NFS/localio: prevent direct reclaim recursion into NFS via nfs_writepages

LOCALIO is an NFS loopback mount optimization that avoids using the
network for READ, WRITE and COMMIT if the NFS client and server are
determined to be on the same system. But because LOCALIO is still
fundamentally "just NFS loopback mount" it is susceptible to recursion
deadlock via direct reclaim, e.g.: NFS LOCALIO down to XFS and then
back into NFS via nfs_writepages.

Fix LOCALIO's potential for direct reclaim deadlock by ensuring that
all its page cache allocations are done from GFP_NOFS context.

Thanks to Ben Coddington for pointing out commit ad22c7a043 ("xfs:
prevent stack overflows from page cache allocation").

Reported-by: John Cagle <john.cagle@hammerspace.com>
Tested-by: Allen Lu <allen.lu@hammerspace.com>
Suggested-by: Benjamin Coddington <bcodding@hammerspace.com>
Fixes: 70ba381e1a ("nfs: add LOCALIO support")
Signed-off-by: Mike Snitzer <snitzer@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
This commit is contained in:
Mike Snitzer 2026-01-07 11:08:55 -05:00 committed by Anna Schumaker
parent 5fcd95831d
commit 67435d2d8a

View file

@ -291,6 +291,18 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
}
EXPORT_SYMBOL_GPL(nfs_local_open_fh);
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into NFS via nfs_writepages.
*/
static void
nfs_local_mapping_set_gfp_nofs_context(struct address_space *m)
{
gfp_t gfp_mask = mapping_gfp_mask(m);
mapping_set_gfp_mask(m, (gfp_mask & ~(__GFP_FS)));
}
static void
nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
{
@ -315,6 +327,7 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
return NULL;
}
nfs_local_mapping_set_gfp_nofs_context(file->f_mapping);
init_sync_kiocb(&iocb->kiocb, file);
iocb->hdr = hdr;
@ -1000,6 +1013,8 @@ nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data)
end = LLONG_MAX;
}
nfs_local_mapping_set_gfp_nofs_context(filp->f_mapping);
dprintk("%s: commit %llu - %llu\n", __func__, start, end);
return vfs_fsync_range(filp, start, end, 0);
}