@@ -62,10 +62,14 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq,
} else {
trace_netfs_folio(folio, netfs_folio_trace_read_done);
}
+
+ folioq_clear(folioq, slot);
} else {
// TODO: Use of PG_private_2 is deprecated.
if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags))
netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot);
+ else
+ folioq_clear(folioq, slot);
}
if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
@@ -77,8 +81,6 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq,
folio_unlock(folio);
}
}
-
- folioq_clear(folioq, slot);
}
/*
At the end of netfs_unlock_read_folio() in which folios are marked appropriately for copying to the cache (either with by being marked dirty and having their private data set or by having PG_private_2 set) and then unlocked, the folio_queue struct has the entry pointing to the folio cleared. This presents a problem for netfs_pgpriv2_write_to_the_cache(), which is used to write folios marked with PG_private_2 to the cache as it expects to be able to trawl the folio_queue list thereafter to find the relevant folios, leading to a hang. Fix this by not clearing the folio_queue entry if we're going to do the deprecated copy-to-cache. The clearance will be done instead as the folios are written to the cache. This can be reproduced by starting cachefiles, mounting a ceph filesystem with "-o fsc" and writing to it. Fixes: 796a4049640b ("netfs: In readahead, put the folio refs as soon extracted") Reported-by: Max Kellermann <max.kellermann@ionos.com> Closes: https://lore.kernel.org/r/CAKPOu+_4m80thNy5_fvROoxBm689YtA0dZ-=gcmkzwYSY4syqw@mail.gmail.com/ Signed-off-by: David Howells <dhowells@redhat.com> cc: Jeff Layton <jlayton@kernel.org> cc: Ilya Dryomov <idryomov@gmail.com> cc: Xiubo Li <xiubli@redhat.com> cc: netfs@lists.linux.dev cc: ceph-devel@vger.kernel.org cc: linux-fsdevel@vger.kernel.org --- fs/netfs/read_collect.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)