diff options
| -rw-r--r-- | drivers/net/ethernet/cavium/liquidio/octeon_console.c | 7 | ||||
| -rw-r--r-- | drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 11 | ||||
| -rw-r--r-- | drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 3 | ||||
| -rw-r--r-- | drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 3 | ||||
| -rw-r--r-- | drivers/net/tap.c | 10 | ||||
| -rw-r--r-- | drivers/net/tun.c | 8 | ||||
| -rw-r--r-- | drivers/net/virtio_net.c | 19 | ||||
| -rw-r--r-- | include/linux/virtio_net.h | 9 | ||||
| -rw-r--r-- | include/net/netfilter/nf_nat.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/if_tun.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/virtio_net.h | 4 | ||||
| -rw-r--r-- | net/ipv4/udp_offload.c | 3 | ||||
| -rw-r--r-- | net/ipv6/udp_offload.c | 3 | ||||
| -rw-r--r-- | net/netfilter/Kconfig | 3 | ||||
| -rw-r--r-- | net/netfilter/Makefile | 1 | ||||
| -rw-r--r-- | net/netfilter/nf_nat_ovs.c | 135 | ||||
| -rw-r--r-- | net/openvswitch/Kconfig | 1 | ||||
| -rw-r--r-- | net/openvswitch/conntrack.c | 146 | ||||
| -rw-r--r-- | net/sched/Kconfig | 1 | ||||
| -rw-r--r-- | net/sched/act_ct.c | 136 |
20 files changed, 229 insertions, 280 deletions
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index 28feabec8fbb..67c3570f875f 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -247,8 +247,7 @@ static const struct cvmx_bootmem_named_block_desc struct cvmx_bootmem_named_block_desc, size)); - strncpy(desc->name, name, sizeof(desc->name)); - desc->name[sizeof(desc->name) - 1] = 0; + strscpy(desc->name, name, sizeof(desc->name)); return &oct->bootmem_named_block_desc; } else { return NULL; @@ -471,8 +470,8 @@ static void output_console_line(struct octeon_device *oct, if (line != &console_buffer[bytes_read]) { console_buffer[bytes_read] = '\0'; len = strlen(console->leftover); - strncpy(&console->leftover[len], line, - sizeof(console->leftover) - len); + strscpy(&console->leftover[len], line, + sizeof(console->leftover) - len + 1); } } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 54faf0f2d1d8..b54f3706fb97 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -644,18 +644,15 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, { struct hns_nic_priv *priv = netdev_priv(net_dev); - strncpy(drvinfo->version, HNAE_DRIVER_VERSION, + strscpy(drvinfo->version, HNAE_DRIVER_VERSION, sizeof(drvinfo->version)); - drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; - strncpy(drvinfo->driver, HNAE_DRIVER_NAME, sizeof(drvinfo->driver)); - drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; + strscpy(drvinfo->driver, HNAE_DRIVER_NAME, sizeof(drvinfo->driver)); - strncpy(drvinfo->bus_info, priv->dev->bus->name, + strscpy(drvinfo->bus_info, priv->dev->bus->name, sizeof(drvinfo->bus_info)); - drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; - strncpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); + strscpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); drvinfo->eedump_len = 0; } diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 9063e2e22cd5..8073d7a90a26 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -552,8 +552,7 @@ myri10ge_validate_firmware(struct myri10ge_priv *mgp, } /* save firmware version for ethtool */ - strncpy(mgp->fw_version, hdr->version, sizeof(mgp->fw_version)); - mgp->fw_version[sizeof(mgp->fw_version) - 1] = '\0'; + strscpy(mgp->fw_version, hdr->version, sizeof(mgp->fw_version)); sscanf(mgp->fw_version, "%d.%d.%d", &mgp->fw_ver_major, &mgp->fw_ver_minor, &mgp->fw_ver_tiny); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 773e415cc2de..2cfb18cef1d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -926,6 +926,9 @@ static int tc_setup_taprio(struct stmmac_priv *priv, int i, ret = 0; u64 ctr; + if (qopt->base_time < 0) + return -ERANGE; + if (!priv->dma_cap.estsel) return -EOPNOTSUPP; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 9e75ed3f08ce..a2be1994b389 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -957,6 +957,10 @@ static int set_offload(struct tap_queue *q, unsigned long arg) if (arg & TUN_F_TSO6) feature_mask |= NETIF_F_TSO6; } + + /* TODO: for now USO4 and USO6 should work simultaneously */ + if ((arg & (TUN_F_USO4 | TUN_F_USO6)) == (TUN_F_USO4 | TUN_F_USO6)) + features |= NETIF_F_GSO_UDP_L4; } /* tun/tap driver inverts the usage for TSO offloads, where @@ -967,7 +971,8 @@ static