diff options
Diffstat (limited to 'net/ipv4')
33 files changed, 337 insertions, 267 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5f70ffdae1b5..9c465bac1eb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -99,6 +99,7 @@ #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> +#include <net/gro.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> @@ -224,7 +225,7 @@ int inet_listen(struct socket *sock, int backlog) tcp_fastopen_init_key_once(sock_net(sk)); } - err = inet_csk_listen_start(sk, backlog); + err = inet_csk_listen_start(sk); if (err) goto out; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); @@ -488,11 +489,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, * is temporarily down) */ err = -EADDRNOTAVAIL; - if (!inet_can_nonlocal_bind(net, inet) && - addr->sin_addr.s_addr != htonl(INADDR_ANY) && - chk_addr_ret != RTN_LOCAL && - chk_addr_ret != RTN_MULTICAST && - chk_addr_ret != RTN_BROADCAST) + if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, + chk_addr_ret)) goto out; snum = ntohs(addr->sin_port); @@ -533,6 +531,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); goto out_release_sock; } } @@ -1454,19 +1454,18 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) proto = iph->protocol; - rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) - goto out_unlock; + goto out; if (*(u8 *)iph != 0x45) - goto out_unlock; + goto out; if (ip_is_fragment(iph)) - goto out_unlock; + goto out; if (unlikely(ip_fast_csum((u8 *)iph, 5))) - goto out_unlock; + goto out; id = ntohl(*(__be32 *)&iph->id); flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); @@ -1543,9 +1542,6 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive, ops->callbacks.gro_receive, head, skb); -out_unlock: - rcu_read_unlock(); - out: skb_gro_flush_final(skb, pp, flush); @@ -1618,10 +1614,9 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; - rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) - goto out_unlock; + goto out; /* Only need to add sizeof(*iph) to get to the next hdr below * because any hdr with option will have been flushed in @@ -1631,9 +1626,7 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) tcp4_gro_complete, udp4_gro_complete, skb, nhoff + sizeof(*iph)); -out_unlock: - rcu_read_unlock(); - +out: return err; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 857a144b1ea9..4db0325f6e1a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1299,21 +1299,6 @@ static struct packet_type arp_packet_type __read_mostly = { .func = arp_rcv, }; -static int arp_proc_init(void); - -void __init arp_init(void) -{ - neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); - - dev_add_pack(&arp_packet_type); - arp_proc_init(); -#ifdef CONFIG_SYSCTL - neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); -#endif - register_netdevice_notifier(&arp_netdev_notifier); -} - -#ifdef CONFIG_PROC_FS #if IS_ENABLED(CONFIG_AX25) /* ------------------------------------------------------------------------ */ @@ -1451,16 +1436,14 @@ static struct pernet_operations arp_net_ops = { .exit = arp_net_exit, }; -static int __init arp_proc_init(void) +void __init arp_init(void) { - return register_pernet_subsys(&arp_net_ops); -} - -#else /* CONFIG_PROC_FS */ + neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); -static int __init arp_proc_init(void) -{ - return 0; + dev_add_pack(&arp_packet_type); + register_pernet_subsys(&arp_net_ops); +#ifdef CONFIG_SYSCTL + neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); +#endif + register_netdevice_notifier(&arp_netdev_notifier); } - -#endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 4bb9401b0a3f..de610cb83694 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -169,7 +169,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) t = bpf_tcp_congestion_ops.type; m = &btf_type_member(t)[midx]; - return btf_member_bit_offset(t, m) / 8; + return __btf_member_bit_offset(t, m) / 8; } static const struct bpf_func_proto * @@ -246,7 +246,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, utcp_ca = (const struct tcp_congestion_ops *)udata; tcp_ca = (struct tcp_congestion_ops *)kdata; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; switch (moff) { case offsetof(struct tcp_congestion_ops, flags): if (utcp_ca->flags & ~TCP_CONG_MASK) @@ -276,7 +276,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, static int bpf_tcp_ca_check_member(const struct btf_type *t, const struct btf_member *member) { - if (is_unsupported(btf_member_bit_offset(t, member) / 8)) + if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) return -ENOTSUPP; return 0; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 323e622ff9b7..fba2bffd65f7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -243,7 +243,7 @@ void in_dev_finish_destroy(struct in_device *idev) #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif - dev_put(dev); + dev_put_track(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else @@ -271,7 +271,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ - dev_hold(dev); + dev_hold_track(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 8e4e9aa12130..d87f02a6e934 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -16,6 +16,7 @@ #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> +#include <net/gro.