Re: [PATCH v3 4/6] xfs: tag folios with AG number during buffered write via iomap attach hook

["Darrick J. Wong" <djwong@kernel.org>]

On Wed, Jan 28, 2026 at 04:47:45PM -0800, Darrick J. Wong wrote:
> On Fri, Jan 16, 2026 at 03:38:16PM +0530, Kundan Kumar wrote:
> > Use the iomap attach hook to tag folios with their predicted
> > allocation group at write time. Mapped extents derive AG directly;
> > delalloc and hole cases use a lightweight predictor.
> > 
> > Signed-off-by: Kundan Kumar <kundan.kumar@samsung.com>
> > Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
> > ---
> >  fs/xfs/xfs_iomap.c | 114 +++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 114 insertions(+)
> > 
> > diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> > index 490e12cb99be..3c927ce118fe 100644
> > --- a/fs/xfs/xfs_iomap.c
> > +++ b/fs/xfs/xfs_iomap.c
> > @@ -12,6 +12,9 @@
> >  #include "xfs_trans_resv.h"
> >  #include "xfs_mount.h"
> >  #include "xfs_inode.h"
> > +#include "xfs_alloc.h"
> > +#include "xfs_ag.h"
> > +#include "xfs_ag_resv.h"
> >  #include "xfs_btree.h"
> >  #include "xfs_bmap_btree.h"
> >  #include "xfs_bmap.h"
> > @@ -92,8 +95,119 @@ xfs_iomap_valid(
> >  	return true;
> >  }
> >  
> > +static xfs_agnumber_t
> > +xfs_predict_delalloc_agno(const struct xfs_inode *ip, loff_t pos, loff_t len)
> > +{
> > +	struct xfs_mount *mp = ip->i_mount;
> > +	xfs_agnumber_t start_agno, agno, best_agno;
> > +	struct xfs_perag *pag;
> > +
> > +	xfs_extlen_t free, resv, avail;
> > +	xfs_extlen_t need_fsbs, min_free_fsbs;
> > +	xfs_extlen_t best_free = 0;
> > +	xfs_agnumber_t agcount = mp->m_sb.sb_agcount;
> > +
> > +	/* RT inodes allocate from the realtime volume */
> > +	if (XFS_IS_REALTIME_INODE(ip))
> > +		return XFS_INO_TO_AGNO(mp, ip->i_ino);
> > +
> > +	start_agno =  XFS_INO_TO_AGNO(mp, ip->i_ino);
> > +
> > +	/*
> > +	 * size-based minimum free requirement.
> > +	 * Convert bytes to fsbs and require some slack.
> > +	 */
> > +	need_fsbs = XFS_B_TO_FSB(mp, (xfs_fsize_t)len);
> > +	min_free_fsbs = need_fsbs + max_t(xfs_extlen_t, need_fsbs >> 2, 128);
> > +
> > +	/*
> > +	 * scan AGs starting at start_agno and wrapping.
> > +	 * Pick the first AG that meets min_free_fsbs after reservations.
> > +	 * Keep a "best" fallback = maximum (free - resv).
> > +	 */
> > +	best_agno = start_agno;
> > +
> > +	for (xfs_agnumber_t i = 0; i < agcount; i++) {
> > +		agno = (start_agno + i) % agcount;
> > +		pag = xfs_perag_get(mp, agno);
> > +
> > +		if (!xfs_perag_initialised_agf(pag))
> > +			goto next;
> > +
> > +		free = READ_ONCE(pag->pagf_freeblks);
> > +		resv = xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE);
> > +
> > +		if (free <= resv)
> > +			goto next;
> > +
> > +		avail = free - resv;
> > +
> > +		if (avail >= min_free_fsbs) {
> > +			xfs_perag_put(pag);
> > +			return agno;
> > +		}
> > +
> > +		if (avail > best_free) {
> > +			best_free = avail;
> > +			best_agno = agno;
> > +		}
> > +next:
> > +		xfs_perag_put(pag);
> > +	}
> > +
> > +	return best_agno;
> > +}
> > +
> > +static inline xfs_agnumber_t xfs_ag_from_iomap(const struct xfs_mount *mp,
> > +		const struct iomap *iomap,
> > +		const struct xfs_inode *ip, loff_t pos, size_t len)
> > +{
> > +	if (iomap->type == IOMAP_MAPPED || iomap->type == IOMAP_UNWRITTEN) {
> > +		/* iomap->addr is byte address on device for buffered I/O */
> > +		xfs_fsblock_t fsb = XFS_BB_TO_FSBT(mp, BTOBB(iomap->addr));
> > +
> > +		return XFS_FSB_TO_AGNO(mp, fsb);

Also, what happens if this is a realtime file?  For pre-rtgroups
filesystems there is no group number to use; and for rtgroups you have
to use xfs_rtb_to_rgno.  The i_ag_dirty_bitmap and the m_ag_wb array
will be the wrong size if rgcount != agcount; and also you probably
don't want to have in the same per-group writeback list two inodes with
folios having the same group number but writing to two different devices
(data vs. rt).

--D

> > +	} else if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_DELALLOC) {
> > +		return xfs_predict_delalloc_agno(ip, pos, len);
> 
> Is it worth doing an AG scan to guess where the allocation might come
> from?  The predictions could turn out to be wrong by virtue of other
> delalloc regions being written back between the time that xfs_agp_set is
> called, and the actual bmapi_write call.
> 
> > +	}
> > +
> > +	return XFS_INO_TO_AGNO(mp, ip->i_ino);
> > +}
> > +
> > +static void xfs_agp_set(struct xfs_inode *ip, pgoff_t index,
> > +			xfs_agnumber_t agno, u8 type)
> > +{
> > +	u32 packed = xfs_agp_pack((u32)agno, type, true);
> > +
> > +	/* store as immediate value */
> > +	xa_store(&ip->i_ag_pmap, index, xa_mk_value(packed), GFP_NOFS);
> > +
> > +	/* Mark this AG as having potential dirty work */
> > +	if (ip->i_ag_dirty_bitmap && (u32)agno < ip->i_ag_dirty_bits)
> > +		set_bit((u32)agno, ip->i_ag_dirty_bitmap);
> > +}
> > +
> > +static void
> > +xfs_iomap_tag_folio(const struct iomap *iomap, struct folio *folio,
> > +		loff_t pos, size_t len)
> > +{
> > +	struct inode *inode;
> > +	struct xfs_inode *ip;
> > +	struct xfs_mount *mp;
> > +	xfs_agnumber_t agno;
> > +
> > +	inode = folio_mapping(folio)->host;
> > +	ip = XFS_I(inode);
> > +	mp = ip->i_mount;
> > +
> > +	agno = xfs_ag_from_iomap(mp, iomap, ip, pos, len);
> > +
> > +	xfs_agp_set(ip, folio->index, agno, (u8)iomap->type);
> 
> Hrm, so no, the ag_pmap only caches the ag number for the index of a
> folio, even if it spans many many blocks.
> 
> --D
> 
> > +}
> > +
> >  const struct iomap_write_ops xfs_iomap_write_ops = {
> >  	.iomap_valid		= xfs_iomap_valid,
> > +	.tag_folio		= xfs_iomap_tag_folio,
> >  };
> >  
> >  int
> > -- 
> > 2.25.1
> > 
> > 
>