mm/gup: Implement the dev_pagemap() logic in the generic get_user_pages_fast() function

This is a preparation patch for the transition of x86 to the generic GUP_fast()
implementation.

Prepare generic GUP_fast() to handle dev_pagemap(). At the moment, it's
only implemented on x86. On non-x86, the new code will be compiled out.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aneesh Kumar K . V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dann Frazier <dann.frazier@canonical.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20170316152655.37789-6-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/mm.h

@@ -430,6 +430,10 @@ static inline int pud_devmap(pud_t pud)
 {
 	return 0;
 }
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif
 
 /*

mm/gup.c

@@ -1200,12 +1200,23 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 }
 #endif
 
+static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
+{
+	while ((*nr) - nr_start) {
+		struct page *page = pages[--(*nr)];
+
+		ClearPageReferenced(page);
+		put_page(page);
+	}
+}
+
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
 {
+	struct dev_pagemap *pgmap = NULL;
+	int nr_start = *nr, ret = 0;
 	pte_t *ptep, *ptem;
-	int ret = 0;
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
 	do {
@@ -1222,7 +1233,13 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		if (!pte_access_permitted(pte, write))
 			goto pte_unmap;
 
-		if (pte_special(pte))
+		if (pte_devmap(pte)) {
+			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
+			if (unlikely(!pgmap)) {
+				undo_dev_pagemap(nr, nr_start, pages);
+				goto pte_unmap;
+			}
+		} else if (pte_special(pte))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -1239,6 +1256,7 @@ 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)++;
@@ -1269,6 +1287,64 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 }
 #endif /* __HAVE_ARCH_PTE_SPECIAL */
 
+#ifdef __HAVE_ARCH_PTE_DEVMAP
+static int __gup_device_huge(unsigned long pfn, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	int nr_start = *nr;
+	struct dev_pagemap *pgmap = NULL;
+
+	do {
+		struct page *page = pfn_to_page(pfn);
+
+		pgmap = get_dev_pagemap(pfn, pgmap);
+		if (unlikely(!pgmap)) {
+			undo_dev_pagemap(nr, nr_start, pages);
+			return 0;
+		}
+		SetPageReferenced(page);
+		pages[*nr] = page;
+		get_page(page);
+		put_dev_pagemap(pgmap);
+		(*nr)++;
+		pfn++;
+	} while (addr += PAGE_SIZE, addr != end);
+	return 1;
+}
+
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+
+static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+#else
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	BUILD_BUG();
+	return 0;
+}
+
+static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	BUILD_BUG();
+	return 0;
+}
+#endif
+
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -1278,6 +1354,9 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (!pmd_access_permitted(orig, write))
 		return 0;
 
+	if (pmd_devmap(orig))
+		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
+
 	refs = 0;
 	head = pmd_page(orig);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1314,6 +1393,9 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (!pud_access_permitted(orig, write))
 		return 0;
 
+	if (pud_devmap(orig))
+		return __gup_device_huge_pud(orig, addr, end, pages, nr);
+
 	refs = 0;
 	head = pud_page(orig);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
@@ -1351,6 +1433,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 	if (!pgd_access_permitted(orig, write))
 		return 0;
 
+	BUILD_BUG_ON(pgd_devmap(orig));
 	refs = 0;
 	head = pgd_page(orig);
 	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);