Hi Eric,
> From: Auger Eric
> Sent: Saturday, July 18, 2020 1:14 AM
>
> Hi Yi,
>
> Missing a proper commit message. You can comment on the fact you only
> support the case where all the physical iomms have the same CAP/ECAP MASKS
got it. will add it. it looks like the subject is straightforward, so I removed
commit
message.
>
> On 7/12/20 1:21 PM, Liu Yi L wrote:
> > Cc: Kevin Tian
> > CC: Jacob Pan
> > Cc: Alex Williamson
> > Cc: Eric Auger
> > Cc: Jean-Philippe Brucker
> > Cc: Joerg Roedel
> > Cc: Lu Baolu
> > Signed-off-by: Liu Yi L
> > Signed-off-by: Jacob Pan
> > ---
> > v2 -> v3:
> > *) remove cap/ecap_mask in iommu_nesting_info.
> > ---
> > drivers/iommu/intel/iommu.c | 81
> +++--
> > include/linux/intel-iommu.h | 16 +
> > 2 files changed, 95 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
> > index a9504cb..9f7ad1a 100644
> > --- a/drivers/iommu/intel/iommu.c
> > +++ b/drivers/iommu/intel/iommu.c
> > @@ -5659,12 +5659,16 @@ static inline bool iommu_pasid_support(void)
> > static inline bool nested_mode_support(void)
> > {
> > struct dmar_drhd_unit *drhd;
> > - struct intel_iommu *iommu;
> > + struct intel_iommu *iommu, *prev = NULL;
> > bool ret = true;
> >
> > rcu_read_lock();
> > for_each_active_iommu(iommu, drhd) {
> > - if (!sm_supported(iommu) || !ecap_nest(iommu->ecap)) {
> > + if (!prev)
> > + prev = iommu;
> > + if (!sm_supported(iommu) || !ecap_nest(iommu->ecap) ||
> > + (VTD_CAP_MASK & (iommu->cap ^ prev->cap)) ||
> > + (VTD_ECAP_MASK & (iommu->ecap ^ prev->ecap))) {
> > ret = false;
> > break;> }
> > @@ -6079,6 +6083,78 @@ intel_iommu_domain_set_attr(struct iommu_domain
> *domain,
> > return ret;
> > }
> >
> > +static int intel_iommu_get_nesting_info(struct iommu_domain *domain,
> > + struct iommu_nesting_info *info)
> > +{
> > + struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> > + u64 cap = VTD_CAP_MASK, ecap = VTD_ECAP_MASK;
> > + struct device_domain_info *domain_info;
> > + struct iommu_nesting_info_vtd vtd;
> > + unsigned long flags;
> > + unsigned int size;
> > +
> > + if (domain->type != IOMMU_DOMAIN_UNMANAGED ||
> > + !(dmar_domain->flags & DOMAIN_FLAG_NESTING_MODE))
> > + return -ENODEV;
> > +
> > + if (!info)
> > + return -EINVAL;
> > +
> > + size = sizeof(struct iommu_nesting_info) +
> > + sizeof(struct iommu_nesting_info_vtd);
> > + /*
> > +* if provided buffer size is smaller than expected, should
> > +* return 0 and also the expected buffer size to caller.
> > +*/
> > + if (info->size < size) {
> > + info->size = size;
> > + return 0;
> > + }
> > +
> > + spin_lock_irqsave(&device_domain_lock, flags);
> > + /*
> > +* arbitrary select the first domain_info as all nesting
> > +* related capabilities should be consistent across iommu
> > +* units.
> > +*/
> > + domain_info = list_first_entry(&dmar_domain->devices,
> > + struct device_domain_info, link);
> > + cap &= domain_info->iommu->cap;
> > + ecap &= domain_info->iommu->ecap;
> > + spin_unlock_irqrestore(&device_domain_lock, flags);
> > +
> > + info->format = IOMMU_PASID_FORMAT_INTEL_VTD;
> > + info->features = IOMMU_NESTING_FEAT_SYSWIDE_PASID |
> > +IOMMU_NESTING_FEAT_BIND_PGTBL |
> > +IOMMU_NESTING_FEAT_CACHE_INVLD;
> > + info->addr_width = dmar_domain->gaw;
> > + info->pasid_bits = ilog2(intel_pasid_max_id);
> > + info->padding = 0;
> > + vtd.flags = 0;
> > + vtd.padding = 0;
> > + vtd.cap_reg = cap;
> > + vtd.ecap_reg = ecap;
> > +
> > + memcpy(info->data, &vtd, sizeof(vtd));
> > + return 0;
> > +}
> > +
> > +static int intel_iommu_domain_get_attr(struct iommu_domain *domain,
> > + enum iommu_attr attr, void *data)
> > +{
> > + switch (attr) {
> > + case DOMAIN_ATTR_NESTING:
> > + {
> > + struct iommu_nesting_info *info =
> > + (struct iommu_nesting_info *)data;
> > +
> > + return intel_iommu_get_nesting_info(domain, info);
> > + }
> > + default:
> > + return -ENODEV;
> -ENOENT?
arm_smmu_domain_get_attr() is using -ENODEV, so I used the same. I can
modify it if -ENOENT is better. :-)
Regards,
Yi Liu
> > + }
> > +}
> > +
> > /*
> > * Check that the device does not live on an external facing PCI port that
> > is
> > * marked as untrusted. Such devices should not be able to apply quirks and
> > @@ -6101,6 +6177,7 @@ const struct iommu_ops intel_iommu_ops = {
> > .domain_alloc = intel_iommu_domain_alloc,
> > .domain_free= intel_iommu_domain_free,
>