linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Auger Eric <eric.auger@redhat.com>
To: Robin Murphy <robin.murphy@arm.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, joro@8bytes.org,
	alex.williamson@redhat.com, jacob.jun.pan@linux.intel.com,
	yi.l.liu@intel.com, jean-philippe.brucker@arm.com,
	will.deacon@arm.com
Cc: kevin.tian@intel.com, ashok.raj@intel.com, marc.zyngier@arm.com,
	christoffer.dall@arm.com, peter.maydell@linaro.org,
	vincent.stehle@arm.com
Subject: Re: [PATCH v7 14/23] iommu/smmuv3: Implement cache_invalidate
Date: Mon, 13 May 2019 14:16:02 +0200	[thread overview]
Message-ID: <edff2a6f-66e6-6d7e-49ca-3065e93a41a4@redhat.com> (raw)
In-Reply-To: <a53d72f5-c8a2-a9e9-eb0b-2fac65964caf@arm.com>

Hi Robin,
On 5/8/19 5:01 PM, Robin Murphy wrote:
> On 08/04/2019 13:19, Eric Auger wrote:
>> Implement domain-selective and page-selective IOTLB invalidations.
>>
>> Signed-off-by: Eric Auger <eric.auger@redhat.com>
>>
>> ---
>> v6 -> v7
>> - check the uapi version
>>
>> v3 -> v4:
>> - adapt to changes in the uapi
>> - add support for leaf parameter
>> - do not use arm_smmu_tlb_inv_range_nosync or arm_smmu_tlb_inv_context
>>    anymore
>>
>> v2 -> v3:
>> - replace __arm_smmu_tlb_sync by arm_smmu_cmdq_issue_sync
>>
>> v1 -> v2:
>> - properly pass the asid
>> ---
>>   drivers/iommu/arm-smmu-v3.c | 60 +++++++++++++++++++++++++++++++++++++
>>   1 file changed, 60 insertions(+)
>>
>> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
>> index 1486baf53425..4366921d8318 100644
>> --- a/drivers/iommu/arm-smmu-v3.c
>> +++ b/drivers/iommu/arm-smmu-v3.c
>> @@ -2326,6 +2326,65 @@ static void arm_smmu_detach_pasid_table(struct
>> iommu_domain *domain)
>>       mutex_unlock(&smmu_domain->init_mutex);
>>   }
>>   +static int
>> +arm_smmu_cache_invalidate(struct iommu_domain *domain, struct device
>> *dev,
>> +              struct iommu_cache_invalidate_info *inv_info)
>> +{
>> +    struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
>> +    struct arm_smmu_device *smmu = smmu_domain->smmu;
>> +
>> +    if (smmu_domain->stage != ARM_SMMU_DOMAIN_NESTED)
>> +        return -EINVAL;
>> +
>> +    if (!smmu)
>> +        return -EINVAL;
>> +
>> +    if (inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
>> +        return -EINVAL;
>> +
>> +    if (inv_info->cache & IOMMU_CACHE_INV_TYPE_IOTLB) {
>> +        if (inv_info->granularity == IOMMU_INV_GRANU_PASID) {
>> +            struct arm_smmu_cmdq_ent cmd = {
>> +                .opcode = CMDQ_OP_TLBI_NH_ASID,
>> +                .tlbi = {
>> +                    .vmid = smmu_domain->s2_cfg.vmid,
>> +                    .asid = inv_info->pasid,
>> +                },
>> +            };
>> +
>> +            arm_smmu_cmdq_issue_cmd(smmu, &cmd);
>> +            arm_smmu_cmdq_issue_sync(smmu);
> 
> I'd much rather make arm_smmu_tlb_inv_context() understand nested
> domains than open-code commands all over the place.


