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: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Eric Farman <farman@linux.ibm.com>
Tested-by: Terrence Xu <terrence.xu@intel.com>
Tested-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/20220723020256.30081-11-nicolinc@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

3 files changed, 16 insertions, 13 deletions

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 606a20b605ba..8e23ca59ceed 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -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;
 
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index e9767e13f00f..503bea6c843d 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -52,7 +52,7 @@ struct vfio_iommu_driver_ops {
 				     struct iommu_group *group,
 				     dma_addr_t user_iova,
 				     int npage, int prot,
-				     unsigned long *phys_pfn);
+				     struct page **pages);
 	void		(*unpin_pages)(void *iommu_data,
 				       dma_addr_t user_iova, int npage);
 	void		(*register_device)(void *iommu_data,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index e629e059118c..db516c90a977 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -831,7 +831,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 				      struct iommu_group *iommu_group,
 				      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;
@@ -841,7 +841,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 	bool do_accounting;
 	dma_addr_t iova;
 
-	if (!iommu || !phys_pfn)
+	if (!iommu || !pages)
 		return -EINVAL;
 
 	/* Supported for v2 version only */
@@ -880,6 +880,7 @@ again:
 	do_accounting = list_empty(&iommu->domain_list);
 
 	for (i = 0; i < npage; i++) {
+		unsigned long phys_pfn;
 		struct vfio_pfn *vpfn;
 
 		iova = user_iova + PAGE_SIZE * i;
@@ -896,23 +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);
 
@@ -935,14 +938,14 @@ 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_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);