Re: [PATCH v3 06/16] iommu/vt-d: add svm/sva invalidate function

[Lu Baolu]

Hi,

On 11/18/2017 02:55 AM, Jacob Pan wrote:
> 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@xxxxxxxxxxxxxxx>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
> ---
>  drivers/iommu/intel-iommu.c | 200 +++++++++++++++++++++++++++++++++++++++++++-
>  include/linux/intel-iommu.h |  17 +++-
>  2 files changed, 211 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 556bdd2..000b2b3 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -4981,6 +4981,183 @@ 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 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
> + *
> + */
> +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)
> +{
> +	struct intel_iommu *iommu;
> +	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	struct device_domain_info *info;
> +	struct pci_dev *pdev;
> +	u16 did, sid, pfsid;
> +	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);
> +		/* For SRIOV VF, invalidation of device IOTLB requires PFSID */
> +		pdev = to_pci_dev(dev);
> +		if (pdev && pdev->is_virtfn)
> +			pfsid = PCI_DEVID(pdev->physfn->bus->number, pdev->physfn->devfn);
> +		else
> +			pfsid = sid;
> +
> +		/**
> +		 * Always flush device IOTLB if ATS is enabled since guest
> +		 * vIOMMU exposes CM = 1, no device IOTLB flush will be passed
> +		 * down.
> +		 * TODO: check if device is VF, use PF ATS data if spec does not require
> +		 * VF to include all PF capabilities,  VF qdep and VF ats_enabled.
> +		 */
> +		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, info->pfsid,
> +						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;
> +	}
> +out_unlock:
> +	spin_unlock(&iommu->lock);
> +	spin_unlock_irqrestore(&device_domain_lock, flags);
> +
> +	return ret;
> +}
> +
>  static int intel_iommu_map(struct iommu_domain *domain,
>  			   unsigned long iova, phys_addr_t hpa,
>  			   size_t size, int iommu_prot)
> @@ -5304,7 +5481,7 @@ static int intel_iommu_bind_pasid_table(struct iommu_domain *domain,
>  	iommu = device_to_iommu(dev, &bus, &devfn);
>  	if (!iommu)
>  		return -ENODEV;
> -	/* VT-d spec 9.4 says pasid table size is encoded as 2^(x+5) */
> +	/* VT-d spec section 9.4 says pasid table size is encoded as 2^(x+5) */
>  	host_table_pasid_bits = intel_iommu_get_pts(iommu) + MIN_NR_PASID_BITS;
>  	if (!pasidt_binfo || pasidt_binfo->pasid_bits > host_table_pasid_bits ||
>  		pasidt_binfo->pasid_bits < MIN_NR_PASID_BITS) {
> @@ -5313,7 +5490,11 @@ static int intel_iommu_bind_pasid_table(struct iommu_domain *domain,
>  			MIN_NR_PASID_BITS, host_table_pasid_bits);
>  		return -ERANGE;
>  	}
> -
> +	if (!ecap_nest(iommu->ecap)) {
> +		dev_err(dev, "Cannot bind PASID table, no nested translation\n");
> +		ret = -EINVAL;
> +		goto out;
> +	}

This and some of below changes could be included in patch 02/16.

