Merge branch 'slub-tiny-v1r6' into slab/for-next

Merge my series [1] to deprecate the SLOB allocator.
- Renames CONFIG_SLOB to CONFIG_SLOB_DEPRECATED with deprecation notice.
- The recommended replacement is CONFIG_SLUB, optionally with the new
  CONFIG_SLUB_TINY tweaks for systems with 16MB or less RAM.
- Use cases that stopped working with CONFIG_SLUB_TINY instead of SLOB
  should be reported to linux-mm@kvack.org and slab maintainers,
  otherwise SLOB will be removed in few cycles.

[1] https://lore.kernel.org/all/20221121171202.22080-1-vbabka@suse.cz/

5 files changed, 339 insertions, 148 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 57e1d8c5b505..623d95659ff9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -219,17 +219,43 @@ config SLUB
 	   and has enhanced diagnostics. SLUB is the default choice for
 	   a slab allocator.
 
-config SLOB
+config SLOB_DEPRECATED
 	depends on EXPERT
-	bool "SLOB (Simple Allocator)"
+	bool "SLOB (Simple Allocator - DEPRECATED)"
 	depends on !PREEMPT_RT
 	help
+	   Deprecated and scheduled for removal in a few cycles. SLUB
+	   recommended as replacement. CONFIG_SLUB_TINY can be considered
+	   on systems with 16MB or less RAM.
+
+	   If you need SLOB to stay, please contact linux-mm@kvack.org and
+	   people listed in the SLAB ALLOCATOR section of MAINTAINERS file,
+	   with your use case.
+
 	   SLOB replaces the stock allocator with a drastically simpler
 	   allocator. SLOB is generally more space efficient but
 	   does not perform as well on large systems.
 
 endchoice
 
+config SLOB
+	bool
+	default y
+	depends on SLOB_DEPRECATED
+
+config SLUB_TINY
+	bool "Configure SLUB for minimal memory footprint"
+	depends on SLUB && EXPERT
+	select SLAB_MERGE_DEFAULT
+	help
+	   Configures the SLUB allocator in a way to achieve minimal memory
+	   footprint, sacrificing scalability, debugging and other features.
+	   This is intended only for the smallest system that had used the
+	   SLOB allocator and is not recommended for systems with more than
+	   16MB RAM.
+
+	   If unsure, say N.
+
 config SLAB_MERGE_DEFAULT
 	bool "Allow slab caches to be merged"
 	default y
@@ -247,7 +273,7 @@ config SLAB_MERGE_DEFAULT
 
 config SLAB_FREELIST_RANDOM
 	bool "Randomize slab freelist"
-	depends on SLAB || SLUB
+	depends on SLAB || (SLUB && !SLUB_TINY)
 	help
 	  Randomizes the freelist order used on creating new pages. This
 	  security feature reduces the predictability of the kernel slab
@@ -255,7 +281,7 @@ config SLAB_FREELIST_RANDOM
 
 config SLAB_FREELIST_HARDENED
 	bool "Harden slab freelist metadata"
-	depends on SLAB || SLUB
+	depends on SLAB || (SLUB && !SLUB_TINY)
 	help
 	  Many kernel heap attacks try to target slab cache metadata and
 	  other infrastructure. This options makes minor performance
@@ -267,7 +293,7 @@ config SLAB_FREELIST_HARDENED
 config SLUB_STATS
 	default n
 	bool "Enable SLUB performance statistics"
-	depends on SLUB && SYSFS
+	depends on SLUB && SYSFS && !SLUB_TINY
 	help
 	  SLUB statistics are useful to debug SLUBs allocation behavior in
 	  order find ways to optimize the allocator. This should never be
@@ -279,7 +305,7 @@ config SLUB_STATS
 
