RE: [PATCH V9 06/10] iommu/vt-d: Add svm/sva invalidate function

[Liu, Yi L]

> From: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Sent: Wednesday, January 29, 2020 2:02 PM
> Subject: [PATCH V9 06/10] iommu/vt-d: Add svm/sva invalidate function
> 
> When Shared Virtual Address (SVA) is enabled for a guest OS via vIOMMU, we
> need to provide invalidation support at IOMMU API and driver level. This patch
> adds Intel VT-d specific function to implement iommu passdown invalidate API
> for shared virtual address.
> 
> The use case is for supporting caching structure invalidation of assigned SVM
> capable devices. Emulated IOMMU exposes queue invalidation capability and
> passes down all descriptors from the guest to the physical IOMMU.
> 
> The assumption is that guest to host device ID mapping should be resolved prior
> to calling IOMMU driver. Based on the device handle, host IOMMU driver can
> replace certain fields before submit to the invalidation queue.
> 
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
> Signed-off-by: Liu, Yi L <yi.l.liu@xxxxxxxxxxxxxxx>

May be update my  email to Liu Yi L <yi.l.liu@xxxxxxxxx> :-) @linux.intel.com
account no more work for me.  :-(

> ---
>  drivers/iommu/intel-iommu.c | 173
> ++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 173 insertions(+)
> 
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index
> 8a4136e805ac..b8aa6479b87f 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -5605,6 +5605,178 @@ static void intel_iommu_aux_detach_device(struct
> iommu_domain *domain,
>  	aux_domain_remove_dev(to_dmar_domain(domain), dev);  }
> 
> +/*
> + * 2D array for converting and sanitizing IOMMU generic TLB granularity
> +to
> + * VT-d granularity. Invalidation is typically included in the unmap
> +operation
> + * as a result of DMA or VFIO unmap. However, for assigned device where
> +guest
> + * could own the first level page tables without being shadowed by
> +QEMU. In
> + * this case there is no pass down unmap to the host IOMMU as a result
> +of unmap
> + * in the guest. Only invalidations are trapped and passed down.
> + * In all cases, only first level TLB invalidation (request with PASID)
> +can be
> + * passed down, therefore we do not include IOTLB granularity for
> +request
> + * without PASID (second level).
> + *
> + * For an example, to find the VT-d granularity encoding for IOTLB
> + * type and page selective granularity within PASID:
> + * X: indexed by iommu cache type
> + * Y: indexed by enum iommu_inv_granularity
> + * [IOMMU_CACHE_INV_TYPE_IOTLB][IOMMU_INV_GRANU_ADDR]
> + *
> + * Granu_map array indicates validity of the table. 1: valid, 0:
> +invalid
> + *
> + */
> +const static int
> inv_type_granu_map[IOMMU_CACHE_INV_TYPE_NR][IOMMU_INV_GRANU_N
> R] = {
> +	/* PASID based IOTLB, support PASID selective and page selective */
> +	{0, 1, 1},
> +	/* PASID based dev TLBs, only support all PASIDs or single PASID */
> +	{1, 1, 0},
> +	/* PASID cache */
> +	{1, 1, 0}
> +};
> +
> +const static u64
> inv_type_granu_table[IOMMU_CACHE_INV_TYPE_NR][IOMMU_INV_GRANU_
> NR] = {
> +	/* PASID based IOTLB */
> +	{0, QI_GRAN_NONG_PASID, QI_GRAN_PSI_PASID},
> +	/* PASID based dev TLBs */
> +	{QI_DEV_IOTLB_GRAN_ALL, QI_DEV_IOTLB_GRAN_PASID_SEL, 0},
> +	/* PASID cache */
> +	{QI_PC_ALL_PASIDS, QI_PC_PASID_SEL, 0}, };
> +
> +static inline int to_vtd_granularity(int type, int granu, u64
> +*vtd_granu) {
> +	if (type >= IOMMU_CACHE_INV_TYPE_NR || granu >=
> IOMMU_INV_GRANU_NR ||
> +		!inv_type_granu_map[type][granu])
> +		return -EINVAL;
> +
> +	*vtd_granu = inv_type_granu_table[type][granu];
> +
> +	return 0;
> +}
> +
> +static inline u64 to_vtd_size(u64 granu_size, u64 nr_granules) {
> +	u64 nr_pages = (granu_size * nr_granules) >> VTD_PAGE_SHIFT;
> +
> +	/* VT-d size is encoded as 2^size of 4K pages, 0 for 4k, 9 for 2MB, etc.
> +	 * IOMMU cache invalidate API passes granu_size in bytes, and number
> of
> +	 * granu size in contiguous memory.
> +	 */
> +	return order_base_2(nr_pages);
> +}
> +
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> +static int intel_iommu_sva_invalidate(struct iommu_domain *domain,
> +		struct device *dev, struct iommu_cache_invalidate_info
> *inv_info) {
> +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	struct device_domain_info *info;
> +	struct intel_iommu *iommu;
> +	unsigned long flags;
> +	int cache_type;
> +	u8 bus, devfn;
> +	u16 did, sid;
> +	int ret = 0;
> +	u64 size;
> +
> +	if (!inv_info || !dmar_domain ||
> +		inv_info->version !=
> IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
> +		return -EINVAL;
> +
> +	if (!dev || !dev_is_pci(dev))
> +		return -ENODEV;
> +
> +	iommu = device_to_iommu(dev, &bus, &devfn);
> +	if (!iommu)
> +		return -ENODEV;
> +
> +	spin_lock_irqsave(&device_domain_lock, flags);
> +	spin_lock(&iommu->lock);
> +	info = iommu_support_dev_iotlb(dmar_domain, iommu, bus, devfn);
> +	if (!info) {
> +		ret = -EINVAL;
> +		goto out_unlock;
> +	}
> +	did = dmar_domain->iommu_did[iommu->seq_id];
> +	sid = PCI_DEVID(bus, devfn);
> +	size = to_vtd_size(inv_info->addr_info.granule_size,
> +inv_info->addr_info.nb_granules);

Here I have a concern that we always try to get size via to_vtd_size(). But
the inv_info->addr_info.granule_size and inv_info->addr_info.nb_granules
may be meaningless if the invalidation is not a page selective one. May we
add a check here on the invalidation granularity. :-)

> +	for_each_set_bit(cache_type, (unsigned long *)&inv_info->cache,
> IOMMU_CACHE_INV_TYPE_NR) {
> +		u64 granu = 0;
> +		u64 pasid = 0;
> +
> +		ret = to_vtd_granularity(cache_type, inv_info->granularity,
> &granu);
> +		if (ret) {
> +			pr_err("Invalid cache type and granu
> combination %d/%d\n", cache_type,
> +				inv_info->granularity);
> +			break;
> +		}
> +
> +		/* PASID is stored in different locations based on granularity */
> +		if (inv_info->granularity == IOMMU_INV_GRANU_PASID)
> +			pasid = inv_info->pasid_info.pasid;
> +		else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
> +			pasid = inv_info->addr_info.pasid;
> +		else {
> +			pr_err("Cannot find PASID for given cache type and
> granularity\n");
> +			break;
> +		}
> +
> +		switch (BIT(cache_type)) {
> +		case IOMMU_CACHE_INV_TYPE_IOTLB:
> +			if (size && (inv_info->addr_info.addr &
> ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {

May  need to update acoordingly if the above comment was accepted.  :-)

Regards,
Yi Liu