Merge tag 'vfio-v7.0-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:
 "A small cycle with the bulk in selftests and reintroducing poison
  handling in the nvgrace-gpu driver. The rest are fixes, cleanups, and
  some dmabuf structure consolidation.

   - Update outdated mdev comment referencing the renamed
     mdev_type_add() function (Julia Lawall)

   - Introduce selftest support for IOMMU mapping of PCI MMIO BARs (Alex
     Mastro)

   - Relax selftest assertion relative to differences in huge page
     handling between legacy (v1) TYPE1 IOMMU mapping behavior and the
     compatibility mode supported by IOMMUFD (David Matlack)

   - Reintroduce memory poison handling support for non-struct-page-
     backed memory in the nvgrace-gpu variant driver (Ankit Agrawal)

   - Replace dma_buf_phys_vec with phys_vec to avoid duplicate structure
     and semantics (Leon Romanovsky)

   - Add missing upstream bridge locking across PCI function reset,
     resolving an assertion failure when secondary bus reset is used to
     provide that reset (Anthony Pighin)

   - Fixes to hisi_acc vfio-pci variant driver to resolve corner case
     issues related to resets, repeated migration, and error injection
     scenarios (Longfang Liu, Weili Qian)

   - Restrict vfio selftest builds to arm64 and x86_64, resolving
     compiler warnings on 32-bit archs (Ted Logan)

   - Un-deprecate the fsl-mc vfio bus driver as a new maintainer has
     stepped up (Ioana Ciornei)"

* tag 'vfio-v7.0-rc1' of https://github.com/awilliam/linux-vfio:
  vfio/fsl-mc: add myself as maintainer
  vfio: selftests: only build tests on arm64 and x86_64
  hisi_acc_vfio_pci: fix the queue parameter anomaly issue
  hisi_acc_vfio_pci: resolve duplicate migration states
  hisi_acc_vfio_pci: update status after RAS error
  hisi_acc_vfio_pci: fix VF reset timeout issue
  vfio/pci: Lock upstream bridge for vfio_pci_core_disable()
  types: reuse common phys_vec type instead of DMABUF open‑coded variant
  vfio/nvgrace-gpu: register device memory for poison handling
  mm: add stubs for PFNMAP memory failure registration functions
  vfio: selftests: Drop IOMMU mapping size assertions for VFIO_TYPE1_IOMMU
  vfio: selftests: Add vfio_dma_mapping_mmio_test
  vfio: selftests: Align BAR mmaps for efficient IOMMU mapping
  vfio: selftests: Centralize IOMMU mode name definitions
  vfio/mdev: update outdated comment

26 files changed, 411 insertions, 67 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 398045c00495..28d6fd75d43a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27606,8 +27606,9 @@ F:	include/uapi/linux/vfio.h
 F:	tools/testing/selftests/vfio/
 
 VFIO FSL-MC DRIVER
+M:	Ioana Ciornei <ioana.ciornei@nxp.com>
 L:	kvm@vger.kernel.org
-S:	Obsolete
+S:	Maintained
 F:	drivers/vfio/fsl-mc/
 
 VFIO HISILICON PCI DRIVER
diff --git a/drivers/dma-buf/dma-buf-mapping.c b/drivers/dma-buf/dma-buf-mapping.c
index b7352e609fbd..174677faa577 100644
--- a/drivers/dma-buf/dma-buf-mapping.c
+++ b/drivers/dma-buf/dma-buf-mapping.c
@@ -33,8 +33,8 @@ static struct scatterlist *fill_sg_entry(struct scatterlist *sgl, size_t length,
 }
 
 static unsigned int calc_sg_nents(struct dma_iova_state *state,
-				  struct dma_buf_phys_vec *phys_vec,
-				  size_t nr_ranges, size_t size)
+				  struct phys_vec *phys_vec, size_t nr_ranges,
+				  size_t size)
 {
 	unsigned int nents = 0;
 	size_t i;
@@ -91,7 +91,7 @@ struct dma_buf_dma {
  */
 struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach,
 					 struct p2pdma_provider *provider,
-					 struct dma_buf_phys_vec *phys_vec,
+					 struct phys_vec *phys_vec,
 					 size_t nr_ranges, size_t size,
 					 enum dma_data_direction dir)
 {
diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h
index 14cd052fd320..27e3e311d395 100644
--- a/drivers/iommu/iommufd/io_pagetable.h
+++ b/drivers/iommu/iommufd/io_pagetable.h
@@ -202,7 +202,7 @@ struct iopt_pages_dmabuf_track {
 
 struct iopt_pages_dmabuf {
 	struct dma_buf_attachment *attach;
-	struct dma_buf_phys_vec phys;
+	struct phys_vec phys;
 	/* Always PAGE_SIZE aligned */
 	unsigned long start;
 	struct list_head tracker;
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index eb6d1a70f673..6ac1965199e9 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -20,7 +20,6 @@ struct iommu_group;
 struct iommu_option;
 struct iommufd_device;
 struct dma_buf_attachment;
-struct dma_buf_phys_vec;
 
