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: 1. restrict access to a limited set of __sk_buff fields from flow dissector programs; in eth_get_headlen context, they don't make sense (for skb-context, they are also not relevant for flow dissector) 2. switch kernel context to new xdp_buff-like structure (struct bpf_flow_dissector) for flow dissector program 3. minor fix for nhoff clamping; doesn't affect anything besides tests 4. convert flow dissector BPF_PROG_TEST_RUN to skb-less mode to show that it works 5. add new optional network namespace argument to __skb_flow_dissect and plumb through the callers 6. handle __skb_flow_dissect with skb == NULL 7. add new net namespace argument to eth_get_headlen and adjust all users 8. add selftest that makes sure bpf_skb_load_bytes is prohibited in skb-less context v3: * new kernel xdp_buff-like context per Alexey 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 Stanislav Fomichev (8): flow_dissector: allow access only to a subset of __sk_buff fields flow_dissector: switch kernel context to struct bpf_flow_dissector flow_dissector: fix clamping of BPF flow_keys for non-zero nhoff bpf: when doing BPF_PROG_TEST_RUN for flow dissector use no-skb mode net: plumb network namespace into __skb_flow_dissect flow_dissector: handle no-skb use case net: pass net argument to the eth_get_headlen selftests/bpf: add flow dissector bpf_skb_load_bytes helper test drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 3 +- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 3 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 3 +- drivers/net/ethernet/intel/igc/igc_main.c | 3 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en_tx.c | 3 +- drivers/net/tun.c | 3 +- include/linux/etherdevice.h | 2 +- include/linux/skbuff.h | 23 ++- include/net/flow_dissector.h | 11 ++ include/net/sch_generic.h | 11 +- net/bpf/test_run.c | 51 ++---- net/core/filter.c | 151 +++++++++++++----- net/core/flow_dissector.c | 85 +++++----- net/ethernet/eth.c | 8 +- .../prog_tests/flow_dissector_load_bytes.c | 48 ++++++ 22 files changed, 280 insertions(+), 145 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c -- 2.21.0.392.gf8f6787159e-goog
