Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames

[PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 1/9] firmware/psci: fix missing '%u' format literal in kthread_create_on_cpu() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
Re: [PATCH bpf-next 1/9] firmware/psci: fix missing '%u' format literal in kthread_create_on_cpu() · Daniel Xu <hidden> · 2024-08-30
[PATCH bpf-next 2/9] kthread: allow vararg kthread_{create,run}_on_cpu() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
Re: [PATCH bpf-next 2/9] kthread: allow vararg kthread_{create,run}_on_cpu() · Stanislav Fomichev <sdf@fomichev.me> · 2024-08-30
Re: [PATCH bpf-next 2/9] kthread: allow vararg kthread_{create,run}_on_cpu() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-09-03
Re: [PATCH bpf-next 2/9] kthread: allow vararg kthread_{create,run}_on_cpu() · Stanislav Fomichev <sdf@fomichev.me> · 2024-09-03
[PATCH bpf-next 3/9] net: napi: add ability to create CPU-pinned threaded NAPI · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
Re: [PATCH bpf-next 3/9] net: napi: add ability to create CPU-pinned threaded NAPI · Daniel Xu <hidden> · 2024-08-31
[PATCH bpf-next 4/9] bpf: cpumap: use CPU-pinned threaded NAPI w/GRO instead of kthread · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 5/9] bpf: cpumap: reuse skb array instead of a linked list to chain skbs · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 6/9] net: skbuff: introduce napi_skb_cache_get_bulk() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 7/9] bpf: cpumap: switch to napi_skb_cache_get_bulk() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 8/9] veth: use napi_skb_cache_get_bulk() instead of xdp_alloc_skb_bulk() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
[PATCH bpf-next 9/9] xdp: remove xdp_alloc_skb_bulk() · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-08-30
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Jakub Kicinski <kuba@kernel.org> · 2024-09-03
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Lorenzo Bianconi <lorenzo@kernel.org> · 2024-09-03
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Jesper Dangaard Brouer <hawk@kernel.org> · 2024-09-05
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Lorenzo Bianconi <lorenzo@kernel.org> · 2024-09-05
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Jakub Kicinski <kuba@kernel.org> · 2024-09-06
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Lorenzo Bianconi <lorenzo@kernel.org> · 2024-09-06
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Lorenzo Bianconi <lorenzo@kernel.org> · 2024-09-07
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-09-04
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Jakub Kicinski <kuba@kernel.org> · 2024-09-04
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Alexander Lobakin <aleksander.lobakin@intel.com> · 2024-09-04
Re: [PATCH bpf-next 0/9] bpf: cpumap: enable GRO for XDP_PASS frames · Jakub Kicinski <kuba@kernel.org> · 2024-09-04

From: Jakub Kicinski <kuba@kernel.org>
Date: 2024-09-06 00:20:31
Also in: bpf, lkml

On Thu, 5 Sep 2024 19:01:42 +0200 Lorenzo Bianconi wrote:

In particular, the cpumap kthread pinned on cpu 'n' can schedule the
backlog NAPI associated to cpu 'n'. However according to my understanding
it seems the backlog NAPI APIs (in process_backlog()) do not support GRO,
right? Am I missing something?

I meant to use the struct directly, not to schedule it. All you need
is GRO - feed it packets, flush it. 
But maybe you can avoid the netdev allocation and patch 3 in other ways.
Using backlog NAPI was just the first thing that came to mind.

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help