 struct iommufd_sw_msi_map {
 	struct list_head sw_msi_item;
@@ -718,7 +717,7 @@ int __init iommufd_test_init(void);
 void iommufd_test_exit(void);
 bool iommufd_selftest_is_mock_dev(struct device *dev);
 int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				     struct dma_buf_phys_vec *phys);
+				     struct phys_vec *phys);
 #else
 static inline void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 						 unsigned int ioas_id,
@@ -742,7 +741,7 @@ static inline bool iommufd_selftest_is_mock_dev(struct device *dev)
 }
 static inline int
 iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				 struct dma_buf_phys_vec *phys)
+				 struct phys_vec *phys)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index f606148920fa..f863fea75b98 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -1078,7 +1078,7 @@ static int pfn_reader_user_update_pinned(struct pfn_reader_user *user,
 }
 
 struct pfn_reader_dmabuf {
-	struct dma_buf_phys_vec phys;
+	struct phys_vec phys;
 	unsigned long start_offset;
 };
 
@@ -1461,7 +1461,7 @@ static struct dma_buf_attach_ops iopt_dmabuf_attach_revoke_ops = {
  */
 static int
 sym_vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				 struct dma_buf_phys_vec *phys)
+				 struct phys_vec *phys)
 {
 	typeof(&vfio_pci_dma_buf_iommufd_map) fn;
 	int rc;
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 550ff36dec3a..989d8c4c60a7 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -2002,7 +2002,7 @@ static const struct dma_buf_ops iommufd_test_dmabuf_ops = {
 };
 
 int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				     struct dma_buf_phys_vec *phys)
+				     struct phys_vec *phys)
 {
 	struct iommufd_test_dma_buf *priv = attachment->dmabuf->priv;
 
diff --git a/drivers/vfio/fsl-mc/Kconfig b/drivers/vfio/fsl-mc/Kconfig
index 43c145d17971..7d1d690348f0 100644
--- a/drivers/vfio/fsl-mc/Kconfig
+++ b/drivers/vfio/fsl-mc/Kconfig
@@ -2,12 +2,9 @@ menu "VFIO support for FSL_MC bus devices"
 	depends on FSL_MC_BUS
 
 config VFIO_FSL_MC
-	tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices (DEPRECATED)"
+	tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices"
 	select EVENTFD
 	help
-	  The vfio-fsl-mc driver is deprecated and will be removed in a
-	  future kernel release.
-
 	  Driver to enable support for the VFIO QorIQ DPAA2 fsl-mc
 	  (Management Complex) devices. This is required to passthrough
 	  fsl-mc bus devices using the VFIO framework.
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index ba47100f28c1..3985613e6830 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -531,8 +531,6 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev)
 	struct device *dev = &mc_dev->dev;
 	int ret;
 
-	dev_err_once(dev, "DEPRECATION: vfio-fsl-mc is deprecated and will be removed in a future kernel release\n");
-
 	vdev = vfio_alloc_device(vfio_fsl_mc_device, vdev, dev,
 				 &vfio_fsl_mc_ops);
 	if (IS_ERR(vdev))
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index e44bb44c581e..b2596020e62f 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -156,7 +156,7 @@ static void mdev_type_release(struct kobject *kobj)
 	struct mdev_type *type = to_mdev_type(kobj);
 
 	pr_debug("Releasing group %s\n", kobj->name);
-	/* Pairs with the get in add_mdev_supported_type() */
+	/* Pairs with the get in mdev_type_add() */
 	put_device(type->parent->dev);
 }
 
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index cf45f6370c36..e61df3fe0db9 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -426,7 +426,7 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	ret = qm_get_vft(vf_qm, &vf_qm->qp_base);
 	if (ret <= 0) {
 		dev_err(dev, "failed to get vft qp nums\n");
-		return ret;
+		return ret < 0 ? ret : -EINVAL;
 	}
 
 	if (ret != vf_data->qp_num) {
@@ -1188,12 +1188,34 @@ hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 	return 0;
 }
 
+static void hisi_acc_vf_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
+	struct hisi_qm *qm = hisi_acc_vdev->pf_qm;
+	struct device *dev = &qm->pdev->dev;
+	u32 delay = 0;
+
+	/* All reset requests need to be queued for processing */
+	while (test_and_set_bit(QM_RESETTING, &qm->misc_ctl)) {
+		msleep(1);
+		if (++delay > QM_RESET_WAIT_TIMEOUT) {
+			dev_err(dev, "reset prepare failed\n");
+			return;
+		}
+	}
+
+	hisi_acc_vdev->set_reset_flag = true;
+}
+
 static void hisi_acc_vf_pci_aer_reset_done(struct pci_dev *pdev)
 {
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
+	struct hisi_qm *qm = hisi_acc_vdev->pf_qm;
+
+	if (hisi_acc_vdev->set_reset_flag)
+		clear_bit(QM_RESETTING, &qm->misc_ctl);
 
