netdev - Re: [PATCH net 1/2] net: ionic: add dma_wmb() before ringing TX doorbell

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

Message-ID: <78ea772b-bd14-4732-b685-c320ebcb5c55@amd.com>
Date: Mon, 10 Nov 2025 09:28:09 -0800
From: Brett Creeley <bcreeley@....com>
To: patchwork-bot+netdevbpf@...nel.org, mohammad heib <mheib@...hat.com>
Cc: netdev@...r.kernel.org, brett.creeley@....com, andrew+netdev@...n.ch,
 davem@...emloft.net, kuba@...nel.org
Subject: Re: [PATCH net 1/2] net: ionic: add dma_wmb() before ringing TX
 doorbell



On 11/3/2025 5:30 PM, patchwork-bot+netdevbpf@...nel.org wrote:
> Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.
> 
> 
> Hello:
> 
> This series was applied to netdev/net.git (main)
> by Jakub Kicinski <kuba@...nel.org>:
> 
> On Fri, 31 Oct 2025 17:52:02 +0200 you wrote:
>> From: Mohammad Heib <mheib@...hat.com>
>>
>> The TX path currently writes descriptors and then immediately writes to
>> the MMIO doorbell register to notify the NIC.  On weakly ordered
>> architectures, descriptor writes may still be pending in CPU or DMA
>> write buffers when the doorbell is issued, leading to the device
>> fetching stale or incomplete descriptors.

Apologies for the late response, but it's not clear to me why this is 
necessary.

In other vendors the "doorbell record" (dbr) is writing another location 
in system memory, not an mmio write. These cases do use a dma_wmb().

Why isn't the writeq() sufficient in our case? According to 
Documentation/memory-barriers.txt it seems like writeq() should be 
sufficient.

Thanks,

Brett
>>
>> [...]
> 
> Here is the summary with links:
>    - [net,1/2] net: ionic: add dma_wmb() before ringing TX doorbell
>      https://git.kernel.org/netdev/net/c/d261f5b09c28
>    - [net,2/2] net: ionic: map SKB after pseudo-header checksum prep
>      https://git.kernel.org/netdev/net/c/de0337d641bf
> 
> You are awesome, thank you!
> --
> Deet-doot-dot, I am a bot.
> https://korg.docs.kernel.org/patchwork/pwbot.html
> 
>