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 <[email protected]>
Tested-by: Logan Gunthorpe <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: djbw

arch/x86/include/asm/pgtable.h

@@ -479,6 +479,13 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
+#ifdef __HAVE_ARCH_PTE_DEVMAP
+static inline int pte_devmap(pte_t a)
+{
+	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
+}
+#endif
+
 #define pte_accessible pte_accessible
 static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {

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 @@ 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);
+	}
+}
+
 /*
  * 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 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 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);

include/linux/huge_mm.h

@@ -38,7 +38,6 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			int prot_numa);
 int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
 			pfn_t pfn, bool write);
-
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
@@ -55,6 +54,9 @@ enum transparent_hugepage_flag {
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, int flags);
+
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
 #define HPAGE_PMD_MASK	(~(HPAGE_PMD_SIZE - 1))
@@ -205,6 +207,12 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+
+static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmd, int flags)
+{
+	return NULL;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */

include/linux/mm.h

@@ -16,6 +16,7 @@
 #include <linux/mm_types.h>
 #include <linux/range.h>
 #include <linux/pfn.h>
+#include <linux/percpu-refcount.h>
 #include <linux/bit_spinlock.h>
 #include <linux/shrinker.h>
 #include <linux/resource.h>
@@ -465,17 +466,6 @@ static inline int page_count(struct page *page)
 	return atomic_read(&compound_head(page)->_count);
 }
 
-static inline void get_page(struct page *page)
-{
-	page = compound_head(page);
-	/*
-	 * Getting a normal page or the head of a compound page
-	 * requires to already have an elevated page->_count.
-	 */
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
-	atomic_inc(&page->_count);
-}
-
 static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
@@ -494,13 +484,6 @@ static inline void init_page_count(struct page *page)
 
 void __put_page(struct page *page);
 
-static inline void put_page(struct page *page)
-{
-	page = compound_head(page);
-	if (put_page_testzero(page))
-		__put_page(page);
-}
-
 void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
@@ -682,17 +665,50 @@ static inline enum zone_type page_zonenum(const struct page *page)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
+void get_zone_device_page(struct page *page);
+void put_zone_device_page(struct page *page);
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_DEVICE;
 }
 #else
+static inline void get_zone_device_page(struct page *page)
+{
+}
+static inline void put_zone_device_page(struct page *page)
+{
+}
 static inline bool is_zone_device_page(const struct page *page)
 {
 	return false;
 }
 #endif
 
+static inline void get_page(struct page *page)
+{
+	page = compound_head(page);
+	/*
+	 * Getting a normal page or the head of a compound page
+	 * requires to already have an elevated page->_count.
+	 */
+	VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
+	atomic_inc(&page->_count);
+
+	if (unlikely(is_zone_device_page(page)))
+		get_zone_device_page(page);
+}
+
+static inline void put_page(struct page *page)
+{
+	page = compound_head(page);
+
+	if (put_page_testzero(page))
+		__put_page(page);
+
+	if (unlikely(is_zone_device_page(page)))
+		put_zone_device_page(page);
+}
+
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTION_IN_PAGE_FLAGS
 #endif
@@ -1444,6 +1460,13 @@ static inline void sync_mm_rss(struct mm_struct *mm)
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTE_DEVMAP
+static inline int pte_devmap(pte_t pte)
+{
+	return 0;
+}
+#endif
+
 int vma_wants_writenotify(struct vm_area_struct *vma);
 
 extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,

kernel/memremap.c

@@ -169,6 +169,18 @@ struct page_map {
 	struct vmem_altmap altmap;
 };
 
+void get_zone_device_page(struct page *page)
+{
+	percpu_ref_get(page->pgmap->ref);
+}
+EXPORT_SYMBOL(get_zone_device_page);
+
+void put_zone_device_page(struct page *page)
+{
+	put_dev_pagemap(page->pgmap);
+}
+EXPORT_SYMBOL(put_zone_device_page);
+
 static void pgmap_radix_release(struct resource *res)
 {
 	resource_size_t key;

mm/gup.c

@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 
 #include <linux/mm.h>
+#include <linux/memremap.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
@@ -62,6 +63,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd, unsigned int flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct dev_pagemap *pgmap = NULL;
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t *ptep, pte;
@@ -98,7 +100,17 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	}
 
 	page = vm_normal_page(vma, address, pte);
-	if (unlikely(!page)) {
+	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
+		/*
+		 * Only return device mapping pages in the FOLL_GET case since
+		 * they are only valid while holding the pgmap reference.
+		 */
+		pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
+		if (pgmap)
+			page = pte_page(pte);
+		else
+			goto no_page;
+	} else if (unlikely(!page)) {
 		if (flags & FOLL_DUMP) {
 			/* Avoid special (like zero) pages in core dumps */
 			page = ERR_PTR(-EFAULT);
@@ -129,8 +141,15 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto retry;
 	}
 
-	if (flags & FOLL_GET)
+	if (flags & FOLL_GET) {
 		get_page(page);
+
+		/* drop the pgmap reference now that we hold the page */
+		if (pgmap) {
+			put_dev_pagemap(pgmap);
+			pgmap = NULL;
+		}
+	}
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
@@ -237,6 +256,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	}
 	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		return no_page_table(vma, flags);
+	if (pmd_devmap(*pmd)) {
+		ptl = pmd_lock(mm, pmd);
+		page = follow_devmap_pmd(vma, address, pmd, flags);
+		spin_unlock(ptl);
+		if (page)
+			return page;
+	}
 	if (likely(!pmd_trans_huge(*pmd)))
 		return follow_page_pte(vma, address, pmd, flags);