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

Pull iommufd updates from Jason Gunthorpe:
 "Several fixes:

   - Add missing static const

   - Correct type 1 emulation for VFIO_CHECK_EXTENSION when no-iommu is
     turned on

   - Fix selftest memory leak and syzkaller splat

   - Fix missed -EFAULT in fault reporting write() fops

   - Fix a race where map/unmap with the internal IOVA allocator can
     unmap things it should not"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd:
  iommufd: Fix a race with concurrent allocation and unmap
  iommufd/selftest: Remove MOCK_IOMMUPT_AMDV1 format
  iommufd: Fix return value of iommufd_fault_fops_write()
  iommufd: update outdated comment for renamed iommufd_hw_pagetable_alloc()
  iommufd/selftest: Fix page leaks in mock_viommu_{init,destroy}
  iommufd: vfio compatibility extension check for noiommu mode
  iommufd: Constify struct dma_buf_attach_ops

Author: torvalds

drivers/iommu/iommufd/device.c

@@ -866,7 +866,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev, ioasid_t pasid,
 {
 	/*
 	 * iommufd_hw_pagetable_attach() is called by
-	 * iommufd_hw_pagetable_alloc() in immediate attachment mode, same as
+	 * iommufd_hwpt_paging_alloc() in immediate attachment mode, same as
 	 * iommufd_device_do_attach(). So if we are in this mode then we prefer
 	 * to use the immediate_attach path as it supports drivers that can't
 	 * directly allocate a domain.

drivers/iommu/iommufd/eventq.c

@@ -187,9 +187,10 @@ static ssize_t iommufd_fault_fops_write(struct file *filep, const char __user *b
 
 	mutex_lock(&fault->mutex);
 	while (count > done) {
-		rc = copy_from_user(&response, buf + done, response_size);
-		if (rc)
+		if (copy_from_user(&response, buf + done, response_size)) {
+			rc = -EFAULT;
 			break;
+		}
 
 		static_assert((int)IOMMUFD_PAGE_RESP_SUCCESS ==
 			      (int)IOMMU_PAGE_RESP_SUCCESS);

drivers/iommu/iommufd/io_pagetable.c

@@ -814,6 +814,16 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start,
 		unmapped_bytes += area_last - area_first + 1;
 
 		down_write(&iopt->iova_rwsem);
+
+		/*
+		 * After releasing the iova_rwsem concurrent allocation could
+		 * place new areas at IOVAs we have already unmapped. Keep
+		 * moving the start of the search forward to ignore the area
+		 * already unmapped.
+		 */
+		if (area_last >= last)
+			break;
+		start = area_last + 1;
 	}
 
 out_unlock_iova:

drivers/iommu/iommufd/iommufd_test.h

@@ -36,7 +36,6 @@ enum {
 enum {
 	MOCK_IOMMUPT_DEFAULT = 0,
 	MOCK_IOMMUPT_HUGE,
-	MOCK_IOMMUPT_AMDV1,
 };
 
 /* These values are true for MOCK_IOMMUPT_DEFAULT */

drivers/iommu/iommufd/pages.c

@@ -1450,7 +1450,7 @@ static void iopt_revoke_notify(struct dma_buf_attachment *attach)
 	pages->dmabuf.phys.len = 0;
 }
 
-static struct dma_buf_attach_ops iopt_dmabuf_attach_revoke_ops = {
+static const struct dma_buf_attach_ops iopt_dmabuf_attach_revoke_ops = {
 	.allow_peer2peer = true,
 	.invalidate_mappings = iopt_revoke_notify,
 };

drivers/iommu/iommufd/selftest.c

@@ -421,19 +421,6 @@ static const struct iommu_dirty_ops amdv1_mock_dirty_ops = {
 	.set_dirty_tracking = mock_domain_set_dirty_tracking,
 };
 
-static const struct iommu_domain_ops amdv1_ops = {
-	IOMMU_PT_DOMAIN_OPS(amdv1),
-	.free = mock_domain_free,
-	.attach_dev = mock_domain_nop_attach,
-	.set_dev_pasid = mock_domain_set_dev_pasid_nop,
-	.iotlb_sync = &mock_iotlb_sync,
-};
-
-static const struct iommu_dirty_ops amdv1_dirty_ops = {
-	IOMMU_PT_DIRTY_OPS(amdv1),
-	.set_dirty_tracking = mock_domain_set_dirty_tracking,
-};
-
 static struct mock_iommu_domain *
 mock_domain_alloc_pgtable(struct device *dev,
 			  const struct iommu_hwpt_selftest *user_cfg, u32 flags)
@@ -477,24 +464,6 @@ mock_domain_alloc_pgtable(struct device *dev,
 			mock->domain.dirty_ops = &amdv1_mock_dirty_ops;
 		break;
 	}
-
-	case MOCK_IOMMUPT_AMDV1: {
-		struct pt_iommu_amdv1_cfg cfg = {};
-
-		cfg.common.hw_max_vasz_lg2 = 64;
-		cfg.common.hw_max_oasz_lg2 = 52;
-		cfg.common.features = BIT(PT_FEAT_DYNAMIC_TOP) |
-				      BIT(PT_FEAT_AMDV1_ENCRYPT_TABLES) |
-				      BIT(PT_FEAT_AMDV1_FORCE_COHERENCE);
-		cfg.starting_level = 2;
-		mock->domain.ops = &amdv1_ops;
-		rc = pt_iommu_amdv1_init(&mock->amdv1, &cfg, GFP_KERNEL);
-		if (rc)
-			goto err_free;
-		if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING)
-			mock->domain.dirty_ops = &amdv1_dirty_ops;
-		break;
-	}
 	default:
 		rc = -EOPNOTSUPP;
 		goto err_free;
@@ -636,7 +605,7 @@ static void mock_viommu_destroy(struct iommufd_viommu *viommu)
 	if (mock_viommu->mmap_offset)
 		iommufd_viommu_destroy_mmap(&mock_viommu->core,
 					    mock_viommu->mmap_offset);
-	free_page((unsigned long)mock_viommu->page);
+	free_pages((unsigned long)mock_viommu->page, 1);
 	mutex_destroy(&mock_viommu->queue_mutex);
 
 	/* iommufd core frees mock_viommu and viommu */
@@ -870,7 +839,7 @@ static int mock_viommu_init(struct iommufd_viommu *viommu,
 	iommufd_viommu_destroy_mmap(&mock_viommu->core,
 				    mock_viommu->mmap_offset);
 err_free_page:
-	free_page((unsigned long)mock_viommu->page);
+	free_pages((unsigned long)mock_viommu->page, 1);
 	return rc;
 }
 

drivers/iommu/iommufd/vfio_compat.c

@@ -283,7 +283,7 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx,
 	case VFIO_TYPE1_IOMMU:
 	case VFIO_TYPE1v2_IOMMU:
 	case VFIO_UNMAP_ALL:
-		return 1;
+		return !ictx->no_iommu_mode;
 
 	case VFIO_NOIOMMU_IOMMU:
 		return IS_ENABLED(CONFIG_VFIO_NOIOMMU);