1 files changed, 129 insertions, 221 deletions

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index e13d9bf2f9a5..26ca00c325d9 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,155 +7,114 @@
 #include <linux/migrate_mode.h>
 #include <linux/hugetlb.h>
 
-typedef struct page *new_page_t(struct page *page, unsigned long private);
-typedef void free_page_t(struct page *page, unsigned long private);
-
-/*
- * Return values from addresss_space_operations.migratepage():
- * - negative errno on page migration failure;
- * - zero on page migration success;
+typedef struct folio *new_folio_t(struct folio *folio, unsigned long private);
+typedef void free_folio_t(struct folio *folio, unsigned long private);
+
+struct migration_target_control;
+
+/**
+ * struct movable_operations - Driver page migration
+ * @isolate_page:
+ * The VM calls this function to prepare the page to be moved.  The page
+ * is locked and the driver should not unlock it.  The driver should
+ * return ``true`` if the page is movable and ``false`` if it is not
+ * currently movable.  After this function returns, the VM uses the
+ * page->lru field, so the driver must preserve any information which
+ * is usually stored here.
+ *
+ * @migrate_page:
+ * After isolation, the VM calls this function with the isolated
+ * @src page.  The driver should copy the contents of the
+ * @src page to the @dst page and set up the fields of @dst page.
+ * Both pages are locked.
+ * If page migration is successful, the driver should return 0.
+ * If the driver cannot migrate the page at the moment, it can return
+ * -EAGAIN.  The VM interprets this as a temporary migration failure and
+ * will retry it later.  Any other error value is a permanent migration
+ * failure and migration will not be retried.
+ * The driver shouldn't touch the @src->lru field while in the
+ * migrate_page() function.  It may write to @dst->lru.
+ *
+ * @putback_page:
+ * If migration fails on the isolated page, the VM informs the driver
+ * that the page is no longer a candidate for migration by calling
+ * this function.  The driver should put the isolated page back into
+ * its own data structure.
  */
-#define MIGRATEPAGE_SUCCESS		0
-
-enum migrate_reason {
-	MR_COMPACTION,
-	MR_MEMORY_FAILURE,
-	MR_MEMORY_HOTPLUG,
-	MR_SYSCALL,		/* also applies to cpusets */
-	MR_MEMPOLICY_MBIND,
-	MR_NUMA_MISPLACED,
-	MR_CONTIG_RANGE,
-	MR_TYPES
+struct movable_operations {
+	bool (*isolate_page)(struct page *, isolate_mode_t);
+	int (*migrate_page)(struct page *dst, struct page *src,
+			enum migrate_mode);
+	void (*putback_page)(struct page *);
 };
 
-/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
+/* Defined in mm/debug.c: */
 extern const char *migrate_reason_names[MR_TYPES];
 
-static inline struct page *new_page_nodemask(struct page *page,
-				int preferred_nid, nodemask_t *nodemask)
-{
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
-	unsigned int order = 0;
-	struct page *new_page = NULL;
-
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
-				preferred_nid, nodemask);
-
-	if (PageTransHuge(page)) {
-		gfp_mask |= GFP_TRANSHUGE;
-		order = HPAGE_PMD_ORDER;
-	}
-
-	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	new_page = __alloc_pages_nodemask(gfp_mask, order,
-				preferred_nid, nodemask);
-
-	if (new_page && PageTransHuge(new_page))
-		prep_transhuge_page(new_page);
-
-	return new_page;
-}
-
 #ifdef CONFIG_MIGRATION
 
-extern void putback_movable_pages(struct list_head *l);
-extern int migrate_page(struct address_space *mapping,
-			struct page *newpage, struct page *page,
-			enum migrate_mode mode);
-extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
-		unsigned long private, enum migrate_mode mode, int reason);
-extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
-extern void putback_movable_page(struct page *page);
+void putback_movable_pages(struct list_head *l);
+int migrate_folio(struct address_space *mapping, struct folio *dst,
+		struct folio *src, enum migrate_mode mode);
+int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free,
+		  unsigned long private, enum migrate_mode mode, int reason,
+		  unsigned int *ret_succeeded);
+struct folio *alloc_migration_target(struct folio *src, unsigned long private);
+bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode);
+bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
+
+int migrate_huge_page_move_mapping(struct address_space *mapping,
+		struct folio *dst, struct folio *src);
+void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+		__releases(ptl);
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
+int folio_migrate_mapping(struct address_space *mapping,
+		struct folio *newfolio, struct folio *folio, int extra_count);
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type);
 
