On Thu, May 8, 2025 at 1:45 AM Cosmin Ratiu cratiu@nvidia.com wrote:
netdev_bind_rx takes ownership of the queue array passed as parameter and frees it, so a queue array buffer cannot be reused across multiple netdev_bind_rx calls.
This commit fixes that by always passing in a newly created queue array to all netdev_bind_rx calls in ncdevmem.
Fixes: 85585b4bc8d8 ("selftests: add ncdevmem, netcat for devmem TCP") Signed-off-by: Cosmin Ratiu cratiu@nvidia.com
Thank you very much.
Reviewed-by: Mina Almasry almasrymina@google.com
Also, I think there was a discussion in v1 about increasing the amount of memory that ncdevmem uses by default (currently it's 64MB) as Stan suggested. I have it in my TODO list to implement that change but I don't think I'll get to it soon. If you (or anyone) gets to it before me, it's a welcome change. AFAIU it'll unblock you from running ncdevmem on your driver which expects much more dmabuf memory available.
But to be clear, that can be a follow up change. I think this is good as-is.