 config SLUB_CPU_PARTIAL
 	default y
-	depends on SLUB && SMP
+	depends on SLUB && SMP && !SLUB_TINY
 	bool "SLUB per cpu partial cache"
 	help
 	  Per cpu partial caches accelerate objects allocation and freeing
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index ce8dded36de9..fca699ad1fb0 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -56,7 +56,7 @@ config DEBUG_SLAB
 config SLUB_DEBUG
 	default y
 	bool "Enable SLUB debugging support" if EXPERT
-	depends on SLUB && SYSFS
+	depends on SLUB && SYSFS && !SLUB_TINY
 	select STACKDEPOT if STACKTRACE_SUPPORT
 	help
 	  SLUB has extensive debug support features. Disabling these can
diff --git a/mm/slab.h b/mm/slab.h
index 060c589a827a..7cc432969945 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -217,8 +217,6 @@ struct kmem_cache {
 	unsigned int size;	/* The aligned/padded/added on size  */
 	unsigned int align;	/* Alignment as calculated */
 	slab_flags_t flags;	/* Active flags on the slab */
-	unsigned int useroffset;/* Usercopy region offset */
-	unsigned int usersize;	/* Usercopy region size */
 	const char *name;	/* Slab name for sysfs */
 	int refcount;		/* Use counter */
 	void (*ctor)(void *);	/* Called on object slot creation */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8276022f0da4..3e49bb830060 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -143,8 +143,10 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (s->ctor)
 		return 1;
 
+#ifdef CONFIG_HARDENED_USERCOPY
 	if (s->usersize)
 		return 1;
+#endif
 
 	/*
 	 * We may have set a slab to be unmergeable during bootstrap.
@@ -223,8 +225,10 @@ static struct kmem_cache *create_cache(const char *name,
 	s->size = s->object_size = object_size;
 	s->align = align;
 	s->ctor = ctor;
+#ifdef CONFIG_HARDENED_USERCOPY
 	s->useroffset = useroffset;
 	s->usersize = usersize;
+#endif
 
 	err = __kmem_cache_create(s, flags);
 	if (err)
@@ -317,7 +321,8 @@ kmem_cache_create_usercopy(const char *name,
 	flags &= CACHE_CREATE_MASK;
 
 	/* Fail closed on bad usersize of useroffset values. */
-	if (WARN_ON(!usersize && useroffset) ||
+	if (!IS_ENABLED(CONFIG_HARDENED_USERCOPY) ||
+	    WARN_ON(!usersize && useroffset) ||
 	    WARN_ON(size < usersize || size - usersize < useroffset))
 		usersize = useroffset = 0;
 
@@ -595,8 +600,8 @@ void kmem_dump_obj(void *object)
 		ptroffset = ((char *)object - (char *)kp.kp_objp) - kp.kp_data_offset;
 		pr_cont(" pointer offset %lu", ptroffset);
 	}
-	if (kp.kp_slab_cache && kp.kp_slab_cache->usersize)
-		pr_cont(" size %u", kp.kp_slab_cache->usersize);
+	if (kp.kp_slab_cache && kp.kp_slab_cache->object_size)
+		pr_cont(" size %u", kp.kp_slab_cache->object_size);
 	if (kp.kp_ret)
 		pr_cont(" allocated at %pS\n", kp.kp_ret);
 	else
@@ -640,8 +645,10 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
 		align = max(align, size);
 	s->align = calculate_alignment(flags, align, size);
 
+#ifdef CONFIG_HARDENED_USERCOPY
 	s->useroffset = useroffset;
 	s->usersize = usersize;
+#endif
 
 	err = __kmem_cache_create(s, flags);
 
@@ -766,10 +773,16 @@ EXPORT_SYMBOL(kmalloc_size_roundup);
 #define KMALLOC_CGROUP_NAME(sz)
 #endif
 