-extern int migrate_prep(void);
-extern int migrate_prep_local(void);
-extern void migrate_page_states(struct page *newpage, struct page *page);
-extern void migrate_page_copy(struct page *newpage, struct page *page);
-extern int migrate_huge_page_move_mapping(struct address_space *mapping,
-				  struct page *newpage, struct page *page);
-extern int migrate_page_move_mapping(struct address_space *mapping,
-		struct page *newpage, struct page *page, enum migrate_mode mode,
-		int extra_count);
 #else
 
 static inline void putback_movable_pages(struct list_head *l) {}
-static inline int migrate_pages(struct list_head *l, new_page_t new,
-		free_page_t free, unsigned long private, enum migrate_mode mode,
-		int reason)
+static inline int migrate_pages(struct list_head *l, new_folio_t new,
+		free_folio_t free, unsigned long private,
+		enum migrate_mode mode, int reason, unsigned int *ret_succeeded)
 	{ return -ENOSYS; }
-static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
-	{ return -EBUSY; }
-
-static inline int migrate_prep(void) { return -ENOSYS; }
-static inline int migrate_prep_local(void) { return -ENOSYS; }
+static inline struct folio *alloc_migration_target(struct folio *src,
+		unsigned long private)
+	{ return NULL; }
+static inline bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
+	{ return false; }
+static inline bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
+	{ return false; }
 
-static inline void migrate_page_states(struct page *newpage, struct page *page)
+static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
+				  struct folio *dst, struct folio *src)
 {
+	return -ENOSYS;
 }
-
-static inline void migrate_page_copy(struct page *newpage,
-				     struct page *page) {}
-
-static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
-				  struct page *newpage, struct page *page)
+static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
 {
 	return -ENOSYS;
 }
 
 #endif /* CONFIG_MIGRATION */
 
-#ifdef CONFIG_COMPACTION
-extern int PageMovable(struct page *page);
-extern void __SetPageMovable(struct page *page, struct address_space *mapping);
-extern void __ClearPageMovable(struct page *page);
-#else
-static inline int PageMovable(struct page *page) { return 0; };
-static inline void __SetPageMovable(struct page *page,
-				struct address_space *mapping)
-{
-}
-static inline void __ClearPageMovable(struct page *page)
-{
-}
-#endif
-
 #ifdef CONFIG_NUMA_BALANCING
-extern bool pmd_trans_migrating(pmd_t pmd);
-extern int migrate_misplaced_page(struct page *page,
-				  struct vm_area_struct *vma, int node);
+int migrate_misplaced_folio_prepare(struct folio *folio,
+		struct vm_area_struct *vma, int node);
+int migrate_misplaced_folio(struct folio *folio, int node);
 #else
-static inline bool pmd_trans_migrating(pmd_t pmd)
+static inline int migrate_misplaced_folio_prepare(struct folio *folio,
+		struct vm_area_struct *vma, int node)
 {
-	return false;
+	return -EAGAIN; /* can't migrate now */
 }
-static inline int migrate_misplaced_page(struct page *page,
-					 struct vm_area_struct *vma, int node)
+static inline int migrate_misplaced_folio(struct folio *folio, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
-			struct vm_area_struct *vma,
-			pmd_t *pmd, pmd_t entry,
-			unsigned long address,
-			struct page *page, int node);
-#else
-static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
-			struct vm_area_struct *vma,
-			pmd_t *pmd, pmd_t entry,
-			unsigned long address,
-			struct page *page, int node)
-{
-	return -EAGAIN;
-}
-#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
-
-
 #ifdef CONFIG_MIGRATION
 
 /*
@@ -165,10 +124,8 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
  */
 #define MIGRATE_PFN_VALID	(1UL << 0)
 #define MIGRATE_PFN_MIGRATE	(1UL << 1)
-#define MIGRATE_PFN_LOCKED	(1UL << 2)
 #define MIGRATE_PFN_WRITE	(1UL << 3)
-#define MIGRATE_PFN_DEVICE	(1UL << 4)
-#define MIGRATE_PFN_ERROR	(1UL << 5)
+#define MIGRATE_PFN_COMPOUND	(1UL << 4)
 #define MIGRATE_PFN_SHIFT	6
 
 static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
@@ -183,107 +140,58 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
 	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
 }
 
