Introduce xmo_rx_checksum netdev callback in order allow the eBPF program bounded to the device to retrieve the RX checksum result computed by the hw NIC.

Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org --- include/net/xdp.h | 6 ++++++ net/core/xdp.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+)

diff --git a/include/net/xdp.h b/include/net/xdp.h index 6fd294fa6841d59c3d7dc4475e09e731996566b0..481b39976ac8c8d4db2de39055c72ba8d0d511c3 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -581,6 +581,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, NETDEV_XDP_RX_METADATA_VLAN_TAG, \ bpf_xdp_metadata_rx_vlan_tag, \ xmo_rx_vlan_tag) \ + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CHECKSUM, \ + NETDEV_XDP_RX_METADATA_CHECKSUM, \ + bpf_xdp_metadata_rx_checksum, \ + xmo_rx_checksum)

enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, @@ -644,6 +648,8 @@ struct xdp_metadata_ops { enum xdp_rss_hash_type *rss_type); int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci); + int (*xmo_rx_checksum)(const struct xdp_md *ctx, u8 *ip_summed, + u32 *cksum_meta); };

#ifdef CONFIG_NET diff --git a/net/core/xdp.c b/net/core/xdp.c index 9100e160113a9a1e2cb88e7602e85c5f36a9f3b9..3edab2d5e5c7c2013b1ef98c949a83655eb94349 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -961,6 +961,35 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, return -EOPNOTSUPP; }

+/** + * bpf_xdp_metadata_rx_checksum - Read XDP frame RX checksum. + * @ctx: XDP context pointer. + * @ip_summed: Return value pointer indicating checksum result. + * @cksum_meta: Return value pointer indicating checksum result metadata. + * + * In case of success, ``ip_summed`` is set to the RX checksum result. Possible + * values are: + * ``CHECKSUM_NONE`` + * ``CHECKSUM_UNNECESSARY`` + * ``CHECKSUM_COMPLETE`` + * ``CHECKSUM_PARTIAL`` + * + * In case of success, ``cksum_meta`` contains the hw computed checksum value + * for ``CHECKSUM_COMPLETE`` or the ``csum_level`` for + * ``CHECKSUM_UNNECESSARY``. It is set to 0 for ``CHECKSUM_NONE`` and + * ``CHECKSUM_PARTIAL``. + * + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc + * * ``-ENODATA`` : means no RX-timestamp available for this frame + */ +__bpf_kfunc int bpf_xdp_metadata_rx_checksum(const struct xdp_md *ctx, + u8 *ip_summed, u32 *cksum_meta) +{ + return -EOPNOTSUPP; +} + __bpf_kfunc_end_defs();

BTF_KFUNCS_START(xdp_metadata_kfunc_ids)

Implement xmo_rx_checksum callback in ice driver to report RX checksum result to the eBPF program bounded to the NIC.

Tested-by: Jesper Dangaard Brouer hawk@kernel.org Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org --- drivers/net/ethernet/intel/ice/ice_base.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx.h | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 82 +++++++++++++++++++++++++++ 3 files changed, 84 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index c5da8e9cc0a0e5551b340e70628813999059bcfe..e8ec419bdc98cb1f01e3c088698b0c4c0f97748f 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -591,6 +591,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } }

+ ring->pkt_ctx.rxq_flags = ring->flags; xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 2fd8e78178a271c15fc054ef553bd509b1c8f8f3..96a2bb79e5e95fa0b9c6287eb9769bdecf47dec1 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -260,6 +260,7 @@ enum ice_rx_dtype { struct ice_pkt_ctx { u64 cached_phctime; __be16 vlan_proto; + u8 rxq_flags; };

struct ice_xdp_buff { diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 45cfaabc41cbeb9b119a0e95547e012e0df1e188..5327b0389ec1a3708a469fa9986a1e565b20ecf7 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -555,6 +555,87 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, return 0; }

