diff options
30 files changed, 155 insertions, 79 deletions
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 883e47c5b1a7..286f0341bdf8 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1929,7 +1929,8 @@ static inline int macb_clear_csum(struct sk_buff *skb) static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) { - bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb); + bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || + skb_is_nonlinear(*skb); int padlen = ETH_ZLEN - (*skb)->len; int headroom = skb_headroom(*skb); int tailroom = skb_tailroom(*skb); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 832a2175636d..c527f4ee1d3a 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -456,6 +456,12 @@ struct bufdesc_ex { */ #define FEC_QUIRK_HAS_FRREG (1 << 16) +/* Some FEC hardware blocks need the MMFR cleared at setup time to avoid + * the generation of an MII event. This must be avoided in the older + * FEC blocks where it will stop MII events being generated. + */ +#define FEC_QUIRK_CLEAR_SETUP_MII (1 << 17) + struct bufdesc_prop { int qid; /* Address of Rx and Tx buffers */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8f7eca1e7716..d7919555250d 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -100,14 +100,14 @@ static const struct fec_devinfo fec_imx27_info = { static const struct fec_devinfo fec_imx28_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME | FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_FRREG, + FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_imx6q_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 | - FEC_QUIRK_HAS_RACC, + FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_mvf600_info = { @@ -119,7 +119,8 @@ static const struct fec_devinfo fec_imx6x_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | - FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE, + FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | + FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_imx6ul_info = { @@ -127,7 +128,7 @@ static const struct fec_devinfo fec_imx6ul_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_COALESCE, + FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII, }; static struct platform_device_id fec_devtype[] = { @@ -2134,15 +2135,17 @@ static int fec_enet_mii_init(struct platform_device *pdev) if (suppress_preamble) fep->phy_speed |= BIT(7); - /* Clear MMFR to avoid to generate MII event by writing MSCR. - * MII event generation condition: - * - writing MSCR: - * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero & - * mscr_reg_data_in[7:0] != 0 - * - writing MMFR: - * - mscr[7:0]_not_zero - */ - writel(0, fep->hwp + FEC_MII_DATA); + if (fep->quirks & FEC_QUIRK_CLEAR_SETUP_MII) { + /* Clear MMFR to avoid to generate MII event by writing MSCR. + * MII event generation condition: + * - writing MSCR: + * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero & + * mscr_reg_data_in[7:0] != 0 + * - writing MMFR: + * - mscr[7:0]_not_zero + */ + writel(0, fep->hwp + FEC_MII_DATA); + } writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 41dd3d0f3452..d391a45cebb6 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1829,20 +1829,12 @@ static netdev_tx_t gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) fcb_len = GMAC_FCB_LEN + GMAC_TXPAL_LEN; /* make space for additional header when fcb is needed */ - if (fcb_len && unlikely(skb_headroom(skb) < fcb_len)) { - struct sk_buff *skb_new; - - skb_new = skb_realloc_headroom(skb, fcb_len); - if (!skb_new) { + if (fcb_len) { + if (unlikely(skb_cow_head(skb, fcb_len))) { dev->stats.tx_errors++; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - - if (skb->sk) - skb_set_owner_w(skb_new, skb->sk); - dev_consume_skb_any(skb); - skb = skb_new; } /* total number of fragments in the SKB */ @@ -3380,7 +3372,7 @@ static int gfar_probe(struct platform_device *ofdev) if (dev->features & NETIF_F_IP_CSUM || priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) - dev->needed_headroom = GMAC_FCB_LEN; + dev->needed_headroom = GMAC_FCB_LEN + GMAC_TXPAL_LEN; /* Initializing some of the rx/tx queue level parameters */ for (i = 0; i < priv->num_tx_queues; i++) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index b6e5e3e36b63..81ee0a071b4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -625,13 +625,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (ret) return ret; - if (plat->eee_usecs_rate > 0) { - u32 tx_lpi_usec; - - tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1; - writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER); - } - ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) return ret; @@ -641,6 +634,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, res.wol_irq = pci_irq_vector(pdev, 0); res.irq = pci_irq_vector(pdev, 0); + if (plat->eee_usecs_rate > 0) { + u32 tx_lpi_usec; + + tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1; + writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER); + } + ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) { pci_free_irq_vectors(pdev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 220626a8d499..d833908b660a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4757,6 +4757,7 @@ static void stmmac_napi_add(struct net_device *dev) ch->priv_data = priv; ch->index = queue; + spin_lock_init(&ch->lock); if (queue < priv->plat->rx_queues_to_use) { netif_napi_add(dev, &ch->rx_napi, stmmac_napi_poll_rx, diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 89016d08f6a2..f6267e2883f2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -24,6 +24,12 @@ struct nfnl_callback { const u_int16_t attr_count; /* number of nlattr's */ }; +enum nfnl_abort_action { + NFNL_ABORT_NONE = 0, + NFNL_ABORT_AUTOLOAD, + NFNL_ABORT_VALIDATE, +}; + struct nfnetlink_subsystem { const char *name; __u8 subsys_id; /* nfnetlink subsystem ID */ @@ -31,7 +37,8 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); - int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); + int (*abort)(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 082e2c41b7ff..5b70ca868bb1 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -16,7 +16,7 @@ struct ip_rt_info { u_int32_t mark; }; -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type); struct nf_queue_entry; diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 9b67394471e1..48314ade1506 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -42,7 +42,7 @@ struct nf_ipv6_ops { #if IS_MODULE(CONFIG_IPV6) int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); - int (*route_me_harder)(struct net *net, struct sk_buff *skb); + int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*dev_get_saddr)(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); @@ -143,9 +143,9 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, #endif } -int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb); -static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) +static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb) { #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); @@ -153,9 +153,9 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!v6_ops) return -EHOSTUNREACH; - return v6_ops->route_me_harder(net, skb); + return v6_ops->route_me_harder(net, sk, skb); #elif IS_BUILTIN(CONFIG_IPV6) - return ip6_route_me_harder(net, skb); + return ip6_route_me_harder(net, sk, skb); #else return -EHOSTUNREACH; #endif diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index c1661febc2dc..0564fd7ccde4 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -138,6 +138,7 @@ struct icmp6hdr { #define ICMPV6_HDR_FIELD 0 #define ICMPV6_UNK_NEXTHDR 1 #define ICMPV6_UNK_OPTION 2 +#define ICMPV6_HDR_INCOMP 3 /* * constants for (set|get)sockopt diff --git a/net/atm/lec.c b/net/atm/lec.c index dbabb65d8b67..7226c784dbe0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -954,9 +954,8 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct lec_state *state = seq->private; - v = lec_get_idx(state, 1); - *pos += !!PTR_ERR(v); - return v; + ++*pos; + return lec_get_idx(state, 1); } static int lec_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 8b04d1dcfec4..ee65c9225178 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -608,9 +608,6 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } - if (!df && skb->protocol == htons(ETH_P_IP)) - df = inner_iph->frag_off & htons(IP_DF); - headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index a058213b77a7..7c841037c533 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,17 +17,19 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - const struct sock *sk = skb_to_full_sk(skb); - __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0; + __u8 flags; struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; + sk = sk_to_full_sk(sk); + flags = sk ? inet_sk_flowi_flags(sk) : 0; + if (addr_type == RTN_UNSPEC) addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index f703a717ab1d..833079589273 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 9dcfa4e461b6..93b07739807b 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -145,7 +145,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; niph = ip_hdr(nskb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index ec448b71bf9a..8956144ea65e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb) tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); - if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) + + /* Based on RFC 8200, Section 4.5 Fragment Header, return + * false if this is a fragment packet with no icmp header info. + */ + if (!tp && frag_off != 0) + return false; + else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a0217e5bf3bc..648db3fe508f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1271,6 +1271,8 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; + skb_set_inner_ipproto(skb, proto); + err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1280,8 +1282,6 @@ route_lookup: ipv6_push_frag_opts(skb, &opt.ops, &proto); } - skb_set_inner_ipproto(skb, proto); - skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 6d0e942d082d..ab9a279dd6d4 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -20,10 +20,10 @@ #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include "../bridge/br_private.h" -int ip6_route_me_harder(struct net *net, struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct sock *sk = sk_to_full_sk(skb->sk); + struct sock *sk = sk_to_full_sk(sk_partial); unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & @@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(entry->state.net, skb); + return ip6_route_me_harder(entry->state.net, entry->state.sk, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 1a2748611e00..cee74803d7a1 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 1f5d4d196dcc..c8cf1bbad74a 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -42,6 +42,8 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <net/sock.h> #include <net/snmp.h> @@ -322,7 +324,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - int iif; + __be16 frag_off; + int iif, offset; + u8 nexthdr; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -351,6 +355,33 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } + /* RFC 8200, Section 4.5 Fragment Header: + * If the first fragment does not include all headers through an + * Upper-Layer header, then that fragment should be discarded and + * an ICMP Parameter Problem, Code 3, message should be sent to + * the source of the fragment, with the Pointer field set to zero. + */ + nexthdr = hdr->nexthdr; + offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off); + if (offset >= 0) { + /* Check some common protocols' header */ + if (nexthdr == IPPROTO_TCP) + offset += sizeof(struct tcphdr); + else if (nexthdr == IPPROTO_UDP) + offset += sizeof(struct udphdr); + else if (nexthdr == IPPROTO_ICMPV6) + offset += sizeof(struct icmp6hdr); + else + offset += 1; + + if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); + return -1; + } + } + iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6f35832f0de3..7cff6e5e7445 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -637,13 +637,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, if (SET_WITH_COUNTER(set)) { struct ip_set_counter *counter = ext_counter(data, set); + ip_set_update_counter(counter, ext, flags); + if (flags & IPSET_FLAG_MATCH_COUNTERS && !(ip_set_match_counter(ip_set_get_packets(counter), mext->packets, mext->packets_op) && ip_set_match_counter(ip_set_get_bytes(counter), mext->bytes, mext->bytes_op))) return false; - ip_set_update_counter(counter, ext, flags); } if (SET_WITH_SKBINFO(set)) ip_set_get_skbinfo(ext_skbinfo(data, set), diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index cc3c275934f4..c0b8215ab3d4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(ipvs->net, skb) != 0) + ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 59151dc07fdc..e87b6bd6b3cd 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9cca35d22927..d7d34a62d3bf 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 65cb8e3c13d9..0f58e98542be 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7137,7 +7137,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, GFP_KERNEL); kfree(buf); - if (ctx->report && + if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; @@ -7259,7 +7259,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq, AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL); - if (nlmsg_report(nlh) && + if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -8053,12 +8053,16 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net, bool autoload) +static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_hook *hook; + if (action == NFNL_ABORT_VALIDATE && + nf_tables_validate(net) < 0) + return -EAGAIN; + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, list) { switch (trans->msg_type) { @@ -8190,7 +8194,7 @@ static int __nf_tables_abort(struct net *net, bool autoload) nf_tables_abort_release(trans); } - if (autoload) + if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); @@ -8203,9 +8207,10 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action) { - int ret = __nf_tables_abort(net, autoload); + int ret = __nf_tables_abort(net, action); mutex_unlock(&net->nft.commit_mutex); @@ -8836,7 +8841,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net, false); + __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 2daa1f6ae344..d3df66a39b5e 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -333,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; - +replay_abort: skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); @@ -499,7 +499,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb, true); + ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -510,11 +510,25 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb, false); + ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb, false); + enum nfnl_abort_action abort_action; + + if (status & NFNL_BATCH_FAILURE) + abort_action = NFNL_ABORT_NONE; + else + abort_action = NFNL_ABORT_VALIDATE; + + err = ss->abort(net, oskb, abort_action); + if (err == -EAGAIN) { + nfnl_err_reset(&err_list); + kfree_skb(skb); + module_put(ss->owner); + status |= NFNL_BATCH_FAILURE; + goto replay_abort; + } } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c index 8826bbe71136..edd02cda57fc 100644 --- a/net/netfilter/nft_chain_route.c +++ b/net/netfilter/nft_chain_route.c @@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv, skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u32 *)ipv6_hdr(skb)))) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index cedf47ab3c6f..2182d361e273 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); } #endif return 0; diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index d77f4829f1e0..74c69b75f6f5 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -316,6 +316,14 @@ pp sleep 3 n2 ping -W 1 -c 1 192.168.241.1 n1 wg set wg0 peer "$pub2" persistent-keepalive 0 +# Test that sk_bound_dev_if works +n1 ping -I wg0 -c 1 -W 1 192.168.241.2 +# What about when the mark changes and the packet must be rerouted? +n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +n1 ping -c 1 -W 1 192.168.241.2 # First the boring case +n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case +n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 + # Test that onion routing works, even when it loops n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 ip1 addr add 192.168.242.1/24 dev wg0 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index d531de13c95b..4eecb432a66c 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -18,10 +18,12 @@ CONFIG_NF_NAT=y CONFIG_NETFILTER_XTABLES=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MARK=y CONFIG_NF_CONNTRACK_IPV4=y CONFIG_NF_NAT_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_MANGLE=y CONFIG_IP_NF_NAT=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y |