mm/zswap: Convert pool to hotplug state machine

Install the callbacks via the state machine. Multi state is used to address the
per-pool notifier. Uppon adding of the intance the callback is invoked for all
online CPUs so the manual init can go.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-mm@kvack.org
Cc: Seth Jennings <sjenning@redhat.com>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-13-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/cpuhotplug.h

@@ -66,6 +66,7 @@ enum cpuhp_state {
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
+	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,

mm/zswap.c

@@ -118,7 +118,7 @@ struct zswap_pool {
 	struct kref kref;
 	struct list_head list;
 	struct work_struct work;
-	struct notifier_block notifier;
+	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
@@ -376,77 +376,34 @@ static int zswap_dstmem_dead(unsigned int cpu)
 	return 0;
 }
 
-static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
-				     unsigned long action, unsigned long cpu)
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_comp *tfm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
 	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-			break;
+		return 0;
+
 	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
 	if (IS_ERR_OR_NULL(tfm)) {
 		pr_err("could not alloc crypto comp %s : %ld\n",
 		       pool->tfm_name, PTR_ERR(tfm));
-			return NOTIFY_BAD;
+		return -ENOMEM;
 	}
 	*per_cpu_ptr(pool->tfm, cpu) = tfm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
+	return 0;
+}
+
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+	struct crypto_comp *tfm;
+
 	tfm = *per_cpu_ptr(pool->tfm, cpu);
 	if (!IS_ERR_OR_NULL(tfm))
 		crypto_free_comp(tfm);
 	*per_cpu_ptr(pool->tfm, cpu) = NULL;
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_comp_notifier(struct notifier_block *nb,
-				   unsigned long action, void *pcpu)
-{
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
-
-	return __zswap_cpu_comp_notifier(pool, action, cpu);
-}
-
-static int zswap_cpu_comp_init(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	memset(&pool->notifier, 0, sizeof(pool->notifier));
-	pool->notifier.notifier_call = zswap_cpu_comp_notifier;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
-}
-
-static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
 }
 
 /*********************************
@@ -527,6 +484,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	int ret;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
@@ -551,7 +509,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
-	if (zswap_cpu_comp_init(pool))
+	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
+				       &pool->node);
+	if (ret)
 		goto error;
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
@@ -605,7 +565,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 {
 	zswap_pool_debug("destroying", pool);
 
-	zswap_cpu_comp_destroy(pool);
+	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->tfm);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -1212,6 +1172,13 @@ static int __init init_zswap(void)
 		goto dstmem_fail;
 	}
 
+	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
+				      "mm/zswap_pool:prepare",
+				      zswap_cpu_comp_prepare,
+				      zswap_cpu_comp_dead);
+	if (ret)
+		goto hp_fail;
+
 	pool = __zswap_pool_create_fallback();
 	if (!pool) {
 		pr_err("pool creation failed\n");
@@ -1228,6 +1195,8 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
+	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
+hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();