diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-06-19 21:00:30 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-06-19 21:00:30 +0000 |
commit | e54def4ad8144ab15f826416e2e0f290ef1901b4 (patch) | |
tree | 583f8d4bd95cd67c44ff37b878a7eddfca9ab97a /net/ipv4 | |
parent | Adding upstream version 6.8.12. (diff) | |
download | linux-e54def4ad8144ab15f826416e2e0f290ef1901b4.tar.xz linux-e54def4ad8144ab15f826416e2e0f290ef1901b4.zip |
Adding upstream version 6.9.2.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'net/ipv4')
46 files changed, 855 insertions, 547 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ce5c26cf1e..fafb123f79 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #endif #include <net/l3mdev.h> #include <net/compat.h> +#include <net/rps.h> #include <trace/events/sock.h> @@ -1103,7 +1104,7 @@ const struct proto_ops inet_dgram_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif @@ -1326,7 +1327,7 @@ int inet_sk_rebuild_header(struct sock *sk) fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, - sk->sk_protocol, RT_CONN_FLAGS(sk), + sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; @@ -1752,19 +1753,6 @@ static const struct net_protocol igmp_protocol = { }; #endif -static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .no_policy = 1, - .icmp_strict_tag_validation = 1, -}; - -static const struct net_protocol udp_protocol = { - .handler = udp_rcv, - .err_handler = udp_err, - .no_policy = 1, -}; - static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, @@ -1905,14 +1893,6 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ -static struct packet_offload ip_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IP), - .callbacks = { - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, - }, -}; static const struct net_offload ipip_offload = { .callbacks = { @@ -1939,7 +1919,15 @@ static int __init ipv4_offload_init(void) if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); - dev_add_offload(&ip_packet_offload); + net_hotdata.ip_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } @@ -1993,9 +1981,22 @@ static int __init inet_init(void) if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); - if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) + + net_hotdata.udp_protocol = (struct net_protocol) { + .handler = udp_rcv, + .err_handler = udp_err, + .no_policy = 1, + }; + if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); - if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) + + net_hotdata.tcp_protocol = (struct net_protocol) { + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .no_policy = 1, + .icmp_strict_tag_validation = 1, + }; + if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e689..7f518ea5f4 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; @@ -191,17 +197,17 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } -BTF_SET8_START(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID_FLAGS(func, tcp_reno_ssthresh) BTF_ID_FLAGS(func, tcp_reno_cong_avoid) BTF_ID_FLAGS(func, tcp_reno_undo_cwnd) BTF_ID_FLAGS(func, tcp_slow_start) BTF_ID_FLAGS(func, tcp_cong_avoid_ai) -BTF_SET8_END(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_END(bpf_tcp_ca_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { .owner = THIS_MODULE, @@ -339,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -350,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index d048aa8332..8b17d83e5f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -864,11 +864,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, net_clen_bits, net_spot + 1, 1); - if (net_spot < 0) { - if (net_spot == -2) - return -EFAULT; + if (net_spot < 0) return 0; - } switch (doi_def->type) { case CIPSO_V4_MAP_PASS: diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 2cc50cbfc2..cc6d0bd7b0 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -119,7 +119,7 @@ void ip4_datagram_release_cb(struct sock *sk) rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bc74f131fe..7a437f0d41 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -713,34 +713,37 @@ static void check_lifetime(struct work_struct *work) rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { - unsigned long age; + unsigned long age, tstamp; + u32 preferred_lft; + u32 valid_lft; + u32 flags; - if (ifa->ifa_flags & IFA_F_PERMANENT) + flags = READ_ONCE(ifa->ifa_flags); + if (flags & IFA_F_PERMANENT) continue; + preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); + valid_lft = READ_ONCE(ifa->ifa_valid_lft); + tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ - age = (now - ifa->ifa_tstamp + + age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && - age >= ifa->ifa_valid_lft) { + if (valid_lft != INFINITY_LIFE_TIME && + age >= valid_lft) { change_needed = true; - } else if (ifa->ifa_preferred_lft == + } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; - } else if (age >= ifa->ifa_preferred_lft) { - if (time_before(ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ, next)) - next = ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ; + } else if (age >= preferred_lft) { + if (time_before(tstamp + valid_lft * HZ, next)) + next = tstamp + valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + if (!(flags & IFA_F_DEPRECATED)) change_needed = true; - } else if (time_before(ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ, + } else if (time_before(tstamp + preferred_lft * HZ, next)) { - next = ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ; + next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); @@ -804,24 +807,26 @@ static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; + u32 flags; - ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) - ifa->ifa_valid_lft = timeout; + WRITE_ONCE(ifa->ifa_valid_lft, timeout); else - ifa->ifa_flags |= IFA_F_PERMANENT; + flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) - ifa->ifa_flags |= IFA_F_DEPRECATED; - ifa->ifa_preferred_lft = timeout; + flags |= IFA_F_DEPRECATED; + WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } - ifa->ifa_tstamp = jiffies; + WRITE_ONCE(ifa->ifa_flags, flags); + WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) - ifa->ifa_cstamp = ifa->ifa_tstamp; + WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, @@ -1312,7 +1317,7 @@ static __be32 in_dev_select_addr(const struct in_device *in_dev, const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { - if (ifa->ifa_flags & IFA_F_SECONDARY) + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) @@ -1340,7 +1345,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { - if (ifa->ifa_flags & IFA_F_SECONDARY) + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; @@ -1671,11 +1676,12 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } -static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, +static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + unsigned long tstamp; u32 preferred, valid; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), @@ -1686,7 +1692,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags; + ifm->ifa_flags = READ_ONCE(ifa->ifa_flags); ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; @@ -1694,11 +1700,12 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; + tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { - preferred = ifa->ifa_preferred_lft; - valid = ifa->ifa_valid_lft; + preferred = READ_ONCE(ifa->ifa_preferred_lft); + valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->ifa_tstamp) / HZ; + long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; @@ -1725,10 +1732,10 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || - nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || + nla_put_u32(skb, IFA_FLAGS, ifm->ifa_flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || - put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; @@ -1798,15 +1805,15 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, + struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; - in_dev_for_each_ifa_rtnl(ifa, in_dev) { - if (ip_idx < s_ip_idx) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ip_idx < *s_ip_idx) { ip_idx++; continue; } @@ -1818,9 +1825,9 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, ip_idx++; } err = 0; - + ip_idx = 0; done: - cb->args[2] = ip_idx; + *s_ip_idx = ip_idx; return err; } @@ -1830,7 +1837,7 @@ done: static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -1852,75 +1859,51 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; - int h, s_h; - int idx, s_idx; - int s_ip_idx; - struct net_device *dev; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct in_device *in_dev; - struct hlist_head *head; + struct net_device *dev; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - + rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; - err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) { - err = -ENODEV; - goto put_tgt_net; - } - - in_dev = __in_dev_get_rtnl(dev); - if (in_dev) { - err = in_dev_dump_addr(in_dev, skb, cb, s_ip_idx, - &fillargs); - } - goto put_tgt_net; - } - } - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet_base_seq(tgt_net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; + err = -ENODEV; + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) + goto done; in_dev = __in_dev_get_rcu(dev); if (!in_dev) - goto cont; - - err = in_dev_dump_addr(in_dev, skb, cb, s_ip_idx, - &fillargs); - if (err < 0) { - rcu_read_unlock(); goto done; - } -cont: - idx++; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + goto done; } - rcu_read_unlock(); } + cb->seq = inet_base_seq(tgt_net); + + for_each_netdev_dump(net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; + } done: - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - - return skb->len ? : err; + rcu_read_unlock(); + return err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, @@ -1982,7 +1965,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) - ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } @@ -2068,9 +2051,9 @@ static int inet_netconf_msgsize_devconf(int type) } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, - struct ipv4_devconf *devconf, u32 portid, - u32 seq, int event, unsigned int flags, - int type) + const struct ipv4_devconf *devconf, + u32 portid, u32 seq, int event, + unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; @@ -2095,27 +2078,28 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, - IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, - IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, - IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, - IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) + IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, - IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) + IPV4_DEVCONF_RO(*devconf, + IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: @@ -2204,21 +2188,20 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); - struct nlattr *tb[NETCONFA_MAX+1]; + struct nlattr *tb[NETCONFA_MAX + 1]; + const struct ipv4_devconf *devconf; + struct in_device *in_dev = NULL; + struct net_device *dev = NULL; struct sk_buff *skb; - struct ipv4_devconf *devconf; - struct in_device *in_dev; - struct net_device *dev; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { @@ -2229,10 +2212,10 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv4.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); - if (!dev) - goto errout; - in_dev = __in_dev_get_rtnl(dev); + err = -ENODEV; + dev = dev_get_by_index(net, ifindex); + if (dev) + in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; @@ -2256,6 +2239,9 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in_dev) + in_dev_put(in_dev); + dev_put(dev); return err; } @@ -2264,11 +2250,13 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - int h, s_h; - int idx, s_idx; + struct { + unsigned long ifindex; + unsigned int all_default; + } *ctx = (void *)cb->ctx; + const struct in_device *in_dev; struct net_device *dev; - struct in_device *in_dev; - struct hlist_head *head; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -2285,64 +2273,45 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet_base_seq(net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - in_dev = __in_dev_get_rcu(dev); - if (!in_dev) - goto cont; - - if (inet_netconf_fill_devconf(skb, dev->ifindex, - &in_dev->cnf, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = inet_netconf_fill_devconf(skb, dev->ifindex, + &in_dev->cnf, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + goto done; } - if (h == NETDEV_HASHENTRIES) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, - net->ipv4.devconf_all, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + if (ctx->all_default == 0) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; - } - if (h == NETDEV_HASHENTRIES + 1) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, - net->ipv4.devconf_dflt, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + ctx->all_default++; + } + if (ctx->all_default == 1) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; + ctx->all_default++; } done: - cb->args[0] = h; - cb->args[1] = idx; - - return skb->len; + rcu_read_unlock(); + return err; } #ifdef CONFIG_SYSCTL @@ -2823,7 +2792,9 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, 0); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, + RTNL_FLAG_DUMP_UNLOCKED); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, - inet_netconf_dump_devconf, 0); + inet_netconf_dump_devconf, + RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 390f4be7f7..c484b1c0fc 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -916,7 +916,8 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct rtmsg *rtm; int err, i; - ASSERT_RTNL(); + if (filter->rtnl_held) + ASSERT_RTNL(); if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); @@ -961,7 +962,10 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); - filter->dev = __dev_get_by_index(net, ifindex); + if (filter->rtnl_held) + filter->dev = __dev_get_by_index(net, ifindex); + else + filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; @@ -983,20 +987,24 @@ EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct fib_dump_filter filter = { .dump_routes = true, - .dump_exceptions = true }; + struct fib_dump_filter filter = { + .dump_routes = true, + .dump_exceptions = true, + .rtnl_held = false, + }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; - int dumped = 0, err; + int dumped = 0, err = 0; + rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) - return err; + goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); @@ -1005,29 +1013,26 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) - return skb->len; + goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) - return skb->len; + goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); - return -ENOENT; + err = -ENOENT; + goto unlock; } - - rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); - rcu_read_unlock(); - return skb->len ? : err; + goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; - rcu_read_lock(); - + err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; @@ -1038,25 +1043,25 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0) { - if (likely(skb->len)) - goto out; - - goto out_err; - } + if (err < 0) + goto out; dumped = 1; next: e++; } } -out: + + /* Don't let NLM_DONE coalesce into a message, even if it could. + * Some user space expects NLM_DONE in a separate recv(). + */ err = skb->len; -out_err: - rcu_read_unlock(); +out: cb->args[1] = e; cb->args[0] = h; +unlock: + rcu_read_unlock(); return err; } @@ -1659,5 +1664,6 @@ void __init ip_fib_init(void) rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, + RTNL_FLAG_DUMP_UNLOCKED); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3ff35f8117..f474106464 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -501,7 +501,7 @@ static void tnode_free(struct key_vector *tn) if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; - synchronize_rcu(); + synchronize_net(); } } @@ -2368,7 +2368,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) - return skb->len; + return 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; @@ -2394,7 +2394,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, cb->args[3] = key; cb->args[2] = count; - return