diff options
Diffstat (limited to 'net/ipv4')
34 files changed, 1283 insertions, 760 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 25a8888826b8..23ba5045e3d3 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -49,7 +49,7 @@ config IP_ADVANCED_ROUTER Note that some distributions enable it in startup scripts. For details about rp_filter strict and loose mode read - <file:Documentation/networking/ip-sysctl.txt>. + <file:Documentation/networking/ip-sysctl.rst>. If unsure, say N here. @@ -384,6 +384,7 @@ config INET_ESPINTCP depends on XFRM && INET_ESP select STREAM_PARSER select NET_SOCK_MSG + select XFRM_ESPINTCP help Support for RFC 8229 encapsulation of ESP and IKE over TCP/IPv4 sockets. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index cf58e29cf746..02aa5cb3a4fd 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -116,6 +116,7 @@ #include <linux/mroute.h> #endif #include <net/l3mdev.h> +#include <net/compat.h> #include <trace/events/sock.h> @@ -450,12 +451,12 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (err) return err; - return __inet_bind(sk, uaddr, addr_len, false, true); + return __inet_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock) + u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); @@ -506,7 +507,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ - if (with_lock) + if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ @@ -520,16 +521,18 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || - force_bind_address_no_port)) { + (flags & BIND_FORCE_ADDRESS_NO_PORT))) { if (sk->sk_prot->get_port(sk, snum)) { inet->inet_saddr = inet->inet_rcv_saddr = 0; err = -EADDRINUSE; goto out_release_sock; } - err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); - if (err) { - inet->inet_saddr = inet->inet_rcv_saddr = 0; - goto out_release_sock; + if (!(flags & BIND_FROM_BPF)) { + err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); + if (err) { + inet->inet_saddr = inet->inet_rcv_saddr = 0; + goto out_release_sock; + } } } @@ -543,7 +546,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, sk_dst_reset(sk); err = 0; out_release_sock: - if (with_lock) + if (flags & BIND_WITH_LOCK) release_sock(sk); out: return err; @@ -753,12 +756,11 @@ do_err: } EXPORT_SYMBOL(inet_accept); - /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, - int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -779,6 +781,11 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; } + if (cgroup_bpf_enabled) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + peer ? BPF_CGROUP_INET4_GETPEERNAME : + BPF_CGROUP_INET4_GETSOCKNAME, + NULL); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } @@ -968,17 +975,42 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT +static int inet_compat_routing_ioctl(struct sock *sk, unsigned int cmd, + struct compat_rtentry __user *ur) +{ + compat_uptr_t rtdev; + struct rtentry rt; + + if (copy_from_user(&rt.rt_dst, &ur->rt_dst, + 3 * sizeof(struct sockaddr)) || + get_user(rt.rt_flags, &ur->rt_flags) || + get_user(rt.rt_metric, &ur->rt_metric) || + get_user(rt.rt_mtu, &ur->rt_mtu) || + get_user(rt.rt_window, &ur->rt_window) || + get_user(rt.rt_irtt, &ur->rt_irtt) || + get_user(rtdev, &ur->rt_dev)) + return -EFAULT; + + rt.rt_dev = compat_ptr(rtdev); + return ip_rt_ioctl(sock_net(sk), cmd, &rt); +} + static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { + void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; - int err = -ENOIOCTLCMD; - - if (sk->sk_prot->compat_ioctl) - err = sk->sk_prot->compat_ioctl(sk, cmd, arg); - return err; + switch (cmd) { + case SIOCADDRT: + case SIOCDELRT: + return inet_compat_routing_ioctl(sk, cmd, argp); + default: + if (!sk->sk_prot->compat_ioctl) + return -ENOIOCTLCMD; + return sk->sk_prot->compat_ioctl(sk, cmd, arg); + } } -#endif +#endif /* CONFIG_COMPAT */ const struct proto_ops inet_stream_ops = { .family = PF_INET, @@ -1835,6 +1867,7 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; net->ipv4.sysctl_tcp_early_demux = 1; + net->ipv4.sysctl_nexthop_compat_mode = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif @@ -1914,7 +1947,7 @@ static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; - int rc = -EINVAL; + int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 0bd10a1f477f..a23094b050f8 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 30fa42f5997d..123a6d39438f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev) err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; + neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; @@ -614,12 +615,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } -static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) { +#if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; + struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); @@ -632,6 +636,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) release_sock(sk); return ret; +#else + return -EOPNOTSUPP; +#endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -675,7 +682,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, continue; if (ipv4_is_multicast(ifa->ifa_address)) - ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); + ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -940,8 +947,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { - int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, - true, ifa); + int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); @@ -2361,8 +2367,7 @@ static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) } static int devinet_conf_proc(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); @@ -2414,8 +2419,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, } static int devinet_sysctl_forward(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; @@ -2458,8 +2462,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, } static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; @@ -2664,11 +2667,24 @@ static __net_init int devinet_init_net(struct net *net) tbl[0].extra2 = net; #endif - if ((!IS_ENABLED(CONFIG_SYSCTL) || - sysctl_devconf_inherit_init_net != 2) && - !net_eq(net, &init_net)) { - memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); - memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); + if (!net_eq(net, &init_net)) { + if (IS_ENABLED(CONFIG_SYSCTL) && + sysctl_devconf_inherit_init_net == 3) { + /* copy from