Merge tag 'slab-for-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab fixes from Vlastimil Babka:

 - Fix for spurious page allocation warnings on sheaf refill (Harry Yoo)

 - Fix for CONFIG_MEM_ALLOC_PROFILING_DEBUG warnings (Suren
   Baghdasaryan)

 - Fix for kernel-doc warning on ksize() (Sanjay Chitroda)

 - Fix to avoid setting slab->stride later than on slab allocation.
   Doesn't yet fix the reports from powerpc; debugging is making
   progress (Harry Yoo)

* tag 'slab-for-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
  mm/slab: initialize slab->stride early to avoid memory ordering issues
  mm/slub: drop duplicate kernel-doc for ksize()
  mm/slab: mark alloc tags empty for sheaves allocated with __GFP_NO_OBJ_EXT
  mm/slab: pass __GFP_NOWARN to refill_sheaf() if fallback is available

Author: torvalds

include/linux/gfp_types.h

@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)

include/linux/slab.h

@@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp);
 DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T))
 DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T))
 
-/**
- * ksize - Report actual allocation size of associated object
- *
- * @objp: Pointer returned from a prior kmalloc()-family allocation.
- *
- * This should not be used for writing beyond the originally requested
- * allocation size. Either use krealloc() or round up the allocation size
- * with kmalloc_size_roundup() prior to allocation. If this is used to
- * access beyond the originally requested allocation size, UBSAN_BOUNDS
- * and/or FORTIFY_SOURCE may trip, since they only know about the
- * originally allocated size via the __alloc_size attribute.
- */
 size_t ksize(const void *objp);
 
 #ifdef CONFIG_PRINTK

mm/slab.h

@@ -290,14 +290,14 @@ static inline void *nearest_obj(struct kmem_cache *cache,
 
 /* Determine object index from a given position */
 static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
-					  void *addr, void *obj)
+					  void *addr, const void *obj)
 {
 	return reciprocal_divide(kasan_reset_tag(obj) - addr,
 				 cache->reciprocal_size);
 }
 
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
+					const struct slab *slab, const void *obj)
 {
 	if (is_kfence_address(obj))
 		return 0;

mm/slub.c

@@ -2041,18 +2041,18 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
+static inline void mark_obj_codetag_empty(const void *obj)
 {
-	struct slab *obj_exts_slab;
+	struct slab *obj_slab;
 	unsigned long slab_exts;
 
-	obj_exts_slab = virt_to_slab(obj_exts);
-	slab_exts = slab_obj_exts(obj_exts_slab);
+	obj_slab = virt_to_slab(obj);
+	slab_exts = slab_obj_exts(obj_slab);
 	if (slab_exts) {
 		get_slab_obj_exts(slab_exts);
-		unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
-						 obj_exts_slab, obj_exts);
-		struct slabobj_ext *ext = slab_obj_ext(obj_exts_slab,
+		unsigned int offs = obj_to_index(obj_slab->slab_cache,
+						 obj_slab, obj);
+		struct slabobj_ext *ext = slab_obj_ext(obj_slab,
 						       slab_exts, offs);
 
 		if (unlikely(is_codetag_empty(&ext->ref))) {
@@ -2090,7 +2090,7 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 
 #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {}
+static inline void mark_obj_codetag_empty(const void *obj) {}
 static inline bool mark_failed_objexts_alloc(struct slab *slab) { return false; }
 static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 			struct slabobj_ext *vec, unsigned int objects) {}
@@ -2196,7 +2196,6 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 retry:
 	old_exts = READ_ONCE(slab->obj_exts);
 	handle_failed_objexts_alloc(old_exts, vec, objects);
-	slab_set_stride(slab, sizeof(struct slabobj_ext));
 
 	if (new_slab) {
 		/*
@@ -2211,7 +2210,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 		 * assign slabobj_exts in parallel. In this case the existing
 		 * objcg vector should be reused.
 		 */
-		mark_objexts_empty(vec);
+		mark_obj_codetag_empty(vec);
 		if (unlikely(!allow_spin))
 			kfree_nolock(vec);
 		else
@@ -2254,7 +2253,7 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin)
 	 * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that
 	 * the extension for obj_exts is expected to be NULL.
 	 */
-	mark_objexts_empty(obj_exts);
+	mark_obj_codetag_empty(obj_exts);
 	if (allow_spin)
 		kfree(obj_exts);
 	else
@@ -2272,6 +2271,9 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 	void *addr;
 	unsigned long obj_exts;
 
+	/* Initialize stride early to avoid memory ordering issues */
+	slab_set_stride(slab, sizeof(struct slabobj_ext));
+
 	if (!need_slab_obj_exts(s))
 		return;
 
@@ -2288,7 +2290,6 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 		obj_exts |= MEMCG_DATA_OBJEXTS;
 #endif
 		slab->obj_exts = obj_exts;
-		slab_set_stride(slab, sizeof(struct slabobj_ext));
 	} else if (s->flags & SLAB_OBJ_EXT_IN_OBJ) {
 		unsigned int offset = obj_exts_offset_in_object(s);
 
@@ -2312,6 +2313,10 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 
 #else /* CONFIG_SLAB_OBJ_EXT */
 
+static inline void mark_obj_codetag_empty(const void *obj)
+{
+}
+
 static inline void init_slab_obj_exts(struct slab *slab)
 {
 }
@@ -2783,6 +2788,15 @@ static inline struct slab_sheaf *alloc_empty_sheaf(struct kmem_cache *s,
 
 static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf)
 {
+	/*
+	 * If the sheaf was created with __GFP_NO_OBJ_EXT flag then its
+	 * corresponding extension is NULL and alloc_tag_sub() will throw a
+	 * warning, therefore replace NULL with CODETAG_EMPTY to indicate
+	 * that the extension for this sheaf is expected to be NULL.
+	 */
+	if (s->flags & SLAB_KMALLOC)
+		mark_obj_codetag_empty(sheaf);
+
 	kfree(sheaf);
 
 	stat(s, SHEAF_FREE);
@@ -2822,7 +2836,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 	if (!sheaf)
 		return NULL;
 
-	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC)) {
+	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 		free_empty_sheaf(s, sheaf);
 		return NULL;
 	}
@@ -4575,7 +4589,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 
 	if (empty) {
-		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC)) {
+		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 			full = empty;
 		} else {
 			/*
@@ -4890,9 +4904,14 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_noprof);
 static int __prefill_sheaf_pfmemalloc(struct kmem_cache *s,
 				      struct slab_sheaf *sheaf, gfp_t gfp)
 {
-	int ret = 0;
+	gfp_t gfp_nomemalloc;
+	int ret;
+
+	gfp_nomemalloc = gfp | __GFP_NOMEMALLOC;
+	if (gfp_pfmemalloc_allowed(gfp))
+		gfp_nomemalloc |= __GFP_NOWARN;
 
-	ret = refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC);
+	ret = refill_sheaf(s, sheaf, gfp_nomemalloc);
 
 	if (likely(!ret || !gfp_pfmemalloc_allowed(gfp)))
 		return ret;