xdp: Cpumap redirect use frame_sz and increase skb_tailroom

Knowing the memory size backing the packet/xdp_frame data area, and
knowing it already have reserved room for skb_shared_info, simplifies
using build_skb significantly.

With this change we no-longer lie about the SKB truesize, but more
importantly a significant larger skb_tailroom is now provided, e.g. when
drivers uses a full PAGE_SIZE. This extra tailroom (in linear area) can be
used by the network stack when coalescing SKBs (e.g. in skb_try_coalesce,
see TCP cases where tcp_queue_rcv() can 'eat' skb).

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/158945337822.97035.13557959180460986059.stgit@firesoul
This commit is contained in:
Jesper Dangaard Brouer 2020-05-14 12:49:38 +02:00 committed by Alexei Starovoitov
parent 34cc0b338a
commit db612f749e

View File

@ -162,25 +162,10 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
/* Part of headroom was reserved to xdpf */ /* Part of headroom was reserved to xdpf */
hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom;
/* build_skb need to place skb_shared_info after SKB end, and /* Memory size backing xdp_frame data already have reserved
* also want to know the memory "truesize". Thus, need to * room for build_skb to place skb_shared_info in tailroom.
* know the memory frame size backing xdp_buff.
*
* XDP was designed to have PAGE_SIZE frames, but this
* assumption is not longer true with ixgbe and i40e. It
* would be preferred to set frame_size to 2048 or 4096
* depending on the driver.
* frame_size = 2048;
* frame_len = frame_size - sizeof(*xdp_frame);
*
* Instead, with info avail, skb_shared_info in placed after
* packet len. This, unfortunately fakes the truesize.
* Another disadvantage of this approach, the skb_shared_info
* is not at a fixed memory location, with mixed length
* packets, which is bad for cache-line hotness.
*/ */
frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) + frame_size = xdpf->frame_sz;
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
pkt_data_start = xdpf->data - hard_start_headroom; pkt_data_start = xdpf->data - hard_start_headroom;
skb = build_skb_around(skb, pkt_data_start, frame_size); skb = build_skb_around(skb, pkt_data_start, frame_size);