On Tue, Jul 30, 2019 at 08:43:59AM +0800, Ming Lei wrote:

On Thu, Jul 25, 2019 at 10:04:58AM +0800, Ming Lei wrote:

quoted

Hi,

When one request is dispatched to LLD via dm-rq, if the result is
BLK_STS_*RESOURCE, dm-rq will free the request. However, LLD may allocate
private data for this request, so this way will cause memory leak.

Add .cleanup_rq() callback and implement it in SCSI for fixing the issue,
since SCSI is the only driver which allocates private requst data in
.queue_rq() path.

Another use case of this callback is to free the request and re-submit
bios during cpu hotplug when the hctx is dead, see the following link:

https://lore.kernel.org/linux-block/f122e8f2-5ede-2d83-9ca0-bc713ce66d01@huawei.com/T/#t (local)

V4:
	- add more commit log on the new .cleanup_rq callback, as suggested
	  by Mike

V3:
	- run .cleanup_rq() from dm-rq because this issue is dm-rq specific,
	and even in future it should be still very unusual to free request
	in this way. If we call .cleanup_rq() in generic rq free code(fast
	path), cost will be introduced unnecessarily, also we have to
	consider related race.

V2:
	- run .cleanup_rq() in blk_mq_free_request(), as suggested by Mike 



Ming Lei (2):
  blk-mq: add callback of .cleanup_rq
  scsi: implement .cleanup_rq callback

 drivers/md/dm-rq.c      |  1 +
 drivers/scsi/scsi_lib.c | 13 +++++++++++++
 include/linux/blk-mq.h  | 13 +++++++++++++
 3 files changed, 27 insertions(+)

Cc: Ewan D. Milne <redacted>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <redacted>
Cc: dm-devel@redhat.com
Cc: <redacted>
Fixes: 396eaf21ee17 ("blk-mq: improve DM's blk-mq IO merging via blk_insert_cloned_request feedback")

Hello Jens & guys,

Ping on this fix.

Hi Jens,

Could you make the patcheset merged for 5.4? And it has been verified
that big memory leak issue can be fixed by this patchset.


thanks,
Ming