1 files changed, 168 insertions, 95 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 5c8c5cdc36cf..5db283c17e0d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -22,6 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
+#include <uapi/linux/iommufd.h>
 
 #include "iommu.h"
 #include "../dma-iommu.h"
@@ -113,13 +114,17 @@ static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
-static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn)
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
 {
 	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
 }
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
 static inline unsigned long page_to_dma_pfn(struct page *pg)
 {
-	return mm_to_dma_pfn(page_to_pfn(pg));
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
 }
 static inline unsigned long virt_to_dma_pfn(void *p)
 {
@@ -877,7 +882,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	}
 	/* For request-without-pasid, get the pasid from context entry */
 	if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID)
-		pasid = PASID_RID2PASID;
+		pasid = IOMMU_NO_PASID;
 
 	dir_index = pasid >> PASID_PDE_SHIFT;
 	pde = &dir[dir_index];
@@ -1359,6 +1364,7 @@ domain_lookup_dev_info(struct dmar_domain *domain,
 
 static void domain_update_iotlb(struct dmar_domain *domain)
 {
+	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
 	bool has_iotlb_device = false;
 	unsigned long flags;
@@ -1370,6 +1376,14 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 			break;
 		}
 	}
+
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
+		info = dev_iommu_priv_get(dev_pasid->dev);
+		if (info->ats_enabled) {
+			has_iotlb_device = true;
+			break;
+		}
+	}
 	domain->has_iotlb_device = has_iotlb_device;
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1449,12 +1463,13 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
 	qdep = info->ats_qdep;
 	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
 			   qdep, addr, mask);
-	quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep);
+	quirk_extra_dev_tlb_flush(info, addr, mask, IOMMU_NO_PASID, qdep);
 }
 
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
+	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
 	unsigned long flags;
 
@@ -1464,6 +1479,36 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link)
 		__iommu_flush_dev_iotlb(info, addr, mask);
+
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
+		info = dev_iommu_priv_get(dev_pasid->dev);
+
+		if (!info->ats_enabled)
+			continue;
+
+		qi_flush_dev_iotlb_pasid(info->iommu,
+					 PCI_DEVID(info->bus, info->devfn),
+					 info->pfsid, dev_pasid->pasid,
+					 info->ats_qdep, addr,
+					 mask);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
+				     struct dmar_domain *domain, u64 addr,
+				     unsigned long npages, bool ih)
+{
+	u16 did = domain_id_iommu(domain, iommu);
+	struct dev_pasid_info *dev_pasid;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain)
+		qi_flush_piotlb(iommu, did, dev_pasid->pasid, addr, npages, ih);
+
+	if (!list_empty(&domain->devices))
+		qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, npages, ih);
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
@@ -1484,7 +1529,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 		ih = 1 << 6;
 
 	if (domain->use_first_level) {
-		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih);
+		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
 	} else {
 		unsigned long bitmask = aligned_pages - 1;
 
@@ -1554,7 +1599,7 @@ static void intel_flush_iotlb_all(struct iommu_domain *domain)
 		u16 did = domain_id_iommu(dmar_domain, iommu);
 
 		if (dmar_domain->use_first_level)
-			qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0);
+			domain_flush_pasid_iotlb(iommu, dmar_domain, 0, -1, 0);
 		else
 			iommu->flush.flush_iotlb(iommu, did, 0, 0,
 						 DMA_TLB_DSI_FLUSH);
@@ -1726,6 +1771,7 @@ static struct dmar_domain *alloc_domain(unsigned int type)
 		domain->use_first_level = true;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->dev_pasids);
 	spin_lock_init(&domain->lock);
 	xa_init(&domain->iommu_array);
 
@@ -1940,7 +1986,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 				context_pdts(pds);
 
 		/* Setup the RID_PASID field: */
-		context_set_sm_rid2pasid(context, PASID_RID2PASID);
+		context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
 
 		/*
 		 * Setup the Device-TLB enable bit and Page request
@@ -2362,8 +2408,8 @@ static int __init si_domain_init(int hw)
 
 		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 			ret = iommu_domain_identity_map(si_domain,
-					mm_to_dma_pfn(start_pfn),
-					mm_to_dma_pfn(end_pfn));
+					mm_to_dma_pfn_start(start_pfn),
+					mm_to_dma_pfn_end(end_pfn));
 			if (ret)
 				return ret;
 		}
@@ -2384,8 +2430,8 @@ static int __init si_domain_init(int hw)
 				continue;
 
 			ret = iommu_domain_identity_map(si_domain,
-					mm_to_dma_pfn(start >> PAGE_SHIFT),
-					mm_to_dma_pfn(end >> PAGE_SHIFT));
+					mm_to_dma_pfn_start(start >> PAGE_SHIFT),
+					mm_to_dma_pfn_end(end >> PAGE_SHIFT));
 			if (ret)
 				return ret;
 		}
@@ -2420,13 +2466,13 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 		/* Setup the PASID entry for requests without PASID: */
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
-					dev, PASID_RID2PASID);
+					dev, IOMMU_NO_PASID);
 		else if (domain->use_first_level)
 			ret = domain_setup_first_level(iommu, domain, dev,
-					PASID_RID2PASID);
+					IOMMU_NO_PASID);
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
-					dev, PASID_RID2PASID);
+					dev, IOMMU_NO_PASID);
 		if (ret) {
 			dev_err(dev, "Setup RID2PASID failed\n");
 			device_block_translation(dev);
@@ -2446,30 +2492,6 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	return 0;
 }
 
