1 files changed, 111 insertions, 86 deletions

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c13b9290e357..db516c90a977 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -67,7 +67,8 @@ struct vfio_iommu {
 	struct list_head	iova_list;
 	struct mutex		lock;
 	struct rb_root		dma_list;
-	struct blocking_notifier_head notifier;
+	struct list_head	device_list;
+	struct mutex		device_list_lock;
 	unsigned int		dma_avail;
 	unsigned int		vaddr_invalid_count;
 	uint64_t		pgsize_bitmap;
@@ -828,9 +829,9 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova,
 
 static int vfio_iommu_type1_pin_pages(void *iommu_data,
 				      struct iommu_group *iommu_group,
-				      unsigned long *user_pfn,
+				      dma_addr_t user_iova,
 				      int npage, int prot,
-				      unsigned long *phys_pfn)
+				      struct page **pages)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_iommu_group *group;
@@ -840,7 +841,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 	bool do_accounting;
 	dma_addr_t iova;
 
-	if (!iommu || !user_pfn || !phys_pfn)
+	if (!iommu || !pages)
 		return -EINVAL;
 
 	/* Supported for v2 version only */
@@ -856,7 +857,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 again:
 	if (iommu->vaddr_invalid_count) {
 		for (i = 0; i < npage; i++) {
-			iova = user_pfn[i] << PAGE_SHIFT;
+			iova = user_iova + PAGE_SIZE * i;
 			ret = vfio_find_dma_valid(iommu, iova, PAGE_SIZE, &dma);
 			if (ret < 0)
 				goto pin_done;
@@ -865,8 +866,8 @@ again:
 		}
 	}
 
-	/* Fail if notifier list is empty */
-	if (!iommu->notifier.head) {
+	/* Fail if no dma_umap notifier is registered */
+	if (list_empty(&iommu->device_list)) {
 		ret = -EINVAL;
 		goto pin_done;
 	}
@@ -879,9 +880,10 @@ again:
 	do_accounting = list_empty(&iommu->domain_list);
 
 	for (i = 0; i < npage; i++) {
+		unsigned long phys_pfn;
 		struct vfio_pfn *vpfn;
 
-		iova = user_pfn[i] << PAGE_SHIFT;
+		iova = user_iova + PAGE_SIZE * i;
 		dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
 		if (!dma) {
 			ret = -EINVAL;
@@ -895,23 +897,25 @@ again:
 
 		vpfn = vfio_iova_get_vfio_pfn(dma, iova);
 		if (vpfn) {
-			phys_pfn[i] = vpfn->pfn;
+			pages[i] = pfn_to_page(vpfn->pfn);
 			continue;
 		}
 
 		remote_vaddr = dma->vaddr + (iova - dma->iova);
-		ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i],
+		ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn,
 					     do_accounting);
 		if (ret)
 			goto pin_unwind;
 
-		ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]);
+		ret = vfio_add_to_pfn_list(dma, iova, phys_pfn);
 		if (ret) {
-			if (put_pfn(phys_pfn[i], dma->prot) && do_accounting)
+			if (put_pfn(phys_pfn, dma->prot) && do_accounting)
 				vfio_lock_acct(dma, -1, true);
 			goto pin_unwind;
 		}
 
+		pages[i] = pfn_to_page(phys_pfn);
+
 		if (iommu->dirty_page_tracking) {
 			unsigned long pgshift = __ffs(iommu->pgsize_bitmap);
 
@@ -934,43 +938,38 @@ again:
 	goto pin_done;
 
 pin_unwind:
-	phys_pfn[i] = 0;
+	pages[i] = NULL;
 	for (j = 0; j < i; j++) {
 		dma_addr_t iova;
 
-		iova = user_pfn[j] << PAGE_SHIFT;
+		iova = user_iova + PAGE_SIZE * j;
 		dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
 		vfio_unpin_page_external(dma, iova, do_accounting);
-		phys_pfn[j] = 0;
+		pages[j] = NULL;
 	}
 pin_done:
 	mutex_unlock(&iommu->lock);
 	return ret;
 }
 
-static int vfio_iommu_type1_unpin_pages(void *iommu_data,
-					unsigned long *user_pfn,
-					int npage)
+static void vfio_iommu_type1_unpin_pages(void *iommu_data,
+					 dma_addr_t user_iova, int npage)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	bool do_accounting;
 	int i;
 
-	if (!iommu || !user_pfn || npage <= 0)
-		return -EINVAL;
-
 	/* Supported for v2 version only */
-	if (!iommu->v2)
-		return -EACCES;
+	if (WARN_ON(!iommu->v2))
+		return;
 
 	mutex_lock(&iommu->lock);
 
 	do_accounting = list_empty(&iommu->domain_list);
 	for (i = 0; i < npage; i++) {
+		dma_addr_t iova = user_iova + PAGE_SIZE * i;
 		struct vfio_dma *dma;
-		dma_addr_t iova;
 