the current netns */ + memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, + sizeof(ipv4_devconf)); + memcpy(dflt, + current->nsproxy->net_ns->ipv4.devconf_dflt, + sizeof(ipv4_devconf_dflt)); + } else if (!IS_ENABLED(CONFIG_SYSCTL) || + sysctl_devconf_inherit_init_net != 2) { + /* inherit == 0 or 1: copy from init_net */ + memcpy(all, init_net.ipv4.devconf_all, + sizeof(ipv4_devconf)); + memcpy(dflt, init_net.ipv4.devconf_dflt, + sizeof(ipv4_devconf_dflt)); + } + /* else inherit == 2: use compiled values */ } #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 731022cff600..d14133eac476 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, sp->olen++; xo = xfrm_offload(skb); - if (!xo) { - xfrm_state_put(x); + if (!xo) goto out_reset; - } } xo->flags |= XFRM_GRO; @@ -139,19 +137,27 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x, struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; - int proto = xo->proto; + u8 proto = xo->proto; skb->transport_header += x->props.header_len; - if (proto == IPPROTO_BEETPH) { - struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; + if (x->sel.family != AF_INET6) { + if (proto == IPPROTO_BEETPH) { + struct ip_beet_phdr *ph = + (struct ip_beet_phdr *)skb->data; + + skb->transport_header += ph->hdrlen * 8; + proto = ph->nexthdr; + } else { + skb->transport_header -= IPV4_BEET_PHMAXLEN; + } + } else { + __be16 frag; - skb->transport_header += ph->hdrlen * 8; - proto = ph->nexthdr; - } else if (x->sel.family != AF_INET6) { - skb->transport_header -= IPV4_BEET_PHMAXLEN; - } else if (proto == IPPROTO_TCP) { - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + skb->transport_header += + ipv6_skip_exthdr(skb, 0, &proto, &frag); + if (proto == IPPROTO_TCP) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; } __skb_pull(skb, skb_transport_offset(skb)); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 213be9c050ad..41079490a118 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -309,17 +309,18 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH - int ret; + if (unlikely(fi->nh)) { + dev_match = nexthop_uses_dev(fi->nh, dev); + } else { + int ret; - for (ret = 0; ret < fib_info_num_path(fi); ret++) { - const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); + for (ret = 0; ret < fib_info_num_path(fi); ret++) { + const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); - if (nhc->nhc_dev == dev) { - dev_match = true; - break; - } else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) { - dev_match = true; - break; + if (nhc_l3mdev_matches_dev(nhc, dev)) { + dev_match = true; + break; + } } } #else @@ -918,7 +919,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, else filter->dump_exceptions = false; - filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC); filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; @@ -990,7 +990,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { - if (filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != PF_INET) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 6ed8c9317179..e53871e4a097 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1780,6 +1780,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; if (nexthop_is_blackhole(fi->nh)) rtm->rtm_type = RTN_BLACKHOLE; + if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode) + goto offload; } if (nhs == 1) { @@ -1805,6 +1807,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; } +offload: if (fri->offload) rtm->rtm_flags |= RTM_F_OFFLOAD; if (fri->trap) @@ -2014,7 +2017,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; - struct fib_nh *nh; + struct fib_nh_common *nhc; if (fa->fa_slen != slen) continue; @@ -2037,8 +2040,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) fa->fa_type != RTN_UNICAST) continue; - nh = fib_info_nh(next_fi, 0); - if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK) + nhc = fib_info_nhc(next_fi, 0); + if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK) continue; fib_alias_accessed(fa); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4f334b425538..248f1c1959a6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1371,6 +1371,26 @@ static inline t_key prefix_mismatch(t_key key, struct key_vector *n) return (key ^ prefix) & (prefix | -prefix); } +bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, + const struct flowi4 *flp) +{ + if (nhc->nhc_flags & RTNH_F_DEAD) + return false; + + if (ip_ignore_linkdown(nhc->nhc_dev) && + nhc->nhc_flags & RTNH_F_LINKDOWN && + !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) + return false; + + if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { + if (flp->flowi4_oif && + flp->flowi4_oif != nhc->nhc_oif) + return false; + } + + return true; +} + /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) @@ -1503,6 +1523,7 @@ found: /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; + struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { @@ -1528,26 +1549,25 @@ out_reject: if (fi->fib_flags & RTNH_F_DEAD) continue; - if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) { - err = fib_props[RTN_BLACKHOLE].error; - goto out_reject; + if (unlikely(fi->nh)) { + if (nexthop_is_blackhole(fi->nh)) { + err = fib_props[RTN_BLACKHOLE].error; + goto out_reject; + } + + nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, + &nhsel); + if (nhc) + goto set_result; + goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { - struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); + nhc = fib_info_nhc(fi, nhsel); - if (nhc->nhc_flags & RTNH_F_DEAD) + if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; - if (ip_ignore_linkdown(nhc->nhc_dev) && - nhc->nhc_flags & RTNH_F_LINKDOWN && - !