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 one cpuhp state handled after the CPU is down, so there isn't any chance to quiesce hctx for blk-mq wrt. CPU hotplug. Add new cpuhp state of CPUHP_AP_BLK_MQ_ONLINE for blk-mq to stop queues and wait for completion of in-flight requests. [1] https://lore.kernel.org/linux-block/[email protected]/ Cc: Bart Van Assche <[email protected]> Cc: Hannes Reinecke <[email protected]> Cc: Christoph Hellwig <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Keith Busch <[email protected]> Signed-off-by: Ming Lei <[email protected]> --- block/blk-mq-tag.c | 2 +- block/blk-mq-tag.h | 2 ++ block/blk-mq.c | 65 ++++++++++++++++++++++++++++++++++++++ include/linux/blk-mq.h | 1 + include/linux/cpuhotplug.h | 1 + 5 files changed, 70 insertions(+), 1 deletion(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 008388e82b5c..31828b82552b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -325,7 +325,7 @@ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. */ -static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, +void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv) { if (tags->nr_reserved_tags) diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 61deab0b5a5a..321fd6f440e6 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -35,6 +35,8 @@ extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv); +void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, + busy_tag_iter_fn *fn, void *priv); static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, struct blk_mq_hw_ctx *hctx) diff --git a/block/blk-mq.c b/block/blk-mq.c index ec791156e9cc..d991c122abf2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2225,6 +2225,61 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, return -ENOMEM; } +static bool blk_mq_count_inflight_rq(struct request *rq, void *data, + bool reserved) +{ + unsigned *count = data; + + if ((blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)) + (*count)++; + + return true; +} + +static unsigned blk_mq_tags_inflight_rqs(struct blk_mq_tags *tags) +{ + unsigned count = 0; + + blk_mq_all_tag_busy_iter(tags, blk_mq_count_inflight_rq, &count); + + return count; +} + +static void blk_mq_drain_inflight_rqs(struct blk_mq_hw_ctx *hctx) +{ + while (1) { + if (!blk_mq_tags_inflight_rqs(hctx->tags)) + break; + msleep(5); + } +} + +static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) +{ + struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, + struct blk_mq_hw_ctx, cpuhp_online); + unsigned prev_cpu = -1; + + while (true) { + unsigned next_cpu = cpumask_next_and(prev_cpu, hctx->cpumask, + cpu_online_mask); + + if (next_cpu >= nr_cpu_ids) + break; + + /* return if there is other online CPU on this hctx */ + if (next_cpu != cpu) + return 0; + + prev_cpu = next_cpu; + } + + set_bit(BLK_MQ_S_INTERNAL_STOPPED, &hctx->state); + blk_mq_drain_inflight_rqs(hctx); + + return 0; +} + /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it @@ -2241,6 +2296,8 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; + clear_bit(BLK_MQ_S_INTERNAL_STOPPED, &hctx->state); + spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); @@ -2261,6 +2318,9 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { + if (!(hctx->flags & BLK_MQ_F_NO_MANAGED_IRQ)) + cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } @@ -2320,6 +2380,9 @@ static int blk_mq_init_hctx(struct request_queue *q, { hctx->queue_num = hctx_idx; + if (!(hctx->flags & BLK_MQ_F_NO_MANAGED_IRQ)) + cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; @@ -3547,6 +3610,8 @@ static int __init blk_mq_init(void) { cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); + cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", + NULL, blk_mq_hctx_notify_online); return 0; } subsys_initcall(blk_mq_init); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ee60885ec855..a345f2cf920d 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -58,6 +58,7 @@ struct blk_mq_hw_ctx { atomic_t nr_active; + struct hlist_node cpuhp_online; struct hlist_node cpuhp_dead; struct kobject kobj; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..bb80f52040cb 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -147,6 +147,7 @@ enum cpuhp_state { CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, + CPUHP_AP_BLK_MQ_ONLINE, CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, CPUHP_AP_X86_INTEL_EPB_ONLINE, CPUHP_AP_PERF_ONLINE, -- 2.20.1