+#ifndef CONFIG_SLUB_TINY
+#define KMALLOC_RCL_NAME(sz)	.name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #sz,
+#else
+#define KMALLOC_RCL_NAME(sz)
+#endif
+
 #define INIT_KMALLOC_INFO(__size, __short_size)			\
 {								\
 	.name[KMALLOC_NORMAL]  = "kmalloc-" #__short_size,	\
-	.name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size,	\
+	KMALLOC_RCL_NAME(__short_size)				\
 	KMALLOC_CGROUP_NAME(__short_size)			\
 	KMALLOC_DMA_NAME(__short_size)				\
 	.size = __size,						\
@@ -855,7 +868,7 @@ void __init setup_kmalloc_cache_index_table(void)
 static void __init
 new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
 {
-	if (type == KMALLOC_RECLAIM) {
+	if ((KMALLOC_RECLAIM != KMALLOC_NORMAL) && (type == KMALLOC_RECLAIM)) {
 		flags |= SLAB_RECLAIM_ACCOUNT;
 	} else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) {
 		if (mem_cgroup_kmem_disabled()) {
diff --git a/mm/slub.c b/mm/slub.c
index a24b71041b26..891df05a4d45 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -187,6 +187,12 @@ do {					\
 #define USE_LOCKLESS_FAST_PATH()	(false)
 #endif
 
+#ifndef CONFIG_SLUB_TINY
+#define __fastpath_inline __always_inline
+#else
+#define __fastpath_inline
+#endif
+
 #ifdef CONFIG_SLUB_DEBUG
 #ifdef CONFIG_SLUB_DEBUG_ON
 DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
@@ -241,6 +247,7 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 /* Enable to log cmpxchg failures */
 #undef SLUB_DEBUG_CMPXCHG
 
+#ifndef CONFIG_SLUB_TINY
 /*
  * Minimum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -253,6 +260,10 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
  * sort the partial list by the number of objects in use.
  */
 #define MAX_PARTIAL 10
+#else
+#define MIN_PARTIAL 0
+#define MAX_PARTIAL 0
+#endif
 
 #define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \
 				SLAB_POISON | SLAB_STORE_USER)
@@ -298,7 +309,7 @@ struct track {
 
 enum track_item { TRACK_ALLOC, TRACK_FREE };
 
-#ifdef CONFIG_SYSFS
+#ifdef SLAB_SUPPORTS_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 #else
@@ -332,10 +343,12 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
  */
 static nodemask_t slab_nodes;
 
+#ifndef CONFIG_SLUB_TINY
 /*
  * Workqueue used for flush_cpu_slab().
  */
 static struct workqueue_struct *flushwq;
+#endif
 
 /********************************************************************
  * 			Core slab cache functions
@@ -381,10 +394,12 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
 	return freelist_dereference(s, object + s->offset);
 }
 
+#ifndef CONFIG_SLUB_TINY
 static void prefetch_freepointer(const struct kmem_cache *s, void *object)
 {
 	prefetchw(object + s->offset);
 }
+#endif
 
 /*
  * When running under KMSAN, get_freepointer_safe() may return an uninitialized
@@ -1402,7 +1417,7 @@ static inline int alloc_consistency_checks(struct kmem_cache *s,
 	return 1;
 }
 
-static noinline int alloc_debug_processing(struct kmem_cache *s,
+static noinline bool alloc_debug_processing(struct kmem_cache *s,
 			struct slab *slab, void *object, int orig_size)
 {
 	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
@@ -1414,7 +1429,7 @@ static noinline int alloc_debug_processing(struct kmem_cache *s,
 	trace(s, slab, object, 1);
 	set_orig_size(s, object, orig_size);
 	init_object(s, object, SLUB_RED_ACTIVE);
-	return 1;
+	return true;
 
 bad:
 	if (folio_test_slab(slab_folio(slab))) {
@@ -1427,7 +1442,7 @@ bad:
 		slab->inuse = slab->objects;
 		slab->freelist = NULL;
 	}
-	return 0;
+	return false;
 }
 
 static inline int free_consistency_checks(struct kmem_cache *s,
@@ -1680,17 +1695,17 @@ static inline void setup_object_debug(struct kmem_cache *s, void *object) {}
 static inline
 void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
 
-static inline int alloc_debug_processing(struct kmem_cache *s,
-	struct slab *slab, void *object, int orig_size) { return 0; }
+static inline bool alloc_debug_processing(struct kmem_cache *s,
+	struct slab *slab, void *object, int orig_size) { return true; }
 
