netdev - Re: [RFC net-next 2/2] eth: bnxt: add support rx side device memory TCP

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]

Message-ID: <CAMArcTVn_SmvrsewzoYaFa-sqT=9bS-3W2qwmSnsQc49-eZWWg@mail.gmail.com>
Date: Thu, 3 Apr 2025 10:55:13 +0900
From: Taehee Yoo <ap420073@...il.com>
To: Mina Almasry <almasrymina@...gle.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com, 
	edumazet@...gle.com, andrew+netdev@...n.ch, horms@...nel.org, 
	michael.chan@...adcom.com, pavan.chebbi@...adcom.com, 
	ilias.apalodimas@...aro.org, dw@...idwei.uk, netdev@...r.kernel.org, 
	kuniyu@...zon.com, sdf@...ichev.me, aleksander.lobakin@...el.com
Subject: Re: [RFC net-next 2/2] eth: bnxt: add support rx side device memory TCP

On Thu, Apr 3, 2025 at 7:17 AM Mina Almasry <almasrymina@...gle.com> wrote:
>

Hi Mina,
Thanks a lot for the review!

> On Mon, Mar 31, 2025 at 4:48 AM Taehee Yoo <ap420073@...il.com> wrote:
>
> > -static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
> > -                                  struct bnxt_rx_ring_info *rxr,
> > -                                  int numa_node)
> > +static int bnxt_alloc_rx_netmem_pool(struct bnxt *bp,
> > +                                    struct bnxt_rx_ring_info *rxr,
> > +                                    int numa_node)
> >  {
> >         struct page_pool_params pp = { 0 };
> >         struct page_pool *pool;
> > @@ -3779,15 +3799,20 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
> >         pp.dev = &bp->pdev->dev;
> >         pp.dma_dir = bp->rx_dir;
> >         pp.max_len = PAGE_SIZE;
> > -       pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
> > +       pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
> > +                  PP_FLAG_ALLOW_UNREADABLE_NETMEM;
>
> I was expecting to see a check that hdr_split is enabled and threshold
> is 0 before you allow unreadable netmem. Or are you relying on the
> core check at devmem/io_uring binding time to do that for you?

Yes, it relies on the core.
The core already checks conditions very well, such as HDS.
So I think drivers don't need to check these conditions again.

Thanks a lot!
Taehee Yoo

>
> --
> Thanks,
> Mina