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d279cb8ac158..e0b6c8b6de57 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -216,11 +216,6 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } -static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, - [FRA_FLOW] = { .type = NLA_U32 }, -}; - static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -386,7 +381,6 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, - .policy = fib4_rule_policy, .owner = THIS_MODULE, }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index fde7797b5806..828de171708f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -208,7 +208,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) void fib_nh_common_release(struct fib_nh_common *nhc) { - dev_put(nhc->nhc_dev); + dev_put_track(nhc->nhc_dev, &nhc->nhc_dev_tracker); lwtstate_put(nhc->nhc_lwtstate); rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output); rt_fibinfo_free(&nhc->nhc_rth_input); @@ -662,6 +662,19 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, return nhs; } +static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + if (nla_len(nla) < sizeof(*gw)) { + NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY"); + return -EINVAL; + } + + *gw = nla_get_in_addr(nla); + + return 0; +} + /* only called when fib_nh is integrated into fib_info */ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, @@ -704,7 +717,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, return -EINVAL; } if (nla) { - fib_cfg.fc_gw4 = nla_get_in_addr(nla); + ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla, + extack); + if (ret) + goto errout; + if (fib_cfg.fc_gw4) fib_cfg.fc_gw_family = AF_INET; } else if (nlav) { @@ -714,10 +731,18 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, } nla = nla_find(attrs, attrlen, RTA_FLOW); - if (nla) + if (nla) { + if (nla_len(nla) < sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); + return -EINVAL; + } fib_cfg.fc_flow = nla_get_u32(nla); + } fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + /* RTA_ENCAP_TYPE length checked in + * lwtunnel_valid_encap_type_attr + */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) fib_cfg.fc_encap_type = nla_get_u16(nla); @@ -902,6 +927,7 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh); + int err; nla = nla_find(attrs, attrlen, RTA_GATEWAY); nlav = nla_find(attrs, attrlen, RTA_VIA); @@ -912,12 +938,17 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (nla) { + __be32 gw; + + err = fib_gw_from_attr(&gw, nla, extack); + if (err) + return err; + if (nh->fib_nh_gw_family != AF_INET || - nla_get_in_addr(nla) != nh->fib_nh_gw4) + gw != nh->fib_nh_gw4) return 1; } else if (nlav) { struct fib_config cfg2; - int err; err = fib_gw_from_via(&cfg2, nlav, extack); if (err) @@ -940,8 +971,14 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); - if (nla && nla_get_u32(nla) != nh->nh_tclassid) - return 1; + if (nla) { + if (nla_len(nla) < sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); + return -EINVAL; + } + if (nla_get_u32(nla) != nh->nh_tclassid) + return 1; + } #endif } @@ -1006,7 +1043,7 @@ static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh, err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack); if (!err) { nh->fib_nh_dev = fib6_nh.fib_nh_dev; - dev_hold(nh->fib_nh_dev); + dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_KERNEL); nh->fib_nh_oif = nh->fib_nh_dev->ifindex; nh->fib_nh_scope = RT_SCOPE_LINK; @@ -1090,7 +1127,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; nh->fib_nh_dev = dev; - dev_hold(dev); + dev_hold_track(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_LINK; return 0; } @@ -1144,7 +1181,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, "No egress device for nexthop gateway"); goto out; } - dev_hold(dev); + dev_hold_track(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; @@ -1178,7 +1215,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, } nh->fib_nh_dev = in_dev->dev; - dev_hold(nh->fib_nh_dev); + dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; @@ -1508,6 +1545,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg, err = -ENODEV; if (!nh->fib_nh_dev) goto failure; + netdev_tracker_alloc(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, + GFP_KERNEL); } else { int linkdown = 0; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8fcbc6258ec5..0d085cc8d96c 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <net/genetlink.h> +#include <net/gro.h> #include <net/gue.h> #include <net/fou.h> #include <net/ip.h> @@ -246,17 +247,14 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; - rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (!ops || !ops->callbacks.gro_receive) - goto