Re: [PATCH v4 09/22] iommu/vt-d: add svm/sva invalidate function

[Jacob Pan <jacob.jun.pan@linux.intel.com>]

On Tue, 17 Apr 2018 13:10:45 -0600
Alex Williamson <alex.williamson@redhat.com> wrote:

> On Mon, 16 Apr 2018 14:48:58 -0700
> Jacob Pan <jacob.jun.pan@linux.intel.com> wrote:
> 
> > 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: Liu, Yi L <yi.l.liu@linux.intel.com>
> > Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> > Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> > ---
> >  drivers/iommu/intel-iommu.c | 170
> > ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 170
> > insertions(+)
> > 
> > diff --git a/drivers/iommu/intel-iommu.c
> > b/drivers/iommu/intel-iommu.c index cae4042..c765448 100644
> > --- a/drivers/iommu/intel-iommu.c
> > +++ b/drivers/iommu/intel-iommu.c
> > @@ -4973,6 +4973,175 @@ static void
> > intel_iommu_detach_device(struct iommu_domain *domain,
> > dmar_remove_one_dev_info(to_dmar_domain(domain), dev); }
> >  
> > +/*
> > + * 3D array for converting IOMMU generic type-granularity to VT-d
> > granularity
> > + * X indexed by enum iommu_inv_type
> > + * Y indicates request without and with PASID
> > + * Z indexed by enum iommu_inv_granularity
> > + *
> > + * For an example, if we want to find the VT-d granularity
> > encoding for IOTLB
> > + * type, DMA request with PASID, and page selective. The look up
> > indices are:
> > + * [1][1][8], where
> > + * 1: IOMMU_INV_TYPE_TLB
> > + * 1: with PASID
> > + * 8: IOMMU_INV_GRANU_PAGE_PASID
> > + *
> > + * Granu_map array indicates validity of the table. 1: valid, 0:
> > invalid
> > + *
> > + */
> > +const static int
> > inv_type_granu_map[IOMMU_INV_NR_TYPE][2][IOMMU_INV_NR_GRANU] = {
> > +	/* extended dev IOTLBs, for dev-IOTLB, only global is
> > valid,
> > +	   for dev-EXIOTLB, two valid granu */
> > +	{
> > +		{1},
> > +		{0, 0, 0, 0, 1, 1, 0, 0, 0}
> > +	},
> > +	/* IOTLB and EIOTLB */
> > +	{
> > +		{1, 1, 0, 1, 0, 0, 0, 0, 0},
> > +		{0, 0, 0, 0, 1, 0, 1, 1, 1}
> > +	},
> > +	/* PASID cache */
> > +	{
> > +		{0},
> > +		{0, 0, 0, 0, 1, 1, 0, 0, 0}
> > +	},
> > +	/* context cache */
> > +	{
> > +		{1, 1, 1}
> > +	}
> > +};
> > +
> > +const static u64
> > inv_type_granu_table[IOMMU_INV_NR_TYPE][2][IOMMU_INV_NR_GRANU] = {
> > +	/* extended dev IOTLBs, only global is valid */
> > +	{
> > +		{QI_DEV_IOTLB_GRAN_ALL},
> > +		{0, 0, 0, 0, QI_DEV_IOTLB_GRAN_ALL,
> > QI_DEV_IOTLB_GRAN_PASID_SEL, 0, 0, 0}
> > +	},
> > +	/* IOTLB and EIOTLB */
> > +	{
> > +		{DMA_TLB_GLOBAL_FLUSH, DMA_TLB_DSI_FLUSH, 0,
> > DMA_TLB_PSI_FLUSH},
> > +		{0, 0, 0, 0, QI_GRAN_ALL_ALL, 0, QI_GRAN_NONG_ALL,
> > QI_GRAN_NONG_PASID, QI_GRAN_PSI_PASID}
> > +	},
> > +	/* PASID cache */
> > +	{
> > +		{0},
> > +		{0, 0, 0, 0, QI_PC_ALL_PASIDS, QI_PC_PASID_SEL}
> > +	},
> > +	/* context cache */
> > +	{
> > +		{DMA_CCMD_GLOBAL_INVL, DMA_CCMD_DOMAIN_INVL,
> > DMA_CCMD_DEVICE_INVL}
> > +	}
> > +};
> > +
> > +static inline int to_vtd_granularity(int type, int granu, int
> > with_pasid, u64 *vtd_granu) +{
> > +	if (type >= IOMMU_INV_NR_TYPE || granu >=
> > IOMMU_INV_NR_GRANU || with_pasid > 1)
> > +		return -EINVAL;
> > +
> > +	if (inv_type_granu_map[type][with_pasid][granu] == 0)
> > +		return -EINVAL;
> > +
> > +	*vtd_granu = inv_type_granu_table[type][with_pasid][granu];
> > +
> > +	return 0;
> > +}
> > +
> > +static int intel_iommu_sva_invalidate(struct iommu_domain *domain,
> > +		struct device *dev, struct tlb_invalidate_info
