On Thu, May 5, 2022 at 5:46 AM Guoqing Jiang <guoqing.jiang@xxxxxxxxx> wrote: > > > > On 5/4/22 10:22 PM, Haris Iqbal wrote: > > > >>> We observe the following error, > >>> > >>> [Fri Mar 25 19:08:03 2022] rtrs_client L353: <blya>: Failed > >>> IB_WR_LOCAL_INV: WR flushed > >>> [Fri Mar 25 19:08:03 2022] rtrs_client L333: <blya>: Failed > >>> IB_WR_REG_MR: WR flushed > >>> [Fri Mar 25 19:08:03 2022] rtrs_client L333: <blya>: Failed > >>> IB_WR_REG_MR: WR flushed > >>> [Fri Mar 25 19:08:34 2022] rtrs_client L353: <blya>: Failed > >>> IB_WR_LOCAL_INV: WR flushed > >>> [Fri Mar 25 19:08:34 2022] rtrs_client L353: <blya>:*Failed IB_WR_LOCAL_INV: WR flushed* > >> I got similar message but I am not certain it is the same one, pls see > >> the previous report, > >> > >> https://lore.kernel.org/linux-rdma/20220210073655.42281-1-guoqing.jiang@xxxxxxxxx/ > > I went through the emails, and the error looks similar but I am not > > sure if its related. The change to write_lock_bh was done after v5.14 > > I think, and the code where I am seeing this error still has irq > > versions of those lock (e.g. write_lock_irqsave). > > The lock is irrelevant, pls check > > https://lore.kernel.org/linux-rdma/473a53b6-9ab2-0d48-a9cf-c84b8dc4c3f3@xxxxxxxxx/ > > and > > https://lore.kernel.org/linux-rdma/3b6ddb23-6dfa-29e2-27fd-741c1e3e576d@xxxxxxxxx/ I tried with always_invalidate off, and it still fails. Also, I thought to try your small patch, but it turns out the commit 647bf13ce944 ("RDMA/rxe: Create duplicate mapping tables for FMRs") is not present in the version I am running. > > But I am not certain it is the same issue. > > Thanks, > Guoqing
