[v3,10/13] mm: disable get_user_pages_fast() for dax

Commit Message

Dan Williams Oct. 20, 2017, 2:39 a.m. UTC

In preparation for solving the dax-dma vs truncate race, disable
get_user_pages_fast(). The race fix relies on the vma being available.

We can still support get_user_pages_fast() for 1GB (pud) 'devmap'
mappings since those are only implemented for device-dax, everything
else needs the vma and the gup-slow-path in case it might be a
filesytem-dax mapping.

Cc: Michal Hocko <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: "Kirill A. Shutemov" <[e-mail]>
Signed-off-by: Dan Williams <[e-mail]>
---
 mm/gup.c |   48 +++++++++++++-----------------------------------
 1 file changed, 13 insertions(+), 35 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/mm/gup.c b/mm/gup.c
index b2b4d4263768..308be897d22a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1290,22 +1290,12 @@  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;
+	int ret = 0;
 	pte_t *ptep, *ptem;
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
@@ -1323,13 +1313,7 @@  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_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))
+		if (pte_devmap(pte) || (pte_special(pte)))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -1378,6 +1362,16 @@  static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 #endif /* __HAVE_ARCH_PTE_SPECIAL */
 
 #if defined(__HAVE_ARCH_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+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);
+	}
+}
+
 static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
@@ -1402,15 +1396,6 @@  static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 	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)
 {
@@ -1420,13 +1405,6 @@  static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
 	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)
 {
@@ -1445,7 +1423,7 @@  static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 
 	if (pmd_devmap(orig))
-		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
+		return 0;
 
 	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);