-/*
- * struct migrate_vma_ops - migrate operation callback
- *
- * @alloc_and_copy: alloc destination memory and copy source memory to it
- * @finalize_and_map: allow caller to map the successfully migrated pages
- *
- *
- * The alloc_and_copy() callback happens once all source pages have been locked,
- * unmapped and checked (checked whether pinned or not). All pages that can be
- * migrated will have an entry in the src array set with the pfn value of the
- * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set (other
- * flags might be set but should be ignored by the callback).
- *
- * The alloc_and_copy() callback can then allocate destination memory and copy
- * source memory to it for all those entries (ie with MIGRATE_PFN_VALID and
- * MIGRATE_PFN_MIGRATE flag set). Once these are allocated and copied, the
- * callback must update each corresponding entry in the dst array with the pfn
- * value of the destination page and with the MIGRATE_PFN_VALID and
- * MIGRATE_PFN_LOCKED flags set (destination pages must have their struct pages
- * locked, via lock_page()).
- *
- * At this point the alloc_and_copy() callback is done and returns.
- *
- * Note that the callback does not have to migrate all the pages that are
- * marked with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration
- * from device memory to system memory (ie the MIGRATE_PFN_DEVICE flag is also
- * set in the src array entry). If the device driver cannot migrate a device
- * page back to system memory, then it must set the corresponding dst array
- * entry to MIGRATE_PFN_ERROR. This will trigger a SIGBUS if CPU tries to
- * access any of the virtual addresses originally backed by this page. Because
- * a SIGBUS is such a severe result for the userspace process, the device
- * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an
- * unrecoverable state.
- *
- * For empty entry inside CPU page table (pte_none() or pmd_none() is true) we
- * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
- * allowing device driver to allocate device memory for those unback virtual
- * address. For this the device driver simply have to allocate device memory
- * and properly set the destination entry like for regular migration. Note that
- * this can still fails and thus inside the device driver must check if the
- * migration was successful for those entry inside the finalize_and_map()
- * callback just like for regular migration.
- *
- * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES
- * OR BAD THINGS WILL HAPPEN !
- *
- *
- * The finalize_and_map() callback happens after struct page migration from
- * source to destination (destination struct pages are the struct pages for the
- * memory allocated by the alloc_and_copy() callback).  Migration can fail, and
- * thus the finalize_and_map() allows the driver to inspect which pages were
- * successfully migrated, and which were not. Successfully migrated pages will
- * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
- *
- * It is safe to update device page table from within the finalize_and_map()
- * callback because both destination and source page are still locked, and the
- * mmap_sem is held in read mode (hence no one can unmap the range being
- * migrated).
- *
- * Once callback is done cleaning up things and updating its page table (if it
- * chose to do so, this is not an obligation) then it returns. At this point,
- * the HMM core will finish up the final steps, and the migration is complete.
- *
- * THE finalize_and_map() CALLBACK MUST NOT CHANGE ANY OF THE SRC OR DST ARRAY
- * ENTRIES OR BAD THINGS WILL HAPPEN !
- */
-struct migrate_vma_ops {
-	void (*alloc_and_copy)(struct vm_area_struct *vma,
-			       const unsigned long *src,
-			       unsigned long *dst,
-			       unsigned long start,
-			       unsigned long end,
-			       void *private);
-	void (*finalize_and_map)(struct vm_area_struct *vma,
-				 const unsigned long *src,
-				 const unsigned long *dst,
-				 unsigned long start,
-				 unsigned long end,
-				 void *private);
+enum migrate_vma_direction {
+	MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
+	MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
+	MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2,
+	MIGRATE_VMA_SELECT_COMPOUND = 1 << 3,
 };
 
-#if defined(CONFIG_MIGRATE_VMA_HELPER)
-int migrate_vma(const struct migrate_vma_ops *ops,
-		struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end,
-		unsigned long *src,
-		unsigned long *dst,
-		void *private);
-#else
-static inline int migrate_vma(const struct migrate_vma_ops *ops,
-			      struct vm_area_struct *vma,
-			      unsigned long start,
-			      unsigned long end,
-			      unsigned long *src,
-			      unsigned long *dst,
-			      void *private)
-{
-	return -EINVAL;
-}
-#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
+struct migrate_vma {
+	struct vm_area_struct	*vma;
+	/*
+	 * Both src and dst array must be big enough for
+	 * (end - start) >> PAGE_SHIFT entries.
+	 *
+	 * The src array must not be modified by the caller after
+	 * migrate_vma_setup(), and must not change the dst array after
+	 * migrate_vma_pages() returns.
+	 */
+	unsigned long		*dst;
+	unsigned long		*src;
+	unsigned long		cpages;
+	unsigned long		npages;
+	unsigned long		start;
+	unsigned long		end;
+
+	/*
+	 * Set to the owner value also stored in page_pgmap(page)->owner
+	 * for migrating out of device private memory. The flags also need to
+	 * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
+	 * The caller should always set this field when using mmu notifier
+	 * callbacks to avoid device MMU invalidations for device private
+	 * pages that are not being migrated.
+	 */
+	void			*pgmap_owner;
+	unsigned long		flags;
+
+	/*
+	 * Set to vmf->page if this is being called to migrate a page as part of
+	 * a migrate_to_ram() callback.
+	 */
+	struct page		*fault_page;
+};
+
+int migrate_vma_setup(struct migrate_vma *args);
+void migrate_vma_pages(struct migrate_vma *migrate);
+void migrate_vma_finalize(struct migrate_vma *migrate);
+int migrate_device_range(unsigned long *src_pfns, unsigned long start,
+			unsigned long npages);
+int migrate_device_pfns(unsigned long *src_pfns, unsigned long npages);
+void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns,
+			unsigned long npages);
+void migrate_device_finalize(unsigned long *src_pfns,
+			unsigned long *dst_pfns, unsigned long npages);
 
 #endif /* CONFIG_MIGRATION */