blk-mq uses percpu_ref for its usage counter which tracks the number of in-flight commands and used to synchronously drain the queue on freeze. percpu_ref shutdown takes measureable wallclock time as it involves a sched RCU grace period. This means that draining a blk-mq takes measureable wallclock time. One would think that this shouldn't matter as queue shutdown should be a rare event which takes place asynchronously w.r.t. userland.
Unfortunately, SCSI probing involves synchronously setting up and then tearing down a lot of request_queues back-to-back for non-existent LUNs. This means that SCSI probing may take more than ten seconds when scsi-mq is used. This will be properly fixed by implementing a mechanism to keep q->mq_usage_counter in atomic mode till genhd registration; however, that involves rather big updates to percpu_ref which is difficult to apply late in the devel cycle (v3.17-rc6 at the moment). As a stop-gap measure till the proper fix can be implemented in the next cycle, this patch introduces __percpu_ref_kill_expedited() and makes blk_mq_freeze_queue() use it. This is heavy-handed but should work for testing the experimental SCSI blk-mq implementation. Signed-off-by: Tejun Heo <t...@kernel.org> Reported-by: Christoph Hellwig <h...@infradead.org> Link: http://lkml.kernel.org/g/20140919113815.ga10...@lst.de Fixes: add703fda981 ("blk-mq: use percpu_ref for mq usage count") Cc: Kent Overstreet <k...@daterainc.com> Cc: Jens Axboe <ax...@kernel.dk> --- Hello, Jens, Christoph. How about this one? This is kinda ugly but should work fine in most cases and easy to apply to v3.17 and take out during v3.18. Thanks. block/blk-mq.c | 11 ++++++++++- include/linux/percpu-refcount.h | 1 + lib/percpu-refcount.c | 16 ++++++++++++++++ 3 files changed, 27 insertions(+), 1 deletion(-) --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -120,7 +120,16 @@ void blk_mq_freeze_queue(struct request_ spin_unlock_irq(q->queue_lock); if (freeze) { - percpu_ref_kill(&q->mq_usage_counter); + /* + * XXX: Temporary kludge to work around SCSI blk-mq stall. + * SCSI synchronously creates and destroys many queues + * back-to-back during probe leading to lengthy stalls. + * This will be fixed by keeping ->mq_usage_counter in + * atomic mode until genhd registration, but, for now, + * let's work around using expedited synchronization. + */ + __percpu_ref_kill_expedited(&q->mq_usage_counter); + blk_mq_run_queues(q, false); } wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -72,6 +72,7 @@ void percpu_ref_reinit(struct percpu_ref void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); +void __percpu_ref_kill_expedited(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -189,3 +189,19 @@ void percpu_ref_kill_and_confirm(struct call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu); } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); + +/* + * XXX: Temporary kludge to work around SCSI blk-mq stall. Used only by + * block/blk-mq.c::blk_mq_freeze_queue(). Will be removed during v3.18 + * devel cycle. Do not use anywhere else. + */ +void __percpu_ref_kill_expedited(struct percpu_ref *ref) +{ + WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD, + "percpu_ref_kill() called more than once on %pf!", + ref->release); + + ref->pcpu_count_ptr |= PCPU_REF_DEAD; + synchronize_sched_expedited(); + percpu_ref_kill_rcu(&ref->rcu); +} -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
