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/
[2]:https://docs.ebpf.io/linux/helper-function/bpf_xdp_adjust_meta/
Signed-off-by: Mehdi Ben Hadj Khelifa <mehdi.benhadjkhelifa@gmail.com>
---
Changelog:
Changes from v2:
-Corrected the new comment
Link:https://lore.kernel.org/all/20251020170254.14622-1-mehdi.benhadjkhelifa@gmail.com/
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
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