On Thu, 31 Oct 2024 at 08:21, Jason Gunthorpe <jgg@xxxxxxxxxx> wrote:
>
> For SMMUv3 a IOMMU_DOMAIN_NESTED is composed of a S2 iommu_domain acting
> as the parent and a user provided STE fragment that defines the CD table
> and related data with addresses translated by the S2 iommu_domain.
>
> The kernel only permits userspace to control certain allowed bits of the
> STE that are safe for user/guest control.
>
> IOTLB maintenance is a bit subtle here, the S1 implicitly includes the S2
> translation, but there is no way of knowing which S1 entries refer to a
> range of S2.
>
> For the IOTLB we follow ARM's guidance and issue a CMDQ_OP_TLBI_NH_ALL to
> flush all ASIDs from the VMID after flushing the S2 on any change to the
> S2.
>
> The IOMMU_DOMAIN_NESTED can only be created from inside a VIOMMU as the
> invalidation path relies on the VIOMMU to translate virtual stream ID used
> in the invalidation commands for the CD table and ATS.
>
> Reviewed-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
> Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
> Reviewed-by: Jerry Snitselaar <jsnitsel@xxxxxxxxxx>
> Reviewed-by: Donald Dutile <ddutile@xxxxxxxxxx>
> Signed-off-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
> Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
> ---
> .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 157 ++++++++++++++++++
> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 17 +-
> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 26 +++
> include/uapi/linux/iommufd.h | 20 +++
> 4 files changed, 219 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
> index 60dd9e90759571..0b9fffc5b2f09b 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
> @@ -30,7 +30,164 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type)
> return info;
> }
>
> +static void arm_smmu_make_nested_cd_table_ste(
> + struct arm_smmu_ste *target, struct arm_smmu_master *master,
> + struct arm_smmu_nested_domain *nested_domain, bool ats_enabled)
> +{
> + arm_smmu_make_s2_domain_ste(
> + target, master, nested_domain->vsmmu->s2_parent, ats_enabled);
> +
> + target->data[0] = cpu_to_le64(STRTAB_STE_0_V |
> + FIELD_PREP(STRTAB_STE_0_CFG,
> + STRTAB_STE_0_CFG_NESTED));
> + target->data[0] |= nested_domain->ste[0] &
> + ~cpu_to_le64(STRTAB_STE_0_CFG);
> + target->data[1] |= nested_domain->ste[1];
> +}
> +
> +/*
> + * Create a physical STE from the virtual STE that userspace provided when it
> + * created the nested domain. Using the vSTE userspace can request:
> + * - Non-valid STE
> + * - Abort STE
> + * - Bypass STE (install the S2, no CD table)
> + * - CD table STE (install the S2 and the userspace CD table)
> + */
> +static void arm_smmu_make_nested_domain_ste(
> + struct arm_smmu_ste *target, struct arm_smmu_master *master,
> + struct arm_smmu_nested_domain *nested_domain, bool ats_enabled)
> +{
> + unsigned int cfg =
> + FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(nested_domain->ste[0]));
> +
> + /*
> + * Userspace can request a non-valid STE through the nesting interface.
> + * We relay that into an abort physical STE with the intention that
> + * C_BAD_STE for this SID can be generated to userspace.
> + */
> + if (!(nested_domain->ste[0] & cpu_to_le64(STRTAB_STE_0_V)))
> + cfg = STRTAB_STE_0_CFG_ABORT;
> +
> + switch (cfg) {
> + case STRTAB_STE_0_CFG_S1_TRANS:
> + arm_smmu_make_nested_cd_table_ste(target, master, nested_domain,
> + ats_enabled);
> + break;
> + case STRTAB_STE_0_CFG_BYPASS:
> + arm_smmu_make_s2_domain_ste(target, master,
> + nested_domain->vsmmu->s2_parent,
> + ats_enabled);
> + break;
> + case STRTAB_STE_0_CFG_ABORT:
> + default:
> + arm_smmu_make_abort_ste(target);
> + break;
> + }
> +}
> +
> +static int arm_smmu_attach_dev_nested(struct iommu_domain *domain,
> + struct device *dev)
> +{
> + struct arm_smmu_nested_domain *nested_domain =
> + to_smmu_nested_domain(domain);
> + struct arm_smmu_master *master = dev_iommu_priv_get(dev);
> + struct arm_smmu_attach_state state = {
> + .master = master,
> + .old_domain = iommu_get_domain_for_dev(dev),
> + .ssid = IOMMU_NO_PASID,
> + /* Currently invalidation of ATC is not supported */
> + .disable_ats = true,
> + };
> + struct arm_smmu_ste ste;
> + int ret;
> +
> + if (nested_domain->vsmmu->smmu != master->smmu)
> + return -EINVAL;
> + if (arm_smmu_ssids_in_use(&master->cd_table))
> + return -EBUSY;
> +
> + mutex_lock(&arm_smmu_asid_lock);
> + ret = arm_smmu_attach_prepare(&state, domain);
> + if (ret) {
> + mutex_unlock(&arm_smmu_asid_lock);
> + return ret;
> + }
> +
> + arm_smmu_make_nested_domain_ste(&ste, master, nested_domain,
> + state.ats_enabled);
> + arm_smmu_install_ste_for_dev(master, &ste);
> + arm_smmu_attach_commit(&state);
> + mutex_unlock(&arm_smmu_asid_lock);
> + return 0;
> +}
> +
> +static void arm_smmu_domain_nested_free(struct iommu_domain *domain)
> +{
> + kfree(to_smmu_nested_domain(domain));
> +}
> +
> +static const struct iommu_domain_ops arm_smmu_nested_ops = {
> + .attach_dev = arm_smmu_attach_dev_nested,
> + .free = arm_smmu_domain_nested_free,
> +};
> +
> +static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg)
> +{
> + unsigned int cfg;
> +
> + if (!(arg->ste[0] & cpu_to_le64(STRTAB_STE_0_V))) {
> + memset(arg->ste, 0, sizeof(arg->ste));
> + return 0;
> + }
> +
> + /* EIO is reserved for invalid STE data. */
> + if ((arg->ste[0] & ~STRTAB_STE_0_NESTING_ALLOWED) ||
> + (arg->ste[1] & ~STRTAB_STE_1_NESTING_ALLOWED))
> + return -EIO;
> +
> + cfg = FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(arg->ste[0]));
> + if (cfg != STRTAB_STE_0_CFG_ABORT && cfg != STRTAB_STE_0_CFG_BYPASS &&
> + cfg != STRTAB_STE_0_CFG_S1_TRANS)
> + return -EIO;
> + return 0;
> +}
> +
> +static struct iommu_domain *
> +arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags,
> + const struct iommu_user_data *user_data)
> +{
> + struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core);
> + struct arm_smmu_nested_domain *nested_domain;
> + struct iommu_hwpt_arm_smmuv3 arg;
> + int ret;
> +
> + if (flags)
> + return ERR_PTR(-EOPNOTSUPP);
This check fails when using user page fault, with flags =
IOMMU_HWPT_FAULT_ID_VALID (4)
Strange, the check is not exist in last version?
iommufd_viommu_alloc_hwpt_nested ->
viommu->ops->alloc_domain_nested(viommu, flags, user_data) ->
arm_vsmmu_alloc_domain_nested
Thanks