int set_offload(struct tap_queue *q, unsigned long arg) * When user space turns off TSO, we turn off GSO/LRO so that * user-space will not receive TSO frames. */ - if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6)) + if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6) || + (feature_mask & (TUN_F_USO4 | TUN_F_USO6)) == (TUN_F_USO4 | TUN_F_USO6)) features |= RX_OFFLOADS; else features &= ~RX_OFFLOADS; @@ -1091,7 +1096,8 @@ static long tap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO)) + TUN_F_TSO_ECN | TUN_F_UFO | + TUN_F_USO4 | TUN_F_USO6)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b4baa2001a63..a7d17c680f4a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -185,7 +185,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6) + NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4) int align; int vnet_hdr_sz; @@ -2878,6 +2878,12 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) } arg &= ~TUN_F_UFO; + + /* TODO: for now USO4 and USO6 should work simultaneously */ + if (arg & TUN_F_USO4 && arg & TUN_F_USO6) { + features |= NETIF_F_GSO_UDP_L4; + arg &= ~(TUN_F_USO4 | TUN_F_USO6); + } } /* This gives the user a way to test for new features in future by diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 19eee0655b99..7723b2a49d8e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -60,13 +60,17 @@ static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO6, VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, - VIRTIO_NET_F_GUEST_CSUM + VIRTIO_NET_F_GUEST_CSUM, + VIRTIO_NET_F_GUEST_USO4, + VIRTIO_NET_F_GUEST_USO6 }; #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ - (1ULL << VIRTIO_NET_F_GUEST_UFO)) + (1ULL << VIRTIO_NET_F_GUEST_UFO) | \ + (1ULL << VIRTIO_NET_F_GUEST_USO4) | \ + (1ULL << VIRTIO_NET_F_GUEST_USO6)) struct virtnet_stat_desc { char desc[ETH_GSTRING_LEN]; @@ -3085,7 +3089,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || - virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))) { + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM) || + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) || + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6))) { NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing GRO_HW/CSUM, disable GRO_HW/CSUM first"); return -EOPNOTSUPP; } @@ -3690,7 +3696,9 @@ static bool virtnet_check_guest_gso(const struct virtnet_info *vi) return virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || - virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO); + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || + (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) && + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6)); } static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu) @@ -3759,6 +3767,8 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; + if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_USO)) + dev->hw_features |= NETIF_F_GSO_UDP_L4; dev->features |= NETIF_F_GSO_ROBUST; @@ -4036,6 +4046,7 @@ static struct virtio_device_id id_table[] = { VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \ VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \ VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \ + VIRTIO_NET_F_HOST_USO, VIRTIO_NET_F_GUEST_USO4, VIRTIO_NET_F_GUEST_USO6, \ VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index a960de68ac69..bdf8de2cdd93 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -15,6 +15,7 @@ static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: + case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: @@ -31,6 +32,7 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: + case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: @@ -69,6 +71,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; + case VIRTIO_NET_HDR_GSO_UDP_L4: + gso_type = SKB_GSO_UDP_L4; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); + break; default: return -EINVAL; } @@ -182,6 +189,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP_L4) + hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index e9eb01e99d2f..9877f064548a 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -104,6 +104,10 @@ unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, bool commit); + static inline int nf_nat_initialized(const struct nf_conn *ct, enum nf_nat_manip_type manip) { diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index