-		iova = user_pfn[i] << PAGE_SHIFT;
 		dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
 		if (!dma)
 			break;
@@ -979,7 +978,8 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data,
 	}
 
 	mutex_unlock(&iommu->lock);
-	return i > 0 ? i : -EINVAL;
+
+	WARN_ON(i != npage);
 }
 
 static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain,
@@ -1287,6 +1287,35 @@ static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size)
 	return 0;
 }
 
+/*
+ * Notify VFIO drivers using vfio_register_emulated_iommu_dev() to invalidate
+ * and unmap iovas within the range we're about to unmap. Drivers MUST unpin
+ * pages in response to an invalidation.
+ */
+static void vfio_notify_dma_unmap(struct vfio_iommu *iommu,
+				  struct vfio_dma *dma)
+{
+	struct vfio_device *device;
+
+	if (list_empty(&iommu->device_list))
+		return;
+
+	/*
+	 * The device is expected to call vfio_unpin_pages() for any IOVA it has
+	 * pinned within the range. Since vfio_unpin_pages() will eventually
+	 * call back down to this code and try to obtain the iommu->lock we must
+	 * drop it.
+	 */
+	mutex_lock(&iommu->device_list_lock);
+	mutex_unlock(&iommu->lock);
+
+	list_for_each_entry(device, &iommu->device_list, iommu_entry)
+		device->ops->dma_unmap(device, dma->iova, dma->size);
+
+	mutex_unlock(&iommu->device_list_lock);
+	mutex_lock(&iommu->lock);
+}
+
 static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 			     struct vfio_iommu_type1_dma_unmap *unmap,
 			     struct vfio_bitmap *bitmap)
@@ -1377,12 +1406,6 @@ again:
 
 		if (!iommu->v2 && iova > dma->iova)
 			break;
-		/*
-		 * Task with same address space who mapped this iova range is
-		 * allowed to unmap the iova range.
-		 */
-		if (dma->task->mm != current->mm)
-			break;
 
 		if (invalidate_vaddr) {
 			if (dma->vaddr_invalid) {
@@ -1406,8 +1429,6 @@ again:
 		}
 
 		if (!RB_EMPTY_ROOT(&dma->pfn_list)) {
-			struct vfio_iommu_type1_dma_unmap nb_unmap;
-
 			if (dma_last == dma) {
 				BUG_ON(++retries > 10);
 			} else {
@@ -1415,20 +1436,7 @@ again:
 				retries = 0;
 			}
 
-			nb_unmap.iova = dma->iova;
-			nb_unmap.size = dma->size;
-
-			/*
-			 * Notify anyone (mdev vendor drivers) to invalidate and
-			 * unmap iovas within the range we're about to unmap.
-			 * Vendor drivers MUST unpin pages in response to an
-			 * invalidation.
-			 */
-			mutex_unlock(&iommu->lock);
-			blocking_notifier_call_chain(&iommu->notifier,
-						    VFIO_IOMMU_NOTIFY_DMA_UNMAP,
-						    &nb_unmap);
-			mutex_lock(&iommu->lock);
+			vfio_notify_dma_unmap(iommu, dma);
 			goto again;
 		}
 
@@ -1679,18 +1687,6 @@ out_unlock:
 	return ret;
 }
 
-static int vfio_bus_type(struct device *dev, void *data)
-{
-	struct bus_type **bus = data;
-
-	if (*bus && *bus != dev->bus)
-		return -EINVAL;
-
-	*bus = dev->bus;
-
-	return 0;
-}
-
 static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			     struct vfio_domain *domain)
 {
@@ -2153,13 +2149,26 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
 	list_splice_tail(iova_copy, iova);
 }
 
+/* Redundantly walks non-present capabilities to simplify caller */
+static int vfio_iommu_device_capable(struct device *dev, void *data)
+{
+	return device_iommu_capable(dev, (enum iommu_cap)data);
+}
+
+static int vfio_iommu_domain_alloc(struct device *dev, void *data)
+{
+	struct iommu_domain **domain = data;
+
+	*domain = iommu_domain_alloc(dev->bus);
+	return 1; /* Don't iterate */
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 		struct iommu_group *iommu_group, enum vfio_group_type type)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_iommu_group *group;
 	struct vfio_domain *domain, *d;
-	struct bus_type *bus = NULL;
 	bool resv_msi, msi_remap;
 	phys_addr_t resv_msi_base = 0;
 	struct iommu_domain_geometry *geo;
@@ -2192,18 +2201,19 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_unlock;
 	}
 
-	/* Determine bus_type in order to allocate a domain */
-	ret = iommu_group_for_each_dev(iommu_group, &bus, vfio_bus_type);
-	if (ret)
-		goto out_free_group;
-
 	ret = -ENOMEM;
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
 		goto out_free_group;
 
