From bf0beec0607db3c6f6fb7bd2c6d503792b05cf3f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 29 May 2020 15:53:15 +0200 Subject: blk-mq: drain I/O when all CPUs in a hctx are offline Most of blk-mq drivers depend on managed IRQ's auto-affinity to setup up queue mapping. Thomas mentioned the following point[1]: "That was the constraint of managed interrupts from the very beginning: The driver/subsystem has to quiesce the interrupt line and the associated queue _before_ it gets shutdown in CPU unplug and not fiddle with it until it's restarted by the core when the CPU is plugged in again." However, current blk-mq implementation doesn't quiesce hw queue before the last CPU in the hctx is shutdown. Even worse, CPUHP_BLK_MQ_DEAD is a cpuhp state handled after the CPU is down, so there isn't any chance to quiesce the hctx before shutting down the CPU. Add new CPUHP_AP_BLK_MQ_ONLINE state to stop allocating from blk-mq hctxs where the last CPU goes away, and wait for completion of in-flight requests. This guarantees that there is no inflight I/O before shutting down the managed IRQ. Add a BLK_MQ_F_STACKING and set it for dm-rq and loop, so we don't need to wait for completion of in-flight requests from these drivers to avoid a potential dead-lock. It is safe to do this for stacking drivers as those do not use interrupts at all and their I/O completions are triggered by underlying devices I/O completion. [1] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [hch: different retry mechanism, merged two patches, minor cleanups] Signed-off-by: Ming Lei Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/blk-mq.h') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 856bb10993cf..d6fcae17da5a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -140,6 +140,8 @@ struct blk_mq_hw_ctx { */ atomic_t nr_active; + /** @cpuhp_online: List to store request if CPU is going to die */ + struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ @@ -391,6 +393,11 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, + /* + * Set when this device requires underlying blk-mq device for + * completing IO: + */ + BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, @@ -400,6 +407,9 @@ enum { BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE = 3, + BLK_MQ_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, -- cgit v1.2.3