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) - continue; - if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { - if (flp->flowi4_oif && - flp->flowi4_oif != nhc->nhc_oif) - continue; - } - +set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); @@ -1568,6 +1588,7 @@ out_reject: return err; } } +miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index fc61f51d87a3..956a806649f7 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -853,7 +853,7 @@ static bool icmp_unreach(struct sk_buff *skb) case ICMP_FRAG_NEEDED: /* for documentation of the ip_no_pmtu_disc * values please see - * Documentation/networking/ip-sysctl.txt + * Documentation/networking/ip-sysctl.rst */ switch (net->ipv4.sysctl_ip_no_pmtu_disc) { default: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 47f0502b2101..7b272bbed2b4 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2565,9 +2565,9 @@ done: } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct group_filter __user *optval, int __user *optlen) + struct sockaddr_storage __user *p) { - int err, i, count, copycount; + int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; @@ -2583,37 +2583,29 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!ipv4_is_multicast(addr)) return -EINVAL; - err = -EADDRNOTAVAIL; - for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ - goto done; + return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; - if (put_user(GROUP_FILTER_SIZE(copycount), optlen) || - copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { - return -EFAULT; - } - for (i = 0; i < copycount; i++) { + for (i = 0; i < copycount; i++, p++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; - if (copy_to_user(&optval->gf_slist[i], &ss, sizeof(ss))) + if (copy_to_user(p, &ss, sizeof(ss))) return -EFAULT; } return 0; -done: - return err; } /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5f34eb951627..afaf582a5aa9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -24,17 +24,19 @@ #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) -/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 - * only, and any IPv4 addresses if not IPv6 only - * match_wildcard == false: addresses must be exactly the same, i.e. - * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, - * and 0.0.0.0 equals to 0.0.0.0 only +/* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses + * if IPv6 only, and any IPv4 addresses + * if not IPv6 only + * match_sk*_wildcard == false: addresses must be exactly the same, i.e. + * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, + * and 0.0.0.0 equals to 0.0.0.0 only */ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, const struct in6_addr *sk2_rcv_saddr6, __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk1_ipv6only, bool sk2_ipv6only, - bool match_wildcard) + bool match_sk1_wildcard, + bool match_sk2_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; - if (!sk1_rcv_saddr || !sk2_rcv_saddr) - return match_wildcard; + return (match_sk1_wildcard && !sk1_rcv_saddr) || + (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } @@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) return true; - if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && + if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return true; - if (addr_type == IPV6_ADDR_ANY && match_wildcard && + if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) return true; @@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, } #endif -/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses - * match_wildcard == false: addresses must be exactly the same, i.e. - * 0.0.0.0 only equals to 0.0.0.0 +/* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses + * match_sk*_wildcard == false: addresses must be exactly the same, i.e. + * 0.0.0.0 only equals to 0.0.0.0 */ static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk2_ipv6only, bool match_wildcard) + bool sk2_ipv6only, bool match_sk1_wildcard, + bool match_sk2_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; - if (!sk1_rcv_saddr || !sk2_rcv_saddr) - return match_wildcard; + return (match_sk1_wildcard && !sk1_rcv_saddr) || + (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } @@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, sk2->sk_rcv_saddr, ipv6_only_sock(sk), ipv6_only_sock(sk2), + match_wildcard, match_wildcard); #endif return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr, - ipv6_only_sock(sk2), match_wildcard); + ipv6_only_sock(sk2), match_wildcard, + match_wildcard); } EXPORT_SYMBOL(inet_rcv_saddr_equal); @@ -285,10 +290,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, - ipv6_only_sock(sk), true); + ipv6_only_sock(sk), true, false); #endif return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr, - ipv6_only_sock(sk), true); + ipv6_only_sock(sk), true, false); } /* Obtain a reference to a local port for the given sock, @@ -896,10 +901,7 @@ void inet_csk_prepare_forced_close(struct sock *sk) /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); sock_put(sk); - - /* The below has to be done to allow calling inet_csk_destroy_sock */ - sock_set_flag(sk, SOCK_DEAD); - percpu_counter_inc(sk->sk_prot->orphan_count); + inet_csk_prepare_for_destroy_sock(sk); inet_sk(sk)->inet_num = 0; } EXPORT_SYMBOL(inet_csk_prepare_forced_close); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5d50aad3cdbf..125f4f8a36b4 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -43,6 +43,9 @@ struct inet_diag_entry { u16 userlocks; u32 ifindex; u32 mark; +#ifdef CONFIG_SOCK_CGROUP_DATA + u64 cgroup_id; +#endif }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -162,6 +165,13 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, goto errout; } +#ifdef CONFIG_SOCK_CGROUP_DATA + if (nla_put_u64_64bit(skb, INET_DIAG_CGROUP_ID, + cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)), + INET_DIAG_PAD)) + goto errout; +#endif + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -675,6 +685,16 @@ static int inet_diag_bc_run(const struct nlattr *_bc, yes = 0; break; } +#ifdef CONFIG_SOCK_CGROUP_DATA + case INET_DIAG_BC_CGROUP_COND: { + u64 cgroup_id; + + cgroup_id = get_unaligned((const u64 *)(op + 1)); + if (cgroup_id != entry->cgroup_id) + yes = 0; + break; + } +#endif } if (yes) { @@ -725,6 +745,10 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else entry.mark = 0; +#ifdef CONFIG_SOCK_CGROUP_DATA + entry.cgroup_id = sk_fullsock(sk) ? + cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)) : 0; +#endif return inet_diag_bc_run(bc, &entry); } @@ -814,6 +838,15 @@ static bool valid_markcond(const struct inet_diag_bc_op *op, int len, return len >= *min_len; } +#ifdef CONFIG_SOCK_CGROUP_DATA +static bool valid_cgroupcond(const struct inet_diag_bc_op *op, int len, + int *min_len) +{ + *min_len += sizeof(u64); + return len >= *min_len; +} +#endif + static int inet_diag_bc_audit(const struct nlattr *attr, const struct sk_buff *skb) { @@ -856,6 +889,12 @@ static int inet_diag_bc_audit(const struct nlattr *attr, if (!valid_markcond(bc, len, &min_len)) return -EINVAL; break; +#ifdef CONFIG_SOCK_CGROUP_DATA + case INET_DIAG_BC_CGROUP_COND: + if (!valid_cgroupcond(bc, len, &min_len)) + return -EINVAL; + break; +#endif case INET_DIAG_BC_AUTO: case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 029b24eeafba..4e31f23e4117 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -248,6 +248,15 @@ static void gre_err(struct sk_buff *skb, u32 info) ipgre_err(skb, info, &tpi); } +static bool is_erspan_type1(int gre_hdr_len) +{ + /* Both ERSPAN type I (version 0) and type II (version 1) use + * protocol 0x88BE, but the type I has only 4-byte GRE header, + * while type II has 8-byte. + */ + return gre_hdr_len == 4; +} + static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { @@ -262,17 +271,26 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int len; itn = net_generic(net, erspan_net_id); - iph = ip_hdr(skb); - ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); - ver = ershdr->ver; - - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_KEY, - iph->saddr, iph->daddr, tpi->key); + if (is_erspan_type1(gre_hdr_len)) { + ver = 0; + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, + tpi->flags | TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + } else { + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); + ver = ershdr->ver; + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, + tpi->flags | TUNNEL_KEY, + iph->saddr, iph->daddr, tpi->key); + } if (tunnel) { - len = gre_hdr_len + erspan_hdr_len(ver); + if (is_erspan_type1(gre_hdr_len)) + len = gre_hdr_len; + else + len = gre_hdr_len + erspan_hdr_len(ver); + if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; @@ -665,7 +683,10 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, } /* Push ERSPAN header */ - if (tunnel->erspan_ver == 1) { + if (tunnel->erspan_ver == 0) { + proto = htons(ETH_P_ERSPAN); + tunnel->parms.o_flags &= ~TUNNEL_SEQ; + } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); @@ -747,45 +768,37 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) } } -static int ipgre_tunnel_ioctl(struct net_device *dev, - struct ifreq *ifr, int cmd) +static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, + int cmd) { - struct ip_tunnel_parm p; int err; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) - return -EFAULT; - if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE || - p.iph.ihl != 5 || (p.iph.frag_off & htons(~IP_DF)) || - ((p.i_flags | p.o_flags) & (GRE_VERSION | GRE_ROUTING))) + if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || + p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || + ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } - p.i_flags = gre_flags_to_tnl_flags(p.i_flags); - p.o_flags = gre_flags_to_tnl_flags(p.o_flags); + p->i_flags = gre_flags_to_tnl_flags(p->i_flags); + p->o_flags = gre_flags_to_tnl_flags(p->o_flags); - err = ip_tunnel_ioctl(dev, &p, cmd); + err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + t->parms.i_flags = p->i_flags; + t->parms.o_flags = p->o_flags; if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } - p.i_flags = gre_tnl_flags_to_gre_flags(p.i_flags); - p.o_flags = gre_tnl_flags_to_gre_flags(p.o_flags); - - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - return -EFAULT; - + p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); + p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); return 0; } @@ -903,10 +916,11 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, - .ndo_do_ioctl = ipgre_tunnel_ioctl, + .ndo_do_ioctl = ip_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_tunnel_ctl = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ @@ -1066,7 +1080,11 @@ static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], if (ret) return ret; - /* ERSPAN should only have GRE sequence and key flag */ + if (data[IFLA_GRE_ERSPAN_VER] && + nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) + return 0; + + /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) @@ -1174,7 +1192,7 @@ static int erspan_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - if (t->erspan_ver != 1 && t->erspan_ver != 2) + if (t->erspan_ver > 2) return -EINVAL; } @@ -1259,7 +1277,11 @@ static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - tunnel->tun_hlen = 8; + if (tunnel->erspan_ver == 0) + tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ + else + tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ + tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); @@ -1456,8 +1478,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if (t->erspan_ver == 1 || t->erspan_ver == 2) { - if (!t->collect_md) + if (t->erspan_ver <= 2) { + if (t->erspan_ver != 0 && !t->collect_md) o_flags |= TUNNEL_KEY; if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) @@ -1466,7 +1488,7 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; - } else { + } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index aa3fd61818c4..84ec3703c909 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -560,6 +560,61 @@ out: return err; } +static void __ip_sock_set_tos(struct sock *sk, int val) +{ + if (sk->sk_type == SOCK_STREAM) { + val &= ~INET_ECN_MASK; + val |= inet_sk(sk)->tos & INET_ECN_MASK; + } + if (inet_sk(sk)->tos != val) { + inet_sk(sk)->tos = val; + sk->sk_priority = rt_tos2priority(val); + sk_dst_reset(sk); + } +} + +void ip_sock_set_tos(struct sock *sk, int val) +{ + lock_sock(sk); + __ip_sock_set_tos(sk, val); + release_sock(sk); +} +EXPORT_SYMBOL(ip_sock_set_tos); + +void ip_sock_set_freebind(struct sock *sk) +{ + lock_sock(sk); + inet_sk(sk)->freebind = true; + release_sock(sk); +} +EXPORT_SYMBOL(ip_sock_set_freebind); + +void ip_sock_set_recverr(struct sock *sk) +{ + lock_sock(sk); + inet_sk(sk)->recverr = true; + release_sock(sk); +} +EXPORT_SYMBOL(ip_sock_set_recverr); + +int ip_sock_set_mtu_discover(struct sock *sk, int val) +{ + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) + return -EINVAL; + lock_sock(sk); + inet_sk(sk)->pmtudisc = val; + release_sock(sk); + return 0; +} +EXPORT_SYMBOL(ip_sock_set_mtu_discover); + +void ip_sock_set_pktinfo(struct sock *sk) +{ + lock_sock(sk); + inet_sk(sk)->cmsg_flags |= IP_CMSG_PKTINFO; + release_sock(sk); +} +EXPORT_SYMBOL(ip_sock_set_pktinfo); /* * Socket option code for IP. This is the end of the line after any @@ -587,6 +642,86 @@ static bool setsockopt_needs_rtnl(int