Merging upstream version 6.10.3.

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

1 files changed, 189 insertions, 51 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 07ad2675a8..cc2c5e07fa 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,8 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <linux/tracepoint-defs.h>
 
 struct folio_batch;
@@ -70,13 +72,30 @@ void page_writeback_init(void);
 /*
  * How many individual pages have an elevated _mapcount.  Excludes
  * the folio's entire_mapcount.
+ *
+ * Don't use this function outside of debugging code.
  */
-static inline int folio_nr_pages_mapped(struct folio *folio)
+static inline int folio_nr_pages_mapped(const struct folio *folio)
 {
 	return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
 }
 
-static inline void *folio_raw_mapping(struct folio *folio)
+/*
+ * Retrieve the first entry of a folio based on a provided entry within the
+ * folio. We cannot rely on folio->swap as there is no guarantee that it has
+ * been initialized. Used for calling arch_swap_restore()
+ */
+static inline swp_entry_t folio_swap(swp_entry_t entry,
+		const struct folio *folio)
+{
+	swp_entry_t swap = {
+		.val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)),
+	};
+
+	return swap;
+}
+
+static inline void *folio_raw_mapping(const struct folio *folio)
 {
 	unsigned long mapping = (unsigned long)folio->mapping;
 
@@ -113,6 +132,10 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
  * @flags: Flags to modify the PTE batch semantics.
  * @any_writable: Optional pointer to indicate whether any entry except the
  *		  first one is writable.
+ * @any_young: Optional pointer to indicate whether any entry except the
+ *		  first one is young.
+ * @any_dirty: Optional pointer to indicate whether any entry except the
+ *		  first one is dirty.
  *
  * Detect a PTE batch: consecutive (present) PTEs that map consecutive
  * pages of the same large folio.
@@ -128,16 +151,20 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
  */
 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)
+		bool *any_writable, bool *any_young, bool *any_dirty)
 {
 	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;
+	bool writable, young, dirty;
 	int nr;
 
 	if (any_writable)
 		*any_writable = false;
+	if (any_young)
+		*any_young = false;
+	if (any_dirty)
+		*any_dirty = false;
 
 	VM_WARN_ON_FOLIO(!pte_present(pte), folio);
 	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
@@ -151,6 +178,10 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		pte = ptep_get(ptep);
 		if (any_writable)
 			writable = !!pte_write(pte);
+		if (any_young)
+			young = !!pte_young(pte);
+		if (any_dirty)
+			dirty = !!pte_dirty(pte);
 		pte = __pte_batch_clear_ignored(pte, flags);
 
 		if (!pte_same(pte, expected_pte))
@@ -166,6 +197,10 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 
 		if (any_writable)
 			*any_writable |= writable;
+		if (any_young)
+			*any_young |= young;
+		if (any_dirty)
+			*any_dirty |= dirty;
 
 		nr = pte_batch_hint(ptep, pte);
 		expected_pte = pte_advance_pfn(expected_pte, nr);
@@ -174,6 +209,68 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 
 	return min(ptep - start_ptep, max_nr);
 }
+
+/**
+ * pte_next_swp_offset - Increment the swap entry offset field of a swap pte.
+ * @pte: The initial pte state; is_swap_pte(pte) must be true and
+ *	 non_swap_entry() must be false.
+ *
+ * Increments the swap offset, while maintaining all other fields, including
+ * swap type, and any swp pte bits. The resulting pte is returned.
+ */
+static inline pte_t pte_next_swp_offset(pte_t pte)
+{
+	swp_entry_t entry = pte_to_swp_entry(pte);
+	pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry),
+						   (swp_offset(entry) + 1)));
+
+	if (pte_swp_soft_dirty(pte))
+		new = pte_swp_mksoft_dirty(new);
+	if (pte_swp_exclusive(pte))
+		new = pte_swp_mkexclusive(new);
+	if (pte_swp_uffd_wp(pte))
+		new = pte_swp_mkuffd_wp(new);
+
+	return new;
+}
+
+/**
+ * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
+ * @start_ptep: Page table pointer for the first entry.
+ * @max_nr: The maximum number of table entries to consider.
+ * @pte: Page table entry for the first entry.
+ *
+ * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
+ * containing swap entries all with consecutive offsets and targeting the same
+ * swap type, all with matching swp pte bits.
+ *
+ * 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 swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
+{
+	pte_t expected_pte = pte_next_swp_offset(pte);
+	const pte_t *end_ptep = start_ptep + max_nr;
+	pte_t *ptep = start_ptep + 1;
+
+	VM_WARN_ON(max_nr < 1);
+	VM_WARN_ON(!is_swap_pte(pte));
+	VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte)));
+
+	while (ptep < end_ptep) {
+		pte = ptep_get(ptep);
+
+		if (!pte_same(pte, expected_pte))
+			break;
+
+		expected_pte = pte_next_swp_offset(expected_pte);
+		ptep++;
+	}
+
+	return ptep - start_ptep;
+}
 #endif /* CONFIG_MMU */
 