+	/*
+	 * Going via the iommu_group iterator avoids races, and trivially gives
+	 * us a representative device for the IOMMU API call. We don't actually
+	 * want to iterate beyond the first device (if any).
+	 */
 	ret = -EIO;
-	domain->domain = iommu_domain_alloc(bus);
+	iommu_group_for_each_dev(iommu_group, &domain->domain,
+				 vfio_iommu_domain_alloc);
 	if (!domain->domain)
 		goto out_free_domain;
 
@@ -2258,7 +2268,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	list_add(&group->next, &domain->group_list);
 
 	msi_remap = irq_domain_check_msi_remap() ||
-		    iommu_capable(bus, IOMMU_CAP_INTR_REMAP);
+		    iommu_group_for_each_dev(iommu_group, (void *)IOMMU_CAP_INTR_REMAP,
+					     vfio_iommu_device_capable);
 
 	if (!allow_unsafe_interrupts && !msi_remap) {
 		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
@@ -2478,7 +2489,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 
 		if (list_empty(&iommu->emulated_iommu_groups) &&
 		    list_empty(&iommu->domain_list)) {
-			WARN_ON(iommu->notifier.head);
+			WARN_ON(!list_empty(&iommu->device_list));
 			vfio_iommu_unmap_unpin_all(iommu);
 		}
 		goto detach_group_done;
@@ -2510,7 +2521,8 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		if (list_empty(&domain->group_list)) {
 			if (list_is_singular(&iommu->domain_list)) {
 				if (list_empty(&iommu->emulated_iommu_groups)) {
-					WARN_ON(iommu->notifier.head);
+					WARN_ON(!list_empty(
+						&iommu->device_list));
 					vfio_iommu_unmap_unpin_all(iommu);
 				} else {
 					vfio_iommu_unmap_unpin_reaccount(iommu);
@@ -2571,7 +2583,8 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 	iommu->dma_avail = dma_entry_limit;
 	iommu->container_open = true;
 	mutex_init(&iommu->lock);
-	BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
+	mutex_init(&iommu->device_list_lock);
+	INIT_LIST_HEAD(&iommu->device_list);
 	init_waitqueue_head(&iommu->vaddr_wait);
 	iommu->pgsize_bitmap = PAGE_MASK;
 	INIT_LIST_HEAD(&iommu->emulated_iommu_groups);
@@ -3008,28 +3021,40 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 	}
 }
 
-static int vfio_iommu_type1_register_notifier(void *iommu_data,
-					      unsigned long *events,
-					      struct notifier_block *nb)
+static void vfio_iommu_type1_register_device(void *iommu_data,
+					     struct vfio_device *vdev)
 {
 	struct vfio_iommu *iommu = iommu_data;
 
-	/* clear known events */
-	*events &= ~VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-
-	/* refuse to register if still events remaining */
-	if (*events)
-		return -EINVAL;
+	if (!vdev->ops->dma_unmap)
+		return;
 
-	return blocking_notifier_chain_register(&iommu->notifier, nb);
+	/*
+	 * list_empty(&iommu->device_list) is tested under the iommu->lock while
+	 * iteration for dma_unmap must be done under the device_list_lock.
+	 * Holding both locks here allows avoiding the device_list_lock in
+	 * several fast paths. See vfio_notify_dma_unmap()
+	 */
+	mutex_lock(&iommu->lock);
+	mutex_lock(&iommu->device_list_lock);
+	list_add(&vdev->iommu_entry, &iommu->device_list);
+	mutex_unlock(&iommu->device_list_lock);
+	mutex_unlock(&iommu->lock);
 }
 
-static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
-						struct notifier_block *nb)
+static void vfio_iommu_type1_unregister_device(void *iommu_data,
+					       struct vfio_device *vdev)
 {
 	struct vfio_iommu *iommu = iommu_data;
 
-	return blocking_notifier_chain_unregister(&iommu->notifier, nb);
+	if (!vdev->ops->dma_unmap)
+		return;
+
+	mutex_lock(&iommu->lock);
+	mutex_lock(&iommu->device_list_lock);
+	list_del(&vdev->iommu_entry);
+	mutex_unlock(&iommu->device_list_lock);
+	mutex_unlock(&iommu->lock);
 }
 
 static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
@@ -3163,8 +3188,8 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.detach_group		= vfio_iommu_type1_detach_group,
 	.pin_pages		= vfio_iommu_type1_pin_pages,
 	.unpin_pages		= vfio_iommu_type1_unpin_pages,
-	.register_notifier	= vfio_iommu_type1_register_notifier,
-	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
+	.register_device	= vfio_iommu_type1_register_device,
+	.unregister_device	= vfio_iommu_type1_unregister_device,
 	.dma_rw			= vfio_iommu_type1_dma_rw,
 	.group_iommu_domain	= vfio_iommu_type1_group_iommu_domain,
 	.notify			= vfio_iommu_type1_notify,