-	if (hisi_acc_vdev->core_device.vdev.migration_flags !=
-				VFIO_MIGRATION_STOP_COPY)
+	if (!hisi_acc_vdev->core_device.vdev.mig_ops)
 		return;
 
 	mutex_lock(&hisi_acc_vdev->state_mutex);
@@ -1547,6 +1569,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 		}
 		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
 		hisi_acc_vdev->dev_opened = true;
+		hisi_acc_vdev->match_done = 0;
 		mutex_unlock(&hisi_acc_vdev->open_mutex);
 	}
 
@@ -1734,6 +1757,7 @@ static const struct pci_device_id hisi_acc_vfio_pci_table[] = {
 MODULE_DEVICE_TABLE(pci, hisi_acc_vfio_pci_table);
 
 static const struct pci_error_handlers hisi_acc_vf_err_handlers = {
+	.reset_prepare = hisi_acc_vf_pci_reset_prepare,
 	.reset_done = hisi_acc_vf_pci_aer_reset_done,
 	.error_detected = vfio_pci_core_aer_err_detected,
 };
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
index cd55eba64dfb..a3d91a31e3d8 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -27,6 +27,7 @@
 
 #define ERROR_CHECK_TIMEOUT		100
 #define CHECK_DELAY_TIME		100
+#define QM_RESET_WAIT_TIMEOUT  60000
 
 #define QM_SQC_VFT_BASE_SHIFT_V2	28
 #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
@@ -128,6 +129,7 @@ struct hisi_acc_vf_migration_file {
 struct hisi_acc_vf_core_device {
 	struct vfio_pci_core_device core_device;
 	u8 match_done;
+	bool set_reset_flag;
 	/*
 	 * io_base is only valid when dev_opened is true,
 	 * which is protected by open_mutex.
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index b45a24d00387..fa056b69f899 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -9,6 +9,7 @@
 #include <linux/jiffies.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/pm_runtime.h>
+#include <linux/memory-failure.h>
 
 /*
  * The device memory usable to the workloads running in the VM is cached
@@ -49,6 +50,7 @@ struct mem_region {
 		void *memaddr;
 		void __iomem *ioaddr;
 	};                      /* Base virtual address of the region */
+	struct pfn_address_space pfn_address_space;
 };
 
 struct nvgrace_gpu_pci_core_device {
@@ -88,6 +90,80 @@ nvgrace_gpu_memregion(int index,
 	return NULL;
 }
 
+static int pfn_memregion_offset(struct nvgrace_gpu_pci_core_device *nvdev,
+				unsigned int index,
+				unsigned long pfn,
+				pgoff_t *pfn_offset_in_region)
+{
+	struct mem_region *region;
+	unsigned long start_pfn, num_pages;
+
+	region = nvgrace_gpu_memregion(index, nvdev);
+	if (!region)
+		return -EINVAL;
+
+	start_pfn = PHYS_PFN(region->memphys);
+	num_pages = region->memlength >> PAGE_SHIFT;
+
+	if (pfn < start_pfn || pfn >= start_pfn + num_pages)
+		return -EFAULT;
+
+	*pfn_offset_in_region = pfn - start_pfn;
+
+	return 0;
+}
+
+static inline
+struct nvgrace_gpu_pci_core_device *vma_to_nvdev(struct vm_area_struct *vma);
+
+static int nvgrace_gpu_pfn_to_vma_pgoff(struct vm_area_struct *vma,
+					unsigned long pfn,
+					pgoff_t *pgoff)
+{
+	struct nvgrace_gpu_pci_core_device *nvdev;
+	unsigned int index =
+		vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
+	pgoff_t vma_offset_in_region = vma->vm_pgoff &
+		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	pgoff_t pfn_offset_in_region;
+	int ret;
+
+	nvdev = vma_to_nvdev(vma);
+	if (!nvdev)
+		return -ENOENT;
+
+	ret = pfn_memregion_offset(nvdev, index, pfn, &pfn_offset_in_region);
+	if (ret)
+		return ret;
+
+	/* Ensure PFN is not before VMA's start within the region */
+	if (pfn_offset_in_region < vma_offset_in_region)
+		return -EFAULT;
+
+	/* Calculate offset from VMA start */
+	*pgoff = vma->vm_pgoff +
+		 (pfn_offset_in_region - vma_offset_in_region);
+
+	return 0;
+}
+
+static int
+nvgrace_gpu_vfio_pci_register_pfn_range(struct vfio_device *core_vdev,
+					struct mem_region *region)
+{
+	unsigned long pfn, nr_pages;
+
+	pfn = PHYS_PFN(region->memphys);
+	nr_pages = region->memlength >> PAGE_SHIFT;
+
+	region->pfn_address_space.node.start = pfn;
+	region->pfn_address_space.node.last = pfn + nr_pages - 1;
+	region->pfn_address_space.mapping = core_vdev->inode->i_mapping;
+	region->pfn_address_space.pfn_to_vma_pgoff = nvgrace_gpu_pfn_to_vma_pgoff;
+
+	return register_pfn_address_space(&region->pfn_address_space);
+}
+
 static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
 {
 	struct vfio_pci_core_device *vdev =
@@ -114,14 +190,28 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
 	 * memory mapping.
 	 */
 	ret = vfio_pci_core_setup_barmap(vdev, 0);
-	if (ret) {
-		vfio_pci_core_disable(vdev);
-		return ret;
+	if (ret)
+		goto error_exit;
+
+	if (nvdev->resmem.memlength) {
+		ret = nvgrace_gpu_vfio_pci_register_pfn_range(core_vdev, &nvdev->resmem);
+		if (ret && ret != -EOPNOTSUPP)
+			goto error_exit;
 	}
 
