RE: [PATCH v2 1/6] iommu/vt-d: Setup scalable mode context entry in probe path

[Tian, Kevin]

> From: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> Sent: Tuesday, December 5, 2023 9:22 AM
>
> @@ -304,6 +304,11 @@ int intel_pasid_setup_first_level(struct intel_iommu
> *iommu,
>  		return -EINVAL;
>  	}
> 
> +	if (intel_pasid_setup_sm_context(dev, true)) {
> +		dev_err(dev, "Context entry is not configured\n");
> +		return -ENODEV;
> +	}
> +
>  	spin_lock(&iommu->lock);
>  	pte = intel_pasid_get_entry(dev, pasid);
>  	if (!pte) {
> @@ -384,6 +389,11 @@ int intel_pasid_setup_second_level(struct
> intel_iommu *iommu,
>  		return -EINVAL;
>  	}
> 
> +	if (intel_pasid_setup_sm_context(dev, true)) {
> +		dev_err(dev, "Context entry is not configured\n");
> +		return -ENODEV;
> +	}
> +
>  	pgd = domain->pgd;
>  	agaw = iommu_skip_agaw(domain, iommu, &pgd);
>  	if (agaw < 0) {
> @@ -505,6 +515,11 @@ int intel_pasid_setup_pass_through(struct
> intel_iommu *iommu,
>  	u16 did = FLPT_DEFAULT_DID;
>  	struct pasid_entry *pte;
> 
> +	if (intel_pasid_setup_sm_context(dev, true)) {
> +		dev_err(dev, "Context entry is not configured\n");
> +		return -ENODEV;
> +	}
> +
>  	spin_lock(&iommu->lock);
>  	pte = intel_pasid_get_entry(dev, pasid);
>  	if (!pte) {

instead of replicating the invocation in all three stubs it's simpler to
do once in dmar_domain_attach_device() for all of them.

Then put the deferred check outside of intel_pasid_setup_sm_context()
instead of using a Boolean flag


> @@ -623,6 +638,11 @@ int intel_pasid_setup_nested(struct intel_iommu
> *iommu, struct device *dev,
>  		return -EINVAL;
>  	}
> 
> +	if (intel_pasid_setup_sm_context(dev, true)) {
> +		dev_err_ratelimited(dev, "Context entry is not configured\n");
> +		return -ENODEV;
> +	}
> +

Do we support nested in kdump?

> +
> +	/*
> +	 * Cache invalidation for changes to a scalable-mode context table
> +	 * entry.
> +	 *
> +	 * Section 6.5.3.3 of the VT-d spec:
> +	 * - Device-selective context-cache invalidation;
> +	 * - Domain-selective PASID-cache invalidation to affected domains
> +	 *   (can be skipped if all PASID entries were not-present);
> +	 * - Domain-selective IOTLB invalidation to affected domains;
> +	 * - Global Device-TLB invalidation to affected functions.
> +	 *
> +	 * For kdump cases, old valid entries may be cached due to the
> +	 * in-flight DMA and copied pgtable, but there is no unmapping
> +	 * behaviour for them, thus we need explicit cache flushes for all
> +	 * affected domain IDs and PASIDs used in the copied PASID table.
> +	 * Given that we have no idea about which domain IDs and PASIDs
> were
> +	 * used in the copied tables, upgrade them to global PASID and IOTLB
> +	 * cache invalidation.
> +	 *
> +	 * For kdump case, at this point, the device is supposed to finish
> +	 * reset at its driver probe stage, so no in-flight DMA will exist,
> +	 * and we don't need to worry anymore hereafter.
> +	 */
> +	if (context_copied(iommu, bus, devfn)) {
> +		context_clear_entry(context);
> +		clear_context_copied(iommu, bus, devfn);
> +		iommu->flush.flush_context(iommu, 0,
> +					   (((u16)bus) << 8) | devfn,
> +					   DMA_CCMD_MASK_NOBIT,
> +					   DMA_CCMD_DEVICE_INVL);
> +		qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0);
> +		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
> DMA_TLB_GLOBAL_FLUSH);
> +		devtlb_invalidation_with_pasid(iommu, dev,
> IOMMU_NO_PASID);
> +	}

I don't see this logic from existing code. If it's a bug fix then
please send it separately first.

> +
> +	context_entry_set_pasid_table(context, dev);

and here is additional change to the context entry. Why is the
context cache invalidated in the start?

> +
> +static int pci_pasid_table_setup(struct pci_dev *pdev, u16 alias, void *data)
> +{
> +	struct device *dev = data;
> +
> +	if (dev != &pdev->dev)
> +		return 0;

what is it for? the existing domain_context_mapping_cb() doesn't have
this check then implying a behavior change.