-static inline void free_debug_processing(
-	struct kmem_cache *s, struct slab *slab,
-	void *head, void *tail, int bulk_cnt,
-	unsigned long addr) {}
+static inline bool free_debug_processing(struct kmem_cache *s,
+	struct slab *slab, void *head, void *tail, int *bulk_cnt,
+	unsigned long addr, depot_stack_handle_t handle) { return true; }
 
 static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
 static inline int check_object(struct kmem_cache *s, struct slab *slab,
 			void *object, u8 val) { return 1; }
+static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
 static inline void set_track(struct kmem_cache *s, void *object,
 			     enum track_item alloc, unsigned long addr) {}
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
@@ -1715,11 +1730,13 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+#ifndef CONFIG_SLUB_TINY
 static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
 			       void **freelist, void *nextfree)
 {
 	return false;
 }
+#endif
 #endif /* CONFIG_SLUB_DEBUG */
 
 /*
@@ -2257,7 +2274,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 		if (!pfmemalloc_match(slab, pc->flags))
 			continue;
 
-		if (kmem_cache_debug(s)) {
+		if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
 			object = alloc_single_from_partial(s, n, slab,
 							pc->orig_size);
 			if (object)
@@ -2372,6 +2389,8 @@ static void *get_partial(struct kmem_cache *s, int node, struct partial_context
 	return get_any_partial(s, pc);
 }
 
+#ifndef CONFIG_SLUB_TINY
+
 #ifdef CONFIG_PREEMPTION
 /*
  * Calculate the next globally unique transaction for disambiguation
@@ -2385,7 +2404,7 @@ static void *get_partial(struct kmem_cache *s, int node, struct partial_context
  * different cpus.
  */
 #define TID_STEP 1
-#endif
+#endif /* CONFIG_PREEMPTION */
 
 static inline unsigned long next_tid(unsigned long tid)
 {
@@ -2834,6 +2853,13 @@ static int slub_cpu_dead(unsigned int cpu)
 	return 0;
 }
 
+#else /* CONFIG_SLUB_TINY */
+static inline void flush_all_cpus_locked(struct kmem_cache *s) { }
+static inline void flush_all(struct kmem_cache *s) { }
+static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { }
+static inline int slub_cpu_dead(unsigned int cpu) { return 0; }
+#endif /* CONFIG_SLUB_TINY */
+
 /*
  * Check if the objects in a per cpu structure fit numa
  * locality expectations.
@@ -2859,38 +2885,28 @@ static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
 }
 
 /* Supports checking bulk free of a constructed freelist */
-static noinline void free_debug_processing(
-	struct kmem_cache *s, struct slab *slab,
-	void *head, void *tail, int bulk_cnt,
-	unsigned long addr)
+static inline bool free_debug_processing(struct kmem_cache *s,
+	struct slab *slab, void *head, void *tail, int *bulk_cnt,
+	unsigned long addr, depot_stack_handle_t handle)
 {
-	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
-	struct slab *slab_free = NULL;
+	bool checks_ok = false;
 	void *object = head;
 	int cnt = 0;
-	unsigned long flags;
-	bool checks_ok = false;
-	depot_stack_handle_t handle = 0;
-
-	if (s->flags & SLAB_STORE_USER)
-		handle = set_track_prepare();
-
-	spin_lock_irqsave(&n->list_lock, flags);
 
 	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
 		if (!check_slab(s, slab))
 			goto out;
 	}
 
-	if (slab->inuse < bulk_cnt) {
+	if (slab->inuse < *bulk_cnt) {
 		slab_err(s, slab, "Slab has %d allocated objects but %d are to be freed\n",
-			 slab->inuse, bulk_cnt);
+			 slab->inuse, *bulk_cnt);
 		goto out;
 	}
 
 next_object:
 
-	if (++cnt > bulk_cnt)
+	if (++cnt > *bulk_cnt)
 		goto out_cnt;
 