b6d7b868f290..287cdc81c939 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -90,6 +90,8 @@ #define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */ #define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */ #define TUN_F_UFO 0x10 /* I can handle UFO packets */ +#define TUN_F_USO4 0x20 /* I can handle USO for IPv4 packets */ +#define TUN_F_USO6 0x40 /* I can handle USO for IPv6 packets */ /* Protocol info prepended to the packets (when IFF_NO_PI is not set) */ #define TUN_PKT_STRIP 0x0001 diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 6cb842ea8979..b4062bed186a 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -57,6 +57,9 @@ * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ +#define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ +#define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */ +#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO in. */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -130,6 +133,7 @@ struct virtio_net_hdr_v1 { #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ +#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */ #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ __u8 gso_type; __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aedde65e2268..1f01e15ca24f 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -387,7 +387,8 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index e0e10f6bcdc1..c39c1e32f980 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,7 +42,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0846bd75b1da..f71b41c7ce2f 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -459,6 +459,9 @@ config NF_NAT_REDIRECT config NF_NAT_MASQUERADE bool +config NF_NAT_OVS + bool + config NETFILTER_SYNPROXY tristate diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1d4db1943936..3754eb06fb41 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -59,6 +59,7 @@ obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o obj-$(CONFIG_NF_NAT) += nf_nat.o nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o +nf_nat-$(CONFIG_NF_NAT_OVS) += nf_nat_ovs.o ifeq ($(CONFIG_NF_NAT),m) nf_nat-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_nat_bpf.o diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c new file mode 100644 index 000000000000..551abd2da614 --- /dev/null +++ b/net/netfilter/nf_nat_ovs.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Support nat functions for openvswitch and used by OVS and TC conntrack. */ + +#include <net/netfilter/nf_nat.h> + +/* Modelled after nf_nat_ipv[46]_fn(). + * range is only used for new, uninitialized NAT state. + * Returns either NF_ACCEPT or NF_DROP. + */ +static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, + enum nf_nat_manip_type maniptype) +{ + __be16 proto = skb_protocol(skb, true); + int hooknum, err = NF_ACCEPT; + + /* See HOOK2MANIP(). */ + if (maniptype == NF_NAT_MANIP_SRC) + hooknum = NF_INET_LOCAL_IN; /* Source NAT */ + else + hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + if (proto == htons(ETH_P_IP) && + ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + hooknum)) + err = NF_DROP; + goto out; + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { + __be16 frag_off; + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + int hdrlen = ipv6_skip_exthdr(skb, + sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, + ctinfo, + hooknum, + hdrlen)) + err = NF_DROP; + goto out; + } + } + /* Non-ICMP, fall thru to initialize if needed. */ + fallthrough; + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + /* Initialize according to the NAT action. */ + err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) + /* Action is set up to establish a new + * mapping. + */ + ? nf_nat_setup_info(ct, range, maniptype) + : nf_nat_alloc_null_binding(ct, hooknum); + if (err != NF_ACCEPT) + goto out; + } + break; + + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + break; + + default: + err = NF_DROP; + goto out; + } + + err = nf_nat_packet(ct, ctinfo, hooknum, skb); + if (err == NF_ACCEPT) + *action |= BIT(maniptype); +out: + return err; +} + +int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, bool commit) +{ + enum nf_nat_manip_type maniptype; + int err, ct_action = *action; + + *action = 0; + + /* Add NAT extension if not confirmed yet. */ + if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) + return NF_DROP; /* Can't