mm: optimize dev_pagemap reference counting around get_dev_pagemap

Change the calling convention so that get_dev_pagemap always consumes the
previous reference instead of doing this using an explicit earlier call to
put_dev_pagemap in the callers.

The callers will still need to put the final reference after finishing the
loop over the pages.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

mm/gup.c

@@ -1410,7 +1410,6 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 
-		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
@@ -1420,6 +1419,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 	ret = 1;
 
 pte_unmap:
+	if (pgmap)
+		put_dev_pagemap(pgmap);
 	pte_unmap(ptem);
 	return ret;
 }
@@ -1459,10 +1460,12 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		get_page(page);
-		put_dev_pagemap(pgmap);
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
+
+	if (pgmap)
+		put_dev_pagemap(pgmap);
 	return 1;
 }