On 8/12/19 3:43 PM, Ming Lei wrote: > 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/alpine.DEB.2.21.1904051331270.1802@xxxxxxxxxxxxxxxxxxxxxxx/ > > Cc: Bart Van Assche <bvanassche@xxxxxxx> > Cc: Hannes Reinecke <hare@xxxxxxxx> > Cc: Christoph Hellwig <hch@xxxxxx> > Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> > Cc: Keith Busch <keith.busch@xxxxxxxxx> > Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx> > --- > 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 6968de9d7402..6931b2ba2776 100644 > --- a/block/blk-mq.c > +++ b/block/blk-mq.c > @@ -2206,6 +2206,61 @@ 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 Isn't that inverted? >From the function I would assume it'll be called once the CPU is being set toe 'online', yet from the description I would have assumed the INTERNAL_STOPPED bit is set when the cpu goes offline. Care to elaborate? Cheers, Hannes -- Dr. Hannes Reinecke Teamlead Storage & Networking hare@xxxxxxx +49 911 74053 688 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Mary Higgins, Sri Rasiah HRB 21284 (AG Nürnberg)
