1 files changed, 36 insertions, 98 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9849dfda44d4..c4b238a20b76 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -204,11 +204,11 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
 
-int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -406,6 +406,18 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ALLOW_ANY_UNCACHED		VM_NONE
 #endif
 
+#ifdef CONFIG_64BIT
+#define VM_DROPPABLE_BIT	40
+#define VM_DROPPABLE		BIT(VM_DROPPABLE_BIT)
+#else
+#define VM_DROPPABLE		VM_NONE
+#endif
+
+#ifdef CONFIG_64BIT
+/* VM is sealed, in vm_flags */
+#define VM_SEALED	_BITUL(63)
+#endif
+
 /* Bits set in the VMA until the stack is in its final location */
 #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
 
@@ -1105,7 +1117,7 @@ static inline unsigned int compound_order(struct page *page)
  *
  * Return: The order of the folio.
  */
-static inline unsigned int folio_order(struct folio *folio)
+static inline unsigned int folio_order(const struct folio *folio)
 {
 	if (!folio_test_large(folio))
 		return 0;
@@ -1197,8 +1209,7 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 /*
  * How many times the entire folio is mapped as a single unit (eg by a
  * PMD or PUD entry).  This is probably not what you want, except for
- * debugging purposes - it does not include PTE-mapped sub-pages; look
- * at folio_mapcount() or page_mapcount() instead.
+ * debugging purposes or implementation of other core folio_*() primitives.
  */
 static inline int folio_entire_mapcount(const struct folio *folio)
 {
@@ -1206,40 +1217,6 @@ static inline int folio_entire_mapcount(const struct folio *folio)
 	return atomic_read(&folio->_entire_mapcount) + 1;
 }
 
-/*
- * The atomic page->_mapcount, starts from -1: so that transitions
- * both from it and to it can be tracked, using atomic_inc_and_test
- * and atomic_add_negative(-1).
- */
-static inline void page_mapcount_reset(struct page *page)
-{
-	atomic_set(&(page)->_mapcount, -1);
-}
-
-/**
- * page_mapcount() - Number of times this precise page is mapped.
- * @page: The page.
- *
- * The number of times this page is mapped.  If this page is part of
- * a large folio, it includes the number of times this page is mapped
- * as part of that folio.
- *
- * Will report 0 for pages which cannot be mapped into userspace, eg
- * slab, page tables and similar.
- */
-static inline int page_mapcount(struct page *page)
-{
-	int mapcount = atomic_read(&page->_mapcount) + 1;
-
-	/* Handle page_has_type() pages */
-	if (mapcount < PAGE_MAPCOUNT_RESERVE + 1)
-		mapcount = 0;
-	if (unlikely(PageCompound(page)))
-		mapcount += folio_entire_mapcount(page_folio(page));
-
-	return mapcount;
-}
-
 static inline int folio_large_mapcount(const struct folio *folio)
 {
 	VM_WARN_ON_FOLIO(!folio_test_large(folio), folio);
@@ -1321,6 +1298,7 @@ void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
 void folio_copy(struct folio *dst, struct folio *src);
+int folio_mc_copy(struct folio *dst, struct folio *src);
 
 unsigned long nr_free_buffer_pages(void);
 
@@ -1607,17 +1585,19 @@ static inline void put_page(struct page *page)
  * issue.
  *
  * Locking: the lockless algorithm described in folio_try_get_rcu()
- * provides safe operation for get_user_pages(), page_mkclean() and
+ * provides safe operation for get_user_pages(), folio_mkclean() and
  * other calls that race to set up page table entries.
  */
 #define GUP_PIN_COUNTING_BIAS (1U << 10)
 
 void unpin_user_page(struct page *page);
+void unpin_folio(struct folio *folio);
 void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 				 bool make_dirty);
 void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
 				      bool make_dirty);
 void unpin_user_pages(struct page **pages, unsigned long npages);
+void unpin_folios(struct folio **folios, unsigned long nfolios);
 
 static inline bool is_cow_mapping(vm_flags_t flags)
 {
@@ -1948,8 +1928,8 @@ static inline struct folio *pfn_folio(unsigned long pfn)
  *
  * For more information, please see Documentation/core-api/pin_user_pages.rst.
  *
- * Return: True, if it is likely that the page has been "dma-pinned".
- * False, if the page is definitely not dma-pinned.
+ * Return: True, if it is likely that the folio has been "dma-pinned".
+ * False, if the folio is definitely not dma-pinned.
  */
 static inline bool folio_maybe_dma_pinned(struct folio *folio)
 {
@@ -1968,11 +1948,6 @@ static inline bool folio_maybe_dma_pinned(struct folio *folio)
 		GUP_PIN_COUNTING_BIAS;
 }
 
