1 files changed, 80 insertions, 92 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 261474092e43..74d92aa4a3a2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1788,8 +1788,8 @@ static void *setup_object(struct kmem_cache *s, struct slab *slab,
 /*
  * Slab allocation and freeing
  */
-static inline struct slab *alloc_slab_page(struct kmem_cache *s,
-		gfp_t flags, int node, struct kmem_cache_order_objects oo)
+static inline struct slab *alloc_slab_page(gfp_t flags, int node,
+		struct kmem_cache_order_objects oo)
 {
 	struct folio *folio;
 	struct slab *slab;
@@ -1941,7 +1941,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
 		alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL);
 
-	slab = alloc_slab_page(s, alloc_gfp, node, oo);
+	slab = alloc_slab_page(alloc_gfp, node, oo);
 	if (unlikely(!slab)) {
 		oo = s->min;
 		alloc_gfp = flags;
@@ -1949,7 +1949,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 		 * Allocation may have failed due to fragmentation.
 		 * Try a lower order alloc if possible
 		 */
-		slab = alloc_slab_page(s, alloc_gfp, node, oo);
+		slab = alloc_slab_page(alloc_gfp, node, oo);
 		if (unlikely(!slab))
 			goto out;
 		stat(s, ORDER_FALLBACK);
@@ -2348,10 +2348,10 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
 static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 			    void *freelist)
 {
-	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
+	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE, M_FULL_NOLIST };
 	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
-	int lock = 0, free_delta = 0;
-	enum slab_modes l = M_NONE, m = M_NONE;
+	int free_delta = 0;
+	enum slab_modes mode = M_NONE;
 	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
 	unsigned long flags = 0;
@@ -2393,14 +2393,10 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 	 * Ensure that the slab is unfrozen while the list presence
 	 * reflects the actual number of objects during unfreeze.
 	 *
-	 * We setup the list membership and then perform a cmpxchg
-	 * with the count. If there is a mismatch then the slab
-	 * is not unfrozen but the slab is on the wrong list.
-	 *
-	 * Then we restart the process which may have to remove
-	 * the slab from the list that we just put it on again
-	 * because the number of objects in the slab may have
-	 * changed.
+	 * We first perform cmpxchg holding lock and insert to list
+	 * when it succeed. If there is mismatch then the slab is not
+	 * unfrozen and number of objects in the slab may have changed.
+	 * Then release lock and retry cmpxchg again.
 	 */
 redo:
 
@@ -2419,61 +2415,52 @@ redo:
 
 	new.frozen = 0;
 
-	if (!new.inuse && n->nr_partial >= s->min_partial)
-		m = M_FREE;
-	else if (new.freelist) {
-		m = M_PARTIAL;
-		if (!lock) {
-			lock = 1;
-			/*
-			 * Taking the spinlock removes the possibility that
-			 * acquire_slab() will see a slab that is frozen
-			 */
-			spin_lock_irqsave(&n->list_lock, flags);
-		}
+	if (!new.inuse && n->nr_partial >= s->min_partial) {
+		mode = M_FREE;
+	} else if (new.freelist) {
+		mode = M_PARTIAL;
+		/*
+		 * Taking the spinlock removes the possibility that
+		 * acquire_slab() will see a slab that is frozen
+		 */
+		spin_lock_irqsave(&n->list_lock, flags);
+	} else if (kmem_cache_debug_flags(s, SLAB_STORE_USER)) {
+		mode = M_FULL;
+		/*
+		 * This also ensures that the scanning of full
+		 * slabs from diagnostic functions will not see
+		 * any frozen slabs.
+		 */
+		spin_lock_irqsave(&n->list_lock, flags);
 	} else {
-		m = M_FULL;
-		if (kmem_cache_debug_flags(s, SLAB_STORE_USER) && !lock) {
-			lock = 1;
-			/*
-			 * This also ensures that the scanning of full
-			 * slabs from diagnostic functions will not see
-			 * any frozen slabs.
-			 */
-			spin_lock_irqsave(&n->list_lock, flags);
-		}
+		mode = M_FULL_NOLIST;
 	}
 
