all lists on lists.proxmox.com
 help / color / mirror / Atom feed
From: Stefan Hanreich <s.hanreich@proxmox.com>
To: pve-devel@lists.proxmox.com
Subject: Re: [PATCH proxmox-perl-rs v3 03/17] pve-rs: sdn: add bindings for the eBPF DHCP responder
Date: Tue, 20 Oct 2026 15:10:15 +0200	[thread overview]
Message-ID: <83ea64ef-6097-4f74-a824-bd0cfbdf8860@proxmox.com> (raw)
In-Reply-To: <20261020080005.470757-4-h.laimer@proxmox.com>

On 10/20/26 10:00 AM, Hannes Laimer wrote:
> The responder answers with the records the caller hands in. The
> caller has to build them under the responder's lock, or a full pass
> could write older records over those a plug or record change built
> later. So the lock is an object the caller takes before it builds the
> records, and every call that hands in records is a method of that
> lock.
> 
> Signed-off-by: Hannes Laimer <h.laimer@proxmox.com>
> ---
>  pve-rs/Cargo.toml               |   2 +
>  pve-rs/Makefile                 |   3 +
>  pve-rs/debian/control           |   2 +
>  pve-rs/src/bindings/sdn/dhcp.rs | 229 ++++++++++++++++++++++++++++++++
>  pve-rs/src/bindings/sdn/mod.rs  |   1 +
>  5 files changed, 237 insertions(+)
>  create mode 100644 pve-rs/src/bindings/sdn/dhcp.rs
> 
> diff --git a/pve-rs/Cargo.toml b/pve-rs/Cargo.toml
> index 5ae9082..0adf00b 100644
> --- a/pve-rs/Cargo.toml
> +++ b/pve-rs/Cargo.toml
> @@ -34,6 +34,7 @@ proxmox-apt = { version = "1.0.1", features = ["cache"] }
>  proxmox-apt-api-types = "3"
>  proxmox-base64 = "1"
>  proxmox-config-digest = "1"
> +proxmox-ebpf = { version = "0.1", features = ["dhcp"] }
>  proxmox-frr = { version = "0.5.1" }
>  proxmox-http = { version = "1.0.2", features = ["client-sync", "client-trait"] }
>  proxmox-http-error = "1"
> @@ -70,6 +71,7 @@ proxmox-wireguard = { version = "0.1.2" }
>  # proxmox-config-digest = { path = "../../proxmox/proxmox-config-digest" }
>  # proxmox-daemon = { path = "../../proxmox/proxmox-daemon" }
>  # proxmox-dns-api = { path = "../../proxmox/proxmox-dns-api" }
> +# proxmox-ebpf = { path = "../../proxmox-ebpf" }
>  # proxmox-http-error = { path = "../../proxmox/proxmox-http-error" }
>  # proxmox-http = { path = "../../proxmox/proxmox-http" }
>  # proxmox-human-byte = { path = "../../proxmox/proxmox-human-byte" }
> diff --git a/pve-rs/Makefile b/pve-rs/Makefile
> index bb1cd2d..ebe8bd3 100644
> --- a/pve-rs/Makefile
> +++ b/pve-rs/Makefile
> @@ -32,6 +32,9 @@ PERLMOD_PACKAGES := \
>  	  PVE::RS::OpenId \
>  	  PVE::RS::ResourceScheduling::Static \
>  	  PVE::RS::ResourceScheduling::Dynamic \
> +	  PVE::RS::SDN::Dhcp \
> +	  PVE::RS::SDN::Dhcp::ExclusiveLock \
> +	  PVE::RS::SDN::Dhcp::SharedLock \
>  	  PVE::RS::SDN::Fabrics \
>  	  PVE::RS::SDN::PrefixLists \
>  	  PVE::RS::SDN::RouteMaps \
> diff --git a/pve-rs/debian/control b/pve-rs/debian/control
> index 70367dc..521d966 100644
> --- a/pve-rs/debian/control
> +++ b/pve-rs/debian/control
> @@ -20,6 +20,8 @@ Build-Depends: debhelper-compat (= 13),
>                 librust-proxmox-apt-api-types-3+default-dev (>= 3.0.0-~~),
>                 librust-proxmox-base64-1+default-dev,
>                 librust-proxmox-config-digest-1+default-dev,
> +               librust-proxmox-ebpf-0.1+default-dev,
> +               librust-proxmox-ebpf-0.1+dhcp-dev,
>                 librust-proxmox-frr-0.5+default-dev (>= 0.5.1-~~),
>                 librust-proxmox-http-1+client-sync-dev (>= 1.0.2-~~),
>                 librust-proxmox-http-1+client-trait-dev (>= 1.0.2-~~),
> diff --git a/pve-rs/src/bindings/sdn/dhcp.rs b/pve-rs/src/bindings/sdn/dhcp.rs
> new file mode 100644
> index 0000000..a6cdc95
> --- /dev/null
> +++ b/pve-rs/src/bindings/sdn/dhcp.rs
> @@ -0,0 +1,229 @@
> +#[perlmod::package(name = "PVE::RS::SDN::Dhcp", lib = "pve_rs")]
> +pub mod pve_rs_sdn_dhcp {
> +    //! The `PVE::RS::SDN::Dhcp` package.