 void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
@@ -513,7 +610,8 @@ static inline struct folio *page_rmappable_folio(struct page *page)
 {
 	struct folio *folio = (struct folio *)page;
 
-	folio_prep_large_rmappable(folio);
+	if (folio && folio_test_large(folio))
+		folio_set_large_rmappable(folio);
 	return folio;
 }
 
@@ -522,9 +620,12 @@ static inline void prep_compound_head(struct page *page, unsigned int order)
 	struct folio *folio = (struct folio *)page;
 
 	folio_set_order(folio, order);
+	atomic_set(&folio->_large_mapcount, -1);
 	atomic_set(&folio->_entire_mapcount, -1);
 	atomic_set(&folio->_nr_pages_mapped, 0);
 	atomic_set(&folio->_pincount, 0);
+	if (order > 1)
+		INIT_LIST_HEAD(&folio->_deferred_list);
 }
 
 static inline void prep_compound_tail(struct page *head, int tail_idx)
@@ -559,10 +660,6 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
 		unsigned long, enum meminit_context, struct vmem_altmap *, int);
 
-
-int split_free_page(struct page *free_page,
-			unsigned int order, unsigned long split_pfn_offset);
-
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
@@ -789,13 +886,17 @@ void mlock_drain_remote(int cpu);
 
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
-/*
- * Return the start of user virtual address at the specific offset within
- * a vma.
+/**
+ * vma_address - Find the virtual address a page range is mapped at
+ * @vma: The vma which maps this object.
+ * @pgoff: The page offset within its object.
+ * @nr_pages: The number of pages to consider.
+ *
+ * If any page in this range is mapped by this VMA, return the first address
+ * where any of these pages appear.  Otherwise, return -EFAULT.
  */
-static inline unsigned long
-vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
-		  struct vm_area_struct *vma)
+static inline unsigned long vma_address(struct vm_area_struct *vma,
+		pgoff_t pgoff, unsigned long nr_pages)
 {
 	unsigned long address;
 
@@ -815,18 +916,6 @@ vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
 }
 
 /*
- * Return the start of user virtual address of a page within a vma.
- * Returns -EFAULT if all of the page is outside the range of vma.
- * If page is a compound head, the entire compound page is considered.
- */
-static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
-{
-	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
-	return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
-}
-
-/*
  * Then at what user virtual address will none of the range be found in vma?
  * Assumes that vma_address() already returned a good starting address.
  */
@@ -947,6 +1036,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
 /*
  * mm/memory-failure.c
  */
+void shake_folio(struct folio *folio);
 extern int hwpoison_filter(struct page *p);
 
 extern u32 hwpoison_filter_dev_major;
@@ -961,7 +1051,7 @@ 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, bool ignore_references);
+unsigned long reclaim_pages(struct list_head *folio_list);
 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 */
@@ -1040,17 +1130,13 @@ static inline bool is_migrate_highatomic(enum migratetype migratetype)
 	return migratetype == MIGRATE_HIGHATOMIC;
 }
 
