Hi Jason, On 2019/1/12 5:25, Jason Gunthorpe wrote: > On Wed, Jan 09, 2019 at 09:35:46AM +0800, Xiaofei Tan wrote: >> AEQ overflow will be reported by hardware when too many >> asynchronous events occurred but not be handled in time. >> Normally, AEQ overflow error is not easy to occur. Once >> happened, we have to do physical function reset to recover. >> PF reset is implemented in two steps. Firstly, set reset >> level with ae_dev->ops->set_default_reset_request. >> Secondly, run reset with ae_dev->ops->reset_event. >> >> Signed-off-by: Xiaofei Tan <tanxiaofei@xxxxxxxxxx> >> Signed-off-by: Yixian Liu <liuyixian@xxxxxxxxxx> >> --- >> drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 11 +++++++++++ >> 1 file changed, 11 insertions(+) > > Why should this be a -rc patch? It doesn't look like it meets the > requires for a stable kernel, or fixing something introduced in the > merge window. > > This looks like a new feature to me. > I think we could take this as a bug. Because the device can't continue working, if we don't handle the AEQ overflow error. And the code is simple and doesn't bring any unstable factor. Then i take it as -rc patch. -- thanks tanxiaofei > Jason > >