> 
>> +
>> +        } else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) {
>> +            struct iommu_inv_addr_info *info = &inv_info->addr_info;
>> +            size_t size = info->nb_granules * info->granule_size;
>> +            bool leaf = info->flags & IOMMU_INV_ADDR_FLAGS_LEAF;
>> +            struct arm_smmu_cmdq_ent cmd = {
>> +                .opcode = CMDQ_OP_TLBI_NH_VA,
>> +                .tlbi = {
>> +                    .addr = info->addr,
>> +                    .vmid = smmu_domain->s2_cfg.vmid,
>> +                    .asid = info->pasid,
>> +                    .leaf = leaf,
>> +                },
>> +            };
>> +
>> +            do {
>> +                arm_smmu_cmdq_issue_cmd(smmu, &cmd);
>> +                cmd.tlbi.addr += info->granule_size;
>> +            } while (size -= info->granule_size);
>> +            arm_smmu_cmdq_issue_sync(smmu);
> 
> An this in particular I would really like to go all the way through
> io_pgtable_tlb_add_flush()/io_pgtable_sync() if at all possible. Hooking
> up range-based invalidations is going to be a massive headache if the
> abstraction isn't solid.

The concern is the host does not "own" the s1 config asid
(smmu_domain->s1_cfg.cd.asid is not set, practically). In our case the
asid only is passed by the userspace on CACHE_INVALIDATE ioctl call.

arm_smmu_tlb_inv_context and arm_smmu_tlb_inv_range_nosync use this field

Jean-Philippe highlighted that fact in
https://lkml.org/lkml/2019/1/11/1062 and suggested to open-code commands
instead, hence the current form.

Thanks

Eric
> 
> Robin.
> 
>> +        } else {
>> +            return -EINVAL;
>> +        }
>> +    }
>> +    if (inv_info->cache & IOMMU_CACHE_INV_TYPE_PASID ||
>> +        inv_info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB) {
>> +        return -ENOENT;
>> +    }
>> +    return 0;
>> +}
>> +
>>   static struct iommu_ops arm_smmu_ops = {
>>       .capable        = arm_smmu_capable,
>>       .domain_alloc        = arm_smmu_domain_alloc,
>> @@ -2346,6 +2405,7 @@ static struct iommu_ops arm_smmu_ops = {
>>       .put_resv_regions    = arm_smmu_put_resv_regions,
>>       .attach_pasid_table    = arm_smmu_attach_pasid_table,
>>       .detach_pasid_table    = arm_smmu_detach_pasid_table,
>> +    .cache_invalidate    = arm_smmu_cache_invalidate,
>>       .pgsize_bitmap        = -1UL, /* Restricted during device attach */
>>   };
>>  

