Rework blk_mq_init_hctx() function so all memory allocations are done before data initialization and callbacks invocation. As result, the latter is avoided in tight memory conditions. CC: linux-block@xxxxxxxxxxxxxxx Signed-off-by: Alexander Gordeev <agordeev@xxxxxxxxxx> --- block/blk-mq.c | 50 ++++++++++++++++++++++++-------------------------- 1 file changed, 24 insertions(+), 26 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index af6d049..5ecbb5f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1714,6 +1714,22 @@ static struct blk_mq_hw_ctx *blk_mq_init_hctx(struct request_queue *q, if (!zalloc_cpumask_var_node(&hctx->cpumask, GFP_KERNEL, node)) goto free_hctx; + /* + * Allocate space for all possible cpus to avoid allocation at + * runtime + */ + hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *), + GFP_KERNEL, node); + if (!hctx->ctxs) + goto free_cpumask; + + if (blk_mq_alloc_bitmap(&hctx->ctx_map, node)) + goto free_ctxs; + + hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size); + if (!hctx->fq) + goto free_bitmap; + INIT_WORK(&hctx->run_work, blk_mq_run_work_fn); INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn); spin_lock_init(&hctx->lock); @@ -1722,55 +1738,37 @@ static struct blk_mq_hw_ctx *blk_mq_init_hctx(struct request_queue *q, hctx->numa_node = node; hctx->queue = q; hctx->queue_num = hctx_idx; + hctx->nr_ctx = 0; hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; + hctx->tags = set->tags[hctx_idx]; blk_mq_init_cpu_notifier(&hctx->cpu_notifier, blk_mq_hctx_notify, hctx); blk_mq_register_cpu_notifier(&hctx->cpu_notifier); - hctx->tags = set->tags[hctx_idx]; - - /* - * Allocate space for all possible cpus to avoid allocation at - * runtime - */ - hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *), - GFP_KERNEL, node); - if (!hctx->ctxs) - goto unregister_cpu_notifier; - - if (blk_mq_alloc_bitmap(&hctx->ctx_map, node)) - goto free_ctxs; - - hctx->nr_ctx = 0; - if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) - goto free_bitmap; - - hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size); - if (!hctx->fq) - goto exit_hctx; + goto unregister_cpu_notifier; if (set->ops->init_request && set->ops->init_request(set->driver_data, hctx->fq->flush_rq, hctx_idx, flush_start_tag + hctx_idx, node)) - goto free_fq; + goto exit_hctx; return hctx; - free_fq: - kfree(hctx->fq); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); + unregister_cpu_notifier: + blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier); + kfree(hctx->fq); free_bitmap: blk_mq_free_bitmap(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); - unregister_cpu_notifier: - blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier); + free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); -- 1.8.3.1 -- 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