public inbox for linux-arm-kernel@lists.infradead.org 
 help / color / mirror / Atom feed
From: will.deacon@arm•com (Will Deacon)
To: linux-arm-kernel@lists•infradead.org
Subject: [PATCH 3/5] iommu/arm-smmu-v3: add IOMMU_CAP_BYPASS to the ARM SMMUv3 driver
Date: Wed, 19 Jul 2017 12:25:24 +0100	[thread overview]
Message-ID: <20170719112524.GF13642@arm.com> (raw)
In-Reply-To: <CAALAos8y0kLGrbwgz3u=ZVyteSicuPyQZ3Yp=LPZohXzVaE5NQ@mail.gmail.com>

On Wed, Jul 19, 2017 at 04:53:04PM +0530, Anup Patel wrote:
> On Wed, Jul 19, 2017 at 4:30 PM, Robin Murphy <robin.murphy@arm•com> wrote:
> > On 19/07/17 10:33, Anup Patel wrote:
> >> The ARM SMMUv3 support bypassing transactions for which domain
> >> is not configured. The patch adds corresponding IOMMU capability
> >> to advertise this fact.
> >>
> >> Signed-off-by: Anup Patel <anup.patel@broadcom•com>
> >> ---
> >>  drivers/iommu/arm-smmu-v3.c | 2 ++
> >>  1 file changed, 2 insertions(+)
> >>
> >> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> >> index 568c400..a6c7f66 100644
> >> --- a/drivers/iommu/arm-smmu-v3.c
> >> +++ b/drivers/iommu/arm-smmu-v3.c
> >> @@ -1423,6 +1423,8 @@ static bool arm_smmu_capable(enum iommu_cap cap)
> >>               return true;
> >>       case IOMMU_CAP_NOEXEC:
> >>               return true;
> >> +     case IOMMU_CAP_BYPASS:
> >> +             return true;
> >
> > And this is never true. If Linux knows a device masters through the
> > SMMU, it will always have a default domain of some sort (either identity
> > or DMA ops). If Linux doesn't know, then it won't have been able to
> > initialise the stream table for the relevant stream IDs, thus any
> > 'bypass' DMA is going to raise C_BAD_STE. SMMUv3 can effectively only
> > bypass unknown stream IDs if disabled entirely.
> 
> What if we don't want to use IOMMU for certain device and
> due to this we never provide "iommus" DT attribute in the
> device DT node. Further, we want to access device without
> "iommus" DT attribute from user-space using VFIO no-IOMMU.

Wait, you want to pass a device through to userspace but you don't want to
use the IOMMU? Why not?

If you describe the SMMU in firmware with only a partial topology
description, then you will run into problems with unknown masters trying to
perform DMA. That's the IOMMU doing its job!

Will

  reply	other threads:[~2017-07-19 11:25 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-19  9:33 [PATCH 0/5] FlexRM support in VFIO platform Anup Patel
2017-07-19  9:33 ` [PATCH 1/5] iommu: Add capability IOMMU_CAP_BYPASS Anup Patel
2017-07-19 10:58   ` Robin Murphy
2017-07-19 11:19     ` Anup Patel
2017-07-19 11:23       ` Will Deacon
2017-07-19 11:26         ` Anup Patel
2017-07-19 11:29           ` Robin Murphy
2017-07-19 11:30           ` Will Deacon
2017-07-19 11:33             ` Anup Patel
2017-07-19  9:33 ` [PATCH 2/5] iommu/arm-smmu: add IOMMU_CAP_BYPASS to the ARM SMMU driver Anup Patel
2017-07-19 10:59   ` Robin Murphy
2017-07-19  9:33 ` [PATCH 3/5] iommu/arm-smmu-v3: add IOMMU_CAP_BYPASS to the ARM SMMUv3 driver Anup Patel
2017-07-19 11:00   ` Robin Murphy
2017-07-19 11:23     ` Anup Patel
2017-07-19 11:25       ` Will Deacon [this message]
2017-07-19 11:31         ` Anup Patel
2017-07-19 11:33           ` Will Deacon
2017-07-19 11:39             ` Anup Patel
2017-07-19 11:53               ` Will Deacon
2017-07-20  4:02                 ` Anup Patel
2017-07-20  9:10                   ` Will Deacon
2017-07-20 11:08                     ` Anup Patel
2017-07-20 11:17                       ` Will Deacon
2017-07-20 11:17                     ` Robin Murphy
2017-07-24 17:16                       ` Alex Williamson
2017-07-24 17:23                         ` Robin Murphy
2017-07-24 19:06                           ` Alex Williamson
2017-07-25  8:59                             ` Anup Patel
2017-07-19  9:33 ` [PATCH 4/5] vfio: Allow No-IOMMU mode for IOMMUs with bypass capability Anup Patel
2017-07-19  9:33 ` [PATCH 5/5] vfio: platform: reset: Add Broadcom FlexRM reset module Anup Patel
2017-07-19 16:50   ` Scott Branden
2017-07-20  4:05     ` Anup Patel
2017-07-19 10:57 ` [PATCH 0/5] FlexRM support in VFIO platform Robin Murphy
2017-07-19 11:17   ` Anup Patel
2017-07-19 11:25     ` Robin Murphy
2017-07-19 11:28       ` Anup Patel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170719112524.GF13642@arm.com \
    --to=will.deacon@arm$(echo .)com \
    --cc=linux-arm-kernel@lists$(echo .)infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox