Re: linux-next memleak after IO on dax mountpoint

[Jeff Moyer]

Xiong Zhou <xzhou@xxxxxxxxxx> writes:

> On Fri, May 27, 2016 at 04:46:17PM +0800, Xiong Zhou wrote:
> ...
>> Still working on to id which commit in this merge causes this issuer,
>
> Narrowed down to:

Hi Xiong,

I don't see how any of those could be at all relevant to pmem.  Can you
post the output from 'cat /proc/slabinfo' here?

Thanks,
Jeff

>
> 37e5823 block: add offset in blk_add_request_payload()
> e048948 blk-mq: Export tagset iter function
> 58b4560 nvme: add helper nvme_map_len()
> 03b5929 nvme: rewrite discard support
> 8093f7c nvme: add helper nvme_setup_cmd()
> 21f033f NVMe: Skip async events for degraded controllers
> 82b4552 nvme: Use blk-mq helper for IO termination
> 93e9d8e block: add ability to flag write back caching on a device
> 519a7e1 dm: switch to using blk_queue_write_cache()
> bb8d261 nvme: introduce a controller state machine
> 92911a5 nvme: tighten up state check for namespace scanning
> 5955be2 nvme: move namespace scanning to core
> f866fc4 nvme: move AER handling to common code
> 0bf77e9 nvme: switch to RCU freeing the namespace
> 9082e87 block: remove struct bio_batch
> 38f2525 block: add __blkdev_issue_discard
> 57aac2f lightnvm: fix "warning: âretâ may be used uninitialized"
> ecfb40c lightnvm: handle submit_io failure
> 1145e63 lightnvm: implement nvm_submit_ppa_list
> 22e8c97 lightnvm: move block fold outside of get_bb_tbl()
> 7f7c5d0 lightnvm: avoid memory leak when lun_map kcalloc fails
> 5136061 lightnvm: introduce nvm_for_each_lun_ppa() macro
> e11903f lightnvm: refactor device ops->get_bb_tbl()
> 5ebc7d9 lightnvm: make nvm_set_rqd_ppalist() aware of vblks
> a63d5cf lightnvm: move responsibility for bad blk mgmt to target
> 00ee6cc lightnvm: refactor set_bb_tbl for accepting ppa list
> 003fad3 lightnvm: enable metadata to be sent to device
> 04a8aa1 lightnvm: expose gennvm_mark_blk to targets
>
>
> These commits can not be reverted cleanly.