Best regards,
Lu Baolu

>  	pdev = to_pci_dev(dev);
>  	sid = PCI_DEVID(bus, devfn);
>  	info = dev->archdata.iommu;
> @@ -5323,6 +5504,11 @@ static int intel_iommu_bind_pasid_table(struct iommu_domain *domain,
>  		ret = -EINVAL;
>  		goto out;
>  	}
> +	if (info->pasid_table_bound) {
> +		dev_err(dev, "Device PASID table already bound\n");
> +		ret = -EBUSY;
> +		goto out;
> +	}
>  	if (!info->pasid_enabled) {
>  		ret = pci_enable_pasid(pdev, info->pasid_supported & ~1);
>  		if (ret) {
> @@ -5363,7 +5549,7 @@ static int intel_iommu_bind_pasid_table(struct iommu_domain *domain,
>  				DMA_CCMD_MASK_NOBIT,
>  				DMA_CCMD_DEVICE_INVL);
>  	iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
> -
> +	info->pasid_table_bound = 1;
>  out_unlock:
>  	spin_unlock_irqrestore(&iommu->lock, flags);
>  out:
> @@ -5375,8 +5561,14 @@ static void intel_iommu_unbind_pasid_table(struct iommu_domain *domain,
>  {
>  	struct intel_iommu *iommu;
>  	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
> +	struct device_domain_info *info;
>  	u8 bus, devfn;
>  
> +	info = dev->archdata.iommu;
> +	if (!info) {
> +		dev_err(dev, "Invalid device domain info\n");
> +		return;
> +	}
>  	assert_spin_locked(&device_domain_lock);
>  	iommu = device_to_iommu(dev, &bus, &devfn);
>  	if (!iommu) {
> @@ -5387,6 +5579,7 @@ static void intel_iommu_unbind_pasid_table(struct iommu_domain *domain,
>  	domain_context_clear(iommu, dev);
>  
>  	domain_context_mapping_one(dmar_domain, iommu, bus, devfn);
> +	info->pasid_table_bound = 0;
>  }
>  #endif /* CONFIG_INTEL_IOMMU_SVM */
>  
> @@ -5399,6 +5592,7 @@ const struct iommu_ops intel_iommu_ops = {
>  #ifdef CONFIG_INTEL_IOMMU_SVM
>  	.bind_pasid_table	= intel_iommu_bind_pasid_table,
>  	.unbind_pasid_table	= intel_iommu_unbind_pasid_table,
> +	.sva_invalidate		= intel_iommu_sva_invalidate,
>  #endif
>  	.map			= intel_iommu_map,
>  	.unmap			= intel_iommu_unmap,
> diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> index 3c83f7e..7f05e36 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -258,6 +258,10 @@ enum {
>  #define QI_PGRP_RESP_TYPE	0x9
>  #define QI_PSTRM_RESP_TYPE	0xa
>  
> +#define QI_DID(did)		(((u64)did & 0xffff) << 16)
> +#define QI_DID_MASK		GENMASK(31, 16)
> +#define QI_TYPE_MASK		GENMASK(3, 0)
> +
>  #define QI_IEC_SELECTIVE	(((u64)1) << 4)
>  #define QI_IEC_IIDEX(idx)	(((u64)(idx & 0xffff) << 32))
>  #define QI_IEC_IM(m)		(((u64)(m & 0x1f) << 27))
> @@ -288,8 +292,9 @@ enum {
>  #define QI_PC_DID(did)		(((u64)did) << 16)
>  #define QI_PC_GRAN(gran)	(((u64)gran) << 4)
>  
> -#define QI_PC_ALL_PASIDS	(QI_PC_TYPE | QI_PC_GRAN(0))
> -#define QI_PC_PASID_SEL		(QI_PC_TYPE | QI_PC_GRAN(1))
> +/* PC inv granu */
> +#define QI_PC_ALL_PASIDS	0
> +#define QI_PC_PASID_SEL		1
>  
>  #define QI_EIOTLB_ADDR(addr)	((u64)(addr) & VTD_PAGE_MASK)
>  #define QI_EIOTLB_GL(gl)	(((u64)gl) << 7)
> @@ -299,6 +304,10 @@ enum {
>  #define QI_EIOTLB_DID(did)	(((u64)did) << 16)
>  #define QI_EIOTLB_GRAN(gran) 	(((u64)gran) << 4)
>  
> +/* QI Dev-IOTLB inv granu */
> +#define QI_DEV_IOTLB_GRAN_ALL		0
> +#define QI_DEV_IOTLB_GRAN_PASID_SEL	1
> +
>  #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
>  #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
>  #define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
> @@ -327,6 +336,7 @@ enum {
>  #define QI_RESP_INVALID		0x1
>  #define QI_RESP_FAILURE		0xf
>  
> +/* QI EIOTLB inv granu */
>  #define QI_GRAN_ALL_ALL			0
>  #define QI_GRAN_NONG_ALL		1
>  #define QI_GRAN_NONG_PASID		2
> @@ -471,6 +481,7 @@ struct device_domain_info {
>  	u8 pri_enabled:1;
>  	u8 ats_supported:1;
>  	u8 ats_enabled:1;
> +	u8 pasid_table_bound:1;
>  	u8 ats_qdep;
>  	u64 fault_mask;	/* selected IOMMU faults to be reported */
>  	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
> @@ -502,7 +513,7 @@ extern void qi_flush_eiotlb(struct intel_iommu *iommu, u16 did, u64 addr,
>  extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
>  			u16 qdep, u64 addr, unsigned mask);
>  extern void qi_flush_dev_eiotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> -				u32 pasid, u16 qdep, u64 addr, unsigned size);
> +			u32 pasid, u16 qdep, u64 addr, unsigned size, u64 granu);
>  extern void qi_flush_pasid(struct intel_iommu *iommu, u16 did, u64 granu, int pasid);
>  
>  extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);