-static inline bool is_migrate_highatomic_page(struct page *page)
-{
-	return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC;
-}
-
 void setup_zone_pageset(struct zone *zone);
 
 struct migration_target_control {
 	int nid;		/* preferred node id */
 	nodemask_t *nmask;
 	gfp_t gfp_mask;
+	enum migrate_reason reason;
 };
 
 /*
@@ -1087,24 +1173,25 @@ void vunmap_range_noflush(unsigned long start, unsigned long end);
 
 void __vunmap_range_noflush(unsigned long start, unsigned long end);
 
-int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma,
+int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
 		      unsigned long addr, int page_nid, int *flags);
 
-void free_zone_device_page(struct page *page);
+void free_zone_device_folio(struct folio *folio);
 int migrate_device_coherent_page(struct page *page);
 
 /*
  * mm/gup.c
  */
-struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
-int __must_check try_grab_page(struct page *page, unsigned int flags);
+int __must_check try_grab_folio(struct folio *folio, int refs,
+				unsigned int flags);
 
 /*
  * mm/huge_memory.c
  */
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr, pmd_t *pmd,
-				   unsigned int flags);
+void touch_pud(struct vm_area_struct *vma, unsigned long addr,
+	       pud_t *pud, bool write);
+void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+	       pmd_t *pmd, bool write);
 
 /*
  * mm/mmap.c
@@ -1189,20 +1276,10 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 	}
 
 	/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
-	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+	if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
 		smp_rmb();
 
 	/*
-	 * During GUP-fast we might not get called on the head page for a
-	 * hugetlb page that is mapped using cont-PTE, because GUP-fast does
-	 * not work with the abstracted hugetlb PTEs that always point at the
-	 * head page. For hugetlb, PageAnonExclusive only applies on the head
-	 * page (as it cannot be partially COW-shared), so lookup the head page.
-	 */
-	if (unlikely(!PageHead(page) && PageHuge(page)))
-		page = compound_head(page);
-
-	/*
 	 * Note that PageKsm() pages cannot be exclusive, and consequently,
 	 * cannot get pinned.
 	 */
@@ -1245,6 +1322,35 @@ static inline void vma_iter_config(struct vma_iterator *vmi,
 	__mas_set_range(&vmi->mas, index, last - 1);
 }
 
+static inline void vma_iter_reset(struct vma_iterator *vmi)
+{
+	mas_reset(&vmi->mas);
+}
+
+static inline
+struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min)
+{
+	return mas_prev_range(&vmi->mas, min);
+}
+
+static inline
+struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max)
+{
+	return mas_next_range(&vmi->mas, max);
+}
+
+static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min,
+				       unsigned long max, unsigned long size)
+{
+	return mas_empty_area(&vmi->mas, min, max - 1, size);
+}
+
+static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min,
+					unsigned long max, unsigned long size)
+{
+	return mas_empty_area_rev(&vmi->mas, min, max - 1, size);
+}
+
 /*
  * VMA Iterator functions shared between nommu and mmap
  */
@@ -1328,6 +1434,38 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn,
 unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
 			  int priority);
 
+#ifdef CONFIG_64BIT
+static inline int can_do_mseal(unsigned long flags)
+{
+	if (flags)
+		return -EINVAL;
+
+	return 0;
+}
+
+bool can_modify_mm(struct mm_struct *mm, unsigned long start,
+		unsigned long end);
+bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
+		unsigned long end, int behavior);
+#else
+static inline int can_do_mseal(unsigned long flags)
+{
+	return -EPERM;
+}
+
+static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start,
+		unsigned long end)
+{
+	return true;
+}
+
+static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
+		unsigned long end, int behavior)
+{
+	return true;
+}
+#endif
+
 #ifdef CONFIG_SHRINKER_DEBUG
 static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
 			struct shrinker *shrinker, const char *fmt, va_list ap)