-	vfio_pci_core_finish_enable(vdev);
+	ret = nvgrace_gpu_vfio_pci_register_pfn_range(core_vdev, &nvdev->usemem);
+	if (ret && ret != -EOPNOTSUPP)
+		goto register_mem_failed;
 
+	vfio_pci_core_finish_enable(vdev);
 	return 0;
+
+register_mem_failed:
+	if (nvdev->resmem.memlength)
+		unregister_pfn_address_space(&nvdev->resmem.pfn_address_space);
+error_exit:
+	vfio_pci_core_disable(vdev);
+	return ret;
 }
 
 static void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
@@ -130,6 +220,11 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
 		container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
 			     core_device.vdev);
 
+	if (nvdev->resmem.memlength)
+		unregister_pfn_address_space(&nvdev->resmem.pfn_address_space);
+
+	unregister_pfn_address_space(&nvdev->usemem.pfn_address_space);
+
 	/* Unmap the mapping to the device memory cached region */
 	if (nvdev->usemem.memaddr) {
 		memunmap(nvdev->usemem.memaddr);
@@ -247,6 +342,16 @@ static const struct vm_operations_struct nvgrace_gpu_vfio_pci_mmap_ops = {
 #endif
 };
 
+static inline
+struct nvgrace_gpu_pci_core_device *vma_to_nvdev(struct vm_area_struct *vma)
+{
+	/* Check if this VMA belongs to us */
+	if (vma->vm_ops != &nvgrace_gpu_vfio_pci_mmap_ops)
+		return NULL;
+
+	return vma->vm_private_data;
+}
+
 static int nvgrace_gpu_mmap(struct vfio_device *core_vdev,
 			    struct vm_area_struct *vma)
 {
@@ -784,7 +889,7 @@ nvgrace_gpu_write(struct vfio_device *core_vdev,
 static int nvgrace_get_dmabuf_phys(struct vfio_pci_core_device *core_vdev,
 				   struct p2pdma_provider **provider,
 				   unsigned int region_index,
-				   struct dma_buf_phys_vec *phys_vec,
+				   struct phys_vec *phys_vec,
 				   struct vfio_region_dma_range *dma_ranges,
 				   size_t nr_ranges)
 {
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3a11e6f450f7..72c33b399800 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -588,6 +588,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_enable);
 
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 {
+	struct pci_dev *bridge;
 	struct pci_dev *pdev = vdev->pdev;
 	struct vfio_pci_dummy_resource *dummy_res, *tmp;
 	struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp;
@@ -694,12 +695,20 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 	 * We can not use the "try" reset interface here, which will
 	 * overwrite the previously restored configuration information.
 	 */
-	if (vdev->reset_works && pci_dev_trylock(pdev)) {
-		if (!__pci_reset_function_locked(pdev))
-			vdev->needs_reset = false;
-		pci_dev_unlock(pdev);
+	if (vdev->reset_works) {
+		bridge = pci_upstream_bridge(pdev);
+		if (bridge && !pci_dev_trylock(bridge))
+			goto out_restore_state;
+		if (pci_dev_trylock(pdev)) {
+			if (!__pci_reset_function_locked(pdev))
+				vdev->needs_reset = false;
+			pci_dev_unlock(pdev);
+		}
+		if (bridge)
+			pci_dev_unlock(bridge);
 	}
 
+out_restore_state:
 	pci_restore_state(pdev);
 out:
 	pci_disable_device(pdev);
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 4be4a85005cb..9918713d5774 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -14,7 +14,7 @@ struct vfio_pci_dma_buf {
 	struct vfio_pci_core_device *vdev;
 	struct list_head dmabufs_elm;
 	size_t size;
-	struct dma_buf_phys_vec *phys_vec;
+	struct phys_vec *phys_vec;
 	struct p2pdma_provider *provider;
 	u32 nr_ranges;
 	u8 revoked : 1;
@@ -106,7 +106,7 @@ static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
  *    will fail if it is currently revoked
  */
 int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				 struct dma_buf_phys_vec *phys)
+				 struct phys_vec *phys)
 {
 	struct vfio_pci_dma_buf *priv;
 
