From 7bed45954b95601230ebf387d3e4e20e4a3cc025 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 18 Jan 2018 00:41:51 +0800 Subject: [PATCH] blk-mq: make sure hctx->next_cpu is set correctly When hctx->next_cpu is set from possible online CPUs, there is one race in which hctx->next_cpu may be set as >= nr_cpu_ids, and finally break workqueue. The race can be triggered in the following two sitations: 1) when one CPU is becoming DEAD, blk_mq_hctx_notify_dead() is called to dispatch requests from the DEAD cpu context, but at that time, this DEAD CPU has been cleared from 'cpu_online_mask', so all CPUs in hctx->cpumask may become offline, and cause hctx->next_cpu set a bad value. 2) blk_mq_delay_run_hw_queue() is called from CPU B, and found the queue should be run on the other CPU A, then CPU A may become offline at the same time and all CPUs in hctx->cpumask become offline. This patch deals with this issue by re-selecting next CPU, and making sure it is set correctly. Cc: Christian Borntraeger Cc: Stefan Haberland Cc: Christoph Hellwig Cc: Thomas Gleixner Reported-by: "jianchao.wang" Tested-by: "jianchao.wang" Fixes: 20e4d81393 ("blk-mq: simplify queue mapping & schedule with each possisble CPU") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index c8f62e6be6b6..3bd41f1066ee 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1319,21 +1319,47 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { + bool tried = false; + if (hctx->queue->nr_hw_queues == 1) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { int next_cpu; - +select_cpu: next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = cpumask_first_and(hctx->cpumask,cpu_online_mask); - hctx->next_cpu = next_cpu; + /* + * No online CPU is found, so have to make sure hctx->next_cpu + * is set correctly for not breaking workqueue. + */ + if (next_cpu >= nr_cpu_ids) + hctx->next_cpu = cpumask_first(hctx->cpumask); + else + hctx->next_cpu = next_cpu; hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } + /* + * Do unbound schedule if we can't find a online CPU for this hctx, + * and it should only happen in the path of handling CPU DEAD. + */ + if (!cpu_online(hctx->next_cpu)) { + if (!tried) { + tried = true; + goto select_cpu; + } + + /* + * Make sure to re-select CPU next time once after CPUs + * in hctx->cpumask become online again. + */ + hctx->next_cpu_batch = 1; + return WORK_CPU_UNBOUND; + } return hctx->next_cpu; } -- GitLab