Merge tag 'slab-for-6.13-v2' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/vbabka/slab

Pull slab updates from Vlastimil Babka:

 - Add new slab_strict_numa boot parameter to enforce per-object memory
   policies on top of slab folio policies, for systems where saving cost
   of remote accesses is more important than minimizing slab allocation
   overhead (Christoph Lameter)

 - Fix for freeptr_offset alignment check being too strict for m68k
   (Geert Uytterhoeven)

 - krealloc() fixes for not violating __GFP_ZERO guarantees on
   krealloc() when slub_debug (redzone and object tracking) is enabled
   (Feng Tang)

 - Fix a memory leak in case sysfs registration fails for a slab cache,
   and also no longer fail to create the cache in that case (Hyeonggon
   Yoo)

 - Fix handling of detected consistency problems (due to buggy slab
   user) with slub_debug enabled, so that it does not cause further list
   corruption bugs (yuan.gao)

 - Code cleanup and kerneldocs polishing (Zhen Lei, Vlastimil Babka)

* tag 'slab-for-6.13-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
  slab: Fix too strict alignment check in create_cache()
  mm/slab: Allow cache creation to proceed even if sysfs registration fails
  mm/slub: Avoid list corruption when removing a slab from the full list
  mm/slub, kunit: Add testcase for krealloc redzone and zeroing
  mm/slub: Improve redzone check and zeroing for krealloc()
  mm/slub: Consider kfence case for get_orig_size()
  SLUB: Add support for per object memory policies
  mm, slab: add kerneldocs for common SLAB_ flags
  mm/slab: remove duplicate check in create_cache()
  mm/slub: Move krealloc() and related code to slub.c
  mm/kasan: Don't store metadata inside kmalloc object when slub_debug_orig_size is on

Documentation/admin-guide/kernel-parameters.txt

@@ -6158,6 +6158,16 @@
 			For more information see Documentation/mm/slub.rst.
 			(slub_nomerge legacy name also accepted for now)
 
+	slab_strict_numa	[MM]
+			Support memory policies on a per object level
+			in the slab allocator. The default is for memory
+			policies to be applied at the folio level when
+			a new folio is needed or a partial folio is
+			retrieved from the lists. Increases overhead
+			in the slab fastpaths but gains more accurate
+			NUMA kernel object placement which helps with slow
+			interconnects in NUMA systems.
+
 	slram=		[HW,MTD]
 
 	smart2=		[HW]

Documentation/mm/slub.rst

@@ -175,6 +175,15 @@ can be influenced by kernel parameters:
 	``slab_max_order`` to 0, what cause minimum possible order of
 	slabs allocation.
 
+``slab_strict_numa``
+        Enables the application of memory policies on each
+        allocation. This results in more accurate placement of
+        objects which may result in the reduction of accesses
+        to remote nodes. The default is to only apply memory
+        policies at the folio level when a new folio is acquired
+        or a folio is retrieved from the lists. Enabling this
+        option reduces the fastpath performance of the slab allocator.
+
 SLUB Debug output
 =================
 

include/linux/slab.h

@@ -77,7 +77,17 @@ enum _slab_flag_bits {
 #define SLAB_POISON		__SLAB_FLAG_BIT(_SLAB_POISON)
 /* Indicate a kmalloc slab */
 #define SLAB_KMALLOC		__SLAB_FLAG_BIT(_SLAB_KMALLOC)
-/* Align objs on cache lines */
+/**
+ * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries.
+ *
+ * Sufficiently large objects are aligned on cache line boundary. For object
+ * size smaller than a half of cache line size, the alignment is on the half of
+ * cache line size. In general, if object size is smaller than 1/2^n of cache
+ * line size, the alignment is adjusted to 1/2^n.
+ *
+ * If explicit alignment is also requested by the respective
+ * &struct kmem_cache_args field, the greater of both is alignments is applied.
+ */
 #define SLAB_HWCACHE_ALIGN	__SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN)
 /* Use GFP_DMA memory */
 #define SLAB_CACHE_DMA		__SLAB_FLAG_BIT(_SLAB_CACHE_DMA)
@@ -87,8 +97,8 @@ enum _slab_flag_bits {
 #define SLAB_STORE_USER		__SLAB_FLAG_BIT(_SLAB_STORE_USER)
 /* Panic if kmem_cache_create() fails */
 #define SLAB_PANIC		__SLAB_FLAG_BIT(_SLAB_PANIC)
-/*
- * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
+/**
+ * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
  *
  * This delays freeing the SLAB page by a grace period, it does _NOT_
  * delay object freeing. This means that if you do kmem_cache_free()
@@ -99,20 +109,22 @@ enum _slab_flag_bits {
  * stays valid, the trick to using this is relying on an independent
  * object validation pass. Something like:
  *
- * begin:
- *  rcu_read_lock();
- *  obj = lockless_lookup(key);
- *  if (obj) {
- *    if (!try_get_ref(obj)) // might fail for free objects
- *      rcu_read_unlock();
- *      goto begin;
+ * ::
+ *
+ *  begin:
+ *   rcu_read_lock();
+ *   obj = lockless_lookup(key);
+ *   if (obj) {
+ *     if (!try_get_ref(obj)) // might fail for free objects
+ *       rcu_read_unlock();
+ *       goto begin;
  *
- *    if (obj->key != key) { // not the object we expected
- *      put_ref(obj);
- *      rcu_read_unlock();
- *      goto begin;
- *    }
- *  }
+ *     if (obj->key != key) { // not the object we expected
+ *       put_ref(obj);
+ *       rcu_read_unlock();
+ *       goto begin;
+ *     }
+ *   }
  *  rcu_read_unlock();
  *
  * This is useful if we need to approach a kernel structure obliquely,
@@ -137,7 +149,6 @@ enum _slab_flag_bits {
  *
  * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
  */
-/* Defer freeing slabs to RCU */
 #define SLAB_TYPESAFE_BY_RCU	__SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU)
 /* Trace allocations and frees */
 #define SLAB_TRACE		__SLAB_FLAG_BIT(_SLAB_TRACE)
@@ -170,7 +181,12 @@ enum _slab_flag_bits {
 #else
 # define SLAB_FAILSLAB		__SLAB_FLAG_UNUSED
 #endif
-/* Account to memcg */
+/**
+ * define SLAB_ACCOUNT - Account allocations to memcg.
+ *
+ * All object allocations from this cache will be memcg accounted, regardless of
+ * __GFP_ACCOUNT being or not being passed to individual allocations.
+ */
 #ifdef CONFIG_MEMCG
 # define SLAB_ACCOUNT		__SLAB_FLAG_BIT(_SLAB_ACCOUNT)
 #else
@@ -197,7 +213,13 @@ enum _slab_flag_bits {
 #endif
 
