Thread (22 messages) 22 messages, 4 authors, 2026-03-02

Re: [PATCH bpf v3 7/9] libeth, idpf: use truesize as XDP RxQ info frag_size

From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: 2026-02-17 16:21:15
Also in: bpf, imx, intel-wired-lan, linux-kselftest, lkml

From: Zaremba, Larysa <redacted>
Date: Tue, 17 Feb 2026 14:24:45 +0100
The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead
of DMA write size. Different assumptions in idpf driver configuration lead
to negative tailroom.

To make it worse, buffer sizes are not actually uniform in idpf when
splitq is enabled, as there are several buffer queues, so rxq->rx_buf_size
is meaningless in this case.

Use truesize of the first bufq in AF_XDP ZC, as there is only one. Disable
growinf tail for regular splitq.

Fixes: ac8a861f632e ("idpf: prepare structures to support XDP")
Signed-off-by: Larysa Zaremba <redacted>
Acked-by: Alexander Lobakin <aleksander.lobakin@intel.com>

Thanks for handling this!

Olek
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help