> +    //!
> +    //! Bindings for the per-tap eBPF DHCP responder. Interfaces and the records they answer with
> +    //! are handed in here and served directly from the kernel. The calls that change the responder
> +    //! are methods of a lock object, so nothing writes to it without holding the lock in the mode
> +    //! the change needs.
> +
> +    use std::net::Ipv4Addr;
> +
> +    use anyhow::Error;
> +    use serde::{Deserialize, Deserializer};
> +
> +    use proxmox_ebpf::dhcp::{DhcpSubsystem, Iface, Record, Unplugged};
> +
> +    /// One interface's DHCP answer, the address and every option the reply carries.
> +    #[derive(Deserialize)]
> +    pub struct DhcpRecord {
> +        ip: Ipv4Addr,
> +        prefixlen: u8,
> +        server_id: Ipv4Addr,
> +        lease: u32,
> +        #[serde(default)]
> +        router: Option<Ipv4Addr>,
> +        #[serde(default)]
> +        dns: Option<Ipv4Addr>,
> +        #[serde(default)]
> +        mtu: Option<u16>,
> +        #[serde(deserialize_with = "mac_from_str")]
> +        mac: [u8; 6],

proxmox-network-types has a MAC address type that would fit here if we add an as_slice() method

> +    }
> +
> +    // a MAC as six hex pairs
> +    fn mac_from_str<'de, D: Deserializer<'de>>(d: D) -> Result<[u8; 6], D::Error> {
> +        let text = String::deserialize(d)?;
> +        let mut mac = [0u8; 6];
> +        let mut parts = text.split(':');
> +        for byte in &mut mac {
> +            let part = parts
> +                .next()
> +                .ok_or_else(|| serde::de::Error::custom(format!("MAC {text} is too short")))?;
> +            if part.len() != 2 || !part.bytes().all(|b| b.is_ascii_hexdigit()) {
> +                return Err(serde::de::Error::custom(format!("MAC {text} is malformed")));
> +            }
> +            *byte = u8::from_str_radix(part, 16)
> +                .map_err(|_| serde::de::Error::custom(format!("MAC {text} is malformed")))?;
> +        }
> +        if parts.next().is_some() {
> +            return Err(serde::de::Error::custom(format!("MAC {text} is too long")));
> +        }
> +        Ok(mac)
> +    }

would become obsolete if using the MacAddr type

> +    /// One guest interface, the vnet it sits on if any, whether the responder runs on it and what
> +    /// it answers there.
> +    #[derive(Deserialize)]
> +    pub struct DhcpIface {
> +        name: String,
> +        #[serde(default)]
> +        vnet: Option<String>,
> +        serve: bool,
> +        #[serde(default)]
> +        record: Option<DhcpRecord>,
> +    }
> +
> +    /// Where an unplugged interface went, the vnet it sits on now, none for a plain bridge.
> +    #[derive(Deserialize)]
> +    pub struct DhcpTarget {
> +        #[serde(default)]
> +        vnet: Option<String>,
> +    }
> +
> +    impl From<DhcpRecord> for Record {
> +        fn from(r: DhcpRecord) -> Self {
> +            Record {
> +                ip: r.ip,
> +                prefixlen: r.prefixlen,
> +                server_id: r.server_id,
> +                lease: r.lease,
> +                router: r.router,
> +                dns: r.dns,
> +                mtu: r.mtu,
> +                mac: r.mac,
> +            }
> +        }
> +    }
> +
> +    impl From<DhcpIface> for Iface {
> +        fn from(i: DhcpIface) -> Self {
> +            Iface {
> +                name: i.name,
> +                vnet: i.vnet,
> +                serve: i.serve,
> +                record: i.record.map(Record::from),
> +            }
> +        }
> +    }
> +
> +    pub(super) fn to_ifaces(ifaces: Vec<DhcpIface>) -> Vec<Iface> {
> +        ifaces.into_iter().map(Iface::from).collect()
> +    }
> +
> +    /// A tap unplug. Without a target the interface is gone or going and takes its record with
> +    /// it. With one it was plugged onto a bridge the responder does not serve and keeps a marker
> +    /// naming that place.
> +    #[export]
> +    pub fn detach(iface: &str, target: Option<DhcpTarget>) -> Result<(), Error> {
> +        let unplugged = match target {
> +            None => Unplugged::Gone,
> +            Some(target) => Unplugged::MovedTo(target.vnet),
> +        };
> +        DhcpSubsystem::new().detach(iface, unplugged)
> +    }
> +}
> +
> +#[perlmod::package(name = "PVE::RS::SDN::Dhcp::SharedLock", lib = "pve_rs")]
> +pub mod pve_rs_sdn_dhcp_shared_lock {
> +    //! The `PVE::RS::SDN::Dhcp::SharedLock` package.
> +    //!
> +    //! The responder's lock taken shared, what a tap plug and a guest's own record change hold.
> +    //! Released when the object goes away.
> +
> +    use anyhow::Error;
> +    use perlmod::Value;
> +
> +    use proxmox_ebpf::dhcp::{DhcpSubsystem, Iface, Outcome, Record, SharedLock};
> +
> +    use super::pve_rs_sdn_dhcp::{DhcpIface, DhcpRecord, to_ifaces};
> +
> +    /// The lock as Perl holds it.
> +    pub struct PerlSharedLock {
> +        lock: SharedLock,
> +    }
> +
> +    perlmod::declare_magic!(Box<PerlSharedLock> : &PerlSharedLock as "PVE::RS::SDN::Dhcp::SharedLock");
> +
> +    /// Class method: take the lock. Plugs hold it next to each other and wait only behind a full
> +    /// pass or a record change.
> +    #[export]
> +    pub fn new(#[raw] class: Value) -> Result<Value, Error> {
> +        let lock = DhcpSubsystem::new().lock_shared()?;
> +        Ok(perlmod::instantiate_magic!(&class, MAGIC => Box::new(PerlSharedLock { lock })))
> +    }
> +
> +    /// Method: a tap plug onto a vnet with the record it answers. Without a record the interface
> +    /// gets no answer. Returns false when nothing is loaded yet. An interface gone already counts
> +    /// as done.
> +    #[export]
> +    pub fn attach(
> +        #[try_from_ref] this: &PerlSharedLock,
> +        iface: String,
> +        vnet: String,
> +        record: Option<DhcpRecord>,
> +    ) -> Result<bool, Error> {
> +        let iface = Iface {
> +            name: iface,
> +            vnet: Some(vnet),
> +            serve: true,
> +            record: record.map(Record::from),
> +        };
> +        Ok(this.lock.attach(&iface)? == Outcome::Done)
> +    }
> +
> +    /// Method: a record change for the listed interfaces by a caller holding the guest lock.
> +    /// Returns false when nothing is loaded to write into, so a full pass is due.
