Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "This brings three new iommufd capabilities:

   - Dirty tracking for DMA.

     AMD/ARM/Intel CPUs can now record if a DMA writes to a page in the
     IOPTEs within the IO page table. This can be used to generate a
     record of what memory is being dirtied by DMA activities during a
     VM migration process. A VMM like qemu will combine the IOMMU dirty
     bits with the CPU's dirty log to determine what memory to transfer.

     VFIO already has a DMA dirty tracking framework that requires PCI
     devices to implement tracking HW internally. The iommufd version
     provides an alternative that the VMM can select, if available. The
     two are designed to have very similar APIs.

   - Userspace controlled attributes for hardware page tables
     (HWPT/iommu_domain). There are currently a few generic attributes
     for HWPTs (support dirty tracking, and parent of a nest). This is
     an entry point for the userspace iommu driver to control the HW in
     detail.

   - Nested translation support for HWPTs. This is a 2D translation
     scheme similar to the CPU where a DMA goes through a first stage to
     determine an intermediate address which is then translated trough a
     second stage to a physical address.

     Like for CPU translation the first stage table would exist in VM
     controlled memory and the second stage is in the kernel and matches
     the VM's guest to physical map.

     As every IOMMU has a unique set of parameter to describe the S1 IO
     page table and its associated parameters the userspace IOMMU driver
     has to marshal the information into the correct format.

     This is 1/3 of the feature, it allows creating the nested
     translation and binding it to VFIO devices, however the API to
     support IOTLB and ATC invalidation of the stage 1 io page table,
     and forwarding of IO faults are still in progress.

  The series includes AMD and Intel support for dirty tracking. Intel
  support for nested translation.

  Along the way are a number of internal items:

   - New iommu core items: ops->domain_alloc_user(),
     ops->set_dirty_tracking, ops->read_and_clear_dirty(),
     IOMMU_DOMAIN_NESTED, and iommu_copy_struct_from_user

   - UAF fix in iopt_area_split()

   - Spelling fixes and some test suite improvement"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (52 commits)
  iommufd: Organize the mock domain alloc functions closer to Joerg's tree
  iommufd/selftest: Fix page-size check in iommufd_test_dirty()
  iommufd: Add iopt_area_alloc()
  iommufd: Fix missing update of domains_itree after splitting iopt_area
  iommu/vt-d: Disallow read-only mappings to nest parent domain
  iommu/vt-d: Add nested domain allocation
  iommu/vt-d: Set the nested domain to a device
  iommu/vt-d: Make domain attach helpers to be extern
  iommu/vt-d: Add helper to setup pasid nested translation
  iommu/vt-d: Add helper for nested domain allocation
  iommu/vt-d: Extend dmar_domain to support nested domain
  iommufd: Add data structure for Intel VT-d stage-1 domain allocation
  iommu/vt-d: Enhance capability check for nested parent domain allocation
  iommufd/selftest: Add coverage for IOMMU_HWPT_ALLOC with nested HWPTs
  iommufd/selftest: Add nested domain allocation for mock domain
  iommu: Add iommu_copy_struct_from_user helper
  iommufd: Add a nested HW pagetable object
  iommu: Pass in parent domain with user_data to domain_alloc_user op
  iommufd: Share iommufd_hwpt_alloc with IOMMUFD_OBJ_HWPT_NESTED
  iommufd: Derive iommufd_hwpt_paging from iommufd_hw_pagetable
  ...

1 files changed, 147 insertions, 9 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3685ba90ec88..d1037280abf7 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -282,7 +282,6 @@ static LIST_HEAD(dmar_satc_units);
 #define for_each_rmrr_units(rmrr) \
 	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
 
-static void device_block_translation(struct device *dev);
 static void intel_iommu_domain_free(struct iommu_domain *domain);
 
 int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON);
@@ -300,6 +299,7 @@ static int iommu_skip_te_disable;
 #define IDENTMAP_AZALIA		4
 
 const struct iommu_ops intel_iommu_ops;
+const struct iommu_dirty_ops intel_dirty_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
 {
@@ -560,7 +560,7 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 }
 
 /* Some capabilities may be different across iommus */
-static void domain_update_iommu_cap(struct dmar_domain *domain)
+void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
@@ -1778,8 +1778,7 @@ static struct dmar_domain *alloc_domain(unsigned int type)
 	return domain;
 }
 
-static int domain_attach_iommu(struct dmar_domain *domain,
-			       struct intel_iommu *iommu)
+int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 {
 	struct iommu_domain_info *info, *curr;
 	unsigned long ndomains;
@@ -1828,8 +1827,7 @@ err_unlock:
 	return ret;
 }
 
-static void domain_detach_iommu(struct dmar_domain *domain,
-				struct intel_iommu *iommu)
+void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 {
 	struct iommu_domain_info *info;
 
@@ -2196,6 +2194,11 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
 		return -EINVAL;
 
+	if (!(prot & DMA_PTE_WRITE) && domain->nested_parent) {
+		pr_err_ratelimited("Read-only mapping is disallowed on the domain which serves as the parent in a nested configuration, due to HW errata (ERRATA_772415_SPR17)\n");
+		return -EINVAL;
+	}
+
 	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
 	attr |= DMA_FL_PTE_PRESENT;
 	if (domain->use_first_level) {
@@ -3958,7 +3961,7 @@ static void dmar_remove_one_dev_info(struct device *dev)
  * all DMA requests without PASID from the device are blocked. If the page
  * table has been set, clean up the data structures.
  */
-static void device_block_translation(struct device *dev)
+void device_block_translation(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
@@ -4058,14 +4061,62 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 	return NULL;
 }
 