 /* The following flags affect the page allocator grouping pages by mobility */
-/* Objects are reclaimable */
+/**
+ * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable.
+ *
+ * Use this flag for caches that have an associated shrinker. As a result, slab
+ * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by
+ * mobility, and are accounted in SReclaimable counter in /proc/meminfo
+ */
 #ifndef CONFIG_SLUB_TINY
 #define SLAB_RECLAIM_ACCOUNT	__SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT)
 #else

lib/slub_kunit.c

@@ -192,6 +192,47 @@ static void test_leak_destroy(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 2, slab_errors);
 }
 
+static void test_krealloc_redzone_zeroing(struct kunit *test)
+{
+	u8 *p;
+	int i;
+	struct kmem_cache *s = test_kmem_cache_create("TestSlub_krealloc", 64,
+				SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE);
+
+	p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 48));
+	memset(p, 0xff, 48);
+
+	kasan_disable_current();
+	OPTIMIZER_HIDE_VAR(p);
+
+	/* Test shrink */
+	p = krealloc(p, 40, GFP_KERNEL | __GFP_ZERO);
+	for (i = 40; i < 64; i++)
+		KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE);
+
+	/* Test grow within the same 64B kmalloc object */
+	p = krealloc(p, 56, GFP_KERNEL | __GFP_ZERO);
+	for (i = 40; i < 56; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0);
+	for (i = 56; i < 64; i++)
+		KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE);
+
+	validate_slab_cache(s);
+	KUNIT_EXPECT_EQ(test, 0, slab_errors);
+
+	memset(p, 0xff, 56);
+	/* Test grow with allocating a bigger 128B object */
+	p = krealloc(p, 112, GFP_KERNEL | __GFP_ZERO);
+	for (i = 0; i < 56; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0xff);
+	for (i = 56; i < 112; i++)
+		KUNIT_EXPECT_EQ(test, p[i], 0);
+
+	kfree(p);
+	kasan_enable_current();
+	kmem_cache_destroy(s);
+}
+
 static int test_init(struct kunit *test)
 {
 	slab_errors = 0;
@@ -214,6 +255,7 @@ static struct kunit_case test_cases[] = {
 	KUNIT_CASE(test_kmalloc_redzone_access),
 	KUNIT_CASE(test_kfree_rcu),
 	KUNIT_CASE(test_leak_destroy),
+	KUNIT_CASE(test_krealloc_redzone_zeroing),
 	{}
 };
 

mm/kasan/generic.c

@@ -392,9 +392,12 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 	 * 1. Object is SLAB_TYPESAFE_BY_RCU, which means that it can
 	 *    be touched after it was freed, or
 	 * 2. Object has a constructor, which means it's expected to
-	 *    retain its content until the next allocation.
+	 *    retain its content until the next allocation, or
+	 * 3. It is from a kmalloc cache which enables the debug option
+	 *    to store original size.
 	 */
-	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor) {
+	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor ||
+	     slub_debug_orig_size(cache)) {
 		cache->kasan_info.free_meta_offset = *size;
 		*size += sizeof(struct kasan_free_meta);
 		goto free_meta_added;

mm/slab.h

@@ -73,6 +73,11 @@ struct slab {
 						struct {
 							unsigned inuse:16;
 							unsigned objects:15;
+							/*
+							 * If slab debugging is enabled then the
+							 * frozen bit can be reused to indicate
+							 * that the slab was corrupted
+							 */
 							unsigned frozen:1;
 						};
 					};
@@ -695,6 +700,12 @@ void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
 void __check_heap_object(const void *ptr, unsigned long n,
 			 const struct slab *slab, bool to_user);
 
