From mboxrd@z Thu Jan 1 00:00:00 1970 From: sfeldma@gmail.com Subject: [PATCH net-next 0/5] rocker: revert back to support for nowait processes Date: Fri, 12 Jun 2015 21:35:45 -0700 Message-ID: <1434170150-63838-1-git-send-email-sfeldma@gmail.com> Cc: jiri@resnulli.us, simon.horman@netronome.com, makita.toshiaki@lab.ntt.co.jp To: netdev@vger.kernel.org Return-path: Received: from mail-ig0-f179.google.com ([209.85.213.179]:33069 "EHLO mail-ig0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750765AbbFMEeA (ORCPT ); Sat, 13 Jun 2015 00:34:00 -0400 Received: by igbpi8 with SMTP id pi8so23455573igb.0 for ; Fri, 12 Jun 2015 21:33:59 -0700 (PDT) Sender: netdev-owner@vger.kernel.org List-ID: From: Scott Feldman One of the items removed from the rocker driver in the Spring Cleanup patch series was the ability to mark processing in the driver as "no wait" for those contexts where we cannot sleep. Turns out, we have "no wait" contexts where we want to program the device and we don't want to defer the processing to a process context. So re-add the ROCKER_OP_FLAG_NOWAIT flag to mark such processes, and propagate flags to mem allocator and to the device cmd executor. With NOWAIT, mem allocs are GFP_ATOMIC and device cmds are queued to the device, but the driver will not wait (sleep) for the response back from the device. My bad for removing NOWAIT support in the first place; I thought we could swing non-sleep contexts to process context using a work queue, for example, but there is push-back to keep processing in original context. Scott Feldman (5): rocker: revert back to support for nowait processes rocker: mark neigh update event processing as 'no wait' rocker: mark STP update as 'no wait' processing rocker: move MAC learn event back to 'no wait' processing rocker: move port stop to 'no wait' processing drivers/net/ethernet/rocker/rocker.c | 245 ++++++++++++++++------------------ 1 file changed, 118 insertions(+), 127 deletions(-) -- 1.7.10.4