From f76823e3b284aae30797fded988a807eab2da246 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Jul 2025 07:35:44 +0200 Subject: xfs: split xfs_zone_record_blocks xfs_zone_record_blocks not only records successfully written blocks that now back file data, but is also used for blocks speculatively written by garbage collection that were never linked to an inode and instantly become invalid. Split the latter functionality out to be easier to understand. This also make it clear that we don't need to attach the rmap inode to a transaction for the skipped blocks case as we never dirty any peristent data structure. Also make the argument order to xfs_zone_record_blocks a bit more natural. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_alloc.c | 42 +++++++++++++++++++++++++++++------------- 1 file changed, 29 insertions(+), 13 deletions(-) (limited to 'fs/xfs/xfs_zone_alloc.c') diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 33f7eee521a8..f8bd6d741755 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -166,10 +166,9 @@ xfs_open_zone_mark_full( static void xfs_zone_record_blocks( struct xfs_trans *tp, - xfs_fsblock_t fsbno, - xfs_filblks_t len, struct xfs_open_zone *oz, - bool used) + xfs_fsblock_t fsbno, + xfs_filblks_t len) { struct xfs_mount *mp = tp->t_mountp; struct xfs_rtgroup *rtg = oz->oz_rtg; @@ -179,18 +178,37 @@ xfs_zone_record_blocks( xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); - if (used) { - rmapip->i_used_blocks += len; - ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); - } else { - xfs_add_frextents(mp, len); - } + rmapip->i_used_blocks += len; + ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); oz->oz_written += len; if (oz->oz_written == rtg_blocks(rtg)) xfs_open_zone_mark_full(oz); xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE); } +/* + * Called for blocks that have been written to disk, but not actually linked to + * an inode, which can happen when garbage collection races with user data + * writes to a file. + */ +static void +xfs_zone_skip_blocks( + struct xfs_open_zone *oz, + xfs_filblks_t len) +{ + struct xfs_rtgroup *rtg = oz->oz_rtg; + + trace_xfs_zone_skip_blocks(oz, 0, len); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + oz->oz_written += len; + if (oz->oz_written == rtg_blocks(rtg)) + xfs_open_zone_mark_full(oz); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + + xfs_add_frextents(rtg_mount(rtg), len); +} + static int xfs_zoned_map_extent( struct xfs_trans *tp, @@ -250,8 +268,7 @@ xfs_zoned_map_extent( } } - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - true); + xfs_zone_record_blocks(tp, oz, new->br_startblock, new->br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new); @@ -259,8 +276,7 @@ xfs_zoned_map_extent( skip: trace_xfs_reflink_cow_remap_skip(ip, new); - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - false); + xfs_zone_skip_blocks(oz, new->br_blockcount); return 0; } -- cgit v1.2.3 From d004d70d6cdf03928da0d05c8c15c2ccc15657cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Aug 2025 07:06:43 +0200 Subject: xfs: remove xfs_last_used_zone This was my first attempt at caching the last used zone. But it turns out for O_DIRECT or RWF_DONTCACHE that operate concurrently or in very short sequence, the bmap btree does not record a written extent yet, so it fails. Because it then still finds the last written zone it can lead to a weird ping-pong around a few zones with writers seeing different values. Remove it entirely as the later added xfs_cached_zone actually does a much better job enforcing the locality as the zone is associated with the inode in the MRU cache as soon as the zone is selected. Fixes: 4e4d52075577 ("xfs: add the zoned space allocator") Signed-off-by: Christoph Hellwig Tested-by: Damien Le Moal Reviewed-by: Hans Holmberg Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_alloc.c | 45 ++------------------------------------------- 1 file changed, 2 insertions(+), 43 deletions(-) (limited to 'fs/xfs/xfs_zone_alloc.c') diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index f8bd6d741755..f28214c28ab5 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -374,44 +374,6 @@ xfs_zone_free_blocks( return 0; } -/* - * Check if the zone containing the data just before the offset we are - * writing to is still open and has space. - */ -static struct xfs_open_zone * -xfs_last_used_zone( - struct iomap_ioend *ioend) -{ - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset); - struct xfs_rtgroup *rtg = NULL; - struct xfs_open_zone *oz = NULL; - struct xfs_iext_cursor icur; - struct xfs_bmbt_irec got; - - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb, - &icur, &got)) { - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return NULL; - } - xfs_iunlock(ip, XFS_ILOCK_SHARED); - - rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock)); - if (!rtg) - return NULL; - - xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED); - oz = READ_ONCE(rtg->rtg_open_zone); - if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref))) - oz = NULL; - xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED); - - xfs_rtgroup_rele(rtg); - return oz; -} - static struct xfs_group * xfs_find_free_zone( struct xfs_mount *mp, @@ -918,12 +880,9 @@ xfs_zone_alloc_and_submit( goto out_error; /* - * If we don't have a cached zone in this write context, see if the - * last extent before the one we are writing to points to an active - * zone. If so, just continue writing to it. + * If we don't have a locally cached zone in this write context, see if + * the inode is still associated with a zone and use that if so. */ - if (!*oz && ioend->io_offset) - *oz = xfs_last_used_zone(ioend); if (!*oz) *oz = xfs_cached_zone(mp, ip); -- cgit v1.2.3