RE: [RFC PATCH] mmc: core: Disable REQ_FUA if the eMMC supports an internal cache

[Avri Altman]

> On Fri, 3 Mar 2023 at 10:39, Avri Altman <Avri.Altman@xxxxxxx> wrote:
> >
> > > On 02.03.23 3:43 PM, Ulf Hansson wrote:
> > > > REQ_FUA is in general supported for eMMC cards, which translates
> > > > into so called "reliable writes". To support these write
> > > > operations, the
> > > > CMD23 (MMC_CAP_CMD23), needs to be supported by the mmc host
> too,
> > > > which is common but not always the case.
> > > >
> > > > For some eMMC devices, it has been reported that reliable writes
> > > > are quite costly, leading to performance degradations.
> > > >
> > > > In a way to improve the situation, let's avoid announcing REQ_FUA
> > > > support if the eMMC supports an internal cache, as that allows us
> > > > to rely solely on flush-requests (REQ_OP_FLUSH) instead, which
> > > > seems to be a
> > > lot cheaper.
> > > > Note that, those mmc hosts that lacks CMD23 support are already
> > > > using this type of configuration, whatever that could mean.
> > > >
> > > > Reported-by: Wenchao Chen<wenchao.chen666@xxxxxxxxx>
> > > > Signed-off-by: Ulf Hansson<ulf.hansson@xxxxxxxxxx>
> > > Acked-by: Bean Huo <beanhuo@xxxxxxxxxx>
> > Acked-by: Avri Altman <avri.altman@xxxxxxx>
> 
> Thanks!
> 
> >
> > Another option might be, allowing to report "broken_fua", should the
> > platform owner chooses to, much like scsi does per sdev.
> 
> Are you suggesting a static or dynamic configuration option?
Static

> 
> For mmc, we also have the card quirks that may be used to configure the
> support for FUA, based upon what would work best for the card. Is that
> what you were thinking of?
I was thinking to allow the platform owner the flexibility to decide if to use it or not,
More like SDHCI_QUIRK_xxx

But I am totally fine with your current suggestions.

Thanks,
Avri

> 
> >
> > Thanks,
> > Avri
> 
> Kind regards
> Uffe