NAT. */ + + if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) && + (ctinfo != IP_CT_RELATED || commit)) { + /* NAT an established or related connection like before. */ + if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) + /* This is the REPLY direction for a connection + * for which NAT was applied in the forward + * direction. Do the reverse NAT. + */ + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; + else + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; + } else if (ct_action & BIT(NF_NAT_MANIP_SRC)) { + maniptype = NF_NAT_MANIP_SRC; + } else if (ct_action & BIT(NF_NAT_MANIP_DST)) { + maniptype = NF_NAT_MANIP_DST; + } else { + return NF_ACCEPT; + } + + err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = nf_ct_nat_execute(skb, ct, ctinfo, action, NULL, + NF_NAT_MANIP_SRC); + } + } + return err; +} +EXPORT_SYMBOL_GPL(nf_ct_nat); diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 15bd287f5cbd..747d537a3f06 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -15,6 +15,7 @@ config OPENVSWITCH select NET_MPLS_GSO select DST_CACHE select NET_NSH + select NF_NAT_OVS if NF_NAT help Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d78f0fc4337d..c8b137649ca4 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -726,147 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key, } } -/* Modelled after nf_nat_ipv[46]_fn(). - * range is only used for new, uninitialized NAT state. - * Returns either NF_ACCEPT or NF_DROP. - */ -static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype, struct sw_flow_key *key) -{ - int hooknum, nh_off, err = NF_ACCEPT; - - nh_off = skb_network_offset(skb); - skb_pull_rcsum(skb, nh_off); - - /* See HOOK2MANIP(). */ - if (maniptype == NF_NAT_MANIP_SRC) - hooknum = NF_INET_LOCAL_IN; /* Source NAT */ - else - hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - if (IS_ENABLED(CONFIG_NF_NAT) && - skb->protocol == htons(ETH_P_IP) && - ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - hooknum)) - err = NF_DROP; - goto push; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { - __be16 frag_off; - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - int hdrlen = ipv6_skip_exthdr(skb, - sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, - ctinfo, - hooknum, - hdrlen)) - err = NF_DROP; - goto push; - } - } - /* Non-ICMP, fall thru to initialize if needed. */ - fallthrough; - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - /* Initialize according to the NAT action. */ - err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) - /* Action is set up to establish a new - * mapping. - */ - ? nf_nat_setup_info(ct, range, maniptype) - : nf_nat_alloc_null_binding(ct, hooknum); - if (err != NF_ACCEPT) - goto push; - } - break; - - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - - default: - err = NF_DROP; - goto push; - } - - err = nf_nat_packet(ct, ctinfo, hooknum, skb); -push: - skb_push_rcsum(skb, nh_off); - - /* Update the flow key if NAT successful. */ - if (err == NF_ACCEPT) - ovs_nat_update_key(key, skb, maniptype); - - return err; -} - /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - enum nf_nat_manip_type maniptype; - int err; + int err, action = 0; - /* Add NAT extension if not confirmed yet. */ - if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) - return NF_ACCEPT; /* Can't NAT. */ + if (!(info->nat & OVS_CT_NAT)) + return NF_ACCEPT; + if (info->nat & OVS_CT_SRC_NAT) + action |= BIT(NF_NAT_MANIP_SRC); + if (info->nat & OVS_CT_DST_NAT) + action |= BIT(NF_NAT_MANIP_DST); - /* Determine NAT type. - * Check if the NAT type can be deduced from the tracked connection. - * Make sure new expected connections (IP_CT_RELATED) are NATted only - * when committing. - */ - if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW && - ct->status & IPS_NAT_MASK && - (ctinfo != IP_CT_RELATED || info->commit)) { - /* NAT an established or related connection like before. */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) - /* This is the REPLY direction for a connection - * for which NAT was applied in the forward - * direction. Do the reverse NAT. - */ - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; - else - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; - } else if (info->nat & OVS_CT_SRC_NAT) { - maniptype = NF_NAT_MANIP_SRC; - } else if (info->nat & OVS_CT_DST_NAT) { - maniptype = NF_NAT_MANIP_DST; - } else { - return NF_ACCEPT; /* Connection is not NATed. */ - } - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key); - - if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { - if (ct->status & IPS_SRC_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype, key); - } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { - err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, - NF_NAT_MANIP_SRC, key); - } - } + err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit); + + if (action & BIT(NF_NAT_MANIP_SRC)) + ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC); + if (action & BIT(NF_NAT_MANIP_DST)) + ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST); return err; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 4662a6ce8a7e..777d6b50505c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -977,6 +977,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_NAT_OVS if NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f6df0168c91f..0ca2bb8ed026 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -864,90 +864,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head) tcf_ct_params_free(params); } -#if IS_ENABLED(CONFIG_NF_NAT) -/* Modelled after nf_nat_ipv[46]_fn(). - * range is only used for new, uninitialized NAT state. - * Returns either NF_ACCEPT or NF_DROP. - */ -static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype) -{ - __be16 proto = skb_protocol(skb, true); - int hooknum, err = NF_ACCEPT; - - /* See HOOK2MANIP(). */ - if (maniptype == NF_NAT_MANIP_SRC) - hooknum = NF_INET_LOCAL_IN; /* Source NAT */ - else - hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - if (proto == htons(ETH_P_IP) && - ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - hooknum)) - err = NF_DROP; - goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { - __be16 frag_off; - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - int hdrlen = ipv6_skip_exthdr(skb, - sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, - ctinfo, - hooknum, - hdrlen)) - err = NF_DROP; - goto out; - } - } - /* Non-ICMP, fall thru to initialize if needed. */ - fallthrough; - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - /* Initialize according to the NAT action. */ - err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) - /* Action is set up to establish a new - * mapping. - */ - ? nf_nat_setup_info(ct, range, maniptype) - : nf_nat_alloc_null_binding(ct, hooknum); - if (err != NF_ACCEPT) - goto out; - } - break; - - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - - default: - err = NF_DROP; - goto out; - } - - err = nf_nat_packet(ct, ctinfo, hooknum, skb); - if (err == NF_ACCEPT) { - if (maniptype == NF_NAT_MANIP_SRC) - tc_skb_cb(skb)->post_ct_snat = 1; - if (maniptype == NF_NAT_MANIP_DST) - tc_skb_cb(skb)->post_ct_dnat = 1; - } -out: - return err; -} -#endif /* CONFIG_NF_NAT */ - static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) @@ -987,52 +903,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) - int err; - enum nf_nat_manip_type maniptype; + int err, action = 0; if (!(ct_action & TCA_CT_ACT_NAT)) return NF_ACCEPT; + if (ct_action & TCA_CT_ACT_NAT_SRC) + action |= BIT(NF_NAT_MANIP_SRC); + if (ct_action & TCA_CT_ACT_NAT_DST) + action |= BIT(NF_NAT_MANIP_DST); - /* Add NAT extension if not confirmed yet. */ - if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) - return NF_DROP; /* Can't NAT. */ - - if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) && - (ctinfo != IP_CT_RELATED || commit)) { - /* NAT an established or related connection like before. */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) - /* This is the REPLY direction for a connection - * for which NAT was applied in the forward - * direction. Do the reverse NAT. - */ - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; - else - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; - } else if (ct_action & TCA_CT_ACT_NAT_SRC) { - maniptype = NF_NAT_MANIP_SRC; - } else if (ct_action & TCA_CT_ACT_NAT_DST) { - maniptype = NF_NAT_MANIP_DST; - } else { - return NF_ACCEPT; - } + err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); + + if (action & BIT(NF_NAT_MANIP_SRC)) + tc_skb_cb(skb)->post_ct_snat = 1; + if (action & BIT(NF_NAT_MANIP_DST)) + tc_skb_cb(skb)->post_ct_dnat = 1; - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { - if (ct-&g |