linux-kernel - Re: [PATCH] lightnvm: pblk: take write semaphore on metadata

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Mon, 13 Aug 2018 14:12:04 +0200
From:   Javier González <javier@...igon.com>
To:     Hans Holmberg <hans.ml.holmberg@...tronix.com>
Cc:     Matias Bjørling <mb@...htnvm.io>,
        linux-block@...r.kernel.org,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] lightnvm: pblk: take write semaphore on metadata

> On 10 Aug 2018, at 10.04, Hans Holmberg <hans.ml.holmberg@...tronix.com> wrote:
> 
> On Fri, Aug 3, 2018 at 2:05 PM, Javier González <javier@...igon.com> wrote:
>> pblk guarantees write ordering at a chunk level through a per open chunk
>> semaphore. At this point, since we only have an open I/O stream for both
>> user and GC data, the semaphore is per parallel unit.
>> 
>> Since metadata I/O is synchronous, the semaphore is not needed as
>> ordering is guaranteed. However, if the metadata scheme changes or
>> multiple streams are open, this guarantee might not be preserved.
>> 
>> This patch makes sure that all writes go through the semaphore, even for
>> synchronous I/O. This is consistent with pblk's write I/O model. It also
>> simplifies maintenance since changes in the metdatada scheme could cause
>> ordering issues.
>> 
>> Signed-off-by: Javier González <javier@...xlabs.com>
>> ---
>> drivers/lightnvm/pblk-core.c | 14 ++++++++++++--
>> drivers/lightnvm/pblk.h      |  1 +
>> 2 files changed, 13 insertions(+), 2 deletions(-)
>> 
>> diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
>> index 00984b486fea..160b54d26bfa 100644
>> --- a/drivers/lightnvm/pblk-core.c
>> +++ b/drivers/lightnvm/pblk-core.c
>> @@ -493,6 +493,16 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
>>        return nvm_submit_io_sync(dev, rqd);
>> }
>> 
>> +int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd)
>> +{
>> +       if (rqd->opcode != NVM_OP_PWRITE)
>> +               pblk_submit_io_sync(pblk, rqd);
>> +
>> +       pblk_down_page(pblk, rqd->ppa_list, rqd->nr_ppas);
> 
> This will only work if rqd->nr_ppas > 1, better check if rqd->nr_ppas
> is 1 and pass &ppa->ppa_addr on to pblk_down_page when needed.


For this particular case, we will always get > 1 ppas, but you're right,
it is more robust to do the check for future cases. I'll add that to V3.
Thanks!

Javier

Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)