@@ -128,7 +128,7 @@ int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
 }
 EXPORT_SYMBOL_FOR_MODULES(vfio_pci_dma_buf_iommufd_map, "iommufd");
 
-int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+int vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec,
 				struct vfio_region_dma_range *dma_ranges,
 				size_t nr_ranges, phys_addr_t start,
 				phys_addr_t len)
@@ -160,7 +160,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_fill_phys_vec);
 int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev,
 				  struct p2pdma_provider **provider,
 				  unsigned int region_index,
-				  struct dma_buf_phys_vec *phys_vec,
+				  struct phys_vec *phys_vec,
 				  struct vfio_region_dma_range *dma_ranges,
 				  size_t nr_ranges)
 {
diff --git a/include/linux/dma-buf-mapping.h b/include/linux/dma-buf-mapping.h
index a3c0ce2d3a42..09bde3f748e4 100644
--- a/include/linux/dma-buf-mapping.h
+++ b/include/linux/dma-buf-mapping.h
@@ -9,7 +9,7 @@
 
 struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach,
 					 struct p2pdma_provider *provider,
-					 struct dma_buf_phys_vec *phys_vec,
+					 struct phys_vec *phys_vec,
 					 size_t nr_ranges, size_t size,
 					 enum dma_data_direction dir);
 void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt,
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 91f4939db89b..133b9e637b55 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -520,16 +520,6 @@ struct dma_buf_export_info {
 };
 
 /**
- * struct dma_buf_phys_vec - describe continuous chunk of memory
- * @paddr:   physical address of that chunk
- * @len:     Length of this chunk
- */
-struct dma_buf_phys_vec {
-	phys_addr_t paddr;
-	size_t len;
-};
-
-/**
  * DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters
  * @name: export-info name
  *
diff --git a/include/linux/memory-failure.h b/include/linux/memory-failure.h
index 7b5e11cf905f..d333dcdbeae7 100644
--- a/include/linux/memory-failure.h
+++ b/include/linux/memory-failure.h
@@ -4,8 +4,6 @@
 
 #include <linux/interval_tree.h>
 
-struct pfn_address_space;
-
 struct pfn_address_space {
 	struct interval_tree_node node;
 	struct address_space *mapping;
@@ -13,7 +11,18 @@ struct pfn_address_space {
 				unsigned long pfn, pgoff_t *pgoff);
 };
 
+#ifdef CONFIG_MEMORY_FAILURE
 int register_pfn_address_space(struct pfn_address_space *pfn_space);
 void unregister_pfn_address_space(struct pfn_address_space *pfn_space);
+#else
+static inline int register_pfn_address_space(struct pfn_address_space *pfn_space)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void unregister_pfn_address_space(struct pfn_address_space *pfn_space)
+{
+}
+#endif /* CONFIG_MEMORY_FAILURE */
 
 #endif /* _LINUX_MEMORY_FAILURE_H */
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 1ac86896875c..2ebba746c18f 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -28,7 +28,6 @@
 struct vfio_pci_core_device;
 struct vfio_pci_region;
 struct p2pdma_provider;
-struct dma_buf_phys_vec;
 struct dma_buf_attachment;
 
 struct vfio_pci_eventfd {
@@ -62,25 +61,25 @@ struct vfio_pci_device_ops {
 	int (*get_dmabuf_phys)(struct vfio_pci_core_device *vdev,
 			       struct p2pdma_provider **provider,
 			       unsigned int region_index,
-			       struct dma_buf_phys_vec *phys_vec,
+			       struct phys_vec *phys_vec,
 			       struct vfio_region_dma_range *dma_ranges,
 			       size_t nr_ranges);
 };
 
 #if IS_ENABLED(CONFIG_VFIO_PCI_DMABUF)
-int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+int vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec,
 				struct vfio_region_dma_range *dma_ranges,
 				size_t nr_ranges, phys_addr_t start,
 				phys_addr_t len);
 int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev,
 				  struct p2pdma_provider **provider,
 				  unsigned int region_index,
-				  struct dma_buf_phys_vec *phys_vec,
+				  struct phys_vec *phys_vec,
 				  struct vfio_region_dma_range *dma_ranges,
 				  size_t nr_ranges);
 #else
 static inline int
-vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec,
 			    struct vfio_region_dma_range *dma_ranges,
 			    size_t nr_ranges, phys_addr_t start,
 			    phys_addr_t len)
@@ -89,7 +88,7 @@ vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
 }
 static inline int vfio_pci_core_get_dmabuf_phys(
 	struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider,
-	unsigned int region_index, struct dma_buf_phys_vec *phys_vec,
+	unsigned int region_index, struct phys_vec *phys_vec,
 	struct vfio_region_dma_range *dma_ranges, size_t nr_ranges)
 {
 	return -EOPNOTSUPP;
@@ -236,6 +235,6 @@ static inline bool is_aligned_for_order(struct vm_area_struct *vma,
 }
 
 int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
-				 struct dma_buf_phys_vec *phys);
+				 struct phys_vec *phys);
 
