From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from vulcan.natalenko.name ([104.207.131.136]:19780 "EHLO vulcan.natalenko.name" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752660AbdIBOr1 (ORCPT ); Sat, 2 Sep 2017 10:47:27 -0400 From: Oleksandr Natalenko To: Ming Lei Cc: Jens Axboe , linux-block@vger.kernel.org, Christoph Hellwig , Bart Van Assche , linux-scsi@vger.kernel.org, "Martin K . Petersen" , "James E . J . Bottomley" , Johannes Thumshirn , Tejun Heo Subject: Re: [PATCH V3 0/8] block/scsi: safe SCSI quiescing Date: Sat, 02 Sep 2017 16:47:19 +0200 Message-ID: <9524396.xaYzBpxu59@natalenko.name> In-Reply-To: <20170902130840.24609-1-ming.lei@redhat.com> References: <20170902130840.24609-1-ming.lei@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Sender: linux-block-owner@vger.kernel.org List-Id: linux-block@vger.kernel.org Again, Tested-by: Oleksandr Natalenko On sobota 2. z=C3=A1=C5=99=C3=AD 2017 15:08:32 CEST Ming Lei wrote: > Hi, >=20 > The current SCSI quiesce isn't safe and easy to trigger I/O deadlock. >=20 > Once SCSI device is put into QUIESCE, no new request except for RQF_PREEM= PT > can be dispatched to SCSI successfully, and scsi_device_quiesce() just > simply waits for completion of I/Os dispatched to SCSI stack. It isn't > enough at all. >=20 > Because new request still can be allocated, but all the allocated > requests can't be dispatched successfully, so request pool can be > consumed up easily. >=20 > Then request with RQF_PREEMPT can't be allocated, and system may > hang forever, such as during system suspend or SCSI domain alidation. >=20 > Both IO hang inside system suspend[1] or SCSI domain validation > were reported before. >=20 > This patch introduces preempt freez, and tries to solve the issue > by preempt freezing block queue during SCSI quiesce, and allows > to allocate request of RQF_PREEMPT when queue is preempt-frozen. >=20 > Both SCSI and SCSI_MQ have this IO deadlock issue, this patch fixes > them all by introducing blk_freeze_queue_preempt() and > blk_unfreeze_queue_preempt(), also unifying current interfaces for > freezing queue between block legacy and blk-mq. >=20 > Oleksandr has verified that this patchset V2 fixes his I/O hang > during suspend/resume cycle. >=20 > V3: > - introduce q->preempt_unfreezing to fix one bug of preempt freeze > - call blk_queue_enter_live() only when queue is preempt frozen > - cleanup a bit on the implementation of preempt freeze > - only patch 6 and 7 are changed >=20 > V2: > - drop the 1st patch in V1 because percpu_ref_is_dying() is > enough as pointed by Tejun > - introduce preempt version of blk_[freeze|unfreeze]_queue > - sync between preempt freeze and normal freeze > - fix warning from percpu-refcount as reported by Oleksandr >=20 >=20 > [1] https://marc.info/?t=3D150340250100013&r=3D3&w=3D2 >=20 >=20 >=20 > Ming Lei (8): > blk-mq: rename blk_mq_unfreeze_queue as blk_unfreeze_queue > blk-mq: rename blk_mq_freeze_queue as blk_freeze_queue > blk-mq: only run hw queues for blk-mq > blk-mq: rename blk_mq_freeze_queue_wait as blk_freeze_queue_wait > block: tracking request allocation with q_usage_counter > block: introduce preempt version of blk_[freeze|unfreeze]_queue > block: allow to allocate req with REQF_PREEMPT when queue is preempt > frozen > SCSI: preempt freeze block queue when SCSI device is put into quiesce >=20 > block/bfq-iosched.c | 2 +- > block/blk-cgroup.c | 8 +-- > block/blk-core.c | 53 ++++++++++++--- > block/blk-mq.c | 170 > +++++++++++++++++++++++++++++++++++++++-------- block/blk-mq.h = |=20 > 1 - > block/blk.h | 17 +++++ > block/elevator.c | 4 +- > drivers/block/loop.c | 16 ++--- > drivers/block/rbd.c | 2 +- > drivers/nvme/host/core.c | 8 +-- > drivers/scsi/scsi_lib.c | 22 +++++- > include/linux/blk-mq.h | 15 +++-- > include/linux/blkdev.h | 21 +++++- > 13 files changed, 273 insertions(+), 66 deletions(-)