optname) return false; } +static int set_mcast_msfilter(struct sock *sk, int ifindex, + int numsrc, int fmode, + struct sockaddr_storage *group, + struct sockaddr_storage *list) +{ + int msize = IP_MSFILTER_SIZE(numsrc); + struct ip_msfilter *msf; + struct sockaddr_in *psin; + int err, i; + + msf = kmalloc(msize, GFP_KERNEL); + if (!msf) + return -ENOBUFS; + + psin = (struct sockaddr_in *)group; + if (psin->sin_family != AF_INET) + goto Eaddrnotavail; + msf->imsf_multiaddr = psin->sin_addr.s_addr; + msf->imsf_interface = 0; + msf->imsf_fmode = fmode; + msf->imsf_numsrc = numsrc; + for (i = 0; i < numsrc; ++i) { + psin = (struct sockaddr_in *)&list[i]; + + if (psin->sin_family != AF_INET) + goto Eaddrnotavail; + msf->imsf_slist[i] = psin->sin_addr.s_addr; + } + err = ip_mc_msfilter(sk, msf, ifindex); + kfree(msf); + return err; + +Eaddrnotavail: + kfree(msf); + return -EADDRNOTAVAIL; +} + +static int do_mcast_group_source(struct sock *sk, int optname, + struct group_source_req *greqs) +{ + struct ip_mreq_source mreqs; + struct sockaddr_in *psin; + int omode, add, err; + + if (greqs->gsr_group.ss_family != AF_INET || + greqs->gsr_source.ss_family != AF_INET) + return -EADDRNOTAVAIL; + + psin = (struct sockaddr_in *)&greqs->gsr_group; + mreqs.imr_multiaddr = psin->sin_addr.s_addr; + psin = (struct sockaddr_in *)&greqs->gsr_source; + mreqs.imr_sourceaddr = psin->sin_addr.s_addr; + mreqs.imr_interface = 0; /* use index for mc_source */ + + if (optname == MCAST_BLOCK_SOURCE) { + omode = MCAST_EXCLUDE; + add = 1; + } else if (optname == MCAST_UNBLOCK_SOURCE) { + omode = MCAST_EXCLUDE; + add = 0; + } else if (optname == MCAST_JOIN_SOURCE_GROUP) { + struct ip_mreqn mreq; + + psin = (struct sockaddr_in *)&greqs->gsr_group; + mreq.imr_multiaddr = psin->sin_addr; + mreq.imr_address.s_addr = 0; + mreq.imr_ifindex = greqs->gsr_interface; + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); + if (err && err != -EADDRINUSE) + return err; + greqs->gsr_interface = mreq.imr_ifindex; + omode = MCAST_INCLUDE; + add = 1; + } else /* MCAST_LEAVE_SOURCE_GROUP */ { + omode = MCAST_INCLUDE; + add = 0; + } + return ip_mc_source(add, omode, sk, &mreqs, greqs->gsr_interface); +} + static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { @@ -743,15 +878,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE; break; case IP_TOS: /* This sets both TOS and Precedence */ - if (sk->sk_type == SOCK_STREAM) { - val &= ~INET_ECN_MASK; - val |= inet->tos & INET_ECN_MASK; - } - if (inet->tos != val) { - inet->tos = val; - sk->sk_priority = rt_tos2priority(val); - sk_dst_reset(sk); - } + __ip_sock_set_tos(sk, val); break; case IP_TTL: if (optlen < 1) @@ -1029,9 +1156,6 @@ static int do_ip_setsockopt(struct sock *sk, int level, case MCAST_UNBLOCK_SOURCE: { struct group_source_req greqs; - struct ip_mreq_source mreqs; - struct sockaddr_in *psin; - int omode, add; if (optlen != sizeof(struct group_source_req)) goto e_inval; @@ -1039,50 +1163,12 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -EFAULT; break; } - if (greqs.gsr_group.ss_family != AF_INET || - greqs.gsr_source.ss_family != AF_INET) { - err = -EADDRNOTAVAIL; - break; - } - psin = (struct sockaddr_in *)&greqs.gsr_group; - mreqs.imr_multiaddr = psin->sin_addr.s_addr; - psin = (struct sockaddr_in *)&greqs.gsr_source; - mreqs.imr_sourceaddr = psin->sin_addr.s_addr; - mreqs.imr_interface = 0; /* use index for mc_source */ - - if (optname == MCAST_BLOCK_SOURCE) { - omode = MCAST_EXCLUDE; - add = 1; - } else if (optname == MCAST_UNBLOCK_SOURCE) { - omode = MCAST_EXCLUDE; - add = 0; - } else if (optname == MCAST_JOIN_SOURCE_GROUP) { - struct ip_mreqn mreq; - - psin = (struct sockaddr_in *)&greqs.gsr_group; - mreq.imr_multiaddr = psin->sin_addr; - mreq.imr_address.s_addr = 0; - mreq.imr_ifindex = greqs.gsr_interface; - err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); - if (err && err != -EADDRINUSE) - break; - greqs.gsr_interface = mreq.imr_ifindex; - omode = MCAST_INCLUDE; - add = 1; - } else /* MCAST_LEAVE_SOURCE_GROUP */ { - omode = MCAST_INCLUDE; - add = 0; - } - err = ip_mc_source(add, omode, sk, &mreqs, - greqs.gsr_interface); + err = do_mcast_group_source(sk, optname, &greqs); break; } case MCAST_MSFILTER: { - struct sockaddr_in *psin; - struct ip_msfilter *msf = NULL; struct group_filter *gsf = NULL; - int msize, i, ifindex; if (optlen < GROUP_FILTER_SIZE(0)) goto e_inval; @@ -1095,7 +1181,6 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = PTR_ERR(gsf); break; } - /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) { @@ -1106,36 +1191,10 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -EINVAL; goto mc_msf_out; } - msize = IP_MSFILTER_SIZE(gsf->gf_numsrc); - msf = kmalloc(msize, GFP_KERNEL); - if (!msf) { - err = -ENOBUFS; - goto mc_msf_out; - } - ifindex = gsf->gf_interface; - psin = (struct sockaddr_in *)&gsf->gf_group; - if (psin->sin_family != AF_INET) { - err = -EADDRNOTAVAIL; - goto mc_msf_out; - } - msf->imsf_multiaddr = psin->sin_addr.s_addr; - msf->imsf_interface = 0; - msf->imsf_fmode = gsf->gf_fmode; - msf->imsf_numsrc = gsf->gf_numsrc; - err = -EADDRNOTAVAIL; - for (i = 0; i < gsf->gf_numsrc; ++i) { - psin = (struct sockaddr_in *)&gsf->gf_slist[i]; - - if (psin->sin_family != AF_INET) - goto mc_msf_out; - msf->imsf_slist[i] = psin->sin_addr.s_addr; - } - kfree(gsf); - gsf = NULL; - - err = ip_mc_msfilter(sk, msf, ifindex); + err = set_mcast_msfilter(sk, gsf->gf_interface, + gsf->gf_numsrc, gsf->gf_fmode, + &gsf->gf_group, gsf->gf_slist); mc_msf_out: - kfree(msf); kfree(gsf); break; } @@ -1272,9 +1331,113 @@ int compat_ip_setsockopt(struct sock *sk, int level, int optname, if (level != SOL_IP) return -ENOPROTOOPT; - if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER) - return compat_mc_setsockopt(sk, level, optname, optval, optlen, - ip_setsockopt); + switch (optname) { + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + { + struct compat_group_req __user *gr32 = (void __user *)optval; + struct group_req greq; + struct sockaddr_in *psin = (struct sockaddr_in *)&greq.gr_group; + struct ip_mreqn mreq; + + if (optlen < sizeof(struct compat_group_req)) + return -EINVAL; + + if (get_user(greq.gr_interface, &gr32->gr_interface) || + copy_from_user(&greq.gr_group, &gr32->gr_group, + sizeof(greq.gr_group))) + return -EFAULT; + + if (psin->sin_family != AF_INET) + return -EINVAL; + + memset(&mreq, 0, sizeof(mreq)); + mreq.imr_multiaddr = psin->sin_addr; + mreq.imr_ifindex = greq.gr_interface; + + rtnl_lock(); + lock_sock(sk); + if (optname == MCAST_JOIN_GROUP) + err = ip_mc_join_group(sk, &mreq); + else + err = ip_mc_leave_group(sk, &mreq); + release_sock(sk); + rtnl_unlock(); + return err; + } + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + { + struct compat_group_source_req __user *gsr32 = (void __user *)optval; + struct group_source_req greqs; + + if (optlen != sizeof(struct compat_group_source_req)) + return -EINVAL; + + if (get_user(greqs.gsr_interface, &gsr32->gsr_interface) || + copy_from_user(&greqs.gsr_group, &gsr32->gsr_group, + sizeof(greqs.gsr_group)) || + copy_from_user(&greqs.gsr_source, &gsr32->gsr_source, + sizeof(greqs.gsr_source))) + return -EFAULT; + + rtnl_lock(); + lock_sock(sk); + err = do_mcast_group_source(sk, optname, &greqs); + release_sock(sk); + rtnl_unlock(); + return err; + } + case MCAST_MSFILTER: + { + const int size0 = offsetof(struct compat_group_filter, gf_slist); + struct compat_group_filter *gf32; + unsigned int n; + void *p; + + if (optlen < size0) + return -EINVAL; + if (optlen > sysctl_optmem_max - 4) + return -ENOBUFS; + + p = kmalloc(optlen + 4, GFP_KERNEL); + if (!p) + return -ENOMEM; + gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + if (copy_from_user(gf32, optval, optlen)) { + err = -EFAULT; + goto mc_msf_out; + } + + n = gf32->gf_numsrc; + /* numsrc >= (4G-140)/128 overflow in 32 bits */ + if (n >= 0x1ffffff) { + err = -ENOBUFS; + goto mc_msf_out; + } + if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) { + err = -EINVAL; + goto mc_msf_out; + } + + rtnl_lock(); + lock_sock(sk); + /* numsrc >= (4G-140)/128 overflow in 32 bits */ + if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + err = -ENOBUFS; + else + err = set_mcast_msfilter(sk, gf32->gf_interface, + n, gf32->gf_fmode, + &gf32->gf_group, gf32->gf_slist); + release_sock(sk); + rtnl_unlock(); +mc_msf_out: + kfree(p); + return err; + } + } err = do_ip_setsockopt(sk, level, optname, optval, optlen); #ifdef CONFIG_NETFILTER @@ -1465,19 +1628,28 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, } case MCAST_MSFILTER: { + struct group_filter __user *p = (void __user *)optval; struct group_filter gsf; + const int size0 = offsetof(struct group_filter, gf_slist); + int num; - if (len < GROUP_FILTER_SIZE(0)) { + if (len < size0) { err = -EINVAL; goto out; } - if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) { + if (copy_from_user(&gsf, p, size0)) { err = -EFAULT; goto out; } - err = ip_mc_gsfget(sk, &gsf, - (struct group_filter __user *)optval, - optlen); + num = gsf.gf_numsrc; + err = ip_mc_gsfget(sk, &gsf, p->gf_slist); + if (err) + goto out; + if (gsf.gf_numsrc < num) + num = gsf.gf_numsrc; + if (put_user(GROUP_FILTER_SIZE(num), optlen) || + copy_to_user(p, &gsf, size0)) + err = -EFAULT; goto out; } case IP_MULTICAST_ALL: @@ -1492,7 +1664,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; - msg.msg_control = (__force void *) optval; + msg.msg_control_is_user = true; + msg.msg_control_user = optval; msg.msg_controllen = len; msg.msg_flags = flags; @@ -1589,9 +1762,47 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, { int err; - if (optname == MCAST_MSFILTER) - return compat_mc_getsockopt(sk, level, optname, optval, optlen, - ip_getsockopt); + if (optname == MCAST_MSFILTER) { + const int size0 = offsetof(struct compat_group_filter, gf_slist); + struct compat_group_filter __user *p = (void __user *)optval; + struct compat_group_filter gf32; + struct group_filter gf; + int ulen, err; + int num; + + if (level != SOL_IP) + return -EOPNOTSUPP; + + if (get_user(ulen, optlen)) + return -EFAULT; + + if (ulen < size0) + return -EINVAL; + + if (copy_from_user(&gf32, p, size0)) + return -EFAULT; + + gf.gf_interface = gf32.gf_interface; + gf.gf_fmode = gf32.gf_fmode; + num = gf.gf_numsrc = gf32.gf_numsrc; + gf.gf_group = gf32.gf_group; + + rtnl_lock(); + lock_sock(sk); + err = ip_mc_gsfget(sk, &gf, p->gf_slist); + release_sock(sk); + rtnl_unlock(); + if (err) + return err; + if (gf.gf_numsrc < num) + num = gf.gf_numsrc; + ulen = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32)); + if (put_user(ulen, optlen) || + put_user(gf.gf_fmode, &p->gf_fmode) || + put_user(gf.gf_numsrc, &p->gf_numsrc)) + return -EFAULT; + return 0; + } err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index cd4b84310d92..f4f1d11eab50 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -860,7 +860,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, netdev_state_change(dev); } -int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); @@ -960,6 +960,20 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) done: return err; } +EXPORT_SYMBOL_GPL(ip_tunnel_ctl); + +int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct ip_tunnel_parm p; + int err; + + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + return -EFAULT; + err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); + if (!err && copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + return -EFAULT; + return err; +} EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1b4e6f298648..1d9c8cff5ac3 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb) static int vti_rcv_tunnel(struct sk_buff *skb) { - return vti_rcv(skb, ip_hdr(skb)->saddr, true); + struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id); + const struct iphdr *iph = ip_hdr(skb); + struct ip_tunnel *tunnel; + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + struct tnl_ptk_info tpi = { + .proto = htons(ETH_P_IP), + }; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto, false)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; } static int vti_rcv_cb(struct sk_buff *skb, int err) @@ -378,38 +399,31 @@ static int vti4_err(struct sk_buff *skb, u32 info) } static int -vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; - struct ip_tunnel_parm p; - - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) - return -EFAULT; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || - p.iph.ihl != 5) + if (p->iph.version != 4 || p->iph.protocol != IPPROTO_IPIP || + p->iph.ihl != 5) return -EINVAL; } - if (!(p.i_flags & GRE_KEY)) - p.i_key = 0; - if (!(p.o_flags & GRE_KEY)) - p.o_key = 0; + if (!(p->i_flags & GRE_KEY)) + p->i_key = 0; + if (!