From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx> Install the callbacks via the state machine so we can phase out the cpu hotplug notifiers mess. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: linux-block@xxxxxxxxxxxxxxx Cc: rt@xxxxxxxxxxxxx Cc: Christoph Hellwing <hch@xxxxxx> Link: http://lkml.kernel.org/r/20160919212601.180033814@xxxxxxxxxxxxx Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> --- block/blk-mq.c | 87 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 43 insertions(+), 44 deletions(-) --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2090,50 +2090,18 @@ static void blk_mq_queue_reinit(struct r blk_mq_sysfs_register(q); } -static int blk_mq_queue_reinit_notify(struct notifier_block *nb, - unsigned long action, void *hcpu) +/* + * New online cpumask which is going to be set in this hotplug event. + * Declare this cpumasks as global as cpu-hotplug operation is invoked + * one-by-one and dynamically allocating this could result in a failure. + */ +static struct cpumask cpuhp_online_new; + +static void blk_mq_queue_reinit_work(void) { struct request_queue *q; - int cpu = (unsigned long)hcpu; - /* - * New online cpumask which is going to be set in this hotplug event. - * Declare this cpumasks as global as cpu-hotplug operation is invoked - * one-by-one and dynamically allocating this could result in a failure. - */ - static struct cpumask online_new; - - /* - * Before hotadded cpu starts handling requests, new mappings must - * be established. Otherwise, these requests in hw queue might - * never be dispatched. - * - * For example, there is a single hw queue (hctx) and two CPU queues - * (ctx0 for CPU0, and ctx1 for CPU1). - * - * Now CPU1 is just onlined and a request is inserted into - * ctx1->rq_list and set bit0 in pending bitmap as ctx1->index_hw is - * still zero. - * - * And then while running hw queue, flush_busy_ctxs() finds bit0 is - * set in pending bitmap and tries to retrieve requests in - * hctx->ctxs[0]->rq_list. But htx->ctxs[0] is a pointer to ctx0, - * so the request in ctx1->rq_list is ignored. - */ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DEAD: - case CPU_UP_CANCELED: - cpumask_copy(&online_new, cpu_online_mask); - break; - case CPU_UP_PREPARE: - cpumask_copy(&online_new, cpu_online_mask); - cpumask_set_cpu(cpu, &online_new); - break; - default: - return NOTIFY_OK; - } mutex_lock(&all_q_mutex); - /* * We need to freeze and reinit all existing queues. Freezing * involves synchronous wait for an RCU grace period and doing it @@ -2154,13 +2122,43 @@ static int blk_mq_queue_reinit_notify(st } list_for_each_entry(q, &all_q_list, all_q_node) - blk_mq_queue_reinit(q, &online_new); + blk_mq_queue_reinit(q, &cpuhp_online_new); list_for_each_entry(q, &all_q_list, all_q_node) blk_mq_unfreeze_queue(q); mutex_unlock(&all_q_mutex); - return NOTIFY_OK; +} + +static int blk_mq_queue_reinit_dead(unsigned int cpu) +{ + cpumask_clear_cpu(cpu, &cpuhp_online_new); + blk_mq_queue_reinit_work(); + return 0; +} + +/* + * Before hotadded cpu starts handling requests, new mappings must be + * established. Otherwise, these requests in hw queue might never be + * dispatched. + * + * For example, there is a single hw queue (hctx) and two CPU queues (ctx0 + * for CPU0, and ctx1 for CPU1). + * + * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list + * and set bit0 in pending bitmap as ctx1->index_hw is still zero. + * + * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in + * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list. + * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list + * is ignored. + */ +static int blk_mq_queue_reinit_prepare(unsigned int cpu) +{ + cpumask_copy(&cpuhp_online_new, cpu_online_mask); + cpumask_set_cpu(cpu, &cpuhp_online_new); + blk_mq_queue_reinit_work(); + return 0; } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) @@ -2382,8 +2380,9 @@ static int __init blk_mq_init(void) cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); - hotcpu_notifier(blk_mq_queue_reinit_notify, 0); - + cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare", + blk_mq_queue_reinit_prepare, + blk_mq_queue_reinit_dead); return 0; } subsys_initcall(blk_mq_init); -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
