1 files changed, 150 insertions, 95 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 00bad7793788..f1cd22f2df1a 100644
--- a/include/linux/mm.h
+++ b/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>
@@ -51,6 +52,17 @@ extern int sysctl_legacy_va_layout;
 #define sysctl_legacy_va_layout 0
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+extern const int mmap_rnd_bits_min;
+extern const int mmap_rnd_bits_max;
+extern int mmap_rnd_bits __read_mostly;
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+extern const int mmap_rnd_compat_bits_min;
+extern const int mmap_rnd_compat_bits_max;
+extern int mmap_rnd_compat_bits __read_mostly;
+#endif
+
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -225,10 +237,14 @@ extern pgprot_t protection_map[16];
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
+ * MM layer fills up gfp_mask for page allocations but fault handler might
+ * alter it if its implementation requires a different allocation context.
+ *
  * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
+	gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 	pgoff_t pgoff;			/* Logical page offset based on vma */
 	void __user *virtual_address;	/* Faulting virtual address */
 
@@ -314,6 +330,13 @@ struct inode;
 #define page_private(page)		((page)->private)
 #define set_page_private(page, v)	((page)->private = (v))
 
+#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static inline int pmd_devmap(pmd_t pmd)
+{
+	return 0;
+}
+#endif
+
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -395,39 +418,17 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 
 extern void kvfree(const void *addr);
 
-static inline void compound_lock(struct page *page)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON_PAGE(PageSlab(page), page);
-	bit_spin_lock(PG_compound_lock, &page->flags);
-#endif
-}
-
-static inline void compound_unlock(struct page *page)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON_PAGE(PageSlab(page), page);
-	bit_spin_unlock(PG_compound_lock, &page->flags);
-#endif
-}
-
-static inline unsigned long compound_lock_irqsave(struct page *page)
+static inline atomic_t *compound_mapcount_ptr(struct page *page)
 {
-	unsigned long uninitialized_var(flags);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	local_irq_save(flags);
-	compound_lock(page);
-#endif
-	return flags;
+	return &page[1].compound_mapcount;
 }
 
-static inline void compound_unlock_irqrestore(struct page *page,
-					      unsigned long flags)
+static inline int compound_mapcount(struct page *page)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	compound_unlock(page);
-	local_irq_restore(flags);
-#endif
+	if (!PageCompound(page))
+		return 0;
+	page = compound_head(page);
+	return atomic_read(compound_mapcount_ptr(page)) + 1;
 }
 
 /*
@@ -440,61 +441,29 @@ static inline void page_mapcount_reset(struct page *page)
 	atomic_set(&(page)->_mapcount, -1);
 }
 
+int __page_mapcount(struct page *page);
+
 static inline int page_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(PageSlab(page), page);
-	return atomic_read(&page->_mapcount) + 1;
-}
-
-static inline int page_count(struct page *page)
-{
-	return atomic_read(&compound_head(page)->_count);
-}
-
-static inline bool __compound_tail_refcounted(struct page *page)
-{
-	return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page);
-}
 
-/*
- * This takes a head page as parameter and tells if the
- * tail page reference counting can be skipped.
- *
- * For this to be safe, PageSlab and PageHeadHuge must remain true on
- * any given page where they return true here, until all tail pins
- * have been released.
- */
-static inline bool compound_tail_refcounted(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return __compound_tail_refcounted(page);
+	if (unlikely(PageCompound(page)))
+		return __page_mapcount(page);
+	return atomic_read(&page->_mapcount) + 1;
 }
 
-static inline void get_huge_page_tail(struct page *page)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int total_mapcount(struct page *page);
+#else
+static inline int total_mapcount(struct page *page)
 {
-	/*
-	 * __split_huge_page_refcount() cannot run from under us.
-	 */
-	VM_BUG_ON_PAGE(!PageTail(page), page);
-	VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
-	if (compound_tail_refcounted(compound_head(page)))
-		atomic_inc(&page->_mapcount);
+	return page_mapcount(page);
 }
+#endif
 
-extern bool __get_page_tail(struct page *page);
-
-static inline void get_page(struct page *page)
+static inline int page_count(struct page *page)
 {
-	if (unlikely(PageTail(page)))
-		if (likely(__get_page_tail(page)))
-			return;
-	/*
-	 * 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);
+	return atomic_read(&compound_head(page)->_count);
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -513,7 +482,8 @@ static inline void init_page_count(struct page *page)
 	atomic_set(&page->_count, 1);
 }
 
