Commit 34a255e6 authored by Nicolin Chen's avatar Nicolin Chen Committed by Alex Williamson
Browse files

vfio: Replace phys_pfn with pages for vfio_pin_pages() 



Most of the callers of vfio_pin_pages() want "struct page *" and the
low-level mm code to pin pages returns a list of "struct page *" too.
So there's no gain in converting "struct page *" to PFN in between.

Replace the output parameter "phys_pfn" list with a "pages" list, to
simplify callers. This also allows us to replace the vfio_iommu_type1
implementation with a more efficient one.

And drop the pfn_valid check in the gvt code, as there is no need to
do such a check at a page-backed struct page pointer.

For now, also update vfio_iommu_type1 to fit this new parameter too.

Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarKirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Reviewed-by: default avatarKevin Tian <kevin.tian@intel.com>
Acked-by: default avatarEric Farman <farman@linux.ibm.com>
Tested-by: default avatarTerrence Xu <terrence.xu@intel.com>
Tested-by: default avatarEric Farman <farman@linux.ibm.com>
Signed-off-by: default avatarNicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/20220723020256.30081-11-nicolinc@nvidia.com


Signed-off-by: default avatarAlex Williamson <alex.williamson@redhat.com>
parent c2863feb

Documentation/driver-api/vfio-mediated-device.rst

+1 −1
Original line number Diff line number Diff line
@@ -263,7 +263,7 @@ The following APIs are provided for translating user pfn to host pfn in a VFIO 
driver::



	int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,

				  int npage, int prot, unsigned long *phys_pfn);

				  int npage, int prot, struct page **pages);



	void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova,

				    int npage);

drivers/gpu/drm/i915/gvt/kvmgt.c

+6 −13
Original line number Diff line number Diff line
@@ -240,7 +240,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, 
		unsigned long size, struct page **page)

{

	int total_pages = DIV_ROUND_UP(size, PAGE_SIZE);

	unsigned long base_pfn = 0;

	struct page *base_page = NULL;

	int npage;

	int ret;
@@ -250,26 +250,19 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, 
	 */

	for (npage = 0; npage < total_pages; npage++) {

		dma_addr_t cur_iova = (gfn + npage) << PAGE_SHIFT;

		unsigned long pfn;

		struct page *cur_page;



		ret = vfio_pin_pages(&vgpu->vfio_device, cur_iova, 1,

				     IOMMU_READ | IOMMU_WRITE, &pfn);

				     IOMMU_READ | IOMMU_WRITE, &cur_page);

		if (ret != 1) {

			gvt_vgpu_err("vfio_pin_pages failed for iova %pad, ret %d\n",

				     &cur_iova, ret);

			goto err;

		}



		if (!pfn_valid(pfn)) {

			gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);

			npage++;

			ret = -EFAULT;

			goto err;

		}



		if (npage == 0)

			base_pfn = pfn;

		else if (base_pfn + npage != pfn) {

			base_page = cur_page;

		else if (base_page + npage != cur_page) {

			gvt_vgpu_err("The pages are not continuous\n");

			ret = -EINVAL;

			npage++;
@@ -277,7 +270,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, 
		}

	}



	*page = pfn_to_page(base_pfn);

	*page = base_page;

	return 0;

err:

	gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);

drivers/s390/cio/vfio_ccw_cp.c

+9 −10
Original line number Diff line number Diff line
@@ -22,8 +22,8 @@ 
struct page_array {

	/* Array that stores pages need to pin. */

	dma_addr_t		*pa_iova;

	/* Array that receives PFNs of the pages pinned. */

	unsigned long		*pa_pfn;

	/* Array that receives the pinned pages. */

	struct page		**pa_page;

	/* Number of pages pinned from @pa_iova. */

	int			pa_nr;

};
@@ -68,19 +68,19 @@ static int page_array_alloc(struct page_array *pa, u64 iova, unsigned int len) 
		return -EINVAL;



	pa->pa_iova = kcalloc(pa->pa_nr,

			      sizeof(*pa->pa_iova) + sizeof(*pa->pa_pfn),

			      sizeof(*pa->pa_iova) + sizeof(*pa->pa_page),

			      GFP_KERNEL);

	if (unlikely(!pa->pa_iova)) {

		pa->pa_nr = 0;

		return -ENOMEM;

