Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 9 Mar 2021 18:33:51 +0100
From:   Jean-Philippe Brucker <jean-philippe@linaro.org>
To:     Felix Kuehling <felix.kuehling@amd.com>
Cc:     Arnd Bergmann <arnd@kernel.org>,
        "Suthikulpanit, Suravee" <Suravee.Suthikulpanit@amd.com>,
        David Airlie <airlied@linux.ie>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        dri-devel <dri-devel@lists.freedesktop.org>,
        "open list:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
        amd-gfx list <amd-gfx@lists.freedesktop.org>,
        Alex Deucher <alexander.deucher@amd.com>,
        Will Deacon <will@kernel.org>,
        Christian =?utf-8?B?S8O2bmln?= <christian.koenig@amd.com>
Subject: Re: [PATCH 1/1] drm/amdkfd: fix build error with AMD_IOMMU_V2=m
Message-ID: <YEexf0/V/YF394bf@myrica>
References: <4c692eff-9d57-278e-8da4-36bc2c293506@amd.com>
 <20210309032356.20800-1-Felix.Kuehling@amd.com>
 <CAK8P3a1EeHimbufajcHzV+-bBarWtLHzzFSsa=qdUDsip=Wz_A@mail.gmail.com>
 <8023bb6b-b6aa-230c-afa5-871ce32782c6@amd.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <8023bb6b-b6aa-230c-afa5-871ce32782c6@amd.com>
Precedence: bulk

Hi Felix,

On Tue, Mar 09, 2021 at 11:30:19AM -0500, Felix Kuehling wrote:
> > I think the proper fix would be to not rely on custom hooks into a particular
> > IOMMU driver, but to instead ensure that the amdgpu driver can do everything
> > it needs through the regular linux/iommu.h interfaces. I realize this
> > is more work,
> > but I wonder if you've tried that, and why it didn't work out.
> 
> As far as I know this hasn't been tried. I see that intel-iommu has its
> own SVM thing, which seems to be similar to what our IOMMUv2 does. I
> guess we'd have to abstract that into a common API.

The common API was added in 26b25a2b98e4 and implemented by the Intel
driver in 064a57d7ddfc. To support it an IOMMU driver implements new IOMMU
ops:
	.dev_has_feat()
	.dev_feat_enabled()
	.dev_enable_feat()
	.dev_disable_feat()
	.sva_bind()
	.sva_unbind()
	.sva_get_pasid()

And a device driver calls iommu_dev_enable_feature(IOMMU_DEV_FEAT_SVA)
followed by iommu_sva_bind_device().

If I remember correctly the biggest obstacle for KFD is the PASID
allocation, done by the GPU driver instead of the IOMMU driver, but there
may be others.

Thanks,
Jean