-void put_page(struct page *page);
+void __put_page(struct page *page);
+
 void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
@@ -533,6 +503,9 @@ enum compound_dtor_id {
 #ifdef CONFIG_HUGETLB_PAGE
 	HUGETLB_PAGE_DTOR,
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	TRANSHUGE_PAGE_DTOR,
+#endif
 	NR_COMPOUND_DTORS,
 };
 extern compound_page_dtor * const compound_page_dtors[];
@@ -562,6 +535,8 @@ static inline void set_compound_order(struct page *page, unsigned int order)
 	page[1].compound_order = order;
 }
 
+void free_compound_page(struct page *page);
+
 #ifdef CONFIG_MMU
 /*
  * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
@@ -689,6 +664,51 @@ static inline enum zone_type page_zonenum(const struct page *page)
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
 
+#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
@@ -978,10 +998,21 @@ static inline pgoff_t page_file_index(struct page *page)
 
 /*
  * Return true if this page is mapped into pagetables.
+ * For compound page it returns true if any subpage of compound page is mapped.
  */
-static inline int page_mapped(struct page *page)
-{
-	return atomic_read(&(page)->_mapcount) >= 0;
+static inline bool page_mapped(struct page *page)
+{
+	int i;
+	if (likely(!PageCompound(page)))
+		return atomic_read(&page->_mapcount) >= 0;
+	page = compound_head(page);
+	if (atomic_read(compound_mapcount_ptr(page)) >= 0)
+		return true;
+	for (i = 0; i < hpage_nr_pages(page); i++) {
+		if (atomic_read(&page[i]._mapcount) >= 0)
+			return true;
+	}
+	return false;
 }
 
 /*
@@ -1069,7 +1100,7 @@ static inline bool shmem_mapping(struct address_space *mapping)
 }
 #endif
 
-extern int can_do_mlock(void);
+extern bool can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
 extern void user_shm_unlock(size_t, struct user_struct *);
 
@@ -1163,7 +1194,8 @@ int invalidate_inode_page(struct page *page);
 extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
 extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
-			    unsigned long address, unsigned int fault_flags);
+			    unsigned long address, unsigned int fault_flags,
+			    bool *unlocked);
 #else
 static inline int handle_mm_fault(struct mm_struct *mm,
 			struct vm_area_struct *vma, unsigned long address,
@@ -1175,7 +1207,7 @@ static inline int handle_mm_fault(struct mm_struct *mm,
 }
 static inline int fixup_user_fault(struct task_struct *tsk,
 		struct mm_struct *mm, unsigned long address,
-		unsigned int fault_flags)
+		unsigned int fault_flags, bool *unlocked)
 {
 	/* should never happen if there's no MMU */
 	BUG();
@@ -1361,10 +1393,26 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member)
 	atomic_long_dec(&mm->rss_stat.count[member]);
 }
 
+/* Optimized variant when page is already known not to be PageAnon */
+static inline int mm_counter_file(struct page *page)
+{
+	if (PageSwapBacked(page))
+		return MM_SHMEMPAGES;
+	return MM_FILEPAGES;
+}
+
+static inline int mm_counter(struct page *page)
+{
+	if (PageAnon(page))
+		return MM_ANONPAGES;
+	return mm_counter_file(page);
+}
+
 static inline unsigned long get_mm_rss(struct mm_struct *mm)
 {
 	return get_mm_counter(mm, MM_FILEPAGES) +
-		get_mm_counter(mm, MM_ANONPAGES);
+		get_mm_counter(mm, MM_ANONPAGES) +
+		get_mm_counter(mm, MM_SHMEMPAGES);
 }
 
 static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
@@ -1413,6 +1461,13 @@ 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,
@@ -1898,7 +1953,9 @@ extern void mm_drop_all_locks(struct mm_struct *mm);
 extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 
-extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
+extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);
+extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
+
 extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags,
@@ -2081,7 +2138,7 @@ int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn);
+			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
 
@@ -2116,15 +2173,6 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
 
-#ifdef CONFIG_PROC_FS
-void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
-#else
-static inline void vm_stat_account(struct mm_struct *mm,
-			unsigned long flags, struct file *file, long pages)
-{
-	mm->total_vm += pages;
-}
-#endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
@@ -2200,7 +2248,14 @@ pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
-void *vmemmap_alloc_block_buf(unsigned long size, int node);
+struct vmem_altmap;
+void *__vmemmap_alloc_block_buf(unsigned long size, int node,
+		struct vmem_altmap *altmap);
+static inline void *vmemmap_alloc_block_buf(unsigned long size, int node)
+{
+	return __vmemmap_alloc_block_buf(size, node, NULL);
+}
+
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
 			       int node);
@@ -2222,7 +2277,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
 extern int unpoison_memory(unsigned long pfn);
 extern int get_hwpoison_page(struct page *page);
-extern void put_hwpoison_page(struct page *page);
+#define put_hwpoison_page(page)	put_page(page)
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);