linux-kernel - Re: [PATCH] mmc: queue: replace immediate with hsq->depth

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] [day] [month] [year] [list]

Message-ID: <CA+Da2qynMSjtKHEqD_U3nBfXPxO63kjy8b3hwcB3zOV3NZvfLA@mail.gmail.com>
Date:   Fri, 11 Aug 2023 15:34:32 +0800
From:   Wenchao Chen <wenchao.chen666@...il.com>
To:     Ulf Hansson <ulf.hansson@...aro.org>
Cc:     Wenchao Chen <wenchao.chen@...soc.com>, linux-mmc@...r.kernel.org,
        linux-kernel@...r.kernel.org, zhenxiong.lai@...soc.com,
        chunyan.zhang@...soc.com, yuelin.tang@...soc.com
Subject: Re: [PATCH] mmc: queue: replace immediate with hsq->depth

On Tue, Aug 8, 2023 at 6:57 PM Ulf Hansson <ulf.hansson@...aro.org> wrote:
>
> On Tue, 8 Aug 2023 at 12:41, Wenchao Chen <wenchao.chen666@...il.com> wrote:
> >
> > On Tue, Aug 8, 2023 at 5:28 PM Ulf Hansson <ulf.hansson@...aro.org> wrote:
> > >
> > > On Thu, 3 Aug 2023 at 07:46, Wenchao Chen <wenchao.chen@...soc.com> wrote:
> > > >
> > > > Hsq is similar to cqe, using hsq->depth to represent
> > > > the maximum processing capacity of hsq. We can adjust
> > > > hsq->depth according to the actual situation.
> > >
> > > Sorry, but I don't quite follow here.
> > >
> > > Are you planning to update the host->hsq_depth dynamically from somewhere?
> > >
> > > Kind regards
> > > Uffe
> > >
> > Hi Uffe,
> > Depending on the mmc device, some devices allow host to send more reqs
> > to the device.
>
> In that case, please add a patch for that too, to show how this is
> going to be useful.
>

OK, I'll update it in the next version.

> > Also, we use hsq->hsq_depth instead of immediate number "2" to make
> > the code easier to understand.
>
> Right, but we don't need a new member in struct mmc_host for that. We
> could just be checking HSQ_MAX_DEPTH instead.
>
> Kind regards
> Uffe
>

Using the definition of host in core makes it feel a little strange.

> >
> > Thanks
> > Wenchao.Chen
> > > >
> > > > Signed-off-by: Wenchao Chen <wenchao.chen@...soc.com>
> > > > ---
> > > >  drivers/mmc/core/queue.c   | 6 +-----
> > > >  drivers/mmc/host/mmc_hsq.c | 1 +
> > > >  drivers/mmc/host/mmc_hsq.h | 7 +++++++
> > > >  include/linux/mmc/host.h   | 1 +
> > > >  4 files changed, 10 insertions(+), 5 deletions(-)
> > > >
> > > > diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
> > > > index b396e3900717..a0a2412f62a7 100644
> > > > --- a/drivers/mmc/core/queue.c
> > > > +++ b/drivers/mmc/core/queue.c
> > > > @@ -260,11 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
> > > >                 }
> > > >                 break;
> > > >         case MMC_ISSUE_ASYNC:
> > > > -               /*
> > > > -                * For MMC host software queue, we only allow 2 requests in
> > > > -                * flight to avoid a long latency.
> > > > -                */
> > > > -               if (host->hsq_enabled && mq->in_flight[issue_type] > 2) {
> > > > +               if (host->hsq_enabled && mq->in_flight[issue_type] > host->hsq_depth) {
> > > >                         spin_unlock_irq(&mq->lock);
> > > >                         return BLK_STS_RESOURCE;
> > > >                 }
> > > > diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c
> > > > index 424dc7b07858..7b3952721c17 100644
> > > > --- a/drivers/mmc/host/mmc_hsq.c
> > > > +++ b/drivers/mmc/host/mmc_hsq.c
> > > > @@ -337,6 +337,7 @@ int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc)
> > > >         hsq->mmc = mmc;
> > > >         hsq->mmc->cqe_private = hsq;
> > > >         mmc->cqe_ops = &mmc_hsq_ops;
> > > > +       mmc->hsq_depth = HSQ_MAX_DEPTH;
> > > >
> > > >         for (i = 0; i < HSQ_NUM_SLOTS; i++)
> > > >                 hsq->tag_slot[i] = HSQ_INVALID_TAG;
> > > > diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h
> > > > index 1808024fc6c5..795f6b9421d7 100644
> > > > --- a/drivers/mmc/host/mmc_hsq.h
> > > > +++ b/drivers/mmc/host/mmc_hsq.h
> > > > @@ -5,6 +5,13 @@
> > > >  #define HSQ_NUM_SLOTS  64
> > > >  #define HSQ_INVALID_TAG        HSQ_NUM_SLOTS
> > > >
> > > > +/*
> > > > + * For MMC host software queue, we usually allow 2 requests in
> > > > + * flight to avoid a long latency. But we can adjust hsq->depth
> > > > + * according to the actual situation.
> > > > + */
> > > > +#define HSQ_MAX_DEPTH  2
> > > > +
> > > >  struct hsq_slot {
> > > >         struct mmc_request *mrq;
> > > >  };
> > > > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
> > > > index 461d1543893b..1fd8b1dd8698 100644
> > > > --- a/include/linux/mmc/host.h
> > > > +++ b/include/linux/mmc/host.h
> > > > @@ -520,6 +520,7 @@ struct mmc_host {
> > > >
> > > >         /* Host Software Queue support */
> > > >         bool                    hsq_enabled;
> > > > +       int                     hsq_depth;
> > > >
> > > >         u32                     err_stats[MMC_ERR_MAX];
> > > >         unsigned long           private[] ____cacheline_aligned;
> > > > --
> > > > 2.17.1
> > > >