Merge tag 'slab-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab updates from Vlastimil Babka:

 - Separate struct slab from struct page - an offshot of the page folio
   work.

   Struct page fields used by slab allocators are moved from struct page
   to a new struct slab, that uses the same physical storage. Similar to
   struct folio, it always is a head page. This brings better type
   safety, separation of large kmalloc allocations from true slabs, and
   cleanup of related objcg code.

 - A SLAB_MERGE_DEFAULT config optimization.

* tag 'slab-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab: (33 commits)
  mm/slob: Remove unnecessary page_mapcount_reset() function call
  bootmem: Use page->index instead of page->freelist
  zsmalloc: Stop using slab fields in struct page
  mm/slub: Define struct slab fields for CONFIG_SLUB_CPU_PARTIAL only when enabled
  mm/slub: Simplify struct slab slabs field definition
  mm/sl*b: Differentiate struct slab fields by sl*b implementations
  mm/kfence: Convert kfence_guarded_alloc() to struct slab
  mm/kasan: Convert to struct folio and struct slab
  mm/slob: Convert SLOB to use struct slab and struct folio
  mm/memcg: Convert slab objcgs from struct page to struct slab
  mm: Convert struct page to struct slab in functions used by other subsystems
  mm/slab: Finish struct page to struct slab conversion
  mm/slab: Convert most struct page to struct slab by spatch
  mm/slab: Convert kmem_getpages() and kmem_freepages() to struct slab
  mm/slub: Finish struct page to struct slab conversion
  mm/slub: Convert most struct page to struct slab by spatch
  mm/slub: Convert pfmemalloc_match() to take a struct slab
  mm/slub: Convert __free_slab() to use struct slab
  mm/slub: Convert alloc_slab_page() to return a struct slab
  mm/slub: Convert print_page_info() to print_slab_info()
  ...

Author: torvalds

arch/x86/mm/init_64.c

@@ -981,7 +981,7 @@ static void __meminit free_pagetable(struct page *page, int order)
 	if (PageReserved(page)) {
 		__ClearPageReserved(page);
 
-		magic = (unsigned long)page->freelist;
+		magic = page->index;
 		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
 			while (nr_pages--)
 				put_page_bootmem(page++);

include/linux/bootmem_info.h

@@ -30,7 +30,7 @@ void put_page_bootmem(struct page *page);
  */
 static inline void free_bootmem_page(struct page *page)
 {
-	unsigned long magic = (unsigned long)page->freelist;
+	unsigned long magic = page->index;
 
 	/*
 	 * The reserve_bootmem_region sets the reserved flag on bootmem

include/linux/kasan.h

@@ -9,6 +9,7 @@
 
 struct kmem_cache;
 struct page;
+struct slab;
 struct vm_struct;
 struct task_struct;
 
@@ -193,11 +194,11 @@ static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache)
 	return 0;
 }
 
-void __kasan_poison_slab(struct page *page);
-static __always_inline void kasan_poison_slab(struct page *page)
+void __kasan_poison_slab(struct slab *slab);
+static __always_inline void kasan_poison_slab(struct slab *slab)
 {
 	if (kasan_enabled())
-		__kasan_poison_slab(page);
+		__kasan_poison_slab(slab);
 }
 
 void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
@@ -322,7 +323,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache,
 				      slab_flags_t *flags) {}
 static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {}
 static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
-static inline void kasan_poison_slab(struct page *page) {}
+static inline void kasan_poison_slab(struct slab *slab) {}
 static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
 					void *object) {}
 static inline void kasan_poison_object_data(struct kmem_cache *cache,

include/linux/memcontrol.h

@@ -536,61 +536,13 @@ static inline bool folio_memcg_kmem(struct folio *folio)
 	return folio->memcg_data & MEMCG_DATA_KMEM;
 }
 
-/*
- * page_objcgs - get the object cgroups vector associated with a page
- * @page: a pointer to the page struct
- *
- * Returns a pointer to the object cgroups vector associated with the page,
- * or NULL. This function assumes that the page is known to have an
- * associated object cgroups vector. It's not safe to call this function
- * against pages, which might have an associated memory cgroup: e.g.
- * kernel stack pages.
- */
-static inline struct obj_cgroup **page_objcgs(struct page *page)
-{
-	unsigned long memcg_data = READ_ONCE(page->memcg_data);
-
-	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
-	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
-
-	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
-}
-
-/*
- * page_objcgs_check - get the object cgroups vector associated with a page
- * @page: a pointer to the page struct
- *
- * Returns a pointer to the object cgroups vector associated with the page,
- * or NULL. This function is safe to use if the page can be directly associated
- * with a memory cgroup.
- */
-static inline struct obj_cgroup **page_objcgs_check(struct page *page)
-{
-	unsigned long memcg_data = READ_ONCE(page->memcg_data);
-
-	if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
-		return NULL;
-
-	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
-
-	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
-}
 
 #else
 static inline bool folio_memcg_kmem(struct folio *folio)
 {
 	return false;
 }
 
-static inline struct obj_cgroup **page_objcgs(struct page *page)
-{
-	return NULL;
-}
-
-static inline struct obj_cgroup **page_objcgs_check(struct page *page)
-{
-	return NULL;
-}
 #endif
 
 static inline bool PageMemcgKmem(struct page *page)

include/linux/mm.h

@@ -863,6 +863,13 @@ static inline struct page *virt_to_head_page(const void *x)
 	return compound_head(page);
 }
 
+static inline struct folio *virt_to_folio(const void *x)
+{
+	struct page *page = virt_to_page(x);
+
+	return page_folio(page);
+}
+
 void __put_page(struct page *page);
 
 void put_pages_list(struct list_head *pages);
@@ -1753,6 +1760,11 @@ void page_address_init(void);
 #define page_address_init()  do { } while(0)
 #endif
 
