On 10/04/2019 12:43, Jesper Dangaard Brouer wrote:
> Reduce BH-disable period further by moving cpu_map_build_skb()
> outside/before invoking the network stack. And build up a
> skb_list that is used for netif_receive_skb_list. This is also
> an I-cache optimization.
>
> When injecting packets into the network stack, cpumap uses a special
> function named netif_receive_skb_core(), and we create a equivalent list
> version named netif_receive_skb_list_core().
>
> Signed-off-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
> ---
> include/linux/netdevice.h | 1 +
> kernel/bpf/cpumap.c | 17 ++++++++++-------
> net/core/dev.c | 18 ++++++++++++++++++
> 3 files changed, 29 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 166fdc0a78b4..37e78dc9f30a 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -3621,6 +3621,7 @@ int netif_rx_ni(struct sk_buff *skb);
> int netif_receive_skb(struct sk_buff *skb);
> int netif_receive_skb_core(struct sk_buff *skb);
> void netif_receive_skb_list(struct list_head *head);
> +void netif_receive_skb_list_core(struct list_head *head);
> gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
> void napi_gro_flush(struct napi_struct *napi, bool flush_old);
> struct sk_buff *napi_get_frags(struct napi_struct *napi);
> diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
> index 430103e182a0..cb93df200cd0 100644
> --- a/kernel/bpf/cpumap.c
> +++ b/kernel/bpf/cpumap.c
> @@ -256,6 +256,7 @@ static int cpu_map_kthread_run(void *data)
> while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
> unsigned int drops = 0, sched = 0;
> void *frames[CPUMAP_BATCH];
> + struct list_head skb_list;
> int i, n;
>
> /* Release CPU reschedule checks */
> @@ -279,23 +280,25 @@ static int cpu_map_kthread_run(void *data)
> */
> n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
>
> - local_bh_disable();
> + INIT_LIST_HEAD(&skb_list);
> +
> for (i = 0; i < n; i++) {
> struct xdp_frame *xdpf = frames[i];
> struct sk_buff *skb;
> - int ret;
>
> skb = cpu_map_build_skb(rcpu, xdpf);
> if (!skb) {
> xdp_return_frame(xdpf);
> continue;
> }
> -
> - /* Inject into network stack */
> - ret = netif_receive_skb_core(skb);
> - if (ret == NET_RX_DROP)
> - drops++;
You're losing this `drops` incrementation and not doing anything to
replace it...
> + list_add_tail(&skb->list, &skb_list);
> }
> +
> + local_bh_disable();
> +
> + /* Inject into network stack */
> + netif_receive_skb_list_core(&skb_list);
> +
> /* Feedback loop via tracepoint */
> trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
... yet still feeding it to the tracepoint here.
I ran into something similar with my list-GRO patches (callers wanted to
know how many packets from the list were received vs. dropped); check
those to see how I wired that counting all the way through the listified
stack.
Apart from that, I like this!
-Ed
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 9ca2d3abfd1a..1dee7bd895a0 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -5297,6 +5297,24 @@ void netif_receive_skb_list(struct list_head *head)
> }
> EXPORT_SYMBOL(netif_receive_skb_list);
>
> +/**
> + * netif_receive_skb_list_core - special version of netif_receive_skb_list
> + * @head: list of skbs to process.
> + *
> + * More direct receive version of netif_receive_skb_list(). It should
> + * only be used by callers that have a need to skip RPS and Generic XDP.
> + *
> + * This function may only be called from softirq context and interrupts
> + * should be enabled.
> + */
> +void netif_receive_skb_list_core(struct list_head *head)
> +{
> + rcu_read_lock();
> + __netif_receive_skb_list(head);
> + rcu_read_unlock();
> +}
> +EXPORT_SYMBOL(netif_receive_skb_list_core);
> +
> DEFINE_PER_CPU(struct work_struct, flush_works);
>
> /* Network device is going away, flush any packets still pending */
>