 	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
@@ -2912,61 +2928,22 @@ next_object:
 	checks_ok = true;
 
 out_cnt:
-	if (cnt != bulk_cnt)
+	if (cnt != *bulk_cnt) {
 		slab_err(s, slab, "Bulk free expected %d objects but found %d\n",
-			 bulk_cnt, cnt);
-
-out:
-	if (checks_ok) {
-		void *prior = slab->freelist;
-
-		/* Perform the actual freeing while we still hold the locks */
-		slab->inuse -= cnt;
-		set_freepointer(s, tail, prior);
-		slab->freelist = head;
-
-		/*
-		 * If the slab is empty, and node's partial list is full,
-		 * it should be discarded anyway no matter it's on full or
-		 * partial list.
-		 */
-		if (slab->inuse == 0 && n->nr_partial >= s->min_partial)
-			slab_free = slab;
-
-		if (!prior) {
-			/* was on full list */
-			remove_full(s, n, slab);
-			if (!slab_free) {
-				add_partial(n, slab, DEACTIVATE_TO_TAIL);
-				stat(s, FREE_ADD_PARTIAL);
-			}
-		} else if (slab_free) {
-			remove_partial(n, slab);
-			stat(s, FREE_REMOVE_PARTIAL);
-		}
+			 *bulk_cnt, cnt);
+		*bulk_cnt = cnt;
 	}
 
-	if (slab_free) {
-		/*
-		 * Update the counters while still holding n->list_lock to
-		 * prevent spurious validation warnings
-		 */
-		dec_slabs_node(s, slab_nid(slab_free), slab_free->objects);
-	}
-
-	spin_unlock_irqrestore(&n->list_lock, flags);
+out:
 
 	if (!checks_ok)
 		slab_fix(s, "Object at 0x%p not freed", object);
 
-	if (slab_free) {
-		stat(s, FREE_SLAB);
-		free_slab(s, slab_free);
-	}
+	return checks_ok;
 }
 #endif /* CONFIG_SLUB_DEBUG */
 
-#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS)
+#if defined(CONFIG_SLUB_DEBUG) || defined(SLAB_SUPPORTS_SYSFS)
 static unsigned long count_partial(struct kmem_cache_node *n,
 					int (*get_count)(struct slab *))
 {
@@ -2980,12 +2957,12 @@ static unsigned long count_partial(struct kmem_cache_node *n,
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	return x;
 }
-#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */
+#endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */
 
+#ifdef CONFIG_SLUB_DEBUG
 static noinline void
 slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 {
-#ifdef CONFIG_SLUB_DEBUG
 	static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 	int node;
@@ -3016,8 +2993,11 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 		pr_warn("  node %d: slabs: %ld, objs: %ld, free: %ld\n",
 			node, nr_slabs, nr_objs, nr_free);
 	}
-#endif
 }
+#else /* CONFIG_SLUB_DEBUG */
+static inline void
+slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { }
+#endif
 
 static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
 {
@@ -3027,6 +3007,7 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
 	return true;
 }
 
+#ifndef CONFIG_SLUB_TINY
 /*
  * Check the slab->freelist and either transfer the freelist to the
  * per cpu freelist or deactivate the slab.
@@ -3314,45 +3295,13 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	return p;
 }
 
-/*
- * If the object has been wiped upon free, make sure it's fully initialized by
- * zeroing out freelist pointer.
- */
-static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
-						   void *obj)
-{
-	if (unlikely(slab_want_init_on_free(s)) && obj)
-		memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
-			0, sizeof(void *));
-}
-
-/*
- * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
- * have the fastpath folded into their functions. So no function call
- * overhead for requests that can be satisfied on the fastpath.
- *
- * The fastpath works by first checking if the lockless freelist can be used.
- * If not then __slab_alloc is called for slow processing.
- *
- * Otherwise we can simply pick the next object from the lockless free list.
- */
-static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
+static __always_inline void *__slab_alloc_node(struct kmem_cache *s,
 		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
 {
-	void *object;
 	struct kmem_cache_cpu *c;
 	struct slab *slab;
 	unsigned long tid;
-	struct obj_cgroup *objcg = NULL;
-	bool init = false;
-
-	s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
-	if (!s)
-		return NULL;
-
-	object = kfence_alloc(s, orig_size, gfpflags);
-	if (unlikely(object))
-		goto out;
+	void *object;
 