+/** + * ice_xdp_rx_checksum - RX checksum XDP hint handler + * @ctx: XDP buff pointer + * @ip_summed: RX checksum result destination address + * @cksum_meta: XDP RX checksum metadata destination address + * + * Copy RX checksum result (if available) and its metadata to the + * destination address. + */ +static int ice_xdp_rx_checksum(const struct xdp_md *ctx, u8 *ip_summed, + u32 *cksum_meta) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const union ice_32b_rx_flex_desc *rx_desc = xdp_ext->eop_desc; + u16 rx_status0, rx_status1, ptype = ice_get_ptype(rx_desc); + struct libeth_rx_pt decoded = libie_rx_pt_parse(ptype); + bool ipv4, ipv6; + + if (!libeth_rx_pt_has_checksum(xdp_ext->xdp_buff.rxq->dev, decoded)) + goto checksum_none; + + rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); + rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); + if ((xdp_ext->pkt_ctx->rxq_flags & ICE_RX_FLAGS_RING_GCS) && + rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC && + (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP || + decoded.inner_prot == LIBETH_RX_PT_INNER_UDP || + decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) { + const struct ice_32b_rx_flex_desc_nic *desc; + u16 csum; + + desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + *ip_summed = CHECKSUM_COMPLETE; + csum = (__force u16)desc->raw_csum; + *cksum_meta = csum_unfold((__force __sum16)swab16(csum)); + return 0; + } + + /* check if HW has decoded the packet and checksum */ + if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) + goto checksum_none; + + ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; + if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) + goto checksum_none; + + if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S)))) + goto checksum_none; + + ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; + if (ipv6 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S)))) + goto checksum_none; + + /* check for L4 errors and handle packets that were not able to be + * checksummed due to arrival speed + */ + if (rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S)) + goto checksum_none; + + /* check for outer UDP checksum error in tunneled packets */ + if ((rx_status1 & BIT(ICE_RX_FLEX_DESC_STATUS1_NAT_S)) && + (rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S))) + goto checksum_none; + + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. + */ + if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT) + *cksum_meta = 1; + + *ip_summed = CHECKSUM_UNNECESSARY; + return 0; + +checksum_none: + *ip_summed = CHECKSUM_NONE; + *cksum_meta = 0; + + return 0; +} + /** * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler * @ctx: XDP buff pointer @@ -584,4 +665,5 @@ const struct xdp_metadata_ops ice_xdp_md_ops = { .xmo_rx_timestamp = ice_xdp_rx_hw_ts, .xmo_rx_hash = ice_xdp_rx_hash, .xmo_rx_vlan_tag = ice_xdp_rx_vlan_tag, + .xmo_rx_checksum = ice_xdp_rx_checksum, };

Introduce the capability to dump HW rx checksum in xdp_hw_metadat program via bpf_xdp_metadata_rx_checksum() kfunc.

Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org --- .../testing/selftests/bpf/progs/xdp_hw_metadata.c | 7 ++++++ tools/testing/selftests/bpf/xdp_hw_metadata.c | 27 ++++++++++++++++++++++ tools/testing/selftests/bpf/xdp_metadata.h | 10 +++++--- 3 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 330ece2eabdb454da2bb2cbd297d2b2dd6efddc0..dc62d572e3ac6e2ef173b330da515757ea543415 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -110,6 +110,13 @@ int rx(struct xdp_md *ctx) else meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;

+ err = bpf_xdp_metadata_rx_checksum(ctx, &meta->ip_summed, + &meta->cksum_meta); + if (err) + meta->rx_cksum_err = err; + else + meta->hint_valid |= XDP_META_FIELD_CHECKSUM; + __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3d8de0d4c96a7afdf5f60b2fdff73c22b876ce54..5e38aa1b565735c2e55fcf2f7b9e672db1348233 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -219,6 +219,28 @@ static void print_vlan_tci(__u16 tag) printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id); }

+static void print_rx_cksum(__u8 ip_summed, __u32 cksum_meta) +{ + const char *cksum = "CHECKSUM_NONE"; + + switch (ip_summed) { + case CHECKSUM_UNNECESSARY: + cksum = "CHECKSUM_UNNECESSARY"; + break; + case CHECKSUM_COMPLETE: + cksum = "CHECKSUM_COMPLETE"; + break; + case CHECKSUM_PARTIAL: + cksum = "CHECKSUM_PARTIAL"; + break; + case CHECKSUM_NONE: + default: + break; + } + + printf("rx-cksum: %s, csum_meta=0x%x\n", cksum, cksum_meta); +} + static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; @@ -254,6 +276,11 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id) printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n", meta->rx_vlan_tag_err); } + + if (meta->hint_valid & XDP_META_FIELD_CHECKSUM) + print_rx_cksum(meta->ip_summed, meta->cksum_meta); + else + printf("No rx_chsum, err=%d\n", meta->rx_cksum_err); }

static void verify_skb_metadata(int fd) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index f0ef17b328866206b1e63f7d751abeaa78e90932..0fd5e7172fe891275b3b1eb69c51a93a60ae353e 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -28,6 +28,7 @@ enum xdp_meta_field { XDP_META_FIELD_TS = BIT(0), XDP_META_FIELD_RSS = BIT(1), XDP_META_FIELD_VLAN_TAG = BIT(2), + XDP_META_FIELD_CHECKSUM = BIT(3), };

#define CHECKSUM_NONE 0 @@ -53,9 +54,12 @@ struct xdp_meta { }; __s32 rx_vlan_tag_err; }; - struct { - __u8 ip_summed; - __u32 cksum_meta; + union { + struct { + __u8 ip_summed; + __u32 cksum_meta; + }; + __s32 rx_cksum_err; }; enum xdp_meta_field hint_valid; };