> +    #[export]
> +    pub fn update(
> +        #[try_from_ref] this: &PerlSharedLock,
> +        ifaces: Vec<DhcpIface>,
> +    ) -> Result<bool, Error> {
> +        Ok(this.lock.update(&to_ifaces(ifaces))? == Outcome::Done)
> +    }
> +}
> +
> +#[perlmod::package(name = "PVE::RS::SDN::Dhcp::ExclusiveLock", lib = "pve_rs")]
> +pub mod pve_rs_sdn_dhcp_exclusive_lock {
> +    //! The `PVE::RS::SDN::Dhcp::ExclusiveLock` package.
> +    //!
> +    //! The responder's lock taken exclusively, what a full pass and a record change hold. Released
> +    //! when the object goes away.
> +
> +    use anyhow::Error;
> +    use perlmod::Value;
> +
> +    use proxmox_ebpf::dhcp::{DhcpSubsystem, ExclusiveLock, Outcome};
> +
> +    use super::pve_rs_sdn_dhcp::{DhcpIface, to_ifaces};
> +
> +    /// The lock as Perl holds it.
> +    pub struct PerlExclusiveLock {
> +        lock: ExclusiveLock,
> +    }
> +
> +    perlmod::declare_magic!(Box<PerlExclusiveLock> : &PerlExclusiveLock as "PVE::RS::SDN::Dhcp::ExclusiveLock");
> +
> +    /// Class method: take the lock, waiting out every plug in flight.
> +    #[export]
> +    pub fn new(#[raw] class: Value) -> Result<Value, Error> {
> +        let lock = DhcpSubsystem::new().lock_exclusive()?;
> +        Ok(perlmod::instantiate_magic!(&class, MAGIC => Box::new(PerlExclusiveLock { lock })))
> +    }
> +
> +    /// Method: the full pass over every guest interface of the cluster. Those found here get
> +    /// their entry and a link where served.
> +    #[export]
> +    pub fn apply(
> +        #[try_from_ref] this: &PerlExclusiveLock,
> +        ifaces: Vec<DhcpIface>,
> +    ) -> Result<(), Error> {
> +        this.lock.apply(&to_ifaces(ifaces))
> +    }
> +
> +    /// Method: a record change for the listed interfaces. Those not found here are skipped.
> +    /// Returns false when nothing is loaded to write into, so a full pass is due.
> +    #[export]
> +    pub fn update(
> +        #[try_from_ref] this: &PerlExclusiveLock,
> +        ifaces: Vec<DhcpIface>,
> +    ) -> Result<bool, Error> {
> +        Ok(this.lock.update(&to_ifaces(ifaces))? == Outcome::Done)
> +    }
> +
> +    /// Method: detach the responder everywhere and drop its pinned state.
> +    #[export]
> +    pub fn clear(#[try_from_ref] this: &PerlExclusiveLock) -> Result<(), Error> {
> +        this.lock.clear()
> +    }
> +}
> diff --git a/pve-rs/src/bindings/sdn/mod.rs b/pve-rs/src/bindings/sdn/mod.rs
> index dcae046..4b99b8f 100644
> --- a/pve-rs/src/bindings/sdn/mod.rs
> +++ b/pve-rs/src/bindings/sdn/mod.rs
> @@ -1,3 +1,4 @@
> +pub(crate) mod dhcp;
>  pub(crate) mod fabrics;
>  pub(crate) mod prefix_lists;
>  pub(crate) mod route_maps;





  reply	other threads:[~2026-10-20 13:10 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-20  7:59 [PATCH container/docs/manager/network/proxmox{-ebpf,-perl-rs}/qemu-server v3 00/17] sdn: implement DHCP for all zones using eBPF Hannes Laimer
2026-10-20  7:59 ` [PATCH proxmox-ebpf v3 01/17] dhcp: add the per-tap DHCPv4 responder program Hannes Laimer
2026-10-20  7:59 ` [PATCH proxmox-ebpf v3 02/17] dhcp: add the subsystem that loads the responder and keeps its records Hannes Laimer