	}

	pa->pa_pfn = (unsigned long *)&pa->pa_iova[pa->pa_nr];

	pa->pa_page = (struct page **)&pa->pa_iova[pa->pa_nr];



	pa->pa_iova[0] = iova;

	pa->pa_pfn[0] = -1ULL;

	pa->pa_page[0] = NULL;

	for (i = 1; i < pa->pa_nr; i++) {

		pa->pa_iova[i] = pa->pa_iova[i - 1] + PAGE_SIZE;

		pa->pa_pfn[i] = -1ULL;

		pa->pa_page[i] = NULL;

	}



	return 0;
@@ -144,7 +144,7 @@ static int page_array_pin(struct page_array *pa, struct vfio_device *vdev) 


		ret = vfio_pin_pages(vdev, *first, npage,

				     IOMMU_READ | IOMMU_WRITE,

				     &pa->pa_pfn[pinned]);

				     &pa->pa_page[pinned]);

		if (ret < 0) {

			goto err_out;

		} else if (ret > 0 && ret != npage) {
@@ -195,7 +195,7 @@ static inline void page_array_idal_create_words(struct page_array *pa, 
	 */



	for (i = 0; i < pa->pa_nr; i++)

		idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT;

		idaws[i] = page_to_phys(pa->pa_page[i]);



	/* Adjust the first IDAW, since it may not start on a page boundary */

	idaws[0] += pa->pa_iova[0] & (PAGE_SIZE - 1);
@@ -246,8 +246,7 @@ static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova, 


	l = n;

	for (i = 0; i < pa.pa_nr; i++) {

		struct page *page = pfn_to_page(pa.pa_pfn[i]);

		void *from = kmap_local_page(page);

		void *from = kmap_local_page(pa.pa_page[i]);



		m = PAGE_SIZE;

		if (i == 0) {

drivers/s390/crypto/vfio_ap_ops.c

+3 −3
Original line number Diff line number Diff line
@@ -234,9 +234,9 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, 
	struct ap_qirq_ctrl aqic_gisa = {};

	struct ap_queue_status status = {};

	struct kvm_s390_gisa *gisa;

	struct page *h_page;

	int nisc;

	struct kvm *kvm;

	unsigned long h_pfn;

	phys_addr_t h_nib;

	dma_addr_t nib;

	int ret;
@@ -251,7 +251,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, 
	}



	ret = vfio_pin_pages(&q->matrix_mdev->vdev, nib, 1,

			     IOMMU_READ | IOMMU_WRITE, &h_pfn);

			     IOMMU_READ | IOMMU_WRITE, &h_page);

	switch (ret) {

	case 1:

		break;
@@ -267,7 +267,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, 
	kvm = q->matrix_mdev->kvm;

	gisa = kvm->arch.gisa_int.origin;



	h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK);

	h_nib = page_to_phys(h_page) | (nib & ~PAGE_MASK);

	aqic_gisa.gisc = isc;



	nisc = kvm_s390_gisc_register(kvm, isc);

drivers/vfio/vfio.c

+4 −4
Original line number Diff line number Diff line
@@ -1941,18 +1941,18 @@ EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare); 
 * @npage [in]   : count of pages to be pinned.  This count should not

 *		   be greater than VFIO_PIN_PAGES_MAX_ENTRIES.

 * @prot [in]    : protection flags

 * @phys_pfn[out]: array of host PFNs

 * @pages[out]   : array of host pages

 * Return error or number of pages pinned.

 */

int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,

		   int npage, int prot, unsigned long *phys_pfn)

		   int npage, int prot, struct page **pages)

{

	struct vfio_container *container;

	struct vfio_group *group = device->group;

	struct vfio_iommu_driver *driver;

	int ret;



	if (!phys_pfn || !npage || !vfio_assert_device_open(device))

	if (!pages || !npage || !vfio_assert_device_open(device))

		return -EINVAL;



	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
@@ -1967,7 +1967,7 @@ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova, 
	if (likely(driver && driver->ops->pin_pages))

		ret = driver->ops->pin_pages(container->iommu_data,

					     group->iommu_group, iova,

					     npage, prot, phys_pfn);

					     npage, prot, pages);

	else

		ret = -ENOTTY;