+static struct iommu_domain *
+intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
+			      struct iommu_domain *parent,
+			      const struct iommu_user_data *user_data)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+	bool nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
+	struct intel_iommu *iommu = info->iommu;
+	struct iommu_domain *domain;
+
+	/* Must be NESTING domain */
+	if (parent) {
+		if (!nested_supported(iommu) || flags)
+			return ERR_PTR(-EOPNOTSUPP);
+		return intel_nested_domain_alloc(parent, user_data);
+	}
+
+	if (flags &
+	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING)))
+		return ERR_PTR(-EOPNOTSUPP);
+	if (nested_parent && !nested_supported(iommu))
+		return ERR_PTR(-EOPNOTSUPP);
+	if (user_data || (dirty_tracking && !ssads_supported(iommu)))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/*
+	 * domain_alloc_user op needs to fully initialize a domain before
+	 * return, so uses iommu_domain_alloc() here for simple.
+	 */
+	domain = iommu_domain_alloc(dev->bus);
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	if (nested_parent)
+		to_dmar_domain(domain)->nested_parent = true;
+
+	if (dirty_tracking) {
+		if (to_dmar_domain(domain)->use_first_level) {
+			iommu_domain_free(domain);
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+		domain->dirty_ops = &intel_dirty_ops;
+	}
+
+	return domain;
+}
+
 static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
 	if (domain != &si_domain->domain && domain != &blocking_domain)
 		domain_exit(to_dmar_domain(domain));
 }
 
-static int prepare_domain_attach_device(struct iommu_domain *domain,
-					struct device *dev)
+int prepare_domain_attach_device(struct iommu_domain *domain,
+				 struct device *dev)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu;
@@ -4078,6 +4129,9 @@ static int prepare_domain_attach_device(struct iommu_domain *domain,
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
+	if (domain->dirty_ops && !ssads_supported(iommu))
+		return -EINVAL;
+
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
 	if (addr_width > cap_mgaw(iommu->cap))
@@ -4332,6 +4386,8 @@ static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap)
 		return dmar_platform_optin();
 	case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
 		return ecap_sc_support(info->iommu->ecap);
+	case IOMMU_CAP_DIRTY_TRACKING:
+		return ssads_supported(info->iommu);
 	default:
 		return false;
 	}
@@ -4729,6 +4785,9 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
 		return -EOPNOTSUPP;
 
+	if (domain->dirty_ops)
+		return -EINVAL;
+
 	if (context_copied(iommu, info->bus, info->devfn))
 		return -EBUSY;
 
@@ -4780,6 +4839,7 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
 	if (!vtd)
 		return ERR_PTR(-ENOMEM);
 
+	vtd->flags = IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17;
 	vtd->cap_reg = iommu->cap;
 	vtd->ecap_reg = iommu->ecap;
 	*length = sizeof(*vtd);
@@ -4787,10 +4847,88 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
 	return vtd;
 }
 
+static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain,
+					  bool enable)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct device_domain_info *info;
+	int ret;
+
+	spin_lock(&dmar_domain->lock);
+	if (dmar_domain->dirty_tracking == enable)
+		goto out_unlock;
+
+	list_for_each_entry(info, &dmar_domain->devices, link) {
+		ret = intel_pasid_setup_dirty_tracking(info->iommu,
+						       info->domain, info->dev,
+						       IOMMU_NO_PASID, enable);
+		if (ret)
+			goto err_unwind;
+	}
+
+	dmar_domain->dirty_tracking = enable;
+out_unlock:
+	spin_unlock(&dmar_domain->lock);
+
+	return 0;
+
+err_unwind:
+	list_for_each_entry(info, &dmar_domain->devices, link)
+		intel_pasid_setup_dirty_tracking(info->iommu, dmar_domain,
+						 info->dev, IOMMU_NO_PASID,
+						 dmar_domain->dirty_tracking);
+	spin_unlock(&dmar_domain->lock);
+	return ret;
+}
+
+static int intel_iommu_read_and_clear_dirty(struct iommu_domain *domain,
+					    unsigned long iova, size_t size,
+					    unsigned long flags,
+					    struct iommu_dirty_bitmap *dirty)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long end = iova + size - 1;
+	unsigned long pgsize;
+
+	/*
+	 * IOMMUFD core calls into a dirty tracking disabled domain without an
+	 * IOVA bitmap set in order to clean dirty bits in all PTEs that might
+	 * have occurred when we stopped dirty tracking. This ensures that we
+	 * never inherit dirtied bits from a previous cycle.
+	 */
+	if (!dmar_domain->dirty_tracking && dirty->bitmap)
+		return -EINVAL;
+
+	do {
+		struct dma_pte *pte;
+		int lvl = 0;
+
+		pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &lvl,
+				     GFP_ATOMIC);
+		pgsize = level_size(lvl) << VTD_PAGE_SHIFT;
+		if (!pte || !dma_pte_present(pte)) {
+			iova += pgsize;
+			continue;
+		}
+
+		if (dma_sl_pte_test_and_clear_dirty(pte, flags))
+			iommu_dirty_bitmap_record(dirty, iova, pgsize);
+		iova += pgsize;
+	} while (iova < end);
+
+	return 0;
+}
+
+const struct iommu_dirty_ops intel_dirty_ops = {
+	.set_dirty_tracking = intel_iommu_set_dirty_tracking,
+	.read_and_clear_dirty = intel_iommu_read_and_clear_dirty,
+};
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc		= intel_iommu_domain_alloc,
+	.domain_alloc_user	= intel_iommu_domain_alloc_user,
 	.probe_device		= intel_iommu_probe_device,
 	.probe_finalize		= intel_iommu_probe_finalize,
 	.release_device		= intel_iommu_release_device,