(p->o_flags & GRE_KEY)) + p->o_key = 0; - p.i_flags = VTI_ISVTI; + p->i_flags = VTI_ISVTI; - err = ip_tunnel_ioctl(dev, &p, cmd); + err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p.i_flags |= GRE_KEY; - p.o_flags |= GRE_KEY; + p->i_flags |= GRE_KEY; + p->o_flags |= GRE_KEY; } - - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - return -EFAULT; return 0; } @@ -417,10 +431,11 @@ static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, - .ndo_do_ioctl = vti_tunnel_ioctl, + .ndo_do_ioctl = ip_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_tunnel_ctl = vti_tunnel_ctl, }; static void vti_tunnel_setup(struct net_device *dev) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 2f01cf6fa0de..40fea52c8277 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -327,41 +327,29 @@ static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) } static int -ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { - int err = 0; - struct ip_tunnel_parm p; - - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) - return -EFAULT; - if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { - if (p.iph.version != 4 || - !ipip_tunnel_ioctl_verify_protocol(p.iph.protocol) || - p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) + if (p->iph.version != 4 || + !ipip_tunnel_ioctl_verify_protocol(p->iph.protocol) || + p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; } - p.i_key = p.o_key = 0; - p.i_flags = p.o_flags = 0; - err = ip_tunnel_ioctl(dev, &p, cmd); - if (err) - return err; - - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - return -EFAULT; - - return 0; + p->i_key = p->o_key = 0; + p->i_flags = p->o_flags = 0; + return ip_tunnel_ctl(dev, p, cmd); } static const struct net_device_ops ipip_netdev_ops = { .ndo_init = ipip_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = ipip_tunnel_xmit, - .ndo_do_ioctl = ipip_tunnel_ioctl, + .ndo_do_ioctl = ip_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_tunnel_ctl = ipip_tunnel_ctl, }; #define IPIP_FEATURES (NETIF_F_SG | \ @@ -698,7 +686,7 @@ out: rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) - xfrm4_tunnel_deregister(&mplsip_handler, AF_INET); + xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mplsip_failed: #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9cf83cc85e4a..f5c7a58844a4 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES -#define ipmr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ + lockdep_rtnl_is_held() || \ + list_empty(&net->ipv4.mr_tables)) static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) @@ -419,37 +421,6 @@ static void ipmr_free_table(struct mr_table *mrt) /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ -static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) -{ - struct net *net = dev_net(dev); - - dev_close(dev); - - dev = __dev_get_by_name(net, "tunl0"); - if (dev) { - const struct net_device_ops *ops = dev->netdev_ops; - struct ifreq ifr; - struct ip_tunnel_parm p; - - memset(&p, 0, sizeof(p)); - p.iph.daddr = v->vifc_rmt_addr.s_addr; - p.iph.saddr = v->vifc_lcl_addr.s_addr; - p.iph.version = 4; - p.iph.ihl = 5; - p.iph.protocol = IPPROTO_IPIP; - sprintf(p.name, "dvmrp%d", v->vifc_vifi); - ifr.ifr_ifru.ifru_data = (__force void __user *)&p; - - if (ops->ndo_do_ioctl) { - mm_segment_t oldfs = get_fs(); - - set_fs(KERNEL_DS); - ops->ndo_do_ioctl(dev, &ifr, SIOCDELTUNNEL); - set_fs(oldfs); - } - } -} - /* Initialize ipmr pimreg/tunnel in_device */ static bool ipmr_init_vif_indev(const struct net_device *dev) { @@ -469,51 +440,52 @@ static bool ipmr_init_vif_indev(const struct net_device *dev) static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { - struct net_device *dev; - - dev = __dev_get_by_name(net, "tunl0"); + struct net_device *tunnel_dev, *new_dev; + struct ip_tunnel_parm p = { }; + int err; - if (dev) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; - struct ifreq ifr; - struct ip_tunnel_parm p; + tunnel_dev = __dev_get_by_name(net, "tunl0"); + if (!tunnel_dev) + goto out; - memset(&p, 0, sizeof(p)); - p.iph.daddr = v->vifc_rmt_addr.s_addr; - p.iph.saddr = v->vifc_lcl_addr.s_addr; - p.iph.version = 4; - p.iph.ihl = 5; - p.iph.protocol = IPPROTO_IPIP; - sprintf(p.name, "dvmrp%d", v->vifc_vifi); - ifr.ifr_ifru.ifru_data = (__force void __user *)&p; + p.iph.daddr = v->vifc_rmt_addr.s_addr; + p.iph.saddr = v->vifc_lcl_addr.s_addr; + p.iph.version = 4; + p.iph.ihl = 5; + p.iph.protocol = IPPROTO_IPIP; + sprintf(p.name, "dvmrp%d", v->vifc_vifi); - if (ops->ndo_do_ioctl) { - mm_segment_t oldfs = get_fs(); + if (!tunnel_dev->netdev_ops->ndo_tunnel_ctl) + goto out; + err = tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, + SIOCADDTUNNEL); + if (err) + goto out; - set_fs(KERNEL_DS); - err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); - set_fs(oldfs); - } else { - err = -EOPNOTSUPP; - } - dev = NULL; - - if (err == 0 && - (dev = __dev_get_by_name(net, p.name)) != NULL) { - dev->flags |= IFF_MULTICAST; - if (!ipmr_init_vif_indev(dev)) - goto failure; - if (dev_open(dev, NULL)) - goto failure; - dev_hold(dev); - } - } - return dev; + new_dev = __dev_get_by_name(net, p.name); + if (!new_dev) + goto out; -failure: - unregister_netdevice(dev); - return NULL; + new_dev->flags |= IFF_MULTICAST; + if (!ipmr_init_vif_indev(new_dev)) + goto out_unregister; + if (dev_open(new_dev, NULL)) + goto out_unregister; + dev_hold(new_dev); + err = dev_set_allmulti(new_dev, 1); + if (err) { + dev_close(new_dev); + tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, + SIOCDELTUNNEL); + dev_put(new_dev); + new_dev = ERR_PTR(err); + } + return new_dev; + +out_unregister: + unregister_netdevice(new_dev); +out: + return ERR_PTR(-ENOBUFS); } #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) @@ -865,14 +837,8 @@ static int vif_add(struct net *net, struct mr_table *mrt, break; case VIFF_TUNNEL: dev = ipmr_new_tunnel(net, vifc); - if (!dev) - return -ENOBUFS; - err = dev_set_allmulti(dev, 1); - if (err) { - ipmr_del_tunnel(dev, vifc); - dev_put(dev); - return err; - } + if (IS_ERR(dev)) + return PTR_ERR(dev); break; case VIFF_USE_IFINDEX: case 0: @@ -2611,7 +2577,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { - if (filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 3c25a467b3ef..7afde8828b4c 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb, break; default: pr_debug("unknown