mm/gup: migrate device coherent pages when pinning instead of failing

Currently any attempts to pin a device coherent page will fail.  This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.

However this is no reason to fail pinning of these pages.  These are
coherent and accessible from the CPU so can be migrated just like pinning
ZONE_MOVABLE pages.  So instead of failing all attempts to pin them first
try migrating them out of ZONE_DEVICE.

[hch@lst.de: rebased to the split device memory checks, moved migrate_device_page to migrate_device.c]
Link: https://lkml.kernel.org/r/20220715150521.18165-7-alex.sierra@amd.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 52 insertions, 0 deletions

diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 18bc6483f63a..7feeb447e3b9 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -686,6 +686,12 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 		}
 
 		if (!page) {
+			/*
+			 * The only time there is no vma is when called from
+			 * migrate_device_coherent_page(). However this isn't
+			 * called if the page could not be unmapped.
+			 */
+			VM_BUG_ON(!migrate->vma);
 			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
 				continue;
 			if (!notified) {
@@ -794,3 +800,49 @@ void migrate_vma_finalize(struct migrate_vma *migrate)
 	}
 }
 EXPORT_SYMBOL(migrate_vma_finalize);
+
+/*
+ * Migrate a device coherent page back to normal memory. The caller should have
+ * a reference on page which will be copied to the new page if migration is
+ * successful or dropped on failure.
+ */
+int migrate_device_coherent_page(struct page *page)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma args;
+	struct page *dpage;
+
+	WARN_ON_ONCE(PageCompound(page));
+
+	lock_page(page);
+	src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE;
+	args.src = &src_pfn;
+	args.dst = &dst_pfn;
+	args.cpages = 1;
+	args.npages = 1;
+	args.vma = NULL;
+
+	/*
+	 * We don't have a VMA and don't need to walk the page tables to find
+	 * the source page. So call migrate_vma_unmap() directly to unmap the
+	 * page as migrate_vma_setup() will fail if args.vma == NULL.
+	 */
+	migrate_vma_unmap(&args);
+	if (!(src_pfn & MIGRATE_PFN_MIGRATE))
+		return -EBUSY;
+
+	dpage = alloc_page(GFP_USER | __GFP_NOWARN);
+	if (dpage) {
+		lock_page(dpage);
+		dst_pfn = migrate_pfn(page_to_pfn(dpage));
+	}
+
+	migrate_vma_pages(&args);
+	if (src_pfn & MIGRATE_PFN_MIGRATE)
+		copy_highpage(dpage, page);
+	migrate_vma_finalize(&args);
+
+	if (src_pfn & MIGRATE_PFN_MIGRATE)
+		return 0;
+	return -EBUSY;
+}