skb->len; + return 0; } void __init fib_trie_init(void) diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 4da03bf45c..06e5572f29 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -100,10 +100,10 @@ __bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, __bpf_kfunc_end_defs(); -BTF_SET8_START(fou_kfunc_set) +BTF_KFUNCS_START(fou_kfunc_set) BTF_ID_FLAGS(func, bpf_skb_set_fou_encap) BTF_ID_FLAGS(func, bpf_skb_get_fou_encap) -BTF_SET8_END(fou_kfunc_set) +BTF_KFUNCS_END(fou_kfunc_set) static const struct btf_kfunc_id_set fou_bpf_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 0c41076e31..a8494f796d 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -351,7 +351,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, optlen = guehdr->hlen << 2; len += optlen; - if (skb_gro_header_hard(skb, len)) { + if (!skb_gro_may_pull(skb, len)) { guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index cbb2b4bb0d..3757fd9352 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -217,5 +217,5 @@ module_init(gre_init); module_exit(gre_exit); MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver"); -MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); +MODULE_AUTHOR("D. Kozlov <xeb@mail.ru>"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 311e70bfce..5028c72d49 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -174,7 +174,7 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, grehlen += GRE_HEADER_SECTION; hlen = off + grehlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) goto out; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index efeeca2b13..717e97a389 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -120,12 +120,12 @@ */ #define IGMP_V1_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d1492c649a..3b38610958 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -930,8 +930,9 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, - req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; @@ -1491,7 +1492,7 @@ static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *f rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 9804e9608a..7adace541f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -32,7 +32,7 @@ #include <linux/inet_diag.h> #include <linux/sock_diag.h> -static const struct inet_diag_handler **inet_diag_table; +static const struct inet_diag_handler __rcu **inet_diag_table; struct inet_diag_entry { const __be32 *saddr; @@ -48,28 +48,28 @@ struct inet_diag_entry { #endif }; -static DEFINE_MUTEX(inet_diag_table_mutex); - static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { - if (proto < 0 || proto >= IPPROTO_MAX) { - mutex_lock(&inet_diag_table_mutex); - return ERR_PTR(-ENOENT); - } + const struct inet_diag_handler *handler; + + if (proto < 0 || proto >= IPPROTO_MAX) + return NULL; if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); - mutex_lock(&inet_diag_table_mutex); - if (!inet_diag_table[proto]) - return ERR_PTR(-ENOENT); + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[proto]); + if (handler && !try_module_get(handler->owner)) + handler = NULL; + rcu_read_unlock(); - return inet_diag_table[proto]; + return handler; } static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) { - mutex_unlock(&inet_diag_table_mutex); + module_put(handler->owner); } void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) @@ -104,9 +104,12 @@ static size_t inet_sk_attr_size(struct sock *sk, const struct inet_diag_handler *handler; size_t aux = 0; - handler = inet_diag_table[req->sdiag_protocol]; + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[req->sdiag_protocol]); + DEBUG_NET_WARN_ON_ONCE(!handler); if (handler && handler->idiag_get_aux_size) aux = handler->idiag_get_aux_size(sk, net_admin); + rcu_read_unlock(); return nla_total_size(sizeof(struct tcp_info)) + nla_total_size(sizeof(struct inet_diag_msg)) @@ -244,10 +247,16 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; + int protocol; cb_data = cb->data; - handler = inet_diag_table[inet_diag_get_protocol(req, cb_data)]; - BUG_ON(!handler); + protocol = inet_diag_get_protocol(req, cb_data); + + /* inet_diag_lock_handler() made sure inet_diag_table[] is stable. */ + handler = rcu_dereference_protected(inet_diag_table[protocol], 1); + DEBUG_NET_WARN_ON_ONCE(!handler); + if (!handler) + return -ENXIO; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); @@ -605,9 +614,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); - if (IS_ERR(handler)) { - err = PTR_ERR(handler); - } else if (cmd == SOCK_DIAG_BY_FAMILY) { + if (!handler) + return -ENOENT; + + if (cmd == SOCK_DIAG_BY_FAMILY) { struct netlink_callback cb = { .nlh = nlh, .skb = in_skb, @@ -1035,6 +1045,10 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, num = 0; ilb = &hashinfo->lhash2[i]; + if (hlist_nulls_empty(&ilb->nulls_head)) { + s_num = 0; + continue; + } spin_lock(&ilb->lock); sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); @@ -1099,6 +1113,10 @@ resume_bind_walk: accum = 0; ibb = &hashinfo->bhash2[i]; + if (hlist_empty(&ibb->chain)) { + s_num = 0; + continue; + } spin_lock_bh(&ibb->lock); inet_bind_bucket_for_each(tb2, &ibb->chain) { if (!net_eq(ib2_net(tb2), net)) @@ -1259,12 +1277,12 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, again: prev_min_dump_alloc = cb->min_dump_alloc; handler = inet_diag_lock_handler(protocol); - if (!IS_ERR(handler)) + if (handler) { handler->dump(skb, cb, r); - else - err = PTR_ERR(handler); - inet_diag_unlock_handler(handler); - + inet_diag_unlock_handler(handler); + } else { + err = -ENOENT; + } /* The skb is not large enough to fit one sk info and * inet_sk_diag_fill() has requested for a larger skb. */ @@ -1457,10 +1475,9 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } handler = inet_diag_lock_handler(sk->sk_protocol); - if (IS_ERR(handler)) { - inet_diag_unlock_handler(handler); + if (!handler) { nlmsg_cancel(skb, nlh); - return PTR_ERR(handler); + return -ENOENT; } attr = handler->idiag_info_size @@ -1479,6 +1496,7 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } static const struct sock_diag_handler inet_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1486,6 +1504,7 @@ static const struct sock_diag_handler inet_diag_handler = { }; static const struct sock_diag_handler inet6_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET6, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1495,20 +1514,12 @@ static const struct sock_diag_handler inet6_diag_handler = { int inet_diag_register(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; - int err = -EINVAL; if (type >= IPPROTO_MAX) - goto out; + return -EINVAL; - mutex_lock(&inet_diag_table_mutex); - err = -EEXIST; - if (!inet_diag_table[type]) { - WRITE_ONCE(inet_diag_table[type], h); - err = 0; - } - mutex_unlock(&inet_diag_table_mutex); -out: - return err; + return !cmpxchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL, h) ? 0 : -EEXIST; } EXPORT_SYMBOL_GPL(inet_diag_register); @@ -1519,12 +1530,16 @@ void inet_diag_unregister(const struct inet_diag_handler *h) if (type >= IPPROTO_MAX) return; - mutex_lock(&inet_diag_table_mutex); - WRITE_ONCE(inet_diag_table[type], NULL); - mutex_unlock(&inet_diag_table_mutex); + xchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL); } EXPORT_SYMBOL_GPL(inet_diag_unregister); +static const struct sock_diag_inet_compat inet_diag_compat = { + .owner = THIS_MODULE, + .fn = inet_diag_rcv_msg_compat, +}; + static int __init inet_diag_init(void) { const int inet_diag_table_size = (IPPROTO_MAX * @@ -1543,7 +1558,7 @@ static int __init inet_diag_init(void) if (err) goto out_free_inet; - sock_diag_register_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_register_inet_compat(&inet_diag_compat); out: return err; @@ -1558,7 +1573,7 @@ static void __exit inet_diag_exit(void) { sock_diag_unregister(&inet6_diag_handler); sock_diag_unregister(&inet_diag_handler); - sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_unregister_inet_compat(&inet_diag_compat); kfree(inet_diag_table); } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 4e470f1848..cf88eca5f1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,6 +24,7 @@ #include <net/inet6_hashtables.h> #endif #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/ip.h> #include <net/tcp.h> #include <net/sock_reuseport.h> @@ -32,8 +33,6 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 inet_ehash_secret __read_mostly; - net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e9fed83e9b..5bd7599634 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -81,10 +81,7 @@ void __init inet_initpeers(void) inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128); - peer_cachep = kmem_cache_create("inet_peer_cache", - sizeof(struct inet_peer), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, - NULL); + peer_cachep = KMEM_CACHE(inet_peer, SLAB_HWCACHE_ALIGN | SLAB_PANIC); } /* Called with rcu_read_lock() or base->lock held */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 1954a56fec..57ddcd8c62 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1030,14 +1030,16 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); + ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, + dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit_batch = ipgre_exit_batch_net, + .