linux-kernel - Re: [RFC PATCH 3/3] nvme: Introduce nvme_execute_passthru_rq

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <55aaecf5-e094-1ef6-e4ac-3460d5eaf02c@deltatee.com>
Date:   Fri, 25 Oct 2019 15:55:21 -0600
From:   Logan Gunthorpe <logang@...tatee.com>
To:     Sagi Grimberg <sagi@...mberg.me>, linux-kernel@...r.kernel.org,
        linux-nvme@...ts.infradead.org
Cc:     Keith Busch <kbusch@...nel.org>, Max Gurtovoy <maxg@...lanox.com>,
        Christoph Hellwig <hch@....de>,
        Chaitanya Kulkarni <Chaitanya.Kulkarni@....com>,
        Stephen Bates <sbates@...thlin.com>
Subject: Re: [RFC PATCH 3/3] nvme: Introduce nvme_execute_passthru_rq_nowait()



On 2019-10-25 3:40 p.m., Sagi Grimberg wrote:
>> Hmm, that's going to be a bit tricky. Seeing the work_struct belongs
>> potentially to a number of different requests, we can't just flush the
>> individual work items. I think we'd have to create a work-queue per ctrl
>> and flush that. Any objections to that?
> 
> I'd object to that overhead...
> 
> How about marking the request if the workqueue path is taken and
> in nvme_stop_ctrl you add a blk_mq_tagset_busy_iter and cancel
> it in the callback?

Oh, cool. That looks great, I'll do that. Thanks!

Logan

> Something like:
> -- 
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index fa7ba09dca77..13dbbec5497d 100644
> --- a/drivers/nvme/host/core.c
> +++ b/drivers/nvme/host/core.c
> @@ -3955,12 +3955,33 @@ void nvme_complete_async_event(struct nvme_ctrl
> *ctrl, __le16 status,
>  }
>  EXPORT_SYMBOL_GPL(nvme_complete_async_event);
> 
> +static bool nvme_flush_async_passthru_request(struct request *rq,
> +               void *data, bool reserved)
> +{
> +       if (!(nvme_req(rq)->flags & NVME_REQ_ASYNC_PASSTHRU))
> +               return true;
> +
> +       dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
> +                               "Cancelling passthru I/O %d", req->tag);
> +       flush_work(&nvme_req(rq)->work);
> +       return true;
> +}
> +
> +static void nvme_flush_async_passthru_requests(struct nvme_ctrl *ctrl)
> +{
> +       blk_mq_tagset_busy_iter(ctrl->tagset,
> +               nvme_flush_async_passthru_request, ctrl);
> +       blk_mq_tagset_busy_iter(ctrl->admin_tagset,
> +               nvme_flush_async_passthru_request, ctrl);
> +}
> +
>  void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
>  {
>         nvme_mpath_stop(ctrl);
>         nvme_stop_keep_alive(ctrl);
>         flush_work(&ctrl->async_event_work);
>         cancel_work_sync(&ctrl->fw_act_work);
> +       nvme_flush_async_passthru_requests(ctrl);
>  }
>  EXPORT_SYMBOL_GPL(nvme_stop_ctrl);
> --