"Linux regression tracking (Thorsten Leemhuis)" wrote:
Thx. FWIW, there were some other corruption bugs related to netfs, one of them [1] was recently solved by c26096ee0278c5 ("mm: Fix filemap_invalidate_inode() to use invalidate_inode_pages2_range()"); this is a v6.11-rc6-post commit.
filemap_invalidate_inode() is not used directly by ceph yet, and ceph doesn't yet use the netfs DIO that would also use that.
David