 #endif /* VFIO_PCI_CORE_H */
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index 3c796ca99a50..8e90e409e91d 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -1,5 +1,13 @@
+ARCH ?= $(shell uname -m)
+
+ifeq (,$(filter $(ARCH),arm64 x86_64))
+# Do nothing on unsupported architectures
+include ../lib.mk
+else
+
 CFLAGS = $(KHDR_INCLUDES)
 TEST_GEN_PROGS += vfio_dma_mapping_test
+TEST_GEN_PROGS += vfio_dma_mapping_mmio_test
 TEST_GEN_PROGS += vfio_iommufd_setup_test
 TEST_GEN_PROGS += vfio_pci_device_test
 TEST_GEN_PROGS += vfio_pci_device_init_perf_test
@@ -27,3 +35,5 @@ TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O) $(LIBVFIO_O))
 -include $(TEST_DEP_FILES)
 
 EXTRA_CLEAN += $(TEST_GEN_PROGS_O) $(TEST_DEP_FILES)
+
+endif
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio.h b/tools/testing/selftests/vfio/lib/include/libvfio.h
index 279ddcd70194..1b6da54cc2cb 100644
--- a/tools/testing/selftests/vfio/lib/include/libvfio.h
+++ b/tools/testing/selftests/vfio/lib/include/libvfio.h
@@ -23,4 +23,13 @@
 const char *vfio_selftests_get_bdf(int *argc, char *argv[]);
 char **vfio_selftests_get_bdfs(int *argc, char *argv[], int *nr_bdfs);
 
+/*
+ * Reserve virtual address space of size at an address satisfying
+ * (vaddr % align) == offset.
+ *
+ * Returns the reserved vaddr. The caller is responsible for unmapping
+ * the returned region.
+ */
+void *mmap_reserve(size_t size, size_t align, size_t offset);
+
 #endif /* SELFTESTS_VFIO_LIB_INCLUDE_LIBVFIO_H */
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
index 5c9b9dc6d993..e9a3386a4719 100644
--- a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
+++ b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
@@ -61,6 +61,12 @@ iova_t iommu_hva2iova(struct iommu *iommu, void *vaddr);
 
 struct iommu_iova_range *iommu_iova_ranges(struct iommu *iommu, u32 *nranges);
 
+#define MODE_VFIO_TYPE1_IOMMU "vfio_type1_iommu"
+#define MODE_VFIO_TYPE1V2_IOMMU "vfio_type1v2_iommu"
+#define MODE_IOMMUFD_COMPAT_TYPE1 "iommufd_compat_type1"
+#define MODE_IOMMUFD_COMPAT_TYPE1V2 "iommufd_compat_type1v2"
+#define MODE_IOMMUFD "iommufd"
+
 /*
  * Generator for VFIO selftests fixture variants that replicate across all
  * possible IOMMU modes. Tests must define FIXTURE_VARIANT_ADD_IOMMU_MODE()
diff --git a/tools/testing/selftests/vfio/lib/iommu.c b/tools/testing/selftests/vfio/lib/iommu.c
index 58b7fb7430d4..035dac069d60 100644
--- a/tools/testing/selftests/vfio/lib/iommu.c
+++ b/tools/testing/selftests/vfio/lib/iommu.c
@@ -20,32 +20,32 @@
 #include "../../../kselftest.h"
 #include <libvfio.h>
 
-const char *default_iommu_mode = "iommufd";
+const char *default_iommu_mode = MODE_IOMMUFD;
 
 /* Reminder: Keep in sync with FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(). */
 static const struct iommu_mode iommu_modes[] = {
 	{
-		.name = "vfio_type1_iommu",
+		.name = MODE_VFIO_TYPE1_IOMMU,
 		.container_path = "/dev/vfio/vfio",
 		.iommu_type = VFIO_TYPE1_IOMMU,
 	},
 	{
-		.name = "vfio_type1v2_iommu",
+		.name = MODE_VFIO_TYPE1V2_IOMMU,
 		.container_path = "/dev/vfio/vfio",
 		.iommu_type = VFIO_TYPE1v2_IOMMU,
 	},
 	{
-		.name = "iommufd_compat_type1",
+		.name = MODE_IOMMUFD_COMPAT_TYPE1,
 		.container_path = "/dev/iommu",
 		.iommu_type = VFIO_TYPE1_IOMMU,
 	},
 	{
-		.name = "iommufd_compat_type1v2",
+		.name = MODE_IOMMUFD_COMPAT_TYPE1V2,
 		.container_path = "/dev/iommu",
 		.iommu_type = VFIO_TYPE1v2_IOMMU,
 	},
 	{
-		.name = "iommufd",
+		.name = MODE_IOMMUFD,
 	},
 };
 
diff --git a/tools/testing/selftests/vfio/lib/libvfio.c b/tools/testing/selftests/vfio/lib/libvfio.c
index a23a3cc5be69..3a3d1ed635c1 100644
--- a/tools/testing/selftests/vfio/lib/libvfio.c
+++ b/tools/testing/selftests/vfio/lib/libvfio.c
@@ -2,6 +2,9 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/mman.h>
+
+#include <linux/align.h>
 