> > *inv_info)  
> 
> inv_info->hdr.version is never checked, why do we have these if
> they're not used?
> 
the version was added to leave room for future extension. you are
right, it should be checked.
> > +{
> > +	struct intel_iommu *iommu;
> > +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> > +	struct device_domain_info *info;
> > +	u16 did, sid;
> > +	u8 bus, devfn;
> > +	int ret = 0;
> > +	u64 granu;
> > +	unsigned long flags;
> > +
> > +	if (!inv_info || !dmar_domain)
> > +		return -EINVAL;
> > +
> > +	iommu = device_to_iommu(dev, &bus, &devfn);
> > +	if (!iommu)
> > +		return -ENODEV;
> > +
> > +	if (!dev || !dev_is_pci(dev))
> > +		return -ENODEV;
> > +
> > +	did = dmar_domain->iommu_did[iommu->seq_id];
> > +	sid = PCI_DEVID(bus, devfn);
> > +	ret = to_vtd_granularity(inv_info->hdr.type,
> > inv_info->granularity,
> > +				!!(inv_info->flags &
> > IOMMU_INVALIDATE_PASID_TAGGED), &granu);
> > +	if (ret) {
> > +		pr_err("Invalid range type %d, granu %d\n",
> > inv_info->hdr.type,
> > +			inv_info->granularity);
> > +		return ret;
> > +	}
> > +
> > +	spin_lock(&iommu->lock);
> > +	spin_lock_irqsave(&device_domain_lock, flags);
> > +
> > +	switch (inv_info->hdr.type) {
> > +	case IOMMU_INV_TYPE_CONTEXT:
> > +		iommu->flush.flush_context(iommu, did, sid,
> > +					DMA_CCMD_MASK_NOBIT,
> > granu);
> > +		break;
> > +	case IOMMU_INV_TYPE_TLB:
> > +		/* We need to deal with two scenarios:
> > +		 * - IOTLB for request w/o PASID
> > +		 * - extended IOTLB for request with PASID.
> > +		 */
> > +		if (inv_info->size &&
> > +			(inv_info->addr & ((1 << (VTD_PAGE_SHIFT +
> > inv_info->size)) - 1))) {
> > +			pr_err("Addr out of range, addr 0x%llx,
> > size order %d\n",
> > +				inv_info->addr, inv_info->size);
> > +			ret = -ERANGE;
> > +			goto out_unlock;
> > +		}
> > +
> > +		if (inv_info->flags &
> > IOMMU_INVALIDATE_PASID_TAGGED)
> > +			qi_flush_eiotlb(iommu, did,
> > mm_to_dma_pfn(inv_info->addr),
> > +					inv_info->pasid,
> > +					inv_info->size, granu,
> > +					inv_info->flags &
> > IOMMU_INVALIDATE_GLOBAL_PAGE);
> > +		else
> > +			qi_flush_iotlb(iommu, did,
> > mm_to_dma_pfn(inv_info->addr),
> > +				inv_info->size, granu);
> > +		/**
> > +		 * Always flush device IOTLB if ATS is enabled
> > since guest
> > +		 * vIOMMU exposes CM = 1, no device IOTLB flush
> > will be passed
> > +		 * down.
> > +		 */
> > +		info = iommu_support_dev_iotlb(dmar_domain, iommu,
> > bus, devfn);
> > +		if (info && info->ats_enabled) {
> > +			if (inv_info->flags &
> > IOMMU_INVALIDATE_PASID_TAGGED)
> > +				qi_flush_dev_eiotlb(iommu, sid,
> > +						inv_info->pasid,
> > info->ats_qdep,
> > +						inv_info->addr,
> > inv_info->size,
> > +						granu);
> > +			else
> > +				qi_flush_dev_iotlb(iommu, sid,
> > info->pfsid,
> > +						info->ats_qdep,
> > inv_info->addr,
> > +						inv_info->size);
> > +		}
> > +		break;
> > +	case IOMMU_INV_TYPE_PASID:
> > +		qi_flush_pasid(iommu, did, granu, inv_info->pasid);
> > +
> > +		break;
> > +	default:
> > +		dev_err(dev, "Unknown IOMMU invalidation type
> > %d\n",
> > +			inv_info->hdr.type);
> > +		ret = -EINVAL;
> > +	}  
> 
> 
> More verbose logging,
you mean dev_err is unnecessary? I will remove that.
> is vfio just passing these through allowing them
> to be user reachable?  Thanks,
yes, the invalidation types are in uapi, expect qemu traps invalidation
from vIOMMU and passdown to physical IOMMU.
> 
> Alex
> 
>  [...]  
> 

[Jacob Pan]