Adding upstream version 6.9.7.upstream/6.9.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 116 insertions, 7 deletions

diff --git a/mm/internal.h b/mm/internal.h
index c3f3e0f191..07ad2675a8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -83,6 +83,99 @@ static inline void *folio_raw_mapping(struct folio *folio)
 	return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
 }
 
+#ifdef CONFIG_MMU
+
+/* Flags for folio_pte_batch(). */
+typedef int __bitwise fpb_t;
+
+/* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */
+#define FPB_IGNORE_DIRTY		((__force fpb_t)BIT(0))
+
+/* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */
+#define FPB_IGNORE_SOFT_DIRTY		((__force fpb_t)BIT(1))
+
+static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
+{
+	if (flags & FPB_IGNORE_DIRTY)
+		pte = pte_mkclean(pte);
+	if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
+		pte = pte_clear_soft_dirty(pte);
+	return pte_wrprotect(pte_mkold(pte));
+}
+
+/**
+ * folio_pte_batch - detect a PTE batch for a large folio
+ * @folio: The large folio to detect a PTE batch for.
+ * @addr: The user virtual address the first page is mapped at.
+ * @start_ptep: Page table pointer for the first entry.
+ * @pte: Page table entry for the first page.
+ * @max_nr: The maximum number of table entries to consider.
+ * @flags: Flags to modify the PTE batch semantics.
+ * @any_writable: Optional pointer to indicate whether any entry except the
+ *		  first one is writable.
+ *
+ * Detect a PTE batch: consecutive (present) PTEs that map consecutive
+ * pages of the same large folio.
+ *
+ * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
+ * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
+ * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
+ *
+ * start_ptep must map any page of the folio. max_nr must be at least one and
+ * must be limited by the caller so scanning cannot exceed a single page table.
+ *
+ * Return: the number of table entries in the batch.
+ */
+static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
+		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
+		bool *any_writable)
+{
+	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
+	const pte_t *end_ptep = start_ptep + max_nr;
+	pte_t expected_pte, *ptep;
+	bool writable;
+	int nr;
+
+	if (any_writable)
+		*any_writable = false;
+
+	VM_WARN_ON_FOLIO(!pte_present(pte), folio);
+	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
+	VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
+
+	nr = pte_batch_hint(start_ptep, pte);
+	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
+	ptep = start_ptep + nr;
+
+	while (ptep < end_ptep) {
+		pte = ptep_get(ptep);
+		if (any_writable)
+			writable = !!pte_write(pte);
+		pte = __pte_batch_clear_ignored(pte, flags);
+
+		if (!pte_same(pte, expected_pte))
+			break;
+
+		/*
+		 * Stop immediately once we reached the end of the folio. In
+		 * corner cases the next PFN might fall into a different
+		 * folio.
+		 */
+		if (pte_pfn(pte) >= folio_end_pfn)
+			break;
+
+		if (any_writable)
+			*any_writable |= writable;
+
+		nr = pte_batch_hint(ptep, pte);
+		expected_pte = pte_advance_pfn(expected_pte, nr);
+		ptep += nr;
+	}
+
+	return min(ptep - start_ptep, max_nr);
+}
+#endif /* CONFIG_MMU */
+
 void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
 						int nr_throttled);
 static inline void acct_reclaim_writeback(struct folio *folio)
@@ -103,6 +196,7 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat)
 		wake_up(wqh);
 }
 
+vm_fault_t vmf_anon_prepare(struct vm_fault *vmf);
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 void folio_rotate_reclaimable(struct folio *folio);
 bool __folio_end_writeback(struct folio *folio);
@@ -419,8 +513,7 @@ static inline struct folio *page_rmappable_folio(struct page *page)
 {
 	struct folio *folio = (struct folio *)page;
 
-	if (folio && folio_order(folio) > 1)
-		folio_prep_large_rmappable(folio);
+	folio_prep_large_rmappable(folio);
 	return folio;
 }
 
@@ -447,10 +540,12 @@ extern void prep_compound_page(struct page *page, unsigned int order);
 
 extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
+extern bool free_pages_prepare(struct page *page, unsigned int order);
+
 extern int user_min_free_kbytes;
 
-extern void free_unref_page(struct page *page, unsigned int order);
-extern void free_unref_page_list(struct list_head *list);
+void free_unref_page(struct page *page, unsigned int order);
+void free_unref_folios(struct folio_batch *fbatch);
 
 extern void zone_pcp_reset(struct zone *zone);
 extern void zone_pcp_disable(struct zone *zone);
@@ -481,7 +576,7 @@ int split_free_page(struct page *free_page,
  * completes when free_pfn <= migrate_pfn
  */
 struct compact_control {
-	struct list_head freepages;	/* List of free pages to migrate to */
+	struct list_head freepages[NR_PAGE_ORDERS];	/* List of free pages to migrate to */
 	struct list_head migratepages;	/* List of pages being migrated */
 	unsigned int nr_freepages;	/* Number of isolated free pages */
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
@@ -537,7 +632,8 @@ isolate_migratepages_range(struct compact_control *cc,
 			   unsigned long low_pfn, unsigned long end_pfn);
 
 int __alloc_contig_migrate_range(struct compact_control *cc,
-					unsigned long start, unsigned long end);
+					unsigned long start, unsigned long end,
+					int migratetype);
 
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void init_cma_reserved_pageblock(struct page *page);
@@ -865,7 +961,7 @@ extern unsigned long  __must_check vm_mmap_pgoff(struct file *, unsigned long,
         unsigned long, unsigned long);
 
 extern void set_pageblock_order(void);
-unsigned long reclaim_pages(struct list_head *folio_list);
+unsigned long reclaim_pages(struct list_head *folio_list, bool ignore_references);
 unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 					    struct list_head *folio_list);
 /* The ALLOC_WMARK bits are used as an index to zone->watermark */
@@ -1116,6 +1212,15 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 extern bool mirrored_kernelcore;
 extern bool memblock_has_mirror(void);
 
+static __always_inline void vma_set_range(struct vm_area_struct *vma,
+					  unsigned long start, unsigned long end,
+					  pgoff_t pgoff)
+{
+	vma->vm_start = start;
+	vma->vm_end = end;
+	vma->vm_pgoff = pgoff;
+}
+
 static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 {
 	/*
@@ -1268,4 +1373,8 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
 }
 #endif /* CONFIG_SHRINKER_DEBUG */
 
+/* Only track the nodes of mappings with shadow entries */
+void workingset_update_node(struct xa_node *node);
+extern struct list_lru shadow_nodes;
+
 #endif	/* __MM_INTERNAL_H */