+static inline bool slub_debug_orig_size(struct kmem_cache *s)
+{
+	return (kmem_cache_debug_flags(s, SLAB_STORE_USER) &&
+			(s->flags & SLAB_KMALLOC));
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 void skip_orig_size_check(struct kmem_cache *s, const void *object);
 #endif

mm/slab_common.c

@@ -222,15 +222,12 @@ static struct kmem_cache *create_cache(const char *name,
 	struct kmem_cache *s;
 	int err;
 
-	if (WARN_ON(args->useroffset + args->usersize > object_size))
-		args->useroffset = args->usersize = 0;
-
 	/* If a custom freelist pointer is requested make sure it's sane. */
 	err = -EINVAL;
 	if (args->use_freeptr_offset &&
 	    (args->freeptr_offset >= object_size ||
 	     !(flags & SLAB_TYPESAFE_BY_RCU) ||
-	     !IS_ALIGNED(args->freeptr_offset, sizeof(freeptr_t))))
+	     !IS_ALIGNED(args->freeptr_offset, __alignof__(freeptr_t))))
 		goto out;
 
 	err = -ENOMEM;
@@ -257,11 +254,23 @@ static struct kmem_cache *create_cache(const char *name,
  * @object_size: The size of objects to be created in this cache.
  * @args: Additional arguments for the cache creation (see
  *        &struct kmem_cache_args).
- * @flags: See %SLAB_* flags for an explanation of individual @flags.
+ * @flags: See the desriptions of individual flags. The common ones are listed
+ *         in the description below.
  *
  * Not to be called directly, use the kmem_cache_create() wrapper with the same
  * parameters.
  *
+ * Commonly used @flags:
+ *
+ * &SLAB_ACCOUNT - Account allocations to memcg.
+ *
+ * &SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries.
+ *
+ * &SLAB_RECLAIM_ACCOUNT - Objects are reclaimable.
+ *
+ * &SLAB_TYPESAFE_BY_RCU - Slab page (not individual objects) freeing delayed
+ * by a grace period - see the full description before using.
+ *
  * Context: Cannot be called within a interrupt, but can be interrupted.
  *
  * Return: a pointer to the cache on success, NULL on failure.
@@ -1199,90 +1208,6 @@ module_init(slab_proc_init);
 
 #endif /* CONFIG_SLUB_DEBUG */
 
-static __always_inline __realloc_size(2) void *
-__do_krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	void *ret;
-	size_t ks;
-
-	/* Check for double-free before calling ksize. */
-	if (likely(!ZERO_OR_NULL_PTR(p))) {
-		if (!kasan_check_byte(p))
-			return NULL;
-		ks = ksize(p);
-	} else
-		ks = 0;
-
-	/* If the object still fits, repoison it precisely. */
-	if (ks >= new_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags)) {
-			kasan_disable_current();
-			memset(kasan_reset_tag(p) + new_size, 0, ks - new_size);
-			kasan_enable_current();
-		}
-
-		p = kasan_krealloc((void *)p, new_size, flags);
-		return (void *)p;
-	}
-
-	ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_);
-	if (ret && p) {
-		/* Disable KASAN checks as the object's redzone is accessed. */
-		kasan_disable_current();
-		memcpy(ret, kasan_reset_tag(p), ks);
-		kasan_enable_current();
-	}
-
-	return ret;
-}
-
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * If @p is %NULL, krealloc() behaves exactly like kmalloc().  If @new_size
- * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
- *
- * If __GFP_ZERO logic is requested, callers must ensure that, starting with the
- * initial memory allocation, every subsequent call to this API for the same
- * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
- * __GFP_ZERO is not fully honored by this API.
- *
- * This is the case, since krealloc() only knows about the bucket size of an
- * allocation (but not the exact size it was allocated with) and hence
- * implements the following semantics for shrinking and growing buffers with
- * __GFP_ZERO.
- *
- *         new             bucket
- * 0       size             size
- * |--------|----------------|
- * |  keep  |      zero      |
- *
- * In any case, the contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes.
- *
- * Return: pointer to the allocated memory or %NULL in case of error
- */
-void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags)
-{
-	void *ret;
-
-	if (unlikely(!new_size)) {
-		kfree(p);
-		return ZERO_SIZE_PTR;
-	}
-
-	ret = __do_krealloc(p, new_size, flags);
-	if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
-		kfree(p);
-
-	return ret;
-}
-EXPORT_SYMBOL(krealloc_noprof);
-
 /**
  * kfree_sensitive - Clear sensitive information in memory before freeing
  * @p: object to free memory of