1 files changed, 65 insertions, 13 deletions

diff --git a/mm/internal.h b/mm/internal.h
index a7d9e980429a..d1d4bf4e63c0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -62,6 +62,12 @@ void page_writeback_init(void);
 #define FOLIO_PAGES_MAPPED	(COMPOUND_MAPPED - 1)
 
 /*
+ * Flags passed to __show_mem() and show_free_areas() to suppress output in
+ * various contexts.
+ */
+#define SHOW_MEM_FILTER_NODES		(0x0001u)	/* disallowed nodes */
+
+/*
  * How many individual pages have an elevated _mapcount.  Excludes
  * the folio's entire_mapcount.
  */
@@ -103,7 +109,7 @@ bool __folio_end_writeback(struct folio *folio);
 void deactivate_file_folio(struct folio *folio);
 void folio_activate(struct folio *folio);
 
-void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt,
+void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		   struct vm_area_struct *start_vma, unsigned long floor,
 		   unsigned long ceiling, bool mm_wr_locked);
 void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
@@ -170,6 +176,17 @@ static inline void set_page_refcounted(struct page *page)
 	set_page_count(page, 1);
 }
 
+/*
+ * Return true if a folio needs ->release_folio() calling upon it.
+ */
+static inline bool folio_needs_release(struct folio *folio)
+{
+	struct address_space *mapping = folio_mapping(folio);
+
+	return folio_has_private(folio) ||
+		(mapping && mapping_release_always(mapping));
+}
+
 extern unsigned long highest_memmap_pfn;
 
 /*
@@ -390,17 +407,18 @@ static inline void folio_set_order(struct folio *folio, unsigned int order)
 	if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
 		return;
 
-	folio->_folio_order = order;
+	folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
 #ifdef CONFIG_64BIT
 	folio->_folio_nr_pages = 1U << order;
 #endif
 }
 
+void folio_undo_large_rmappable(struct folio *folio);
+
 static inline void prep_compound_head(struct page *page, unsigned int order)
 {
 	struct folio *folio = (struct folio *)page;
 
-	folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
 	folio_set_order(folio, order);
 	atomic_set(&folio->_entire_mapcount, -1);
 	atomic_set(&folio->_nr_pages_mapped, 0);
@@ -689,7 +707,7 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
 	if (fault_flag_allow_retry_first(flags) &&
 	    !(flags & FAULT_FLAG_RETRY_NOWAIT)) {
 		fpin = get_file(vmf->vma->vm_file);
-		mmap_read_unlock(vmf->vma->vm_mm);
+		release_fault_lock(vmf);
 	}
 	return fpin;
 }
@@ -924,6 +942,13 @@ int migrate_device_coherent_page(struct page *page);
 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);
 
+/*
+ * mm/huge_memory.c
+ */
+struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
+				   unsigned long addr, pmd_t *pmd,
+				   unsigned int flags);
+
 enum {
 	/* mark page accessed */
 	FOLL_TOUCH = 1 << 16,
@@ -998,6 +1023,16 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 		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.
 	 */
@@ -1005,6 +1040,7 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 }
 
 extern bool mirrored_kernelcore;
+extern bool memblock_has_mirror(void);
 
 static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 {
@@ -1024,21 +1060,39 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 	return !(vma->vm_flags & VM_SOFTDIRTY);
 }
 
+static inline void vma_iter_config(struct vma_iterator *vmi,
+		unsigned long index, unsigned long last)
+{
+	MAS_BUG_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+		   (vmi->mas.index > index || vmi->mas.last < index));
+	__mas_set_range(&vmi->mas, index, last - 1);
+}
+
 /*
  * VMA Iterator functions shared between nommu and mmap
  */
-static inline int vma_iter_prealloc(struct vma_iterator *vmi)
+static inline int vma_iter_prealloc(struct vma_iterator *vmi,
+		struct vm_area_struct *vma)
 {
-	return mas_preallocate(&vmi->mas, GFP_KERNEL);
+	return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
 }
 
-static inline void vma_iter_clear(struct vma_iterator *vmi,
-				  unsigned long start, unsigned long end)
+static inline void vma_iter_clear(struct vma_iterator *vmi)
 {
-	mas_set_range(&vmi->mas, start, end - 1);
 	mas_store_prealloc(&vmi->mas, NULL);
 }
 
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+			unsigned long start, unsigned long end, gfp_t gfp)
+{
+	__mas_set_range(&vmi->mas, start, end - 1);
+	mas_store_gfp(&vmi->mas, NULL, gfp);
+	if (unlikely(mas_is_err(&vmi->mas)))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
 {
 	return mas_walk(&vmi->mas);
@@ -1068,8 +1122,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
-	vmi->mas.index = vma->vm_start;
-	vmi->mas.last = vma->vm_end - 1;
+	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
 	mas_store_prealloc(&vmi->mas, vma);
 }
 
@@ -1080,8 +1133,7 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
-	vmi->mas.index = vma->vm_start;
-	vmi->mas.last = vma->vm_end - 1;
+	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
 	mas_store_gfp(&vmi->mas, vma, gfp);
 	if (unlikely(mas_is_err(&vmi->mas)))
 		return -ENOMEM;