out_unlock; + goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); -out_unlock: - rcu_read_unlock(); - +out: return pp; } @@ -268,19 +266,16 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, const struct net_offload *ops; int err = -ENOSYS; - rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) - goto out_unlock; + goto out; err = ops->callbacks.gro_complete(skb, nhoff); skb_set_inner_mac_header(skb, nhoff); -out_unlock: - rcu_read_unlock(); - +out: return err; } @@ -438,17 +433,14 @@ next_proto: /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; - rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) - goto out_unlock; + goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); flush = 0; -out_unlock: - rcu_read_unlock(); out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); @@ -485,18 +477,16 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) return err; } - rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) - goto out_unlock; + goto out; err = ops->callbacks.gro_complete(skb, nhoff + guehlen); skb_set_inner_mac_header(skb, nhoff + guehlen); -out_unlock: - rcu_read_unlock(); +out: return err; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1121a9d5fed9..07073fa35205 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <net/protocol.h> #include <net/gre.h> +#include <net/gro.h> static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -162,10 +163,9 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, type = greh->protocol; - rcu_read_lock(); ptype = gro_find_receive_by_type(type); if (!ptype) - goto out_unlock; + goto out; grehlen = GRE_HEADER_SECTION; @@ -179,13 +179,13 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, if (skb_gro_header_hard(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) - goto out_unlock; + goto out; } /* Don't bother verifying checksum if we're going to flush anyway. */ if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) { if (skb_gro_checksum_simple_validate(skb)) - goto out_unlock; + goto out; skb_gro_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); @@ -229,8 +229,6 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; -out_unlock: - rcu_read_unlock(); out: skb_gro_flush_final(skb, pp, flush); @@ -255,13 +253,10 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) if (greh->flags & GRE_CSUM) grehlen += GRE_HEADER_SECTION; - rcu_read_lock(); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); - rcu_read_unlock(); - skb_set_inner_mac_header(skb, nhoff + grehlen); return err; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d2e2b3d18c66..2ad3c7b42d6d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2558,7 +2558,6 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { - len = 0; count = 0; } else { count = psl->sl_count; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 62a67fdc344c..fc2a985f6064 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1035,7 +1035,7 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); -int inet_csk_listen_start(struct sock *sk, int backlog) +int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 75737267746f..30ab717ff1b8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -307,7 +307,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -315,8 +315,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (hashinfo != &tcp_hashinfo) return NULL; /* only TCP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -340,7 +340,7 @@ struct sock *__inet_lookup_listener(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (result) goto done; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9bca57ef8b83..57c1d8431386 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -672,7 +672,6 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) struct sk_buff *skb2; struct iphdr *iph; - len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 38d29b175ca6..445a9ecaefa1 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -576,7 +576,7 @@ out: return err; } -static void __ip_sock_set_tos(struct sock *sk, int val) +void __ip_sock_set_tos(struct sock *sk, int val) { if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2dda856ca260..07274619b9ea 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -195,10 +195,6 @@ static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) return 1; } -static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { - FRA_GENERIC_POLICY, -}; - static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) @@ -231,7 +227,6 @@ static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .compare = ipmr_rule_compare, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, - .policy = ipmr_rule_policy, .owner = THIS_MODULE, }; @@ -696,7 +691,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put(dev); + dev_put_track(dev, &v->dev_tracker); return 0; } @@ -896,6 +891,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; + netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); if (v->flags & VIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; if (vifi+1 > mrt->maxvif) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 63cb953bd019..67087f95579f 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -59,12 +59,8 @@ config NF_TABLES_ARP endif # NF_TABLES config NF_FLOW_TABLE_IPV4 - tristate "Netfilter flow table IPv4 module" - depends on NF_FLOW_TABLE - help - This option adds the flow table IPv4 support. - - To compile it as a module, choose M here. + tristate + select NF_FLOW_TABLE_INET config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index f38fb1368ddb..93bad1184251 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -24,9 +24,6 @@ obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o -# flow table support -obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o - # generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 8fd1aba8af31..b518f20c9a24 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -520,8 +520,11 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) if (IS_ERR(config)) return PTR_ERR(config); } - } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) + } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) { + clusterip_config_entry_put(config); + clusterip_config_put(config); return -EINVAL; + } ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index aba65fe90345..e69de29bb2d1 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -1,37 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/netfilter.h> -#include <net/netfilter/nf_flow_table.h> -#include <net/netfilter/nf_tables.h> - -static struct nf_flowtable_type flowtable_ipv4 = { - .family = NFPROTO_IPV4, - .init = nf_flow_table_init, - .setup = nf_flow_table_offload_setup, - .action = nf_flow_rule_route_ipv4, - .free = nf_flow_table_free, - .hook = nf_flow_offload_ip_hook, - .owner = THIS_MODULE, -}; - -static int __init nf_flow_ipv4_module_init(void) -{ - nft_register_flowtable_type(&flowtable_ipv4); - - return 0; -} - -static void __exit nf_flow_ipv4_module_exit(void) -{ - nft_unregister_flowtable_type(&flowtable_ipv4); -} - -module_init(nf_flow_ipv4_module_init); -module_exit(nf_flow_ipv4_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_ALIAS_NF_FLOWTABLE(AF_INET); -MODULE_DESCRIPTION("Netfilter flow table support"); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 5dbd4b5505eb..eeafeccebb8d 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -8,6 +8,7 @@ #include <linux/nexthop.h> #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/lwtunnel.h> @@ -1918,9 +1919,6 @@ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, if (!replaced_nh->is_group) return; - /* new dsts must use only the new nexthop group */ - synchronize_net(); - nhg = rtnl_dereference(replaced_nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; @@ -2002,9 +2000,10 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_grp, newg); + /* Make sure concurrent readers are not using 'oldg' anymore. */ + synchronize_net(); + if (newg->resilient) { - /* Make sure concurrent readers are not using 'oldg' anymore. */ - synchronize_net(); rcu_assign_pointer(oldg->res_table, tmp_table); rcu_assign_pointer(oldg->spare->res_table, tmp_table); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1e44a43acfe2..0e56df3a45e2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -311,15 +311,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) - chk_addr_ret = RTN_LOCAL; - else - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); - - if ((!inet_can_nonlocal_bind(net, isk) && - chk_addr_ret != RTN_LOCAL) || - chk_addr_ret == RTN_MULTICAST || - chk_addr_ret == RTN_BROADCAST) + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + + if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk), + addr->sin_addr.s_addr, + chk_addr_ret)) return -EADDRNOTAVAIL; #if IS_ENABLED(CONFIG_IPV6) @@ -998,6 +994,7 @@ struct proto ping_prot = { .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, + .put_port = ping_unhash, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bb446e60cf58..a53f256bf9d3 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -99,8 +99,8 @@ int raw_hash_sk(struct sock *sk) write_lock_bh(&h->lock); sk_add_node(sk, head); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock_bh(&h->lock); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); return 0; } @@ -717,6 +717,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + struct net *net = sock_net(sk); u32 tb_id = RT_TABLE_LOCAL; int ret = -EINVAL; int chk_addr_ret; @@ -725,16 +726,16 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; if (sk->sk_bound_dev_if) - tb_id = l3mdev_fib_table_by_index(sock_net(sk), - sk->sk_bound_dev_if) ? : tb_id; + tb_id = l3mdev_fib_table_by_index(net, + sk->sk_bound_dev_if) ? : tb_id; - chk_addr_ret = inet_addr_type_table(sock_net(sk), addr->sin_addr.s_addr, - tb_id); + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); ret = -EADDRNOTAVAIL; - if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL && - chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) + if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, + chk_addr_ret)) goto out; + inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0b4103b1e622..ff6f91cdb6c4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -110,14 +110,15 @@ #define RT_GC_TIMEOUT (300*HZ) +#define DEFAULT_MIN_PMTU (512 + 20 + 20) +#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) + static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; -static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; @@ -602,7 +603,7 @@ static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) static u32 fnhe_hashfun(__be32 daddr) { - static siphash_key_t fnhe_hash_key __read_mostly; + static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); @@ -1018,13 +1019,13 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (old_mtu < mtu) return; - if (mtu < ip_rt_min_pmtu) { + if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; - mtu = min(old_mtu, ip_rt_min_pmtu); + mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && - time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) + time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) return; rcu_read_lock(); @@ -1034,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) fib_select_path(net, &res, fl4, NULL); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, - jiffies + ip_rt_mtu_expires); + jiffies + net->ipv4.ip_rt_mtu_expires); } rcu_read_unlock(); } @@ -1531,8 +1532,9 @@ void rt_flush_dev(struct net_device *dev) if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; - dev_hold(rt->dst.dev); - dev_put(dev); + dev_replace_track(dev, blackhole_netdev, + &rt->dst.dev_tracker, + GFP_ATOMIC); } spin_unlock_bh(&ul->lock); } @@ -2819,7 +2821,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->output = dst_discard_out; new->dev = net->loopback_dev; - dev_hold(new->dev); + dev_hold_track(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; @@ -3534,21 +3536,6 @@ static struct ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .procname = "mtu_expires", - .data = &ip_rt_mtu_expires, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "min_pmtu", - .data = &ip_rt_min_pmtu, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &ip_min_valid_pmtu, - }, - { .procname = "min_adv_mss", .data = &ip_rt_min_advmss, .maxlen = sizeof(int), @@ -3560,13 +3547,28 @@ static struct ctl_table ipv4_route_table[] = { static const char ipv4_route_flush_procname[] = "flush"; -static struct ctl_table ipv4_route_flush_table[] = { +static struct ctl_table ipv4_route_netns_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, + { + .procname = "min_pmtu", + .data = &init_net.ipv4.ip_rt_min_pmtu, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, + }, + { + .procname = "mtu_expires", + .data = &init_net.ipv4.ip_rt_mtu_expires, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { }, }; @@ -3574,9 +3576,11 @@ static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; - tbl = ipv4_route_flush_table; + tbl = ipv4_route_netns_table; if (!net_eq(net, &init_net)) { - tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); + int i; + + tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL); if (!tbl) goto err_dup; @@ -3585,6 +3589,12 @@ static __net_init int sysctl_route_net_init(struct net *net) if (tbl[0].procname != ipv4_route_flush_procname) tbl[0].procname = NULL; } + + /* Update the variables to point into the current struct net + * except for the first element flush + */ + for (i = 1; i < ARRAY_SIZE(ipv4_route_netns_table) - 1; i++) + tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; @@ -3594,7 +3604,7 @@ static __net_init int sysctl_route_net_init(struct net *net) return 0; err_reg: - if (tbl != ipv4_route_flush_table) + if (tbl != ipv4_route_netns_table) kfree(tbl); err_dup: return -ENOMEM; @@ -3606,7 +3616,7 @@ static __net_exit void sysctl_route_net_exit(struct net *net) tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); - BUG_ON(tbl == ipv4_route_flush_table); + BUG_ON(tbl == ipv4_route_netns_table); kfree(tbl); } @@ -3616,6 +3626,18 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { }; #endif +static __net_init int netns_ip_rt_init(struct net *net) +{ + /* Set default value for namespaceified sysctls */ + net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; + net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; + return 0; +} + +static struct pernet_operations __net_initdata ip_rt_ops = { + .init = netns_ip_rt_init, +}; + static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); @@ -3721,6 +3743,7 @@ int __init ip_rt_init(void) #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif + register_pernet_subsys(&ip_rt_ops); register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 8696dc343ad2..2cb3b852d148 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -14,7 +14,7 @@ #include <net/tcp.h> #include <net/route.h> -static siphash_key_t syncookie_secret[2] __read_mostly; +static siphash_aligned_key_t