[PATCH bpf-next v3] bpf/cpumap.c: Remove unnecessary TODO comment
From: Mehdi Ben Hadj Khelifa <hidden>
Date: 2025-10-21 10:47:32
Also in:
bpf, linux-kernel-mentees, lkml
Subsystem:
bpf [general] (safe dynamic programs and tools), the rest, xdp (express data path) · Maintainers:
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko, Eduard Zingerman, Kumar Kartikeya Dwivedi, Linus Torvalds, David S. Miller, Jakub Kicinski, Jesper Dangaard Brouer, John Fastabend
After discussion with bpf maintainers[1], queue_index could be propagated to the remote XDP program by the xdp_md struct[2] which makes this todo a misguide for future effort. [1]:https://lore.kernel.org/all/87y0q23j2w.fsf@cloudflare.com/ (local) [2]:https://docs.ebpf.io/linux/helper-function/bpf_xdp_adjust_meta/ Signed-off-by: Mehdi Ben Hadj Khelifa <redacted> --- Changelog: Changes from v2: -Corrected the new comment Link:https://lore.kernel.org/all/20251020170254.14622-1-mehdi.benhadjkhelifa@gmail.com/ (local) Changes from v1: -Added a comment to clarify that RX queue_index is lost after the frame redirection. Link:https://lore.kernel.org/bpf/d9819687-5b0d-4bfa-9aec-aef71b847383@gmail.com/T/#mcb6a0315f174d02db3c9bc4fa556cc939c87a706 (local) kernel/bpf/cpumap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 703e5df1f4ef..ee37186fea35 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c@@ -195,8 +195,10 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, rxq.dev = xdpf->dev_rx; rxq.mem.type = xdpf->mem_type; - /* TODO: report queue_index to xdp_rxq_info */ - + /* RX queue_index is not preserved after redirection. + * If needed, the sender can embed it in XDP metadata + * (via bpf_xdp_adjust_meta) for the remote program. + */ xdp_convert_frame_to_buff(xdpf, &xdp); act = bpf_prog_run_xdp(rcpu->prog, &xdp);
--
2.51.1.dirty