slab: decouple pointer to barn from kmem_cache_node

The pointer to barn currently exists in struct kmem_cache_node. That
struct is instantiated for every NUMA node with memory, but we want to
have a barn for every online node (including memoryless).

Thus decouple the two structures. In struct kmem_cache we have an array
for kmem_cache_node pointers that appears to be sized MAX_NUMNODES but
the actual size calculation in kmem_cache_init() uses nr_node_ids.
Therefore we can't just add another array of barn pointers. Instead
change the array to newly introduced struct kmem_cache_per_node_ptrs
holding both kmem_cache_node and barn pointer.

Adjust barn accessor and allocation/initialization code accordingly. For
now no functional change intended, barns are created 1:1 together with
kmem_cache_nodes.

Link: https://patch.msgid.link/20260311-b4-slab-memoryless-barns-v1-1-70ab850be4ce@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>

mm/slab.h

@@ -191,6 +191,11 @@ struct kmem_cache_order_objects {
 	unsigned int x;
 };
 
+struct kmem_cache_per_node_ptrs {
+	struct node_barn *barn;
+	struct kmem_cache_node *node;
+};
+
 /*
  * Slab cache management.
  */
@@ -247,7 +252,7 @@ struct kmem_cache {
 	struct kmem_cache_stats __percpu *cpu_stats;
 #endif
 
-	struct kmem_cache_node *node[MAX_NUMNODES];
+	struct kmem_cache_per_node_ptrs per_node[MAX_NUMNODES];
 };
 
 /*

mm/slub.c

@@ -59,7 +59,7 @@
  *   0.  cpu_hotplug_lock
  *   1.  slab_mutex (Global Mutex)
  *   2a. kmem_cache->cpu_sheaves->lock (Local trylock)
- *   2b. node->barn->lock (Spinlock)
+ *   2b. barn->lock (Spinlock)
  *   2c. node->list_lock (Spinlock)
  *   3.  slab_lock(slab) (Only on some arches)
  *   4.  object_map_lock (Only for debugging)
@@ -136,7 +136,7 @@
  *   or spare sheaf can handle the allocation or free, there is no other
  *   overhead.
  *
- *   node->barn->lock (spinlock)
+ *   barn->lock (spinlock)
  *
  *   This lock protects the operations on per-NUMA-node barn. It can quickly
  *   serve an empty or full sheaf if available, and avoid more expensive refill
@@ -436,26 +436,24 @@ struct kmem_cache_node {
 	atomic_long_t total_objects;
 	struct list_head full;
 #endif
-	struct node_barn *barn;
 };
 
 static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 {
-	return s->node[node];
+	return s->per_node[node].node;
+}
+
+static inline struct node_barn *get_barn_node(struct kmem_cache *s, int node)
+{
+	return s->per_node[node].barn;
 }
 
 /*
- * Get the barn of the current cpu's closest memory node. It may not exist on
+ * Get the barn of the current cpu's NUMA node. It may be a memoryless node.
- * systems with memoryless nodes but without CONFIG_HAVE_MEMORYLESS_NODES
  */
 static inline struct node_barn *get_barn(struct kmem_cache *s)
 {
-	struct kmem_cache_node *n = get_node(s, numa_mem_id());
+	return get_barn_node(s, numa_mem_id());
-
-	if (!n)
-		return NULL;
-
-	return n->barn;
 }
 
 /*
@@ -5771,7 +5769,6 @@ bool free_to_pcs(struct kmem_cache *s, void *object, bool allow_spin)
 
 static void rcu_free_sheaf(struct rcu_head *head)
 {
-	struct kmem_cache_node *n;
 	struct slab_sheaf *sheaf;
 	struct node_barn *barn = NULL;
 	struct kmem_cache *s;
@@ -5794,12 +5791,10 @@ static void rcu_free_sheaf(struct rcu_head *head)
 	if (__rcu_free_sheaf_prepare(s, sheaf))
 		goto flush;
 
-	n = get_node(s, sheaf->node);
+	barn = get_barn_node(s, sheaf->node);
-	if (!n)
+	if (!barn)
 		goto flush;
 
-	barn = n->barn;
-
 	/* due to slab_free_hook() */
 	if (unlikely(sheaf->size == 0))
 		goto empty;
@@ -7410,7 +7405,7 @@ static inline int calculate_order(unsigned int size)
 }
 
 static void
-init_kmem_cache_node(struct kmem_cache_node *n, struct node_barn *barn)
+init_kmem_cache_node(struct kmem_cache_node *n)
 {
 	n->nr_partial = 0;
 	spin_lock_init(&n->list_lock);
@@ -7420,9 +7415,6 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct node_barn *barn)
 	atomic_long_set(&n->total_objects, 0);
 	INIT_LIST_HEAD(&n->full);
 #endif
-	n->barn = barn;
-	if (barn)
-		barn_init(barn);
 }
 
 #ifdef CONFIG_SLUB_STATS
@@ -7517,8 +7509,8 @@ static void early_kmem_cache_node_alloc(int node)
 	n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false);
 	slab->freelist = get_freepointer(kmem_cache_node, n);
 	slab->inuse = 1;
-	kmem_cache_node->node[node] = n;
+	kmem_cache_node->per_node[node].node = n;
-	init_kmem_cache_node(n, NULL);
+	init_kmem_cache_node(n);
 	inc_slabs_node(kmem_cache_node, node, slab->objects);
 
 	/*
@@ -7533,15 +7525,20 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 	int node;
 	struct kmem_cache_node *n;
 
-	for_each_kmem_cache_node(s, node, n) {
+	for_each_node(node) {
-		if (n->barn) {
+		struct node_barn *barn = get_barn_node(s, node);
-			WARN_ON(n->barn->nr_full);
-			WARN_ON(n->barn->nr_empty);
-			kfree(n->barn);
-			n->barn = NULL;
-		}
 
-		s->node[node] = NULL;
+		if (!barn)
+			continue;
+
+		WARN_ON(barn->nr_full);
+		WARN_ON(barn->nr_empty);
+		kfree(barn);
+		s->per_node[node].barn = NULL;
+	}
+
+	for_each_kmem_cache_node(s, node, n) {
+		s->per_node[node].node = NULL;
 		kmem_cache_free(kmem_cache_node, n);
 	}
 }
@@ -7562,31 +7559,36 @@ static int init_kmem_cache_nodes(struct kmem_cache *s)
 
 	for_each_node_mask(node, slab_nodes) {
 		struct kmem_cache_node *n;
-		struct node_barn *barn = NULL;
 
 		if (slab_state == DOWN) {
 			early_kmem_cache_node_alloc(node);
 			continue;
 		}
 
-		if (cache_has_sheaves(s)) {
-			barn = kmalloc_node(sizeof(*barn), GFP_KERNEL, node);
-
-			if (!barn)
-				return 0;
-		}
-
 		n = kmem_cache_alloc_node(kmem_cache_node,
 						GFP_KERNEL, node);
-		if (!n) {
+		if (!n)
-			kfree(barn);
 			return 0;
-		}
 
-		init_kmem_cache_node(n, barn);
+		init_kmem_cache_node(n);
-
+		s->per_node[node].node = n;
-		s->node[node] = n;
 	}
+
+	if (slab_state == DOWN || !cache_has_sheaves(s))
+		return 1;
+
+	for_each_node_mask(node, slab_nodes) {
+		struct node_barn *barn;
+
+		barn = kmalloc_node(sizeof(*barn), GFP_KERNEL, node);
+
+		if (!barn)
+			return 0;
+
+		barn_init(barn);
+		s->per_node[node].barn = barn;
+	}
+
 	return 1;
 }
 
@@ -7875,10 +7877,15 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 	if (cache_has_sheaves(s))
 		rcu_barrier();
 
+	for_each_node(node) {
+		struct node_barn *barn = get_barn_node(s, node);
+
+		if (barn)
+			barn_shrink(s, barn);
+	}
+
 	/* Attempt to free all objects */
 	for_each_kmem_cache_node(s, node, n) {
-		if (n->barn)
-			barn_shrink(s, n->barn);
 		free_partial(s, n);
 		if (n->nr_partial || node_nr_slabs(n))
 			return 1;
@@ -8088,14 +8095,18 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s)
 	unsigned long flags;
 	int ret = 0;
 
+	for_each_node(node) {
+		struct node_barn *barn = get_barn_node(s, node);
+
+		if (barn)
+			barn_shrink(s, barn);
+	}
+
 	for_each_kmem_cache_node(s, node, n) {
 		INIT_LIST_HEAD(&discard);
 		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
 			INIT_LIST_HEAD(promote + i);
 
-		if (n->barn)
-			barn_shrink(s, n->barn);
-
 		spin_lock_irqsave(&n->list_lock, flags);
 
 		/*
@@ -8184,7 +8195,8 @@ static int slab_mem_going_online_callback(int nid)
 		if (get_node(s, nid))
 			continue;
 
-		if (cache_has_sheaves(s)) {
+		if (cache_has_sheaves(s) && !get_barn_node(s, nid)) {
+
 			barn = kmalloc_node(sizeof(*barn), GFP_KERNEL, nid);
 
 			if (!barn) {
@@ -8205,13 +8217,17 @@ static int slab_mem_going_online_callback(int nid)
 			goto out;
 		}
 
-		init_kmem_cache_node(n, barn);
+		init_kmem_cache_node(n);
+		s->per_node[nid].node = n;
 
-		s->node[nid] = n;
+		if (barn) {
+			barn_init(barn);
+			s->per_node[nid].barn = barn;
+		}
 	}
 	/*
 	 * Any cache created after this point will also have kmem_cache_node
-	 * initialized for the new node.
+	 * and barn initialized for the new node.
 	 */
 	node_set(nid, slab_nodes);
 out:
@@ -8303,7 +8319,7 @@ static void __init bootstrap_cache_sheaves(struct kmem_cache *s)
 		}
 
 		barn_init(barn);
-		get_node(s, node)->barn = barn;
+		s->per_node[node].barn = barn;
 	}
 
 	for_each_possible_cpu(cpu) {
@@ -8374,8 +8390,8 @@ void __init kmem_cache_init(void)
 	slab_state = PARTIAL;
 
 	create_boot_cache(kmem_cache, "kmem_cache",
-			offsetof(struct kmem_cache, node) +
+			offsetof(struct kmem_cache, per_node) +
-				nr_node_ids * sizeof(struct kmem_cache_node *),
+				nr_node_ids * sizeof(struct kmem_cache_per_node_ptrs),
 			SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0);
 
 	kmem_cache = bootstrap(&boot_kmem_cache);