  reply	other threads:[~2019-05-13 12:16 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-08 12:18 [PATCH v7 00/23] SMMUv3 Nested Stage Setup Eric Auger
2019-04-08 12:18 ` [PATCH v7 01/23] driver core: add per device iommu param Eric Auger
2019-04-08 12:18 ` [PATCH v7 02/23] iommu: introduce device fault data Eric Auger
2019-04-08 12:18 ` [PATCH v7 03/23] iommu: introduce device fault report API Eric Auger
2019-04-08 12:18 ` [PATCH v7 04/23] iommu: Introduce attach/detach_pasid_table API Eric Auger
2019-05-15 12:09   ` Jean-Philippe Brucker
2019-05-15 13:06     ` Auger Eric
2019-05-15 15:57       ` Jean-Philippe Brucker
2019-04-08 12:18 ` [PATCH v7 05/23] iommu: Introduce cache_invalidate API Eric Auger
2019-05-01 10:38   ` Jean-Philippe Brucker
2019-05-02  6:58     ` Auger Eric
2019-05-02 10:53       ` Jean-Philippe Brucker
2019-05-02 16:46         ` Jacob Pan
2019-05-07 11:45           ` Jean-Philippe Brucker
2019-04-08 12:18 ` [PATCH v7 06/23] iommu: Introduce bind/unbind_guest_msi Eric Auger
2019-05-08 13:59   ` Robin Murphy
2019-05-10 14:35     ` Auger Eric
2019-04-08 12:18 ` [PATCH v7 07/23] vfio: VFIO_IOMMU_ATTACH/DETACH_PASID_TABLE Eric Auger
2019-04-08 12:18 ` [PATCH v7 08/23] vfio: VFIO_IOMMU_CACHE_INVALIDATE Eric Auger
2019-04-08 12:18 ` [PATCH v7 09/23] vfio: VFIO_IOMMU_BIND/UNBIND_MSI Eric Auger
2019-04-08 12:18 ` [PATCH v7 10/23] iommu/arm-smmu-v3: Link domains and devices Eric Auger
2019-04-08 12:18 ` [PATCH v7 11/23] iommu/arm-smmu-v3: Maintain a SID->device structure Eric Auger
2019-05-08 14:05   ` Robin Murphy
2019-05-08 18:31     ` Jean-Philippe Brucker
2019-04-08 12:19 ` [PATCH v7 12/23] iommu/smmuv3: Get prepared for nested stage support Eric Auger
2019-05-08 14:24   ` Robin Murphy
2019-05-10 14:34     ` Auger Eric
2019-05-13 11:43       ` Robin Murphy
2019-05-13 14:40         ` Auger Eric
2019-04-08 12:19 ` [PATCH v7 13/23] iommu/smmuv3: Implement attach/detach_pasid_table Eric Auger
2019-05-08 14:38   ` Robin Murphy
2019-05-10 14:35     ` Auger Eric
2019-05-13 12:04       ` Robin Murphy
2019-04-08 12:19 ` [PATCH v7 14/23] iommu/smmuv3: Implement cache_invalidate Eric Auger
2019-05-08 15:01   ` Robin Murphy
2019-05-13 12:16     ` Auger Eric [this message]
2019-05-13 14:01       ` Robin Murphy
2019-05-13 14:04         ` Auger Eric
2019-04-08 12:19 ` [PATCH v7 15/23] dma-iommu: Implement NESTED_MSI cookie Eric Auger
2019-05-08 16:42   ` Robin Murphy
2019-04-08 12:19 ` [PATCH v7 16/23] iommu/smmuv3: Nested mode single MSI doorbell per domain enforcement Eric Auger
2019-04-08 12:19 ` [PATCH v7 17/23] iommu/smmuv3: Implement bind/unbind_guest_msi Eric Auger
2019-04-08 12:19 ` [PATCH v7 18/23] iommu/smmuv3: Report non recoverable faults Eric Auger
2019-05-08 17:20   ` Robin Murphy
2019-05-13  7:46     ` Auger Eric
2019-05-13 11:54       ` Robin Murphy
2019-05-13 12:32         ` Auger Eric
2019-05-13 13:47           ` Robin Murphy
2019-04-08 12:19 ` [PATCH v7 19/23] vfio-pci: Add a new VFIO_REGION_TYPE_NESTED region type Eric Auger
2019-04-08 12:19 ` [PATCH v7 20/23] vfio-pci: Register an iommu fault handler Eric Auger
2019-04-08 12:19 ` [PATCH v7 21/23] vfio_pci: Allow to mmap the fault queue Eric Auger
2019-04-08 12:19 ` [PATCH v7 22/23] vfio-pci: Add VFIO_PCI_DMA_FAULT_IRQ_INDEX Eric Auger
2019-04-08 12:19 ` [PATCH v7 23/23] vfio: Document nested stage control Eric Auger
2019-04-30  7:09 ` [PATCH v7 00/23] SMMUv3 Nested Stage Setup Auger Eric

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=edff2a6f-66e6-6d7e-49ca-3065e93a41a4@redhat.com \
    --to=eric.auger@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=christoffer.dall@arm.com \
    --cc=eric.auger.pro@gmail.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jean-philippe.brucker@arm.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marc.zyngier@arm.com \
    --cc=peter.maydell@linaro.org \
    --cc=robin.murphy@arm.com \
    --cc=vincent.stehle@arm.com \
    --cc=will.deacon@arm.com \
    --cc=yi.l.liu@intel.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).