 redo:
 	/*
@@ -3422,6 +3371,75 @@ redo:
 		stat(s, ALLOC_FASTPATH);
 	}
 
+	return object;
+}
+#else /* CONFIG_SLUB_TINY */
+static void *__slab_alloc_node(struct kmem_cache *s,
+		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
+{
+	struct partial_context pc;
+	struct slab *slab;
+	void *object;
+
+	pc.flags = gfpflags;
+	pc.slab = &slab;
+	pc.orig_size = orig_size;
+	object = get_partial(s, node, &pc);
+
+	if (object)
+		return object;
+
+	slab = new_slab(s, gfpflags, node);
+	if (unlikely(!slab)) {
+		slab_out_of_memory(s, gfpflags, node);
+		return NULL;
+	}
+
+	object = alloc_single_from_new_slab(s, slab, orig_size);
+
+	return object;
+}
+#endif /* CONFIG_SLUB_TINY */
+
+/*
+ * If the object has been wiped upon free, make sure it's fully initialized by
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+						   void *obj)
+{
+	if (unlikely(slab_want_init_on_free(s)) && obj)
+		memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
+			0, sizeof(void *));
+}
+
+/*
+ * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
+ * have the fastpath folded into their functions. So no function call
+ * overhead for requests that can be satisfied on the fastpath.
+ *
+ * The fastpath works by first checking if the lockless freelist can be used.
+ * If not then __slab_alloc is called for slow processing.
+ *
+ * Otherwise we can simply pick the next object from the lockless free list.
+ */
+static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
+		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
+{
+	void *object;
+	struct obj_cgroup *objcg = NULL;
+	bool init = false;
+
+	s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
+	if (!s)
+		return NULL;
+
+	object = kfence_alloc(s, orig_size, gfpflags);
+	if (unlikely(object))
+		goto out;
+
+	object = __slab_alloc_node(s, gfpflags, node, addr, orig_size);
+
 	maybe_wipe_obj_freeptr(s, object);
 	init = slab_want_init_on_alloc(gfpflags, s);
 
@@ -3435,13 +3453,13 @@ out:
 	return object;
 }
 
-static __always_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
+static __fastpath_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
 		gfp_t gfpflags, unsigned long addr, size_t orig_size)
 {
 	return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
 }
 
-static __always_inline
+static __fastpath_inline
 void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
 			     gfp_t gfpflags)
 {
@@ -3483,6 +3501,67 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
+static noinline void free_to_partial_list(
+	struct kmem_cache *s, struct slab *slab,
+	void *head, void *tail, int bulk_cnt,
+	unsigned long addr)
+{
+	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
+	struct slab *slab_free = NULL;
+	int cnt = bulk_cnt;
+	unsigned long flags;
+	depot_stack_handle_t handle = 0;
+
+	if (s->flags & SLAB_STORE_USER)
+		handle = set_track_prepare();
+
+	spin_lock_irqsave(&n->list_lock, flags);
+
+	if (free_debug_processing(s, slab, head, tail, &cnt, addr, handle)) {
+		void *prior = slab->freelist;
+
+		/* Perform the actual freeing while we still hold the locks */
+		slab->inuse -= cnt;
+		set_freepointer(s, tail, prior);
+		slab->freelist = head;
+
+		/*
+		 * If the slab is empty, and node's partial list is full,
+		 * it should be discarded anyway no matter it's on full or
+		 * partial list.
+		 */
+		if (slab->inuse == 0 && n->nr_partial >= s->min_partial)
+			slab_free = slab;
+
+		if (!prior) {
+			/* was on full list */
+			remove_full(s, n, slab);
+			if (!slab_free) {
+				add_partial(n, slab, DEACTIVATE_TO_TAIL);
+				stat(s, FREE_ADD_PARTIAL);
+			}
+		} else if (slab_free) {
+			remove_partial(n, slab);
+			stat(s, FREE_REMOVE_PARTIAL);
+		}
+	}
+
+	if (slab_free) {
+		/*
+		 * Update the counters while still holding n->list_lock to
+		 * prevent spurious validation warnings
+		 */
+		dec_slabs_node(s, slab_nid(slab_free), slab_free->objects);
+	}
+
+	spin_unlock_irqrestore(&n->list_lock, flags);
+
+	if (slab_free) {
+		stat(s, FREE_SLAB);
+		free_slab(s, slab_free);
+	}
+}
+
 /*
  * Slow path handling. This may still be called frequently since objects
  * have a longer lifetime than the cpu slabs in most processing loads.
@@ -3508,8 +3587,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
 	if (kfence_free(head))
 		return;
 
