Re: [PATCH 4/4] iommu/vt-d: Add page response ops support

[Lu Baolu]

Hi Kevin,

On 6/30/20 2:19 PM, Tian, Kevin wrote:
> > From: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> > Sent: Sunday, June 28, 2020 8:34 AM
> >
> > After a page request is handled, software must response the device which
> > raised the page request with the handling result. This is done through
> > the iommu ops.page_response if the request was reported to outside of
> > vendor iommu driver through iommu_report_device_fault(). This adds the
> > VT-d implementation of page_response ops.
> >
> > Co-developed-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> > Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> > Co-developed-by: Liu Yi L <yi.l.liu@xxxxxxxxx>
> > Signed-off-by: Liu Yi L <yi.l.liu@xxxxxxxxx>
> > Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> > ---
> >   drivers/iommu/intel/iommu.c |  1 +
> >   drivers/iommu/intel/svm.c   | 73
> > +++++++++++++++++++++++++++++++++++++
> >   include/linux/intel-iommu.h |  3 ++
> >   3 files changed, 77 insertions(+)
> >
> > diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
> > index de17952ed133..7eb29167e8f9 100644
> > --- a/drivers/iommu/intel/iommu.c
> > +++ b/drivers/iommu/intel/iommu.c
> > @@ -6057,6 +6057,7 @@ const struct iommu_ops intel_iommu_ops = {
> >   	.sva_bind		= intel_svm_bind,
> >   	.sva_unbind		= intel_svm_unbind,
> >   	.sva_get_pasid		= intel_svm_get_pasid,
> > +	.page_response		= intel_svm_page_response,
> >   #endif
> >   };
> >
> > diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
> > index 4800bb6f8794..003ea9579632 100644
> > --- a/drivers/iommu/intel/svm.c
> > +++ b/drivers/iommu/intel/svm.c
> > @@ -1092,3 +1092,76 @@ int intel_svm_get_pasid(struct iommu_sva *sva)
> >
> >   	return pasid;
> >   }
> > +
> > +int intel_svm_page_response(struct device *dev,
> > +			    struct iommu_fault_event *evt,
> > +			    struct iommu_page_response *msg)
> > +{
> > +	struct iommu_fault_page_request *prm;
> > +	struct intel_svm_dev *sdev;
> > +	struct intel_iommu *iommu;
> > +	struct intel_svm *svm;
> > +	bool private_present;
> > +	bool pasid_present;
> > +	bool last_page;
> > +	u8 bus, devfn;
> > +	int ret = 0;
> > +	u16 sid;
> > +
> > +	if (!dev || !dev_is_pci(dev))
> > +		return -ENODEV;
> > +
> > +	iommu = device_to_iommu(dev, &bus, &devfn);
> > +	if (!iommu)
> > +		return -ENODEV;
>
> move to the place when iommu is referenced. This place is too early.

I took this as a sanity check. If the device has no iommu backed, we
should consider it as an invalid input.

> > +
> > +	if (!msg || !evt)
> > +		return -EINVAL;
> > +
> > +	mutex_lock(&pasid_mutex);
> > +
> > +	prm = &evt->fault.prm;
> > +	sid = PCI_DEVID(bus, devfn);
> > +	pasid_present = prm->flags &
> > IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
> > +	private_present = prm->flags &
> > IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
> > +	last_page = prm->flags &
> > IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
> > +
> > +	if (pasid_present) {
> > +		/* VT-d supports devices with full 20 bit PASIDs only */
> > +		if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX) {
> > +			ret = -EINVAL;
> > +			goto out;
> > +		}
>
> shouldn't we check prm->pasid here? Above is more reasonable to be
> checked when page request is reported.

Yes. I will check the pasid in both places.

> > +
> > +		ret = pasid_to_svm_sdev(dev, prm->pasid, &svm, &sdev);
> > +		if (ret || !sdev)
>
> if sdev==NULL, suppose an error (-ENODEV) should be returned here?

Yes. Good catch. I should return an error if sdev==NULL.

> > +			goto out;
> > +	}
> > +
> > +	/*
> > +	 * Per VT-d spec. v3.0 ch7.7, system software must respond
> > +	 * with page group response if private data is present (PDP)
> > +	 * or last page in group (LPIG) bit is set. This is an
> > +	 * additional VT-d feature beyond PCI ATS spec.
>
> feature->requirement

Agreed.

> Thanks
> Kevin

Best regards,
baolu

> > +	 */
> > +	if (last_page || private_present) {
> > +		struct qi_desc desc;
> > +
> > +		desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid)
> > |
> > +				QI_PGRP_PASID_P(pasid_present) |
> > +				QI_PGRP_PDP(private_present) |
> > +				QI_PGRP_RESP_CODE(msg->code) |
> > +				QI_PGRP_RESP_TYPE;
> > +		desc.qw1 = QI_PGRP_IDX(prm->grpid) |
> > QI_PGRP_LPIG(last_page);
> > +		desc.qw2 = 0;
> > +		desc.qw3 = 0;
> > +		if (private_present)
> > +			memcpy(&desc.qw2, prm->private_data,
> > +			       sizeof(prm->private_data));
> > +
> > +		qi_submit_sync(iommu, &desc, 1, 0);
> > +	}
> > +out:
> > +	mutex_unlock(&pasid_mutex);
> > +	return ret;
> > +}
> > diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> > index fc2cfc3db6e1..bf6009a344f5 100644
> > --- a/include/linux/intel-iommu.h
> > +++ b/include/linux/intel-iommu.h
> > @@ -741,6 +741,9 @@ struct iommu_sva *intel_svm_bind(struct device
> > *dev, struct mm_struct *mm,
> >   				 void *drvdata);
> >   void intel_svm_unbind(struct iommu_sva *handle);
> >   int intel_svm_get_pasid(struct iommu_sva *handle);
> > +int intel_svm_page_response(struct device *dev, struct iommu_fault_event
> > *evt,
> > +			    struct iommu_page_response *msg);
> > +
> >   struct svm_dev_ops;
> >
> >   struct intel_svm_dev {
> > --
> > 2.17.1