Commit 2aad3261 authored by Daniel Borkmann's avatar Daniel Borkmann
Browse files

Merge branch 'bpf-eth-get-headlen' 



Stanislav Fomichev says:

====================
Currently, when eth_get_headlen calls flow dissector, it doesn't pass any
skb. Because we use passed skb to lookup associated networking namespace
to find whether we have a BPF program attached or not, we always use
C-based flow dissector in this case.

The goal of this patch series is to add new networking namespace argument
to the eth_get_headlen and make BPF flow dissector programs be able to
work in the skb-less case.

The series goes like this:
* use new kernel context (struct bpf_flow_dissector) for flow dissector
  programs; this makes it easy to distinguish between skb and no-skb
  case and supports calling BPF flow dissector on a chunk of raw data
* convert BPF_PROG_TEST_RUN to use raw data
* plumb network namespace into __skb_flow_dissect from all callers
* handle no-skb case in __skb_flow_dissect
* update eth_get_headlen to include net namespace argument and
  convert all existing users
* add selftest to make sure bpf_skb_load_bytes is not allowed in
  the no-skb mode
* extend test_progs to exercise skb-less flow dissection as well
* stop adjusting nhoff/thoff by ETH_HLEN in BPF_PROG_TEST_RUN

v6:
* more suggestions by Alexei:
  * eth_get_headlen now takes net dev, not net namespace
  * test skb-less case via tun eth_get_headlen
* fix return errors in bpf_flow_load
* don't adjust nhoff/thoff by ETH_HLEN

v5:
* API changes have been submitted via bpf/stable tree

v4:
* prohibit access to vlan fields as well (otherwise, inconsistent
  between skb/skb-less cases)
* drop extra unneeded check for skb->vlan_present in bpf_flow.c

v3:
* new kernel xdp_buff-like context per Alexei suggestion
* drop skb_net helper
* properly clamp flow_keys->nhoff

v2:
* moved temporary skb from stack into percpu (avoids memset of ~200 bytes
  per packet)
* tightened down access to __sk_buff fields from flow dissector programs to
  avoid touching shinfo (whitelist only relevant fields)
* addressed suggestions from Willem
====================

Acked-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarWillem de Bruijn <willemb@google.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parents 7e6e185c 02ee0658

drivers/net/ethernet/aquantia/atlantic/aq_ring.c

+2 −1
Original line number Diff line number Diff line
@@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, 


			hdr_len = buff->len;

			if (hdr_len > AQ_CFG_RX_HDR_SIZE)

				hdr_len = eth_get_headlen(aq_buf_vaddr(&buff->rxdata),

				hdr_len = eth_get_headlen(skb->dev,

							  aq_buf_vaddr(&buff->rxdata),

							  AQ_CFG_RX_HDR_SIZE);



			memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),

drivers/net/ethernet/broadcom/bnxt/bnxt.c

+1 −1
Original line number Diff line number Diff line
@@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, 
			     DMA_ATTR_WEAK_ORDERING);



	if (unlikely(!payload))

		payload = eth_get_headlen(data_ptr, len);

		payload = eth_get_headlen(bp->dev, data_ptr, len);



	skb = napi_alloc_skb(&rxr->bnapi->napi, payload);

	if (!skb) {

drivers/net/ethernet/hisilicon/hns/hns_enet.c

+1 −1
Original line number Diff line number Diff line
@@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, 
	} else {

		ring->stats.seg_pkt_cnt++;



		pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE);

		pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE);

		memcpy(__skb_put(skb, pull_len), va,

		       ALIGN(pull_len, sizeof(long)));

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

+1 −1
Original line number Diff line number Diff line
@@ -2580,7 +2580,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length, 
	ring->stats.seg_pkt_cnt++;

	u64_stats_update_end(&ring->syncp);



	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);

	ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE);

	__skb_put(skb, ring->pull_len);

	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,

			    desc_cb);

drivers/net/ethernet/intel/fm10k/fm10k_main.c

+1 −1
Original line number Diff line number Diff line
@@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, 
	/* we need the header to contain the greater of either ETH_HLEN or

	 * 60 bytes if the skb->len is less than 60 for skb_pad.

	 */

	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);

	pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);



	/* align pull length to size of long to optimize memcpy performance */

	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));