mm, x86: get_user_pages() for dax mappings

A dax mapping establishes a pte with _PAGE_DEVMAP set when the driver
has established a devm_memremap_pages() mapping, i.e.  when the pfn_t
return from ->direct_access() has PFN_DEV and PFN_MAP set.  Later, when
encountering _PAGE_DEVMAP during a page table walk we lookup and pin a
struct dev_pagemap instance to keep the result of pfn_to_page() valid
until put_page().

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/mm/gup.c

@@ -9,6 +9,7 @@
 #include <linux/vmstat.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
+#include <linux/memremap.h>
 
 #include <asm/pgtable.h>
 
@@ -63,6 +64,16 @@ retry:
 #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);
+	}
+}
+
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -71,7 +82,9 @@ retry:
 static noinline 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;
 	unsigned long mask;
+	int nr_start = *nr;
 	pte_t *ptep;
 
 	mask = _PAGE_PRESENT|_PAGE_USER;
@@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
-		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+		page = pte_page(pte);
+		if (pte_devmap(pte)) {
+			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
+			if (unlikely(!pgmap)) {
+				undo_dev_pagemap(nr, nr_start, pages);
+				pte_unmap(ptep);
+				return 0;
+			}
+		} else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
 		}
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
 		get_page(page);
+		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
@@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 	SetPageReferenced(page);
 }
 
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	int nr_start = *nr;
+	unsigned long pfn = pmd_pfn(pmd);
+	struct dev_pagemap *pgmap = NULL;
+
+	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
+	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 noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		mask |= _PAGE_RW;
 	if ((pmd_flags(pmd) & mask) != mask)
 		return 0;
+
+	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));
+	if (pmd_devmap(pmd))
+		return __gup_device_huge_pmd(pmd, addr, end, pages, nr);
+
 	/* hugepages are never "special" */
 	VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL);
-	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));
 
 	refs = 0;
 	head = pmd_page(pmd);