 #include "../../../kselftest.h"
 #include <libvfio.h>
@@ -76,3 +79,25 @@ const char *vfio_selftests_get_bdf(int *argc, char *argv[])
 
 	return vfio_selftests_get_bdfs(argc, argv, &nr_bdfs)[0];
 }
+
+void *mmap_reserve(size_t size, size_t align, size_t offset)
+{
+	void *map_base, *map_align;
+	size_t delta;
+
+	VFIO_ASSERT_GT(align, offset);
+	delta = align - offset;
+
+	map_base = mmap(NULL, size + align, PROT_NONE,
+			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	VFIO_ASSERT_NE(map_base, MAP_FAILED);
+
+	map_align = (void *)(ALIGN((uintptr_t)map_base + delta, align) - delta);
+
+	if (map_align > map_base)
+		VFIO_ASSERT_EQ(munmap(map_base, map_align - map_base), 0);
+
+	VFIO_ASSERT_EQ(munmap(map_align + size, map_base + align - map_align), 0);
+
+	return map_align;
+}
diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
index fac4c0ecadef..4e5871f1ebc3 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -11,10 +11,14 @@
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 
+#include <linux/align.h>
 #include <linux/iommufd.h>
+#include <linux/kernel.h>
 #include <linux/limits.h>
+#include <linux/log2.h>
 #include <linux/mman.h>
 #include <linux/overflow.h>
+#include <linux/sizes.h>
 #include <linux/types.h>
 #include <linux/vfio.h>
 
@@ -123,20 +127,38 @@ static void vfio_pci_region_get(struct vfio_pci_device *device, int index,
 static void vfio_pci_bar_map(struct vfio_pci_device *device, int index)
 {
 	struct vfio_pci_bar *bar = &device->bars[index];
+	size_t align, size;
 	int prot = 0;
+	void *vaddr;
 
 	VFIO_ASSERT_LT(index, PCI_STD_NUM_BARS);
 	VFIO_ASSERT_NULL(bar->vaddr);
 	VFIO_ASSERT_TRUE(bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP);
+	VFIO_ASSERT_TRUE(is_power_of_2(bar->info.size));
 
 	if (bar->info.flags & VFIO_REGION_INFO_FLAG_READ)
 		prot |= PROT_READ;
 	if (bar->info.flags & VFIO_REGION_INFO_FLAG_WRITE)
 		prot |= PROT_WRITE;
 
-	bar->vaddr = mmap(NULL, bar->info.size, prot, MAP_FILE | MAP_SHARED,
+	size = bar->info.size;
+
+	/*
+	 * Align BAR mmaps to improve page fault granularity during potential
+	 * subsequent IOMMU mapping of these BAR vaddr. 1G for x86 is the
+	 * largest hugepage size across any architecture, so no benefit from
+	 * larger alignment. BARs smaller than 1G will be aligned by their
+	 * power-of-two size, guaranteeing sufficient alignment for smaller
+	 * hugepages, if present.
+	 */
+	align = min_t(size_t, size, SZ_1G);
+
+	vaddr = mmap_reserve(size, align, 0);
+	bar->vaddr = mmap(vaddr, size, prot, MAP_SHARED | MAP_FIXED,
 			  device->fd, bar->info.offset);
 	VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED);
+
+	madvise(bar->vaddr, size, MADV_HUGEPAGE);
 }
 