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1702,14 +1704,16 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); + ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, + dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit_batch = ipgre_tap_exit_batch_net, + .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1720,14 +1724,16 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_batch_net(struct list_head *net_list) +static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); + ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, + dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit_batch = erspan_exit_batch_net, + .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a38e63669c..39229fd060 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -493,7 +493,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS_TOS(sk, tos), + RT_TOS(tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 21d2ffa919..cf377377b5 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -894,7 +894,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); - int val = 0, err; + int val = 0, err, retv; bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { @@ -938,8 +938,12 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, /* If optlen==0, it is equivalent to val == 0 */ - if (optname == IP_ROUTER_ALERT) - return ip_ra_control(sk, val ? 1 : 0, NULL); + if (optname == IP_ROUTER_ALERT) { + retv = ip_ra_control(sk, val ? 1 : 0, NULL); + if (retv == 0) + inet_assign_bit(RTALERT, sk, val); + return retv; + } if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); @@ -1575,6 +1579,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_BIND_ADDRESS_NO_PORT: val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); goto copyval; + case IP_ROUTER_ALERT: + val = inet_test_bit(RTALERT, sk); + goto copyval; case IP_TTL: val = READ_ONCE(inet->uc_ttl); if (val < 0) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 55039191b8..1b8d8ff9a2 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -102,10 +102,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else - cand = t; + cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { @@ -117,9 +116,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -137,9 +136,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -150,9 +149,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, !(t->dev->flags & IFF_UP)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -221,7 +220,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - link == t->parms.link && + link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; @@ -774,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), - dev_net(dev), tunnel->parms.link, + dev_net(dev), READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) @@ -894,7 +893,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; - t->parms.link = p->link; + WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) @@ -1084,9 +1083,9 @@ EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { - struct ip_tunnel *tunnel = netdev_priv(dev); + const struct ip_tunnel *tunnel = netdev_priv(dev); - return tunnel->parms.link; + return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); @@ -1157,19 +1156,17 @@ static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, } void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, - struct rtnl_link_ops *ops) + struct rtnl_link_ops *ops, + struct list_head *dev_to_kill) { struct ip_tunnel_net *itn; struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); - ip_tunnel_destroy(net, itn, &list, ops); + ip_tunnel_destroy(net, itn, dev_to_kill, ops); } - unregister_netdevice_many(&list); - rtnl_unlock(); } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d1d6bb28ed..ee587adb16 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -510,14 +510,16 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_batch_net(struct list_head *list_net) +static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); + ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, + dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit_batch = vti_exit_batch_net, + .exit_batch_rtnl = vti_exit_batch_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 03afa3871e..f2696eaadb 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -592,14 +592,16 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_batch_net(struct list_head *list_net) +static void __net_exit ipip_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops, + dev_to_kill); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit_batch = ipip_exit_batch_net, + .exit_batch_rtnl = ipip_exit_batch_rtnl, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b53c36c473..fd5c01c848 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2589,7 +2589,9 @@ errout_free: static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct fib_dump_filter filter = {}; + struct fib_dump_filter filter = { + .rtnl_held = true, + }; int err; if (cb->strict_check) { @@ -3141,10 +3143,7 @@ int __init ip_mr_init(void) { int err; - mrt_cachep = kmem_cache_create("ip_mrt_cache", - sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, - NULL); + mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = register_pernet_subsys(&ipmr_net_ops); if (err) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index f71a7e9a7d..1b991b8895 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -10,6 +10,10 @@ config NF_DEFRAG_IPV4 tristate default n +# old sockopt interface and eval loop +config IP_NF_IPTABLES_LEGACY + tristate + config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" help @@ -152,7 +156,7 @@ config IP_NF_MATCH_ECN config IP_NF_MATCH_RPFILTER tristate '"rpfilter" reverse path filter match support' depends on NETFILTER_ADVANCED - depends on IP_NF_MANGLE || IP_NF_RAW + depends on IP_NF_MANGLE || IP_NF_RAW || NFT_COMPAT help This option allows you to match packets whose replies would go out via the interface the packet came in. @@ -173,6 +177,7 @@ config IP_NF_MATCH_TTL config IP_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -182,7 +187,7 @@ config IP_NF_FILTER config IP_NF_TARGET_REJECT tristate "REJECT target support" - depends on IP_NF_FILTER + depends on IP_NF_FILTER || NFT_COMPAT select NF_REJECT_IPV4 default m if NETFILTER_ADVANCED=n help @@ -212,6 +217,7 @@ config IP_NF_NAT default m if NETFILTER_ADVANCED=n select NF_NAT select NETFILTER_XT_NAT + select IP_NF_IPTABLES_LEGACY help This enables the `nat' table in iptables. This allows masquerading, port forwarding and other forms of full Network Address Port @@ -252,6 +258,7 @@ endif # IP_NF_NAT config IP_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -261,7 +268,7 @@ config IP_NF_MANGLE config IP_NF_TARGET_ECN tristate "ECN target support" - depends on IP_NF_MANGLE + depends on IP_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a `ECN' target, which can be used in the iptables mangle @@ -286,6 +293,7 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' + select IP_NF_IPTABLES_LEGACY