Re: [PATCH net-next v3 10/18] nvme/host: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage

[Aurelien Aptel <aaptel@nvidia.com>]

Sagi Grimberg <sagi@grimberg.me> writes:
> Most likely this also reproduces with blktests?
> https://github.com/osandov/blktests
>
> simple way to check is to run:
> nvme_trtype=tcp ./check nvme
>
> This runs nvme tests over nvme-tcp.

Yes, it crashes similarly during test 10:

root@ktest:~/blktests# nvme_trtype=tcp ./check nvme
nvme/002 (create many subsystems and test discovery)         [not run]
    nvme_trtype=tcp is not supported in this test
nvme/003 (test if we're sending keep-alives to a discovery controller) [passed]
    runtime    ...  10.389s
nvme/004 (test nvme and nvmet UUID NS descriptors)           [passed]
    runtime    ...  1.264s
nvme/005 (reset local loopback target)                       [passed]
    runtime    ...  1.403s
nvme/006 (create an NVMeOF target with a block device-backed ns) [passed]
    runtime    ...  0.129s
nvme/007 (create an NVMeOF target with a file-backed ns)     [passed]
    runtime    ...  0.083s
nvme/008 (create an NVMeOF host with a block device-backed ns) [passed]
    runtime    ...  1.239s
nvme/009 (create an NVMeOF host with a file-backed ns)       [passed]
    runtime    ...  1.229s
nvme/010 (run data verification fio job on NVMeOF block device-backed
ns)

Same trace, null ptr deref at skb_splice_from_iter+0x10a/0x370

Cheers,