-static inline bool page_maybe_dma_pinned(struct page *page)
-{
-	return folio_maybe_dma_pinned(page_folio(page));
-}
-
 /*
  * This should most likely only be called during fork() to see whether we
  * should break the cow immediately for an anon page on the src mm.
@@ -2145,7 +2120,7 @@ static inline struct folio *folio_next(struct folio *folio)
  * it from being split.  It is not necessary for the folio to be locked.
  * Return: The base-2 logarithm of the size of this folio.
  */
-static inline unsigned int folio_shift(struct folio *folio)
+static inline unsigned int folio_shift(const struct folio *folio)
 {
 	return PAGE_SHIFT + folio_order(folio);
 }
@@ -2158,7 +2133,7 @@ static inline unsigned int folio_shift(struct folio *folio)
  * it from being split.  It is not necessary for the folio to be locked.
  * Return: The number of bytes in this folio.
  */
-static inline size_t folio_size(struct folio *folio)
+static inline size_t folio_size(const struct folio *folio)
 {
 	return PAGE_SIZE << folio_order(folio);
 }
@@ -2290,19 +2265,6 @@ static inline void *folio_address(const struct folio *folio)
 	return page_address(&folio->page);
 }
 
-extern pgoff_t __page_file_index(struct page *page);
-
-/*
- * Return the pagecache index of the passed page.  Regular pagecache pages
- * use ->index whereas swapcache pages use swp_offset(->private)
- */
-static inline pgoff_t page_index(struct page *page)
-{
-	if (unlikely(PageSwapCache(page)))
-		return __page_file_index(page);
-	return page->index;
-}
-
 /*
  * Return true only if the page has been allocated with
  * ALLOC_NO_WATERMARKS and the low watermark was not
@@ -2545,6 +2507,9 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
+long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
+		      struct folio **folios, unsigned int max_folios,
+		      pgoff_t *offset);
 
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
@@ -3172,21 +3137,7 @@ extern void reserve_bootmem_region(phys_addr_t start,
 				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
-static inline void free_reserved_page(struct page *page)
-{
-	if (mem_alloc_profiling_enabled()) {
-		union codetag_ref *ref = get_page_tag_ref(page);
-
-		if (ref) {
-			set_codetag_empty(ref);
-			put_page_tag_ref(ref);
-		}
-	}
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	adjust_managed_page_count(page, 1);
-}
+void free_reserved_page(struct page *page);
 #define free_highmem_page(page) free_reserved_page(page)
 
 static inline void mark_page_reserved(struct page *page)
@@ -3776,14 +3727,7 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 static inline bool want_init_on_free(void)
 {
 	return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
-				&init_on_free);
-}
-
-DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free);
-static inline bool want_init_mlocked_on_free(void)
-{
-	return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON,
-				&init_mlocked_on_free);
+				   &init_on_free);
 }
 
 extern bool _debug_pagealloc_enabled_early;
@@ -3896,7 +3840,7 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 #endif
 
@@ -4040,7 +3984,6 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 					bool *migratable_cleared);
 void num_poisoned_pages_inc(unsigned long pfn);
 void num_poisoned_pages_sub(unsigned long pfn, long i);
-struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
 #else
 static inline void memory_failure_queue(unsigned long pfn, int flags)
 {
@@ -4061,12 +4004,6 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM)
-void add_to_kill_ksm(struct task_struct *tsk, struct page *p,
-		     struct vm_area_struct *vma, struct list_head *to_kill,
-		     unsigned long ksm_addr);
-#endif
-
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
 extern void memblk_nr_poison_inc(unsigned long pfn);
 extern void memblk_nr_poison_sub(unsigned long pfn, long i);
@@ -4107,10 +4044,10 @@ enum mf_result {
 enum mf_action_page_type {
 	MF_MSG_KERNEL,
 	MF_MSG_KERNEL_HIGH_ORDER,
-	MF_MSG_SLAB,
 	MF_MSG_DIFFERENT_COMPOUND,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
+	MF_MSG_GET_HWPOISON,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,
@@ -4124,13 +4061,12 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
+	MF_MSG_ALREADY_POISONED,
 	MF_MSG_UNKNOWN,
 };
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
-extern void clear_huge_page(struct page *page,
-			    unsigned long addr_hint,
-			    unsigned int pages_per_huge_page);
+void folio_zero_user(struct folio *folio, unsigned long addr_hint);
 int copy_user_large_folio(struct folio *dst, struct folio *src,
 			  unsigned long addr_hint,
 			  struct vm_area_struct *vma);
@@ -4263,4 +4199,6 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn)
 void vma_pgtable_walk_begin(struct vm_area_struct *vma);
 void vma_pgtable_walk_end(struct vm_area_struct *vma);
 
+int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size);
+
 #endif /* _LINUX_MM_H */