help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -299,6 +307,7 @@ config IP_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED + select IP_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -309,36 +318,36 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES - tristate "ARP tables support" - select NETFILTER_XTABLES - select NETFILTER_FAMILY_ARP - depends on NETFILTER_ADVANCED - help - arptables is a general, extensible packet identification framework. - The ARP packet filtering and mangling (manipulation)subsystems - use this: say Y or M here if you want to use either of those. - - To compile it as a module, choose M here. If unsure, say N. + tristate -if IP_NF_ARPTABLES +config NFT_COMPAT_ARP + tristate + depends on NF_TABLES_ARP && NFT_COMPAT + default m if NFT_COMPAT=m + default y if NFT_COMPAT=y config IP_NF_ARPFILTER - tristate "ARP packet filtering" + tristate "arptables-legacy packet filtering support" + select IP_NF_ARPTABLES + select NETFILTER_FAMILY_ARP + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and - local output. On a bridge, you can also specify filtering rules - for forwarded ARP packets. See the man page for arptables(8). + local output. This is only needed for arptables-legacy(8). + Neither arptables-nft nor nftables need this to work. To compile it as a module, choose M here. If unsure, say N. config IP_NF_ARP_MANGLE tristate "ARP payload mangling" + depends on IP_NF_ARPTABLES || NFT_COMPAT_ARP help Allows altering the ARP packet payload: source and destination hardware and network addresses. -endif # IP_NF_ARPTABLES + This option is needed by both arptables-legacy and arptables-nft. + It is not used by nftables. endmenu diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 5a26f9de1a..85502d4dfb 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # generic IP tables -obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o +obj-$(CONFIG_IP_NF_IPTABLES_LEGACY) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index bbff68b5b5..535856b0f0 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,6 +26,9 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ + NHA_OP_FLAG_DUMP_HW_STATS) + static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, @@ -37,10 +40,17 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, + [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), +}; + +static const struct nla_policy rtm_nh_policy_del[] = { + [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { @@ -48,6 +58,8 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -92,6 +104,7 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; + nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; @@ -131,13 +144,13 @@ static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; + info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); - info->nh_grp->nh_entries[i].id = nhge->nh->id; info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); @@ -162,6 +175,7 @@ static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; + info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; @@ -393,6 +407,7 @@ static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct nh_notifier_info info = { .net = net, .extack = extack, + .id = nh->id, }; struct nh_group *nhg; int err; @@ -474,6 +489,7 @@ static void nexthop_free_group(struct nexthop *nh) struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); + free_percpu(nhge->stats); nexthop_put(nhge->nh); } @@ -654,8 +670,204 @@ nla_put_failure: return -EMSGSIZE; } -static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) +{ + struct nh_grp_entry_stats *cpu_stats; + + cpu_stats = get_cpu_ptr(nhge->stats); + u64_stats_update_begin(&cpu_stats->syncp); + u64_stats_inc(&cpu_stats->packets); + u64_stats_update_end(&cpu_stats->syncp); + put_cpu_ptr(cpu_stats); +} + +static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, + u64 *ret_packets) { + int i; + + *ret_packets = 0; + + for_each_possible_cpu(i) { + struct nh_grp_entry_stats *cpu_stats; + unsigned int start; + u64 packets; + + cpu_stats = per_cpu_ptr(nhge->stats, i); + do { + start = u64_stats_fetch_begin(&cpu_stats->syncp); + packets = u64_stats_read(&cpu_stats->packets); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + *ret_packets += packets; + } +} + +static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + info->id = nh->id; + info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; + info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, + stats, nhg->num_nh), + GFP_KERNEL); + if (!info->nh_grp_hw_stats) + return -ENOMEM; + + info->nh_grp_hw_stats->num_nh = nhg->num_nh; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; + } + + return 0; +} + +static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp_hw_stats); +} + +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets) +{ + info->hw_stats_used = true; + info->stats[nh_idx].packets += delta_packets; +} +EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); + +static void nh_grp_hw_stats_apply_update(struct nexthop *nh, + struct nh_notifier_info *info) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; + } +} + +static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) +{ + struct nh_notifier_info info = { + .net = nh->net, + }; + struct net *net = nh->net; + int err; + + if (nexthop_notifiers_is_empty(net)) { + *hw_stats_used = false; + return 0; + } + + err = nh_notifier_grp_hw_stats_init(&info, nh); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, + &info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + nh_grp_hw_stats_apply_update(nh, &info); + *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; + + nh_notifier_grp_hw_stats_fini(&info); + return notifier_to_errno(err); +} + +static int nla_put_nh_group_stats_entry(struct sk_buff *skb, + struct nh_grp_entry *nhge, + u32 op_flags) +{ + struct nlattr *nest; + u64 packets; + + nh_grp_entry_stats_read(nhge, &packets); + + nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, + packets + nhge->packets_hw)) + goto nla_put_failure; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, + nhge->packets_hw)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + struct nlattr *nest; + bool hw_stats_used; + int err; + int i; + + if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) + goto err_out; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nhg->hw_stats) { + err = nh_grp_hw_stats_update(nh, &hw_stats_used); + if (err) + goto out; + + if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) + goto err_out; + } + + nest = nla_nest_start(skb, NHA_GROUP_STATS); + if (!nest) + goto err_out; + + for (i = 0; i < nhg->num_nh; i++) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], + op_flags)) + goto cancel_out; + + nla_nest_end(skb, nest); + return 0; + +cancel_out: + nla_nest_cancel(skb, nest); +err_out: + err = -EMSGSIZE; +out: + return err; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; @@ -684,6 +896,11 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; + if (op_flags & NHA_OP_FLAG_DUMP_STATS && + (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || + nla_put_nh_group_stats(skb, nh, op_flags))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -691,7 +908,8 @@ nla_put_failure: } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, - int event, u32 portid, u32 seq, unsigned int nlflags) + int event, u32 portid, u32 seq, unsigned int nlflags, + u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; @@ -718,7 +936,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nhg)) + if (nla_put_nh_group(skb, nh, op_flags)) goto nla_put_failure; goto out; } @@ -849,7 +1067,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) if (!skb) goto errout; - err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1104,6 +1322,7 @@ static int nh_check_attr_group(struct net *net, if (!tb[i]) continue; switch (i) { + case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: @@ -1176,6 +1395,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1185,7 +1405,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { - struct nexthop *rc = NULL; + struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) @@ -1200,16 +1420,20 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) if (!nexthop_is_good_nh(nhge->nh)) continue; - if (!rc) - rc = nhge->nh; + if (!nhge0) + nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } - return rc ? : nhg->nh_entries[0].nh; + if (!nhge0) + nhge0 = &nhg->nh_entries[0]; + nh_grp_entry_stats_inc(nhge0); + return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) @@ -1225,6 +1449,7 @@ static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1798,6 +2023,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, newg->has_v4 = true; list_del(&nhges[i].nh_list); + new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; @@ -1813,6 +2039,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); + free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through @@ -2477,6 +2704,13 @@ static struct nexthop *nexthop_create_group(struct net *net, if (nhi->family == AF_INET) nhg->has_v4 = true; + nhg->nh_entries[i].stats = + netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); + if (!nhg->nh_entries[i].stats) { + err = -ENOMEM; + nexthop_put(nhe); + goto out_no_nh; + } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = entry[i].weight + 1; list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); @@ -2509,6 +2743,9 @@ static struct nexthop *nexthop_create_group(struct net *net, if (cfg->nh_fdb) nhg->fdb_nh = 1; + if (cfg->nh_hw_stats) + nhg->hw_stats = true; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -2516,6 +2753,7 @@ static struct nexthop *nexthop_create_group(struct net *net, out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); + free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } @@ -2850,6 +3088,9 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); + if (tb[NHA_HW_STATS_ENABLE]) + cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); + /* no other attributes should be set */ goto out; } @@ -2941,6 +3182,10 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } + if (tb[NHA_HW_STATS_ENABLE]) { + NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); + goto out; + } err = 0; out: @@ -2966,9 +3211,9 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, - struct nlattr **tb, u32 *id, - struct netlink_ext_ack *extack) +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, u32 *op_flags, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); @@ -2988,28 +3233,21 @@ static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } - return 0; -} - -static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; - int err; - - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get) - 1, - rtm_nh_policy_get, extack); - if (err < 0) - return err; + if (op_flags) { + if (tb[NHA_OP_FLAGS]) + *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + *op_flags = 0; + } - return __nh_valid_get_del_req(nlh, tb, id, extack); + return 0; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_del)]; struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, @@ -3020,7 +3258,13 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_del) - 1, rtm_nh_policy_del, + extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, NULL, extack); if (err) return err; @@ -3037,13 +3281,21 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_get) - 1, rtm_nh_policy_get, + extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3058,7 +3310,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; @@ -3079,6 +3331,7 @@ struct nh_dump_filter { bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; + u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -3166,6 +3419,11 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[NHA_OP_FLAGS]) + filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + filter->op_flags = 0; + return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } @@ -3223,7 +3481,7 @@ static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ @@ -3241,10 +3499,6 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3439,11 +3693,6 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, &rtm_dump_nexthop_bucket_cb, &dd); } - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } - cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3483,7 +3732,7 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, if (err < 0) return err; - err = __nh_valid_get_del_req(nlh, tb, id, extack); + err = nh_valid_get_del_req(nlh, tb, id, NULL, extack); if (err) return err; @@ -3631,17 +3880,24 @@ unlock: } EXPORT_SYMBOL(register_nexthop_notifier); -int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; - rtnl_lock(); err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); - if (err) - goto unlock; - nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); -unlock: + if (!err) + nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); + return err; +} +EXPORT_SYMBOL(__unregister_nexthop_notifier); + +int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } @@ -3737,16 +3993,20 @@ out: } EXPORT_SYMBOL(nexthop_res_grp_activity_update); -static void __net_exit nexthop_net_exit_batch(struct list_head *net_list) +static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { + ASSERT_RTNL(); + list_for_each_entry(net, net_list, exit_list) flush_all_nexthops(net); - kfree(net->nexthop.devhash); - } - rtnl_unlock(); +} + +static void __net_exit nexthop_net_exit(struct net *net) +{ + kfree(net->nexthop.devhash); + net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) @@ -3764,7 +4024,8 @@ static int __net_init nexthop_net_init(struct net *net) static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, - .exit_batch = nexthop_net_exit_batch, + .exit = nexthop_net_exit, + .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, }; static int __init nexthop_init(void) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5f4654ebff..914bc9c35c 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -395,7 +395,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) seq_printf(seq, " %s", snmp4_ipstats_list[i].name); seq_printf(seq, "\nIp: %d %d", - IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, + IPV4_DEVCONF_ALL_RO(net, FORWARDING) ? 1 : 2, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a1d8218fa1..4cb43401e0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -175,6 +175,13 @@ static int raw_v4_input(struct net *net, struct sk_buff *skb, if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = 1; if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && ip_mc_sf_allow(sk, iph->daddr, iph->saddr, @@ -310,7 +317,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); raw_rcv_skb(sk, skb); return 0; @@ -819,7 +826,7 @@ static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *o out: return ret; } -static int do_raw_setsockopt(struct sock *sk, int level, int optname, +static int do_raw_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { if (optname == ICMP_FILTER) { @@ -836,11 +843,11 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); - return do_raw_setsockopt(sk, level, optname, optval, optlen); + return do_raw_setsockopt(sk, optname, optval, optlen); } -static int do_raw_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +static int do_raw_getsockopt(struct sock *sk, int optname, + char __user *optval, int __user *optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->inet_num != IPPROTO_ICMP) @@ -856,7 +863,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, { if (level != SOL_RAW) return ip_getsockopt(sk, level, optname, optval, optlen); - return do_raw_getsockopt(sk, level, optname, optval, optlen); + return do_raw_getsockopt(sk, optname, optval, optlen); } static int raw_ioctl(struct sock *sk, int cmd, int *karg) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index fe2140c837..cc793bd8de 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -213,6 +213,7 @@ static int raw_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler raw_diag_handler = { + .owner = THIS_MODULE, .dump = raw_diag_dump, .dump_one = raw_diag_dump_one, .idiag_get_info = raw_diag_get_info, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f67d3d6fe9..b814fdab19 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2314,7 +2314,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ - if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) + if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } @@ -2994,7 +2994,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); @@ -3694,9 +3694,8 @@ int __init ip_rt_init(void) panic("IP: failed to allocate ip_rt_acct\n"); #endif - ipv4_dst_ops.kmem_cachep = - kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + ipv4_dst_ops.kmem_cachep = KMEM_CACHE(rtable, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 61f1c96cfe..500f665f98 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -51,15 +51,6 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } -/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ -static u64 tcp_ns_to_ts(bool usec_ts, u64 val) -{ - if (usec_ts) - return div_u64(val, NSEC_PER_USEC); - - return div_u64(val, NSEC_PER_MSEC); -} - /* * when syncookies are in effect and tcp timestamps are enabled we encode * tcp options in the lower bits of the timestamp value that will be @@ -304,6 +295,24 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, return 0; } +#if IS_ENABLED(CONFIG_BPF) +struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) +{ + struct request_sock *req = inet_reqsk(skb->sk); + + skb->sk = NULL; + skb->destructor = NULL; + + if (cookie_tcp_reqsk_init(sk, skb, req)) { + reqsk_free(req); + req = NULL; + } + + return req; +} +EXPORT_SYMBOL_GPL(cookie_bpf_check); +#endif + struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, @@ -399,16 +408,23 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct rtable *rt; __u8 rcv_wscale; int full_space; + SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; - req = cookie_tcp_check(net, sk, skb); - if (IS_ERR(req)) - goto out; - if (!req) + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } + if (!req) { + SKB_DR_SET(reason, NO_SOCKET); goto out_drop; + } ireq = inet_rsk(req); @@ -420,8 +436,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) */ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); - if (security_inet_conn_request(sk, skb, req)) + if (security_inet_conn_request(sk, skb, req)) { + SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; + } tcp_ao_syncookie(sk, skb, req, AF_INET); @@ -438,8 +456,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) + if (IS_ERR(rt)) { + SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; + } /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); @@ -454,19 +474,27 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ - if (ret) - inet_sk(ret)->cork.fl.u.ip4 = fl4; + if (!ret) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } + inet_sk(ret)->cork.fl.u.ip4 = fl4; out: return ret; out_free: reqsk_free(req); out_drop: + kfree_skb_reason(skb, reason); return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 94b129301d..66d77faca6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/rps.h> /* Track pending CMSGs. */ enum { @@ -974,7 +975,7 @@ int tcp_wmem_schedule(struct sock *sk, int copy) * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ - left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued; + left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); @@ -4653,7 +4654,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 254d6e3f93..781b67a525 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -509,9 +509,9 @@ static int tcp_ao_hash_header(struct tcp_sigpool *hp, bool exclude_options, u8 *hash, int hash_offset, int hash_len) { - int err, len = th->doff << 2; struct scatterlist sg; u8 *hdr = hp->scratch; + int err, len; /* We are not allowed to change tcphdr, make a local copy */ if (exclude_options) { diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 22358032dd..05dc2d05bc 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1155,7 +1155,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; -BTF_SET8_START(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, bbr_init) @@ -1168,7 +1168,7 @@ BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) #endif #endif -BTF_SET8_END(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1b34050a75..28ffcfbeef 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -146,11 +146,7 @@ EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; - int ret; - - ret = tcp_validate_congestion_control(ca); - if (ret) - return ret; + int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0fd78ecb67..44869ea089 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -485,7 +485,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; -BTF_SET8_START(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, cubictcp_init) @@ -496,7 +496,7 @@ BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) #endif #endif -BTF_SET8_END(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index bb23bb5b38..e33fbe4933 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -260,7 +260,7 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; -BTF_SET8_START(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, dctcp_init) @@ -271,7 +271,7 @@ BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) #endif #endif -BTF_SET8_END(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4cbe4b4442..f428ecf912 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -222,6 +222,7 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler tcp_diag_handler = { + .owner = THIS_MODULE, .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ff10be8c76..a140d9f7a0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1164,7 +1164,7 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, * L|R 1 - orig is lost, retransmit is in flight. * S|R 1 - orig reached receiver, retrans is still in flight. * (L|S|R is logically valid, it could occur when L|R is sacked, - * but it is equivalent to plain S and code short-curcuits it to S. + * but it is equivalent to plain S and code short-circuits it to S. * L|S is logically invalid, it would mean -1 packet in flight 8)) * * These 6 states form finite state machine, controlled by the following events: @@ -6361,6 +6361,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_MIN, TCP_RTO_MAX); + SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE); goto reset_and_undo; } @@ -6369,6 +6370,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_time_stamp_ts(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); + SKB_DR_SET(reason, TCP_RFC7323_PAWS); goto reset_and_undo; } @@ -6572,7 +6574,8 @@ discard_and_undo: reset_and_undo: tcp_clear_options(&tp->rx_opt); tp->rx_opt.mss_clamp = saved_clamp; - return 1; + /* we can reuse/return @reason to its caller to handle the exception */ + return reason; } static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) @@ -6616,14 +6619,14 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) * address independent. */ -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) +enum skb_drop_reason +tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; - bool acceptable; SKB_DR(reason); switch (sk->sk_state) { @@ -6633,7 +6636,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LISTEN: if (th->ack) - return 1; + return SKB_DROP_REASON_TCP_FLAGS; if (th->rst) { SKB_DR_SET(reason, TCP_RESET); @@ -6649,12 +6652,10 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) */ rcu_read_lock(); local_bh_disable(); - acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; + icsk->icsk_af_ops->conn_request(sk, skb); local_bh_enable(); rcu_read_unlock(); - if (!acceptable) - return 1; consume_skb(skb); return 0; } @@ -6699,17 +6700,25 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; /* step 5: check the ACK field */ - acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT | - FLAG_NO_CHALLENGE_ACK) > 0; - - if (!acceptable) { - if (sk->sk_state == TCP_SYN_RECV) - return 1; /* send one RST */ - tcp_send_challenge_ack(sk); - SKB_DR_SET(reason, TCP_OLD_ACK); - goto discard; + reason = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT | + FLAG_NO_CHALLENGE_ACK); + + if ((int)reason <= 0) { + if (sk->sk_state == TCP_SYN_RECV) { + /* send one RST */ + if (!reason) + return SKB_DROP_REASON_TCP_OLD_ACK; + return -reason; + } + /* accept old ack during closing */ + if ((int)reason < 0) { + tcp_send_challenge_ack(sk); + reason = -reason; + goto discard; + } } + SKB_DR_SET(reason, NOT_SPECIFIED); switch (sk->sk_state) { case TCP_SYN_RECV: tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ @@ -6779,7 +6788,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (READ_ONCE(tp->linger2) < 0) { tcp_done(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { @@ -6788,7 +6797,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_fastopen_active_disable(sk); tcp_done(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } tmo = tcp_fin_time(sk); @@ -6853,7 +6862,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); tcp_reset(sk, skb); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } } fallthrough; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index abd47159d7..e0cef75f85 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1913,7 +1913,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - reason = SKB_DROP_REASON_NOT_SPECIFIED; if (tcp_checksum_complete(skb)) goto csum_err; @@ -1921,9 +1920,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) - goto discard; + return 0; if (nsk != sk) { - if (tcp_child_process(sk, nsk, skb)) { + reason = tcp_child_process(sk, nsk, skb); + if (reason) { rsk = nsk; goto reset; } @@ -1932,7 +1932,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb)) { + reason = tcp_rcv_state_process(sk, skb); + if (reason) { rsk = sk; goto reset; } @@ -2000,7 +2001,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { - 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; @@ -2009,7 +2010,6 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, bool fragstolen; u32 gso_segs; u32 gso_size; - u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), @@ -2107,13 +2107,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: - /* sk->sk_backlog.len is reset only at the end of __release_sock(). - * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach - * sk_rcvbuf in normal conditions. - */ - limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; - - limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; + limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. @@ -2121,8 +2115,6 @@ no_coalesce: */ limit += 64 * 1024; - limit = min_t(u64, limit, UINT_MAX); - if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; @@ -2290,10 +2282,12 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); - } else if (tcp_child_process(sk, nsk, skb)) { - tcp_v4_send_reset(nsk, skb); - goto discard_and_relse; } else { + drop_reason = tcp_child_process(sk, nsk, skb); + if (drop_reason) { + tcp_v4_send_reset(nsk, skb); + goto discard_and_relse; + } sock_put(sk); return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0ecc7311dc..f0761f060a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -907,11 +907,11 @@ EXPORT_SYMBOL(tcp_check_req); * be created. */ -int tcp_child_process(struct sock *parent, struct sock *child, - struct sk_buff *skb) +enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb) __releases(&((child)->sk_lock.slock)) { - int ret = 0; + enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; int state = child->sk_state; /* record sk_napi_id and sk_rx_queue_mapping of child. */ @@ -919,7 +919,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { - ret = tcp_rcv_state_process(child, skb); + reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) parent->sk_data_ready(parent); @@ -933,6 +933,6 @@ int tcp_child_process(struct sock *parent, struct sock *child, bh_unlock_sock(child); sock_put(child); - return ret; + return reason; } EXPORT_SYMBOL(tcp_child_process); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8311c38267..ebe4722bb0 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -204,7 +204,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) goto out; hlen = off + thlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; @@ -299,18 +299,20 @@ out: void tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); + struct skb_shared_info *shinfo; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; - skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + shinfo = skb_shinfo(skb); + shinfo->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - - if (skb->encapsulation) - skb->inner_transport_header = skb->transport_header; + shinfo->gso_type |= SKB_GSO_TCP_ECN; } EXPORT_SYMBOL(tcp_gro_complete); @@ -335,24 +337,22 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; - if (NAPI_GRO_CB(skb)->is_atomic) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | + (NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; } -static const struct net_offload tcpv4_offload = { - .callbacks = { - .gso_segment = tcp4_gso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - }, -}; - int __init tcpv4_offload_init(void) { - return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); + net_hotdata.tcpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp4_gso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.tcpv4_offload, IPPROTO_TCP); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e980869f18..b32cf2eeeb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -411,8 +411,6 @@ INDIRECT_CALLABLE_SCOPE u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 udp_ehash_secret __read_mostly; - net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, @@ -429,21 +427,15 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; int score, badness; - bool need_rescore; result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - need_rescore = false; -rescore: - score = compute_score(need_rescore ? result : sk, net, saddr, - sport, daddr, hnum, dif, sdif); + score = compute_score(sk, net, saddr, sport, + daddr, hnum, dif, sdif); if (score > badness) { badness = score; - if (need_rescore) - continue; - if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; @@ -464,14 +456,9 @@ rescore: if (IS_ERR(result)) continue; - /* compute_score is too long of a function to be - * inlined, and calling it again here yields - * measureable overhead for some - * workloads. Work around it by jumping - * backwards to rescore 'result'. - */ - need_rescore = true; - goto rescore; + badness = compute_score(result, net, saddr, sport, + daddr, hnum, dif, sdif); + } } return result; @@ -1609,7 +1596,8 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - sk_peek_offset_bwd(sk, len); + if (unlikely(READ_ONCE(udp_sk(sk)->peeking_with_offset))) + sk_peek_offset_bwd(sk, len); if (!skb_unref(skb)) return; @@ -2589,11 +2577,12 @@ int udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif, sdif); } - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return 0; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index dc41a22ee8..38cb3a28e4 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -237,6 +237,7 @@ static int udplite_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler udp_diag_handler = { + .owner = THIS_MODULE, .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, @@ -260,6 +261,7 @@ static int udplite_diag_dump_one(struct netlink_callback *cb, } static const struct inet_diag_handler udplite_diag_handler = { + .owner = THIS_MODULE, .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e5971890d6..8721fe5bec 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -751,15 +751,14 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } -static const struct net_offload udpv4_offload = { - .callbacks = { - .gso_segment = udp4_ufo_fragment, - .gro_receive = udp4_gro_receive, - .gro_complete = udp4_gro_complete, - }, -}; - int __init udpv4_offload_init(void) { - return inet_add_offload(&udpv4_offload, IPPROTO_UDP); + net_hotdata.udpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp4_ufo_fragment, + .gro_receive = udp4_gro_receive, + .gro_complete = udp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 801404f7d6..86382e0814 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -58,7 +58,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) return -iph->protocol; #endif - __skb_push(skb, skb->data - skb_network_header(skb)); + __skb_push(skb, -skb_network_offset(skb)); iph->tot_len = htons(skb->len); ip_send_check(iph); |