netdev - Re: [PATCH] Integration with the user space

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: <CAK8U23a2mF5Q5vW8waB3bRyWjLp9wSAOXFZA1YpC+oSeycTBRA@mail.gmail.com>
Date: Sat, 7 Jun 2025 14:47:04 -0300
From: Ramon Fontes <ramonreisfontes@...il.com>
To: Alexander Aring <aahringo@...hat.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com, 
	linux-wpan@...r.kernel.org, alex.aring@...il.com, miquel.raynal@...tlin.com, 
	netdev@...r.kernel.org
Subject: Re: [PATCH] Integration with the user space

Hi Alex, thanks for the feedback!

You're right, using AF_PACKET raw sockets on a monitor-mode wpan_dev
is indeed sufficient for user-space access to the raw PHY, and we’ve
also tested that setup successfully for basic communication.

However, if the use case focuses on evaluating realistic wireless
scenarios, where connectivity and interference vary across links. For
that, we rely on wmediumd, which integrates at the PHY level
(mac802154_hwsim) and controls per-link delivery based on configurable
SNR values and propagation models (e.g., log-distance, shadowing).
This allows us to emulate asymmetric topologies and partial
connectivity, something raw sockets alone cannot provide (or can?),
since all virtual radios are fully connected by default.

In this context, wmediumd becomes essential for simulating:

- Packet loss due to weak signal or distance;
- Asymmetric links (e.g., node A hears B, but not vice versa);
- Controlled interference between nodes;
- Link-specific behaviors needed for higher-layer protocol evaluation.

Additionally, by inducing realistic transmission failures, wmediumd
allows us to test MAC-layer features like retransmission (ARET) and
ACK handling (AACK) in a meaningful way, which would not be triggered
in a fully-connected environment.

Let me know if you'd like me to elaborate further or clarify anything
about this.

-
Ramon

Em sáb., 7 de jun. de 2025 às 14:27, Alexander Aring
<aahringo@...hat.com> escreveu:
>
> Hi,
>
> On Tue, Jun 3, 2025 at 3:05 PM Ramon Fontes <ramonreisfontes@...il.com> wrote:
> >
> > This PR introduces support for use space tools such as wmediumd in the mac802154_hwsim kernel module, similar to the existing support for Wi-Fi simulations via mac80211_hwsim. With this addition, it becomes possible to simulate interference and control transmission behavior in IEEE 802.15.4 networks using a userspace backend.
> >
>
> that is already being possible by using raw sockets, what is the
> difference here? Depending on your use case it might depend on what
> kind of mac instance "wpan_dev" is created on top of your phy. If you
> just want to have bare phy access you are looking into monitor wpan
> dev types and using AF_PACKET raw sockets. I already connected user
> space stacks (only for development) with it.
>
> If you want to have ARET/AACK support, the answer is more complicated.
>
> - Alex
>