+static inline void *folio_address(const struct folio *folio)
+{
+	return page_address(&folio->page);
+}
+
 extern void *page_rmapping(struct page *page);
 extern struct anon_vma *page_anon_vma(struct page *page);
 extern pgoff_t __page_file_index(struct page *page);

include/linux/mm_types.h

@@ -56,11 +56,11 @@ struct mem_cgroup;
  * in each subpage, but you may need to restore some of their values
  * afterwards.
  *
- * SLUB uses cmpxchg_double() to atomically update its freelist and
- * counters.  That requires that freelist & counters be adjacent and
- * double-word aligned.  We align all struct pages to double-word
- * boundaries, and ensure that 'freelist' is aligned within the
- * struct.
+ * SLUB uses cmpxchg_double() to atomically update its freelist and counters.
+ * That requires that freelist & counters in struct slab be adjacent and
+ * double-word aligned. Because struct slab currently just reinterprets the
+ * bits of struct page, we align all struct pages to double-word boundaries,
+ * and ensure that 'freelist' is aligned within struct slab.
  */
 #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
 #define _struct_page_alignment	__aligned(2 * sizeof(unsigned long))

include/linux/slab.h

@@ -189,14 +189,6 @@ bool kmem_valid_obj(void *object);
 void kmem_dump_obj(void *object);
 #endif
 
-#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
-void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
-			bool to_user);
-#else
-static inline void __check_heap_object(const void *ptr, unsigned long n,
-				       struct page *page, bool to_user) { }
-#endif
-
 /*
  * Some archs want to perform DMA into kmalloc caches and need a guaranteed
  * alignment larger than the alignment of a 64-bit integer.

include/linux/slab_def.h

@@ -87,11 +87,11 @@ struct kmem_cache {
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
-static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
+static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
 				void *x)
 {
-	void *object = x - (x - page->s_mem) % cache->size;
-	void *last_object = page->s_mem + (cache->num - 1) * cache->size;
+	void *object = x - (x - slab->s_mem) % cache->size;
+	void *last_object = slab->s_mem + (cache->num - 1) * cache->size;
 
 	if (unlikely(object > last_object))
 		return last_object;
@@ -106,16 +106,16 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
  *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
  */
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct page *page, void *obj)
+					const struct slab *slab, void *obj)
 {
-	u32 offset = (obj - page->s_mem);
+	u32 offset = (obj - slab->s_mem);
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
-static inline int objs_per_slab_page(const struct kmem_cache *cache,
-				     const struct page *page)
+static inline int objs_per_slab(const struct kmem_cache *cache,
+				     const struct slab *slab)
 {
-	if (is_kfence_address(page_address(page)))
+	if (is_kfence_address(slab_address(slab)))
 		return 1;
 	return cache->num;
 }

include/linux/slub_def.h

@@ -48,9 +48,9 @@ enum stat_item {
 struct kmem_cache_cpu {
 	void **freelist;	/* Pointer to next available object */
 	unsigned long tid;	/* Globally unique transaction id */
-	struct page *page;	/* The slab from which we are allocating */
+	struct slab *slab;	/* The slab from which we are allocating */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
-	struct page *partial;	/* Partially allocated frozen slabs */
+	struct slab *partial;	/* Partially allocated frozen slabs */
 #endif
 	local_lock_t lock;	/* Protects the fields above */
 #ifdef CONFIG_SLUB_STATS
@@ -99,8 +99,8 @@ struct kmem_cache {
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 	/* Number of per cpu partial objects to keep around */
 	unsigned int cpu_partial;
-	/* Number of per cpu partial pages to keep around */
-	unsigned int cpu_partial_pages;
+	/* Number of per cpu partial slabs to keep around */
+	unsigned int cpu_partial_slabs;
 #endif
 	struct kmem_cache_order_objects oo;
 
@@ -156,16 +156,13 @@ static inline void sysfs_slab_release(struct kmem_cache *s)
 }
 #endif
 
-void object_err(struct kmem_cache *s, struct page *page,
-		u8 *object, char *reason);
-
 void *fixup_red_left(struct kmem_cache *s, void *p);
 
-static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
+static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
 				void *x) {
-	void *object = x - (x - page_address(page)) % cache->size;
-	void *last_object = page_address(page) +
-		(page->objects - 1) * cache->size;
+	void *object = x - (x - slab_address(slab)) % cache->size;
+	void *last_object = slab_address(slab) +
+		(slab->objects - 1) * cache->size;
 	void *result = (unlikely(object > last_object)) ? last_object : object;
 
 	result = fixup_red_left(cache, result);
@@ -181,16 +178,16 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
 }
 
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct page *page, void *obj)
+					const struct slab *slab, void *obj)
 {
 	if (is_kfence_address(obj))
 		return 0;
-	return __obj_to_index(cache, page_address(page), obj);
+	return __obj_to_index(cache, slab_address(slab), obj);
 }
 
-static inline int objs_per_slab_page(const struct kmem_cache *cache,
-				     const struct page *page)
+static inline int objs_per_slab(const struct kmem_cache *cache,
+				     const struct slab *slab)
 {
-	return page->objects;
+	return slab->objects;
 }
 #endif /* _LINUX_SLUB_DEF_H */

init/Kconfig

@@ -1933,6 +1933,7 @@ endchoice
 config SLAB_MERGE_DEFAULT
 	bool "Allow slab caches to be merged"
 	default y
+	depends on SLAB || SLUB
 	help
 	  For reduced kernel memory fragmentation, slab caches can be
 	  merged when they share the same size and other characteristics.