2026-10-20 13:09   ` Stefan Hanreich
2026-10-21  7:09     ` Hannes Laimer
2026-10-20  7:59 ` [PATCH proxmox-perl-rs v3 03/17] pve-rs: sdn: add bindings for the eBPF DHCP responder Hannes Laimer
2026-10-20 13:10   ` Stefan Hanreich [this message]
2026-10-21  7:32     ` Hannes Laimer
2026-10-20  7:59 ` [PATCH pve-network v3 04/17] sdn: dhcp: replace a stale dnsmasq reservation instead of dropping it Hannes Laimer
2026-10-20 13:15   ` Stefan Hanreich
2026-10-20  7:59 ` [PATCH pve-network v3 05/17] sdn: dhcp: update reservations when ip mappings change Hannes Laimer
2026-10-20 13:42   ` Stefan Hanreich
2026-10-21  7:21     ` Hannes Laimer
2026-10-20  7:59 ` [PATCH pve-network v3 06/17] sdn: ipam: key the MAC cache by lower-case MAC, stop caching misses Hannes Laimer
2026-10-20 13:10   ` Stefan Hanreich
2026-10-21  6:17     ` Hannes Laimer
2026-10-20  7:59 ` [PATCH pve-network v3 07/17] sdn: dhcp: make the lease time configurable per subnet Hannes Laimer
2026-10-20 13:17   ` Stefan Hanreich
2026-10-20  7:59 ` [PATCH pve-network v3 08/17] sdn: dhcp: require a backend only if a zone on this node uses it Hannes Laimer
2026-10-20 13:17   ` Stefan Hanreich
2026-10-20  7:59 ` [PATCH pve-network v3 09/17] sdn: dhcp: add an eBPF backend answering on each guest interface Hannes Laimer
2026-10-20 13:10   ` Stefan Hanreich
2026-10-21  6:16     ` Hannes Laimer
2026-10-20  7:59 ` [PATCH pve-network v3 10/17] sdn: zones: report interface plugs and unplugs to the DHCP backends Hannes Laimer
2026-10-20 13:17   ` Stefan Hanreich
2026-10-20  7:59 ` [PATCH pve-network v3 11/17] sdn: dhcp: push IP mapping edits to the guest's node Hannes Laimer
2026-10-20 13:09   ` Stefan Hanreich
2026-10-21  6:44     ` Hannes Laimer
2026-10-20  8:00 ` [PATCH pve-network v3 12/17] sdn: zones: allow the ebpf DHCP backend on every zone type Hannes Laimer
2026-10-20  8:00 ` [PATCH qemu-server v3 13/17] network: sdn: keep the DHCP backends current on guest NICs Hannes Laimer
2026-10-20 13:38   ` Stefan Hanreich
2026-10-20  8:00 ` [PATCH pve-container v3 14/17] net: report NIC plugs and removals to the SDN DHCP backends Hannes Laimer
2026-10-20 13:36   ` Stefan Hanreich
2026-10-21  7:29     ` Hannes Laimer
2026-10-20  8:00 ` [PATCH pve-manager v3 15/17] ui: sdn: add zone DHCP backend selector and subnet DHCP options Hannes Laimer
2026-10-20 13:19   ` Stefan Hanreich
2026-10-20  8:00 ` [PATCH pve-manager v3 16/17] sdn: bring up the DHCP backends at boot before the guests start Hannes Laimer
2026-10-20 13:21   ` Stefan Hanreich
2026-10-21  7:17     ` Hannes Laimer
2026-10-20  8:00 ` [PATCH pve-docs v3 17/17] sdn: dhcp: add eBPF backend section Hannes Laimer
2026-10-20 13:11 ` [PATCH container/docs/manager/network/proxmox{-ebpf,-perl-rs}/qemu-server v3 00/17] sdn: implement DHCP for all zones using eBPF Stefan Hanreich
2026-10-21  7:35   ` Hannes Laimer
2026-10-21  8:46 ` superseded: " Hannes Laimer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=83ea64ef-6097-4f74-a824-bd0cfbdf8860@proxmox.com \
    --to=s.hanreich@proxmox.com \
    --cc=pve-devel@lists.proxmox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal