Re: [PATCH net v5 1/9] xdp: use modulo operation to calculate XDP frag tailroom
From: patchwork-bot+netdevbpf@kernel.org
Date: 2026-03-05 16:10:28
Also in:
bpf, imx, intel-wired-lan, linux-kselftest, lkml
Hello: This series was applied to netdev/net.git (main) by Jakub Kicinski [off-list ref]: On Thu, 5 Mar 2026 12:12:42 +0100 you wrote:
The current formula for calculating XDP tailroom in mbuf packets works only if each frag has its own page (if rxq->frag_size is PAGE_SIZE), this defeats the purpose of the parameter overall and without any indication leads to negative calculated tailroom on at least half of frags, if shared pages are used. There are not many drivers that set rxq->frag_size. Among them: * i40e and enetc always split page uniformly between frags, use shared pages * ice uses page_pool frags via libeth, those are power-of-2 and uniformly distributed across page * idpf has variable frag_size with XDP on, so current API is not applicable * mlx5, mtk and mvneta use PAGE_SIZE or 0 as frag_size for page_pool [...]
Here is the summary with links:
- [net,v5,1/9] xdp: use modulo operation to calculate XDP frag tailroom
https://git.kernel.org/netdev/net/c/88b6b7f7b216
- [net,v5,2/9] xsk: introduce helper to determine rxq->frag_size
https://git.kernel.org/netdev/net/c/16394d805399
- [net,v5,3/9] ice: fix rxq info registering in mbuf packets
https://git.kernel.org/netdev/net/c/02852b47c706
- [net,v5,4/9] ice: change XDP RxQ frag_size from DMA write length to xdp.frame_sz
https://git.kernel.org/netdev/net/c/e142dc4ef0f4
- [net,v5,5/9] i40e: fix registering XDP RxQ info
https://git.kernel.org/netdev/net/c/8f497dc8a614
- [net,v5,6/9] i40e: use xdp.frame_sz as XDP RxQ info frag_size
https://git.kernel.org/netdev/net/c/c69d22c6c46a
- [net,v5,7/9] libeth, idpf: use truesize as XDP RxQ info frag_size
https://git.kernel.org/netdev/net/c/75d9228982f2
- [net,v5,8/9] net: enetc: use truesize as XDP RxQ info frag_size
https://git.kernel.org/netdev/net/c/f8e18abf183d
- [net,v5,9/9] xdp: produce a warning when calculated tailroom is negative
https://git.kernel.org/netdev/net/c/8821e857759b
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html