-	if (l != m) {
-		if (l == M_PARTIAL)
-			remove_partial(n, slab);
-		else if (l == M_FULL)
-			remove_full(s, n, slab);
-
-		if (m == M_PARTIAL)
-			add_partial(n, slab, tail);
-		else if (m == M_FULL)
-			add_full(s, n, slab);
-	}
 
-	l = m;
 	if (!cmpxchg_double_slab(s, slab,
 				old.freelist, old.counters,
 				new.freelist, new.counters,
-				"unfreezing slab"))
+				"unfreezing slab")) {
+		if (mode == M_PARTIAL || mode == M_FULL)
+			spin_unlock_irqrestore(&n->list_lock, flags);
 		goto redo;
+	}
 
-	if (lock)
-		spin_unlock_irqrestore(&n->list_lock, flags);
 
-	if (m == M_PARTIAL)
+	if (mode == M_PARTIAL) {
+		add_partial(n, slab, tail);
+		spin_unlock_irqrestore(&n->list_lock, flags);
 		stat(s, tail);
-	else if (m == M_FULL)
-		stat(s, DEACTIVATE_FULL);
-	else if (m == M_FREE) {
+	} else if (mode == M_FREE) {
 		stat(s, DEACTIVATE_EMPTY);
 		discard_slab(s, slab);
 		stat(s, FREE_SLAB);
+	} else if (mode == M_FULL) {
+		add_full(s, n, slab);
+		spin_unlock_irqrestore(&n->list_lock, flags);
+		stat(s, DEACTIVATE_FULL);
+	} else if (mode == M_FULL_NOLIST) {
+		stat(s, DEACTIVATE_FULL);
 	}
 }
 
@@ -3131,7 +3118,7 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
  *
  * Otherwise we can simply pick the next object from the lockless free list.
  */
-static __always_inline void *slab_alloc_node(struct kmem_cache *s,
+static __always_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;
@@ -3141,7 +3128,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 	struct obj_cgroup *objcg = NULL;
 	bool init = false;
 
-	s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
+	s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
 	if (!s)
 		return NULL;
 
@@ -3232,27 +3219,41 @@ out:
 	return object;
 }
 
-static __always_inline void *slab_alloc(struct kmem_cache *s,
+static __always_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, gfpflags, NUMA_NO_NODE, addr, orig_size);
+	return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
 }
 
-void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
+static __always_inline
+void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
+			     gfp_t gfpflags)
 {
-	void *ret = slab_alloc(s, gfpflags, _RET_IP_, s->object_size);
+	void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
 
 	trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size,
 				s->size, gfpflags);
 
 	return ret;
 }
+
+void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
+{
+	return __kmem_cache_alloc_lru(s, NULL, gfpflags);
+}
 EXPORT_SYMBOL(kmem_cache_alloc);
 
+void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
+			   gfp_t gfpflags)
+{
+	return __kmem_cache_alloc_lru(s, lru, gfpflags);
+}
+EXPORT_SYMBOL(kmem_cache_alloc_lru);
+
 #ifdef CONFIG_TRACING
 void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
-	void *ret = slab_alloc(s, gfpflags, _RET_IP_, size);
+	void *ret = slab_alloc(s, NULL, gfpflags, _RET_IP_, size);
 	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
 	ret = kasan_kmalloc(s, ret, size, gfpflags);
 	return ret;
@@ -3263,7 +3264,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace);
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, s->object_size);
+	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
 
 	trace_kmem_cache_alloc_node(_RET_IP_, ret,
 				    s->object_size, s->size, gfpflags, node);
@@ -3277,7 +3278,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 				    gfp_t gfpflags,
 				    int node, size_t size)
 {
-	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, size);
+	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size);
 
 	trace_kmalloc_node(_RET_IP_, ret,
 			   size, s->size, gfpflags, node);
@@ -3667,7 +3668,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	struct obj_cgroup *objcg = NULL;
 
 	/* memcg and kmem_cache debug support */
-	s = slab_pre_alloc_hook(s, &objcg, size, flags);
+	s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
 	if (unlikely(!s))
 		return false;
 	/*
@@ -4000,15 +4001,6 @@ static int init_kmem_cache_nodes(struct kmem_cache *s)
 	return 1;
 }
 
-static void set_min_partial(struct kmem_cache *s, unsigned long min)
-{
-	if (min < MIN_PARTIAL)
-		min = MIN_PARTIAL;
-	else if (min > MAX_PARTIAL)
-		min = MAX_PARTIAL;
-	s->min_partial = min;
-}
-
 static void set_cpu_partial(struct kmem_cache *s)
 {
 #ifdef CONFIG_SLUB_CPU_PARTIAL
@@ -4046,7 +4038,7 @@ static void set_cpu_partial(struct kmem_cache *s)
  * calculate_sizes() determines the order and the distribution of data within
  * a slab object.
  */
-static int calculate_sizes(struct kmem_cache *s, int forced_order)
+static int calculate_sizes(struct kmem_cache *s)
 {
 	slab_flags_t flags = s->flags;
 	unsigned int size = s->object_size;
@@ -4150,10 +4142,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	size = ALIGN(size, s->align);
 	s->size = size;
 	s->reciprocal_size = reciprocal_value(size);
-	if (forced_order >= 0)
-		order = forced_order;
-	else
-		order = calculate_order(size);
+	order = calculate_order(size);
 
 	if ((int)order < 0)
 		return 0;
@@ -4189,7 +4178,7 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 	s->random = get_random_long();
 #endif
 
-	if (!calculate_sizes(s, -1))
+	if (!calculate_sizes(s))
 		goto error;
 	if (disable_higher_order_debug) {
 		/*
@@ -4199,7 +4188,7 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 		if (get_order(s->size) > get_order(s->object_size)) {
 			s->flags &= ~DEBUG_METADATA_FLAGS;
 			s->offset = 0;
-			if (!calculate_sizes(s, -1))
+			if (!calculate_sizes(s))
 				goto error;
 		}
 	}
@@ -4215,7 +4204,8 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 	 * The larger the object size is, the more slabs we want on the partial
 	 * list to avoid pounding the page allocator excessively.
 	 */
-	set_min_partial(s, ilog2(s->size) / 2);
+	s->min_partial = min_t(unsigned long, MAX_PARTIAL, ilog2(s->size) / 2);
+	s->min_partial = max_t(unsigned long, MIN_PARTIAL, s->min_partial);
 
 	set_cpu_partial(s);
 
@@ -4417,7 +4407,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, flags, _RET_IP_, size);
+	ret = slab_alloc(s, NULL, flags, _RET_IP_, size);
 
 	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
 
@@ -4465,7 +4455,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc_node(s, flags, node, _RET_IP_, size);
+	ret = slab_alloc_node(s, NULL, flags, node, _RET_IP_, size);
 
 	trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
 
@@ -4923,7 +4913,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc(s, gfpflags, caller, size);
+	ret = slab_alloc(s, NULL, gfpflags, caller, size);
 
 	/* Honor the call site pointer we received. */
 	trace_kmalloc(caller, ret, size, s->size, gfpflags);
@@ -4954,7 +4944,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	ret = slab_alloc_node(s, gfpflags, node, caller, size);
+	ret = slab_alloc_node(s, NULL, gfpflags, node, caller, size);
 
 	/* Honor the call site pointer we received. */
 	trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
@@ -5344,12 +5334,10 @@ struct slab_attribute {
 };
 
 #define SLAB_ATTR_RO(_name) \
-	static struct slab_attribute _name##_attr = \
-	__ATTR(_name, 0400, _name##_show, NULL)
+	static struct slab_attribute _name##_attr = __ATTR_RO_MODE(_name, 0400)
 
 #define SLAB_ATTR(_name) \
-	static struct slab_attribute _name##_attr =  \
-	__ATTR(_name, 0600, _name##_show, _name##_store)
+	static struct slab_attribute _name##_attr = __ATTR_RW_MODE(_name, 0600)
 
 static ssize_t slab_size_show(struct kmem_cache *s, char *buf)
 {
@@ -5396,7 +5384,7 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
 	if (err)
 		return err;
 
-	set_min_partial(s, min);
+	s->min_partial = min;
 	return length;
 }
 SLAB_ATTR(min_partial);