From: Auger Eric <eric.auger@redhat.com>
To: Keqian Zhu <zhukeqian1@huawei.com>,
eric.auger.pro@gmail.com, iommu@lists.linux-foundation.org,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
kvmarm@lists.cs.columbia.edu, will@kernel.org, joro@8bytes.org,
maz@kernel.org, robin.murphy@arm.com, alex.williamson@redhat.com
Cc: jean-philippe@linaro.org, vivek.gautam@arm.com, zhangfei.gao@linaro.org
Subject: Re: [PATCH v13 02/15] iommu: Introduce bind/unbind_guest_msi
Date: Fri, 12 Feb 2021 09:55:09 +0100 [thread overview]
Message-ID: <1ef4f5ae-9ca6-7c6d-f8a9-31240e5688c2@redhat.com> (raw)
In-Reply-To: <6a70d93d-329f-4129-bd90-03f8589c5de4@huawei.com>
Hi Keqian,
On 2/1/21 12:52 PM, Keqian Zhu wrote:
> Hi Eric,
>
> On 2020/11/18 19:21, Eric Auger wrote:
>> On ARM, MSI are translated by the SMMU. An IOVA is allocated
>> for each MSI doorbell. If both the host and the guest are exposed
>> with SMMUs, we end up with 2 different IOVAs allocated by each.
>> guest allocates an IOVA (gIOVA) to map onto the guest MSI
>> doorbell (gDB). The Host allocates another IOVA (hIOVA) to map
>> onto the physical doorbell (hDB).
>>
>> So we end up with 2 untied mappings:
>> S1 S2
>> gIOVA -> gDB
>> hIOVA -> hDB
>>
>> Currently the PCI device is programmed by the host with hIOVA
>> as MSI doorbell. So this does not work.
>>
>> This patch introduces an API to pass gIOVA/gDB to the host so
>> that gIOVA can be reused by the host instead of re-allocating
>> a new IOVA. So the goal is to create the following nested mapping:
> Does the gDB can be reused under non-nested mode?
Under non nested mode the hIOVA is allocated within the MSI reserved
region exposed by the SMMU driver, [0x8000000, 80fffff]. see
iommu_dma_prepare_msi/iommu_dma_get_msi_page in dma_iommu.c. this hIOVA
is programmed in the physical device so that the physical SMMU
translates it into the physical doorbell (hDB = host physical ITS
doorbell). The gDB is not used at pIOMMU programming level. It is only
used when setting up the KVM irq route.
Hope this answers your question.
>
>>
>> S1 S2
>> gIOVA -> gDB -> hDB
>>
>> and program the PCI device with gIOVA MSI doorbell.
>>
>> In case we have several devices attached to this nested domain
>> (devices belonging to the same group), they cannot be isolated
>> on guest side either. So they should also end up in the same domain
>> on guest side. We will enforce that all the devices attached to
>> the host iommu domain use the same physical doorbell and similarly
>> a single virtual doorbell mapping gets registered (1 single
>> virtual doorbell is used on guest as well).
>>
> [...]
>
>> + *
>> + * The associated IOVA can be reused by the host to create a nested
>> + * stage2 binding mapping translating into the physical doorbell used
>> + * by the devices attached to the domain.
>> + *
>> + * All devices within the domain must share the same physical doorbell.
>> + * A single MSI GIOVA/GPA mapping can be attached to an iommu_domain.
>> + */
>> +
>> +int iommu_bind_guest_msi(struct iommu_domain *domain,
>> + dma_addr_t giova, phys_addr_t gpa, size_t size)
>> +{
>> + if (unlikely(!domain->ops->bind_guest_msi))
>> + return -ENODEV;
>> +
>> + return domain->ops->bind_guest_msi(domain, giova, gpa, size);
>> +}
>> +EXPORT_SYMBOL_GPL(iommu_bind_guest_msi);
>> +
>> +void iommu_unbind_guest_msi(struct iommu_domain *domain,
>> + dma_addr_t iova)
> nit: s/iova/giova
sure
>
>> +{
>> + if (unlikely(!domain->ops->unbind_guest_msi))
>> + return;
>> +
>> + domain->ops->unbind_guest_msi(domain, iova);
>> +}
>> +EXPORT_SYMBOL_GPL(iommu_unbind_guest_msi);
>> +
> [...]
>
> Thanks,
> Keqian
>
Thanks
Eric
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2021-02-12 8:55 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-18 11:21 [PATCH v13 00/15] SMMUv3 Nested Stage Setup (IOMMU part) Eric Auger
2020-11-18 11:21 ` [PATCH v13 01/15] iommu: Introduce attach/detach_pasid_table API Eric Auger
2020-11-18 16:19 ` Jacob Pan
2020-11-19 17:02 ` Auger Eric
2021-02-01 11:27 ` Keqian Zhu
2021-02-01 17:18 ` Auger Eric
2020-11-18 11:21 ` [PATCH v13 02/15] iommu: Introduce bind/unbind_guest_msi Eric Auger
2021-02-01 11:52 ` Keqian Zhu
2021-02-12 8:55 ` Auger Eric [this message]
2021-02-18 8:43 ` Keqian Zhu
2021-02-18 10:35 ` Auger Eric
2020-11-18 11:21 ` [PATCH v13 03/15] iommu/arm-smmu-v3: Maintain a SID->device structure Eric Auger
2021-02-01 12:26 ` Keqian Zhu
2021-02-01 15:15 ` Jean-Philippe Brucker
2021-02-02 6:39 ` Keqian Zhu
2021-02-01 17:19 ` Auger Eric
2021-02-02 7:20 ` Keqian Zhu
2020-11-18 11:21 ` [PATCH v13 04/15] iommu/smmuv3: Allow s1 and s2 configs to coexist Eric Auger
2021-02-01 12:35 ` Keqian Zhu
2020-11-18 11:21 ` [PATCH v13 05/15] iommu/smmuv3: Get prepared for nested stage support Eric Auger
2020-11-19 3:59 ` kernel test robot
2020-12-03 12:32 ` Kunkun Jiang
2020-12-03 13:01 ` Auger Eric
2020-12-03 13:23 ` Kunkun Jiang
2020-12-09 14:26 ` Shameerali Kolothum Thodi
2021-02-02 7:14 ` Keqian Zhu
2021-02-11 17:36 ` Auger Eric
2020-11-18 11:21 ` [PATCH v13 06/15] iommu/smmuv3: Implement attach/detach_pasid_table Eric Auger
2021-02-02 8:03 ` Keqian Zhu
2021-02-11 17:35 ` Auger Eric
2020-11-18 11:21 ` [PATCH v13 07/15] iommu/smmuv3: Allow stage 1 invalidation with unmanaged ASIDs Eric Auger
2020-12-01 13:33 ` Xingang Wang
2020-12-01 13:58 ` Auger Eric
2020-12-02 12:59 ` Wang Xingang
2020-12-03 18:42 ` Shameerali Kolothum Thodi
2020-12-04 9:53 ` Jean-Philippe Brucker
2020-12-04 10:20 ` Shameerali Kolothum Thodi
2020-12-04 10:23 ` Auger Eric
2021-01-14 16:58 ` Auger Eric
2021-01-14 17:09 ` Shameerali Kolothum Thodi
2021-01-14 17:33 ` Jean-Philippe Brucker
2021-01-14 18:00 ` Auger Eric
2021-02-15 13:17 ` Auger Eric
2020-11-18 11:21 ` [PATCH v13 08/15] iommu/smmuv3: Implement cache_invalidate Eric Auger
2021-01-16 2:24 ` chenxiang (M)
2020-11-18 11:21 ` [PATCH v13 09/15] dma-iommu: Implement NESTED_MSI cookie Eric Auger
2020-11-18 11:21 ` [PATCH v13 10/15] iommu/smmuv3: Nested mode single MSI doorbell per domain enforcement Eric Auger
2020-11-18 11:21 ` [PATCH v13 11/15] iommu/smmuv3: Enforce incompatibility between nested mode and HW MSI regions Eric Auger
2020-11-18 11:21 ` [PATCH v13 12/15] iommu/smmuv3: Implement bind/unbind_guest_msi Eric Auger
2020-11-18 11:21 ` [PATCH v13 13/15] iommu/smmuv3: Report non recoverable faults Eric Auger
2020-11-18 11:21 ` [PATCH v13 14/15] iommu/smmuv3: Accept configs with more than one context descriptor Eric Auger
2020-11-18 11:21 ` [PATCH v13 15/15] iommu/smmuv3: Add PASID cache invalidation per PASID Eric Auger
2021-01-08 17:05 ` [PATCH v13 00/15] SMMUv3 Nested Stage Setup (IOMMU part) Shameerali Kolothum Thodi
2021-01-13 15:37 ` Auger Eric
2021-02-21 18:21 ` Auger Eric
2021-02-22 8:56 ` Shameerali Kolothum Thodi
2021-03-15 18:04 ` Krishna Reddy
2021-03-16 8:22 ` Auger Eric
2021-03-16 18:10 ` Krishna Reddy
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=1ef4f5ae-9ca6-7c6d-f8a9-31240e5688c2@redhat.com \
--to=eric.auger@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=eric.auger.pro@gmail.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jean-philippe@linaro.org \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=robin.murphy@arm.com \
--cc=vivek.gautam@arm.com \
--cc=will@kernel.org \
--cc=zhangfei.gao@linaro.org \
--cc=zhukeqian1@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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;
as well as URLs for NNTP newsgroup(s).