-	if (kmem_cache_debug(s)) {
-		free_debug_processing(s, slab, head, tail, cnt, addr);
+	if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
+		free_to_partial_list(s, slab, head, tail, cnt, addr);
 		return;
 	}
 
@@ -3609,6 +3688,7 @@ slab_empty:
 	discard_slab(s, slab);
 }
 
+#ifndef CONFIG_SLUB_TINY
 /*
  * Fastpath with forced inlining to produce a kfree and kmem_cache_free that
  * can perform fastpath freeing without additional function calls.
@@ -3683,8 +3763,18 @@ redo:
 	}
 	stat(s, FREE_FASTPATH);
 }
+#else /* CONFIG_SLUB_TINY */
+static void do_slab_free(struct kmem_cache *s,
+				struct slab *slab, void *head, void *tail,
+				int cnt, unsigned long addr)
+{
+	void *tail_obj = tail ? : head;
 
-static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab,
+	__slab_free(s, slab, head, tail_obj, cnt, addr);
+}
+#endif /* CONFIG_SLUB_TINY */
+
+static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
 				      void *head, void *tail, void **p, int cnt,
 				      unsigned long addr)
 {
@@ -3817,18 +3907,13 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
-/* Note that interrupts must be enabled when calling this function. */
-int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
-			  void **p)
+#ifndef CONFIG_SLUB_TINY
+static inline int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
+			size_t size, void **p, struct obj_cgroup *objcg)
 {
 	struct kmem_cache_cpu *c;
 	int i;
-	struct obj_cgroup *objcg = NULL;
 
-	/* memcg and kmem_cache debug support */
-	s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
-	if (unlikely(!s))
-		return false;
 	/*
 	 * Drain objects in the per cpu slab, while disabling local
 	 * IRQs, which protects against PREEMPT and interrupts
@@ -3882,18 +3967,71 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	local_unlock_irq(&s->cpu_slab->lock);
 	slub_put_cpu_ptr(s->cpu_slab);
 
-	/*
-	 * memcg and kmem_cache debug support and memory initialization.
-	 * Done outside of the IRQ disabled fastpath loop.
-	 */
-	slab_post_alloc_hook(s, objcg, flags, size, p,
-			slab_want_init_on_alloc(flags, s), s->object_size);
 	return i;
+
 error:
 	slub_put_cpu_ptr(s->cpu_slab);
 	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
 	kmem_cache_free_bulk(s, i, p);
 	return 0;
+
+}
+#else /* CONFIG_SLUB_TINY */
+static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
+			size_t size, void **p, struct obj_cgroup *objcg)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		void *object = kfence_alloc(s, s->object_size, flags);
+
+		if (unlikely(object)) {
+			p[i] = object;
+			continue;
+		}
+
+		p[i] = __slab_alloc_node(s, flags, NUMA_NO_NODE,
+					 _RET_IP_, s->object_size);
+		if (unlikely(!p[i]))
+			goto error;
+
+		maybe_wipe_obj_freeptr(s, p[i]);
+	}
+
+	return i;
+
+error:
+	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
+	kmem_cache_free_bulk(s, i, p);
+	return 0;
+}
+#endif /* CONFIG_SLUB_TINY */
+
+/* Note that interrupts must be enabled when calling this function. */
+int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
+			  void **p)
+{
+	int i;
+	struct obj_cgroup *objcg = NULL;
+
+	if (!size)
+		return 0;
+
+	/* memcg and kmem_cache debug support */
+	s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
+	if (unlikely(!s))
+		return 0;
+
+	i = __kmem_cache_alloc_bulk(s, flags, size, p, objcg);
+
+	/*
+	 * memcg and kmem_cache debug support and memory initialization.
+	 * Done outside of the IRQ disabled fastpath loop.
+	 */
+	if (i != 0)
+		slab_post_alloc_hook(s, objcg, flags, size, p,
+			slab_want_init_on_alloc(flags, s), s->object_size);
+	return i;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
 
