On Wed, 2022-01-05 at 13:43 -0400, Jason Gunthorpe wrote: > On Wed, Jan 05, 2022 at 05:16:06PM +0000, Trond Myklebust wrote: > > > I'm confused, RPC/RDMA should never touch a umem at all. > > > > > > Is this really the other bug where user and kernel MR are getting > > > confused? > > > > > > > As far as I know, RPC/RDMA is just using the RDMA api to register > > and > > unregister chunks of memory, so it is definitely not directly > > touching > > the umem. > > I mean, RPC/RDMA doesn't have a umem at all, so seeing it any stack > trace says something is corrupted > > I suppose it is this: > > https://lore.kernel.org/r/20211222101312.1358616-1-maorg@xxxxxxxxxx > > Jason > Ah... Thanks! I'll try that out. -- Trond Myklebust Linux NFS client maintainer, Hammerspace trond.myklebust@xxxxxxxxxxxxxxx