-static bool device_has_rmrr(struct device *dev)
-{
-	struct dmar_rmrr_unit *rmrr;
-	struct device *tmp;
-	int i;
-
-	rcu_read_lock();
-	for_each_rmrr_units(rmrr) {
-		/*
-		 * Return TRUE if this RMRR contains the device that
-		 * is passed in.
-		 */
-		for_each_active_dev_scope(rmrr->devices,
-					  rmrr->devices_cnt, i, tmp)
-			if (tmp == dev ||
-			    is_downstream_to_pci_bridge(dev, tmp)) {
-				rcu_read_unlock();
-				return true;
-			}
-	}
-	rcu_read_unlock();
-	return false;
-}
-
 /**
  * device_rmrr_is_relaxable - Test whether the RMRR of this device
  * is relaxable (ie. is allowed to be not enforced under some conditions)
@@ -2500,34 +2522,6 @@ static bool device_rmrr_is_relaxable(struct device *dev)
 }
 
 /*
- * There are a couple cases where we need to restrict the functionality of
- * devices associated with RMRRs.  The first is when evaluating a device for
- * identity mapping because problems exist when devices are moved in and out
- * of domains and their respective RMRR information is lost.  This means that
- * a device with associated RMRRs will never be in a "passthrough" domain.
- * The second is use of the device through the IOMMU API.  This interface
- * expects to have full control of the IOVA space for the device.  We cannot
- * satisfy both the requirement that RMRR access is maintained and have an
- * unencumbered IOVA space.  We also have no ability to quiesce the device's
- * use of the RMRR space or even inform the IOMMU API user of the restriction.
- * We therefore prevent devices associated with an RMRR from participating in
- * the IOMMU API, which eliminates them from device assignment.
- *
- * In both cases, devices which have relaxable RMRRs are not concerned by this
- * restriction. See device_rmrr_is_relaxable comment.
- */
-static bool device_is_rmrr_locked(struct device *dev)
-{
-	if (!device_has_rmrr(dev))
-		return false;
-
-	if (device_rmrr_is_relaxable(dev))
-		return false;
-
-	return true;
-}
-
-/*
  * Return the required default domain type for a specific device.
  *
  * @dev: the device in query
@@ -3560,8 +3554,8 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 				       unsigned long val, void *v)
 {
 	struct memory_notify *mhp = v;
-	unsigned long start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
-	unsigned long last_vpfn = mm_to_dma_pfn(mhp->start_pfn +
+	unsigned long start_vpfn = mm_to_dma_pfn_start(mhp->start_pfn);
+	unsigned long last_vpfn = mm_to_dma_pfn_end(mhp->start_pfn +
 			mhp->nr_pages - 1);
 
 	switch (val) {
@@ -3756,7 +3750,6 @@ static int __init probe_acpi_namespace_devices(void)
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, dev) {
 			struct acpi_device_physical_node *pn;
-			struct iommu_group *group;
 			struct acpi_device *adev;
 
 			if (dev->bus != &acpi_bus_type)
@@ -3766,12 +3759,6 @@ static int __init probe_acpi_namespace_devices(void)
 			mutex_lock(&adev->physical_node_lock);
 			list_for_each_entry(pn,
 					    &adev->physical_node_list, node) {
-				group = iommu_group_get(pn->dev);
-				if (group) {
-					iommu_group_put(group);
-					continue;
-				}
-
 				ret = iommu_probe_device(pn->dev);
 				if (ret)
 					break;
@@ -3968,7 +3955,7 @@ static void dmar_remove_one_dev_info(struct device *dev)
 	if (!dev_is_real_dma_subdevice(info->dev)) {
 		if (dev_is_pci(info->dev) && sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, info->dev,
-					PASID_RID2PASID, false);
+					IOMMU_NO_PASID, false);
 
 		iommu_disable_pci_caps(info);
 		domain_context_clear(info);
@@ -3997,7 +3984,7 @@ static void device_block_translation(struct device *dev)
 	if (!dev_is_real_dma_subdevice(dev)) {
 		if (sm_supported(iommu))
 			intel_pasid_tear_down_entry(iommu, dev,
-						    PASID_RID2PASID, false);
+						    IOMMU_NO_PASID, false);
 		else
 			domain_context_clear(info);
 	}
@@ -4139,12 +4126,6 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	int ret;
 
-	if (domain->type == IOMMU_DOMAIN_UNMANAGED &&
-	    device_is_rmrr_locked(dev)) {
-		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
-		return -EPERM;
-	}
-
 	if (info->domain)
 		device_block_translation(dev);
 
@@ -4271,7 +4252,7 @@ static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 	unsigned long i;
 
 	nrpages = aligned_nrpages(gather->start, size);
-	start_pfn = mm_to_dma_pfn(iova_pfn);
+	start_pfn = mm_to_dma_pfn_start(iova_pfn);
 
 	xa_for_each(&dmar_domain->iommu_array, i, info)
 		iommu_flush_iotlb_psi(info->iommu, dmar_domain,
@@ -4331,7 +4312,7 @@ static void domain_set_force_snooping(struct dmar_domain *domain)
 
 	list_for_each_entry(info, &domain->devices, link)
 		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
-						     PASID_RID2PASID);
+						     IOMMU_NO_PASID);
 }
 
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
@@ -4713,27 +4694,118 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
+	unsigned long flags;
 
-	/* Domain type specific cleanup: */
 	domain = iommu_get_domain_for_dev_pasid(dev, pasid, 0);
-	if (domain) {
-		switch (domain->type) {
-		case IOMMU_DOMAIN_SVA:
-			intel_svm_remove_dev_pasid(dev, pasid);
-			break;
-		default:
-			/* should never reach here */
-			WARN_ON(1);
+	if (WARN_ON_ONCE(!domain))
+		goto out_tear_down;
+
+	/*
+	 * The SVA implementation needs to handle its own stuffs like the mm
+	 * notification. Before consolidating that code into iommu core, let
+	 * the intel sva code handle it.
+	 */
+	if (domain->type == IOMMU_DOMAIN_SVA) {
+		intel_svm_remove_dev_pasid(dev, pasid);
+		goto out_tear_down;
+	}
+
+	dmar_domain = to_dmar_domain(domain);
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
+		if (curr->dev == dev && curr->pasid == pasid) {
+			list_del(&curr->link_domain);
+			dev_pasid = curr;
 			break;
 		}
 	}
+	WARN_ON_ONCE(!dev_pasid);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
+	domain_detach_iommu(dmar_domain, iommu);
+	kfree(dev_pasid);
+out_tear_down:
 	intel_pasid_tear_down_entry(iommu, dev, pasid, false);
+	intel_drain_pasid_prq(dev, pasid);
+}
+
+static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
+				     struct device *dev, ioasid_t pasid)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct intel_iommu *iommu = info->iommu;
+	struct dev_pasid_info *dev_pasid;
+	unsigned long flags;
+	int ret;
+
+	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
+		return -EOPNOTSUPP;
+
+	if (context_copied(iommu, info->bus, info->devfn))
+		return -EBUSY;
+
+	ret = prepare_domain_attach_device(domain, dev);
+	if (ret)
+		return ret;
+
+	dev_pasid = kzalloc(sizeof(*dev_pasid), GFP_KERNEL);
+	if (!dev_pasid)
+		return -ENOMEM;
+
+	ret = domain_attach_iommu(dmar_domain, iommu);
+	if (ret)
+		goto out_free;
+
+	if (domain_type_is_si(dmar_domain))
+		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
+						     dev, pasid);
+	else if (dmar_domain->use_first_level)
+		ret = domain_setup_first_level(iommu, dmar_domain,
+					       dev, pasid);
+	else
+		ret = intel_pasid_setup_second_level(iommu, dmar_domain,
+						     dev, pasid);
+	if (ret)
+		goto out_detach_iommu;
+
+	dev_pasid->dev = dev;
+	dev_pasid->pasid = pasid;
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
+
+	return 0;
+out_detach_iommu:
+	domain_detach_iommu(dmar_domain, iommu);
+out_free:
+	kfree(dev_pasid);
+	return ret;
+}
+
+static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct iommu_hw_info_vtd *vtd;
+
+	vtd = kzalloc(sizeof(*vtd), GFP_KERNEL);
+	if (!vtd)
+		return ERR_PTR(-ENOMEM);
+
+	vtd->cap_reg = iommu->cap;
+	vtd->ecap_reg = iommu->ecap;
+	*length = sizeof(*vtd);
+	*type = IOMMU_HW_INFO_TYPE_INTEL_VTD;
+	return vtd;
 }
 
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
+	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc		= intel_iommu_domain_alloc,
 	.probe_device		= intel_iommu_probe_device,
 	.probe_finalize		= intel_iommu_probe_finalize,
@@ -4751,6 +4823,7 @@ const struct iommu_ops intel_iommu_ops = {
 #endif
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= intel_iommu_attach_device,
+		.set_dev_pasid		= intel_iommu_set_dev_pasid,
 		.map_pages		= intel_iommu_map_pages,
 		.unmap_pages		= intel_iommu_unmap_pages,
 		.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
@@ -4987,7 +5060,7 @@ void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
 		return;
 
 	sid = PCI_DEVID(info->bus, info->devfn);
-	if (pasid == PASID_RID2PASID) {
+	if (pasid == IOMMU_NO_PASID) {
 		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
 				   qdep, address, mask);
 	} else {