@@ -3918,7 +4056,8 @@ EXPORT_SYMBOL(kmem_cache_alloc_bulk);
  * take the list_lock.
  */
 static unsigned int slub_min_order;
-static unsigned int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static unsigned int slub_max_order =
+	IS_ENABLED(CONFIG_SLUB_TINY) ? 1 : PAGE_ALLOC_COSTLY_ORDER;
 static unsigned int slub_min_objects;
 
 /*
@@ -4049,6 +4188,7 @@ init_kmem_cache_node(struct kmem_cache_node *n)
 #endif
 }
 
+#ifndef CONFIG_SLUB_TINY
 static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 {
 	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
@@ -4069,6 +4209,12 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 
 	return 1;
 }
+#else
+static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
+{
+	return 1;
+}
+#endif /* CONFIG_SLUB_TINY */
 
 static struct kmem_cache *kmem_cache_node;
 
@@ -4131,7 +4277,9 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 void __kmem_cache_release(struct kmem_cache *s)
 {
 	cache_random_seq_destroy(s);
+#ifndef CONFIG_SLUB_TINY
 	free_percpu(s->cpu_slab);
+#endif
 	free_kmem_cache_nodes(s);
 }
 
@@ -4909,8 +5057,10 @@ void __init kmem_cache_init(void)
 
 void __init kmem_cache_init_late(void)
 {
+#ifndef CONFIG_SLUB_TINY
 	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!flushwq);
+#endif
 }
 
 struct kmem_cache *
@@ -4961,7 +5111,7 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
 	return 0;
 }
 
-#ifdef CONFIG_SYSFS
+#ifdef SLAB_SUPPORTS_SYSFS
 static int count_inuse(struct slab *slab)
 {
 	return slab->inuse;
@@ -5219,7 +5369,7 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 #endif  /* CONFIG_DEBUG_FS   */
 #endif	/* CONFIG_SLUB_DEBUG */
 
-#ifdef CONFIG_SYSFS
+#ifdef SLAB_SUPPORTS_SYSFS
 enum slab_stat_type {
 	SL_ALL,			/* All slabs */
 	SL_PARTIAL,		/* Only partially allocated slabs */
@@ -5539,11 +5689,13 @@ static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
 SLAB_ATTR_RO(cache_dma);
 #endif
 
+#ifdef CONFIG_HARDENED_USERCOPY
 static ssize_t usersize_show(struct kmem_cache *s, char *buf)
 {
 	return sysfs_emit(buf, "%u\n", s->usersize);
 }
 SLAB_ATTR_RO(usersize);
+#endif
 
 static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
 {
@@ -5854,7 +6006,9 @@ static struct attribute *slab_attrs[] = {
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,
 #endif
+#ifdef CONFIG_HARDENED_USERCOPY
 	&usersize_attr.attr,
+#endif
 #ifdef CONFIG_KFENCE
 	&skip_kfence_attr.attr,
 #endif
@@ -6101,7 +6255,7 @@ static int __init slab_sysfs_init(void)
 	return 0;
 }
 late_initcall(slab_sysfs_init);
-#endif /* CONFIG_SYSFS */
+#endif /* SLAB_SUPPORTS_SYSFS */
 
 #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
 static int slab_debugfs_show(struct seq_file *seq, void *v)