[PATCH v7 3/4] iommu/vt-d: Add set_dev_pasid callback for dma domain

[Jacob Pan]

From: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>

This allows the upper layers to set a domain to a PASID of a device
if the PASID feature is supported by the IOMMU hardware. The typical
use cases are, for example, kernel DMA with PASID and hardware
assisted mediated device drivers.

The attaching device and pasid information is tracked in a per-domain
list and is used for IOTLB and devTLB invalidation.

Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
---
 drivers/iommu/intel/iommu.c | 139 +++++++++++++++++++++++++++++++++---
 drivers/iommu/intel/iommu.h |   7 ++
 2 files changed, 135 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 4eba9973f537..6386f7e4da04 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1367,6 +1367,7 @@ 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;
@@ -1378,6 +1379,14 @@ 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);
 }
@@ -1463,6 +1472,7 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
 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;
 
@@ -1472,6 +1482,37 @@ 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);
+		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);
+}
+
+/*
+ * The VT-d spec requires to use PASID-based-IOTLB Invalidation to
+ * invalidate IOTLB and the paging-structure-caches for a first-stage
+ * page table.
+ */
+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);
 }
 
@@ -1492,7 +1533,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 		ih = 1 << 6;
 
 	if (domain->use_first_level) {
-		qi_flush_piotlb(iommu, did, IOMMU_NO_PASID, addr, pages, ih);
+		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
 	} else {
 		unsigned long bitmask = aligned_pages - 1;
 
@@ -1562,7 +1603,7 @@ 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, IOMMU_NO_PASID, 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);
@@ -1734,6 +1775,7 @@ 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);
 
@@ -4720,25 +4762,99 @@ 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 (!domain)
+		goto out_tear_down;
+
+	/*
+	 * The SVA implementation needs to stop mm notification, drain the
+	 * pending page fault requests before tearing down the pasid entry.
+	 * The VT-d spec (section 6.2.3.1) also recommends that software
+	 * could use a reserved domain id for all first-only and pass-through
+	 * translations. Hence there's no need to call domain_detach_iommu()
+	 * in the sva domain case.
+	 */
+	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;
 		}
 	}
+	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);
 }
 
+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;
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
@@ -4758,6 +4874,7 @@ 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,
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 1c5e1d88862b..30c30e00fbdf 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -595,6 +595,7 @@ struct dmar_domain {
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
+	struct list_head dev_pasids;	/* all attached pasids */
 
 	struct dma_pte	*pgd;		/* virtual address */
 	int		gaw;		/* max guest address width */
@@ -717,6 +718,12 @@ struct device_domain_info {
 	struct pasid_table *pasid_table; /* pasid table */
 };
 
+struct dev_pasid_info {
+	struct list_head link_domain;	/* link to domain siblings */
+	struct device *dev;		/* the physical device */
+	ioasid_t pasid;			/* PASID of the physical device */
+};
+
 static inline void __iommu_flush_cache(
 	struct intel_iommu *iommu, void *addr, int size)
 {
-- 
2.25.1