 static void vfio_pci_bar_unmap(struct vfio_pci_device *device, int index)
diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_mmio_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_mmio_test.c
new file mode 100644
index 000000000000..957a89ce7b3a
--- /dev/null
+++ b/tools/testing/selftests/vfio/vfio_dma_mapping_mmio_test.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stdio.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <uapi/linux/types.h>
+#include <linux/pci_regs.h>
+#include <linux/sizes.h>
+#include <linux/vfio.h>
+
+#include <libvfio.h>
+
+#include "../kselftest_harness.h"
+
+static const char *device_bdf;
+
+static struct vfio_pci_bar *largest_mapped_bar(struct vfio_pci_device *device)
+{
+	u32 flags = VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE;
+	struct vfio_pci_bar *largest = NULL;
+	u64 bar_size = 0;
+
+	for (int i = 0; i < PCI_STD_NUM_BARS; i++) {
+		struct vfio_pci_bar *bar = &device->bars[i];
+
+		if (!bar->vaddr)
+			continue;
+
+		/*
+		 * iommu_map() maps with READ|WRITE, so require the same
+		 * abilities for the underlying VFIO region.
+		 */
+		if ((bar->info.flags & flags) != flags)
+			continue;
+
+		if (bar->info.size > bar_size) {
+			bar_size = bar->info.size;
+			largest = bar;
+		}
+	}
+
+	return largest;
+}
+
+FIXTURE(vfio_dma_mapping_mmio_test) {
+	struct iommu *iommu;
+	struct vfio_pci_device *device;
+	struct iova_allocator *iova_allocator;
+	struct vfio_pci_bar *bar;
+};
+
+FIXTURE_VARIANT(vfio_dma_mapping_mmio_test) {
+	const char *iommu_mode;
+};
+
+#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode)			       \
+FIXTURE_VARIANT_ADD(vfio_dma_mapping_mmio_test, _iommu_mode) {		       \
+	.iommu_mode = #_iommu_mode,					       \
+}
+
+FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES();
+
+#undef FIXTURE_VARIANT_ADD_IOMMU_MODE
+
+FIXTURE_SETUP(vfio_dma_mapping_mmio_test)
+{
+	self->iommu = iommu_init(variant->iommu_mode);
+	self->device = vfio_pci_device_init(device_bdf, self->iommu);
+	self->iova_allocator = iova_allocator_init(self->iommu);
+	self->bar = largest_mapped_bar(self->device);
+
+	if (!self->bar)
+		SKIP(return, "No mappable BAR found on device %s", device_bdf);
+}
+
+FIXTURE_TEARDOWN(vfio_dma_mapping_mmio_test)
+{
+	iova_allocator_cleanup(self->iova_allocator);
+	vfio_pci_device_cleanup(self->device);
+	iommu_cleanup(self->iommu);
+}
+
+static void do_mmio_map_test(struct iommu *iommu,
+			     struct iova_allocator *iova_allocator,
+			     void *vaddr, size_t size)
+{
+	struct dma_region region = {
+		.vaddr = vaddr,
+		.size = size,
+		.iova = iova_allocator_alloc(iova_allocator, size),
+	};
+
+	/*
+	 * NOTE: Check for iommufd compat success once it lands. Native iommufd
+	 * will never support this.
+	 */
+	if (!strcmp(iommu->mode->name, MODE_VFIO_TYPE1V2_IOMMU) ||
+	    !strcmp(iommu->mode->name, MODE_VFIO_TYPE1_IOMMU)) {
+		iommu_map(iommu, &region);
+		iommu_unmap(iommu, &region);
+	} else {
+		VFIO_ASSERT_NE(__iommu_map(iommu, &region), 0);
+		VFIO_ASSERT_NE(__iommu_unmap(iommu, &region, NULL), 0);
+	}
+}
+
+TEST_F(vfio_dma_mapping_mmio_test, map_full_bar)
+{
+	do_mmio_map_test(self->iommu, self->iova_allocator,
+			 self->bar->vaddr, self->bar->info.size);
+}
+
+TEST_F(vfio_dma_mapping_mmio_test, map_partial_bar)
+{
+	if (self->bar->info.size < 2 * getpagesize())
+		SKIP(return, "BAR too small (size=0x%llx)", self->bar->info.size);
+
+	do_mmio_map_test(self->iommu, self->iova_allocator,
+			 self->bar->vaddr, getpagesize());
+}
+
+/* Test IOMMU mapping of BAR mmap with intentionally poor vaddr alignment. */
+TEST_F(vfio_dma_mapping_mmio_test, map_bar_misaligned)
+{
+	/* Limit size to bound test time for large BARs */
+	size_t size = min_t(size_t, self->bar->info.size, SZ_1G);
+	void *vaddr;
+
+	vaddr = mmap_reserve(size, SZ_1G, getpagesize());
+	vaddr = mmap(vaddr, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED,
+		     self->device->fd, self->bar->info.offset);
+	VFIO_ASSERT_NE(vaddr, MAP_FAILED);
+
+	do_mmio_map_test(self->iommu, self->iova_allocator, vaddr, size);
+
+	VFIO_ASSERT_EQ(munmap(vaddr, size), 0);
+}
+
+int main(int argc, char *argv[])
+{
+	device_bdf = vfio_selftests_get_bdf(&argc, argv);
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
index 3bf984b337ac..abb170bdcef7 100644
--- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
+++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
@@ -161,12 +161,8 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap)
 	if (rc == -EOPNOTSUPP)
 		goto unmap;
 
-	/*
-	 * IOMMUFD compatibility-mode does not support huge mappings when
-	 * using VFIO_TYPE1_IOMMU.
-	 */
-	if (!strcmp(variant->iommu_mode, "iommufd_compat_type1"))
-		mapping_size = SZ_4K;
+	if (self->iommu->mode->iommu_type == VFIO_TYPE1_IOMMU)
+		goto unmap;
 
 	ASSERT_EQ(0, rc);
 	printf("Found IOMMU mappings for IOVA 0x%lx:\n", region.iova);