syncookie_secret[2]; #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2bb28bfd83bf..3b75836db19b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -292,7 +292,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); -atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ +atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); #if IS_ENABLED(CONFIG_SMC) @@ -303,7 +303,7 @@ EXPORT_SYMBOL(tcp_have_smc); /* * Current number of TCP sockets. */ -struct percpu_counter tcp_sockets_allocated; +struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(tcp_sockets_allocated); /* @@ -456,7 +456,6 @@ void tcp_init_sock(struct sock *sk) WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); - sk->sk_route_forced_caps = NETIF_F_GSO; } EXPORT_SYMBOL(tcp_init_sock); @@ -546,10 +545,11 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); + u16 urg_data = READ_ONCE(tp->urg_data); - if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && - !sock_flag(sk, SOCK_URGINLINE) && - tp->urg_data) + if (unlikely(urg_data) && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && + !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) @@ -574,7 +574,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } else mask |= EPOLLOUT | EPOLLWRNORM; - if (tp->urg_data & TCP_URG_VALID) + if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* Active TCP fastopen socket with defer_connect @@ -608,7 +608,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && + answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: @@ -1466,7 +1466,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) char c = tp->urg_data; if (!(flags & MSG_PEEK)) - tp->urg_data = TCP_URG_READ; + WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; @@ -1580,6 +1580,36 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) tcp_send_ack(sk); } +void __sk_defer_free_flush(struct sock *sk) +{ + struct llist_node *head; + struct sk_buff *skb, *n; + + head = llist_del_all(&sk->defer_list); + llist_for_each_entry_safe(skb, n, head, ll_node) { + prefetch(n); + skb_mark_not_on_list(skb); + __kfree_skb(skb); + } +} +EXPORT_SYMBOL(__sk_defer_free_flush); + +static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) +{ + __skb_unlink(skb, &sk->sk_receive_queue); + if (likely(skb->destructor == sock_rfree)) { + sock_rfree(skb); + skb->destructor = NULL; + skb->sk = NULL; + if (!skb_queue_empty(&sk->sk_receive_queue) || + !llist_empty(&sk->defer_list)) { + llist_add(&skb->ll_node, &sk->defer_list); + return; + } + } + __kfree_skb(skb); +} + static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; @@ -1599,7 +1629,7 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ - sk_eat_skb(sk, skb); + tcp_eat_recv_skb(sk, skb); } return NULL; } @@ -1633,7 +1663,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ - if (tp->urg_data) { + if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; @@ -1665,11 +1695,11 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { - sk_eat_skb(sk, skb); + tcp_eat_recv_skb(sk, skb); ++seq; break; } - sk_eat_skb(sk, skb); + tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(tp->copied_seq, seq); @@ -2329,7 +2359,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ - if (tp->urg_data && tp->urg_seq == *seq) { + if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { @@ -2372,10 +2402,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, break; if (copied) { - if (sk->sk_err || + if (!timeo || + sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || - !timeo || signal_pending(current)) break; } else { @@ -2409,13 +2439,12 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } } - tcp_cleanup_rbuf(sk, copied); - if (copied >= target) { /* Do not sleep, just process backlog. */ - release_sock(sk); - lock_sock(sk); + __sk_flush_backlog(sk); } else { + tcp_cleanup_rbuf(sk, copied); + sk_defer_free_flush(sk); sk_wait_data(sk, &timeo, last); } @@ -2435,7 +2464,7 @@ found_ok_skb: used = len; /* Do we have urgent data here? */ - if (tp->urg_data) { + if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { @@ -2469,8 +2498,8 @@ found_ok_skb: tcp_rcv_space_adjust(sk); skip_copy: - if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) { - tp->urg_data = 0; + if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { + WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } @@ -2485,14 +2514,14 @@ skip_copy: if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) - sk_eat_skb(sk, skb); + tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) - sk_eat_skb(sk, skb); + tcp_eat_recv_skb(sk, skb); break; } while (len > 0); @@ -2534,6 +2563,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss, &cmsg_flags); release_sock(sk); + sk_defer_free_flush(sk); if (cmsg_flags && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) @@ -2964,7 +2994,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); - tp->urg_data = 0; + WRITE_ONCE(tp->urg_data, 0); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -3058,7 +3088,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } - + sk_defer_free_flush(sk); sk_error_report(sk); return 0; } @@ -3176,7 +3206,7 @@ static void tcp_enable_tx_delay(void) * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ -static void __tcp_sock_set_cork(struct sock *sk, bool on) +void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); @@ -3204,7 +3234,7 @@ EXPORT_SYMBOL(tcp_sock_set_cork); * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ -static void __tcp_sock_set_nodelay(struct sock *sk, bool on) +void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; @@ -3773,10 +3803,12 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; - info->tcpi_segs_in = tp->segs_in; + + /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ + info->tcpi_segs_in = READ_ONCE(tp->segs_in); + info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); - info->tcpi_data_segs_in = tp->data_segs_in; info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; @@ -4185,6 +4217,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); release_sock(sk); + sk_defer_free_flush(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f70aa0932bd6..9b9b02052fd3 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -196,12 +196,39 @@ msg_bytes_ready: long timeo; int data; + if (sock_flag(sk, SOCK_DONE)) + goto out; + + if (sk->sk_err) { + copied = sock_error(sk); + goto out; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + goto out; + + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + goto out; + } + timeo = sock_rcvtimeo(sk, nonblock); + if (!timeo) { + copied = -EAGAIN; + goto out; + } + + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + goto out; + } + data = tcp_msg_wait_data(sk, psock, timeo); if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } +out: release_sock(sk); sk_psock_put(sk, psock); return copied; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0ce46849ec3d..dc49a3d551eb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3601,7 +3601,7 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, } /* RFC 5961 7 [ACK Throttling] */ -static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) +static void tcp_send_challenge_ack(struct sock *sk) { /* unprotected vars, we dont care of overwrites */ static u32 challenge_timestamp; @@ -3763,7 +3763,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ if (before(ack, prior_snd_una - tp->max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) - tcp_send_challenge_ack(sk, skb); + tcp_send_challenge_ack(sk); return -1; } goto old_ack; @@ -5591,7 +5591,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } } - tp->urg_data = TCP_URG_NOTYET; + WRITE_ONCE(tp->urg_data, TCP_URG_NOTYET); WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ @@ -5604,11 +5604,11 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t struct tcp_sock *tp = tcp_sk(sk); /* Check if we get a new urgent pointer - normally not. */ - if (th->urg) + if (unlikely(th->urg)) tcp_check_urg(sk, th); /* Do we wait for any urgent data? - normally not... */ - if (tp->urg_data == TCP_URG_NOTYET) { + if (unlikely(tp->urg_data == TCP_URG_NOTYET)) { u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) - th->syn; @@ -5617,7 +5617,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t u8 tmp; if (skb_copy_bits(skb, ptr, &tmp, 1)) BUG(); - tp->urg_data = TCP_URG_VALID | tmp; + WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); } @@ -5726,7 +5726,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (tp->syn_fastopen && !tp->data_segs_in && sk->sk_state == TCP_ESTABLISHED) tcp_fastopen_active_disable(sk); - tcp_send_challenge_ack(sk, skb); + tcp_send_challenge_ack(sk); } goto discard; } @@ -5741,7 +5741,7 @@ syn_challenge: if (syn_inerr) TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); - tcp_send_challenge_ack(sk, skb); + tcp_send_challenge_ack(sk); goto discard; } @@ -6456,7 +6456,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!acceptable) { if (sk->sk_state == TCP_SYN_RECV) return 1; /* send one RST */ - tcp_send_challenge_ack(sk, skb); + tcp_send_challenge_ack(sk); goto discard; } switch (sk->sk_state) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 084df223b5df..b3f34e366b27 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1182,7 +1182,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, if (!md5sig) return -ENOMEM; - sk_nocaps_add(sk, NETIF_F_GSO_MASK); + sk_gso_disable(sk); INIT_HLIST_HEAD(&md5sig->head); rcu_assign_pointer(tp->md5sig_info, md5sig); } @@ -1620,7 +1620,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, */ tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags, key->key, key->keylen, GFP_ATOMIC); - sk_nocaps_add(newsk, NETIF_F_GSO_MASK); + sk_gso_disable(newsk); } #endif @@ -1803,8 +1803,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); - u32 tail_gso_size, tail_gso_segs; + u32 limit, tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -1912,7 +1911,7 @@ no_coalesce: * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ - limit += 64*1024; + limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024; if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); @@ -1972,8 +1971,10 @@ int tcp_v4_rcv(struct sk_buff *skb) const struct tcphdr *th; bool refcounted; struct sock *sk; + int drop_reason; int ret; + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -1985,8 +1986,10 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; - if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) + if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; + } if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; @@ -2091,8 +2094,10 @@ process: nf_reset_ct(skb); - if (tcp_filter(sk, skb)) + if (tcp_filter(sk, skb)) { + drop_reason = SKB_DROP_REASON_TCP_FILTER; goto discard_and_relse; + } th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); @@ -2106,6 +2111,7 @@ process: sk_incoming_cpu_update(sk); + sk_defer_free_flush(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; @@ -2124,6 +2130,7 @@ put_and_return: return ret; no_tcp_socket: + drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; @@ -2131,6 +2138,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -2141,7 +2149,7 @@ bad_packet: discard_it: /* Discard frame. */ - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; discard_and_relse: @@ -3076,6 +3084,7 @@ struct proto tcp_prot = { .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index fc61cd3fea65..30abde86db45 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -8,6 +8,7 @@ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> +#include <net/gro.h> #include <net/tcp.h> #include <net/protocol.h> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2e6e5a70168e..5079832af5c1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1359,7 +1359,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { - sk_nocaps_add(sk, NETIF_F_GSO_MASK); + sk_gso_disable(sk); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, skb); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0cd6b857e7ec..464590ea922e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -74,6 +74,7 @@ #define pr_fmt(fmt) "UDP: " fmt +#include <linux/bpf-cgroup.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/memblock.h> @@ -122,7 +123,7 @@ EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); -atomic_long_t udp_memory_allocated; +atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(udp_memory_allocated); #define MAX_UDP_PORTS 65536 @@ -459,7 +460,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -467,8 +468,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, if (udptable != &udp_table) return NULL; /* only UDP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -504,7 +505,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp4_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; @@ -2410,6 +2411,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, __be32 saddr, daddr; struct net *net = dev_net(skb->dev); bool refcounted; + int drop_reason; + + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* * Validate the packet. @@ -2465,6 +2469,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp_lib_checksum_complete(skb)) goto csum_error; + drop_reason = SKB_DROP_REASON_NO_SOCKET; __UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -2472,10 +2477,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; short_packet: + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), @@ -2488,6 +2494,7 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ + drop_reason = SKB_DROP_REASON_UDP_CSUM; net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), @@ -2495,7 +2502,7 @@ csum_error: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; } @@ -2926,6 +2933,7 @@ struct proto udp_prot = { .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, + .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 86d32a1e62ac..6d1a4bec2614 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -7,6 +7,7 @@ */ #include <linux/skbuff.h> +#include <net/gro.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> @@ -424,6 +425,33 @@ out: return segs; } +static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} + + #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) @@ -600,13 +628,11 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; - rcu_read_lock(); if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); - rcu_read_unlock(); return pp; flush: @@ -641,7 +667,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, uh->len = newlen; - rcu_read_lock(); sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { @@ -662,7 +687,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, } else { err = udp_gro_complete_segment(skb); } - rcu_read_unlock(); if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9ebd54752e03..9e83bcb6bc99 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -77,7 +77,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; - dev_hold(dev); + dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ |