br_startoff;
/* got a delalloc extent? */ if (imap.br_startblock != HOLESTARTBLOCK &&
isnullstartblock(imap.br_startblock)) goto allocate_blocks;
xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq);
trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap); return 0;
allocate_blocks: /* * Convert a dellalloc extent to a real one. The current page is held * locked so nothing could have removed the block backing offset_fsb, * although it could have moved from the COW to the data fork by another * thread.
*/ if (whichfork == XFS_COW_FORK)
seq = &XFS_WPC(wpc)->cow_seq; else
seq = &XFS_WPC(wpc)->data_seq;
error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
&wpc->iomap, seq); if (error) { /* * If we failed to find the extent in the COW fork we might have * raced with a COW to data fork conversion or truncate. * Restart the lookup to catch the extent in the data fork for * the former case, but prevent additional retries to avoid * looping forever for the latter case.
*/ if (error == -EAGAIN && whichfork == XFS_COW_FORK && !retries++) goto retry;
ASSERT(error != -EAGAIN); return error;
}
/* * Due to merging the return real extent might be larger than the * original delalloc one. Trim the return extent to the next COW * boundary again to force a re-lookup.
*/ if (whichfork != XFS_COW_FORK && cow_fsb != NULLFILEOFF) {
loff_t cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
/* * Convert CoW extents to regular. * * We can allocate memory here while doing writeback on behalf of memory * reclaim. To avoid memory allocation deadlocks, set the task-wide * nofs context.
*/ if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) { unsignedint nofs_flag;
/* * Send ioends that might require a transaction to the completion wq.
*/ if (xfs_ioend_needs_wq_completion(ioend))
ioend->io_bio.bi_end_io = xfs_end_bio;
/* * All dirty data must be covered by delalloc extents. But truncate can * remove delalloc extents underneath us or reduce their size. * Returning a hole tells iomap to not write back any data from this * range, which is the right thing to do in that case. * * Otherwise just tell iomap to treat ranges previously covered by a * delalloc extent as mapped. The actual block allocation will be done * just before submitting the bio. * * This implies we never map outside folios that are locked or marked * as under writeback, and thus there is no need check the fork sequence * count here.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL); if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
imap.br_startoff = end_fsb; /* fake a hole past EOF */ if (imap.br_startoff > offset_fsb) {
imap.br_blockcount = imap.br_startoff - offset_fsb;
imap.br_startoff = offset_fsb;
imap.br_startblock = HOLESTARTBLOCK;
imap.br_state = XFS_EXT_NORM;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, 0); return 0;
}
end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount);
count_fsb = end_fsb - offset_fsb;
/* * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasses the file system for actual I/O. We really can't allow * that on reflinks inodes, so we have to skip out here. And yes, * 0 is the magic code for a bmap error. * * Since we don't pass back blockdev info, we can't return bmap * information for rt files either.
*/ if (xfs_is_cow_inode(ip) || XFS_IS_REALTIME_INODE(ip)) return 0; return iomap_bmap(mapping, block, &xfs_read_iomap_ops);
}
/* * Swap file activation can race against concurrent shared extent * removal in files that have been cloned. If this happens, * iomap_swapfile_iter() can fail because it encountered a shared * extent even though an operation is in progress to remove those * shared extents. * * This race becomes problematic when we defer extent removal * operations beyond the end of a syscall (i.e. use async background * processing algorithms). Users think the extents are no longer * shared, but iomap_swapfile_iter() still sees them as shared * because the refcountbt entries for the extents being removed have * not yet been updated. Hence the swapon call fails unexpectedly. * * The race condition is currently most obvious from the unlink() * operation as extent removal is deferred until after the last * reference to the inode goes away. We then process the extent * removal asynchronously, hence triggers the "syscall completed but * work not done" condition mentioned above. To close this race * window, we need to flush any pending inodegc operations to ensure * they have updated the refcountbt records before we try to map the * swapfile.
*/
xfs_inodegc_flush(ip->i_mount);
/* * Direct the swap code to the correct block device when this file * sits on the RT device.
*/
sis->bdev = xfs_inode_buftarg(ip)->bt_bdev;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.