outbound packet 0x%04x:%s\n", msg, - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pptp_msg_name(msg)); fallthrough; case PPTP_SET_LINK_INFO: /* only need to NAT in case PAC is behind NAT box */ @@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb, pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID); break; default: - pr_debug("unknown inbound packet %s\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg)); fallthrough; case PPTP_START_SESSION_REQUEST: case PPTP_START_SESSION_REPLY: diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index fdfca534d094..400a9f89ebdb 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -33,8 +33,20 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, + [NHA_FDB] = { .type = NLA_FLAG }, }; +static int call_nexthop_notifiers(struct net *net, + enum nexthop_event_type event_type, + struct nexthop *nh) +{ + int err; + + err = atomic_notifier_call_chain(&net->nexthop.notifier_chain, + event_type, nh); + return notifier_to_errno(err); +} + static unsigned int nh_dev_hashfn(unsigned int val) { unsigned int mask = NH_DEV_HASHSIZE - 1; @@ -63,9 +75,16 @@ static void nexthop_free_mpath(struct nexthop *nh) int i; nhg = rcu_dereference_raw(nh->nh_grp); - for (i = 0; i < nhg->num_nh; ++i) - WARN_ON(nhg->nh_entries[i].nh); + for (i = 0; i < nhg->num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + WARN_ON(!list_empty(&nhge->nh_list)); + nexthop_put(nhge->nh); + } + + WARN_ON(nhg->spare == nhg); + kfree(nhg->spare); kfree(nhg); } @@ -107,6 +126,7 @@ static struct nexthop *nexthop_alloc(void) INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); + INIT_LIST_HEAD(&nh->fdb_list); } return nh; } @@ -227,6 +247,9 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; + if (nh->is_fdb_nh && nla_put_flag(skb, NHA_FDB)) + goto nla_put_failure; + if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); @@ -241,7 +264,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; - } else { + } else if (!nh->is_fdb_nh) { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; @@ -276,6 +299,7 @@ out: return 0; nla_put_failure: + nlmsg_cancel(skb, nlh); return -EMSGSIZE; } @@ -387,12 +411,35 @@ static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, return true; } +static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, + struct netlink_ext_ack *extack) +{ + struct nh_info *nhi; + + if (!nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); + return -EINVAL; + } + + nhi = rtnl_dereference(nh->nh_info); + if (*nh_family == AF_UNSPEC) { + *nh_family = nhi->family; + } else if (*nh_family != nhi->family) { + NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); + return -EINVAL; + } + + return 0; +} + static int nh_check_attr_group(struct net *net, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); + u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; + u8 nhg_fdb = 0; if (len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, @@ -421,6 +468,8 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], } } + if (tb[NHA_FDB]) + nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; @@ -432,11 +481,20 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], } if (!valid_group_nh(nh, len, extack)) return -EINVAL; + + if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) + return -EINVAL; + + if (!nhg_fdb && nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); + return -EINVAL; + } } - for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) { + for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) { if (!tb[i]) continue; - + if (tb[NHA_FDB]) + continue; NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; @@ -495,6 +553,9 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) if (hash > atomic_read(&nhge->upper_bound)) continue; + if (nhge->nh->is_fdb_nh) + return nhge->nh; + /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ @@ -564,6 +625,11 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, { struct nh_info *nhi; + if (nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + return -EINVAL; + } + /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source @@ -640,6 +706,12 @@ int fib_check_nexthop(struct nexthop *nh, u8 scope, { int err = 0; + if (nh->is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + err = -EINVAL; + goto out; + } + if (nh->is_group) { struct nh_group *nhg; @@ -693,41 +765,56 @@ static void nh_group_rebalance(struct nh_group *nhg) } } -static void remove_nh_grp_entry(struct nh_grp_entry *nhge, - struct nh_group *nhg, +static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { + struct nh_grp_entry *nhges, *new_nhges; + struct nexthop *nhp = nhge->nh_parent; struct nexthop *nh = nhge->nh; - struct nh_grp_entry *nhges; - bool found = false; - int i; + struct nh_group *nhg, *newg; + int i, j; WARN_ON(!nh); - nhges = nhg->nh_entries; - for (i = 0; i < nhg->num_nh; ++i) { - if (found) { - nhges[i-1].nh = nhges[i].nh; - nhges[i-1].weight = nhges[i].weight; - list_del(&nhges[i].nh_list); - list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list); - } else if (nhg->nh_entries[i].nh == nh) { - found = true; - } - } + nhg = rtnl_dereference(nhp->nh_grp); + newg = nhg->spare; - if (WARN_ON(!found)) + /* last entry, keep it visible and remove the parent */ + if (nhg->num_nh == 1) { + remove_nexthop(net, nhp, nlinfo); return; + } + + newg->has_v4 = nhg->has_v4; + newg->mpath = nhg->mpath; + newg->num_nh = nhg->num_nh; + + /* copy old entries to new except the one getting removed */ + nhges = nhg->nh_entries; + new_nhges = newg->nh_entries; + for (i = 0, j = 0; i < nhg->num_nh; ++i) { + /* current nexthop getting removed */ + if (nhg->nh_entries[i].nh == nh) { + newg->num_nh--; + continue; + } - nhg->num_nh--; - nhg->nh_entries[nhg->num_nh].nh = NULL; + list_del(&nhges[i].nh_list); + new_nhges[j].nh_parent = nhges[i].nh_parent; + new_nhges[j].nh = nhges[i].nh; + new_nhges[j].weight = nhges[i].weight; + list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); + j++; + } - nh_group_rebalance(nhg); + nh_group_rebalance(newg); + rcu_assign_pointer(nhp->nh_grp, newg); - nexthop_put(nh); + list_del(&nhge->nh_list); + nexthop_put(nhge->nh); if (nlinfo) - nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo); + nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, @@ -735,17 +822,11 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, { struct nh_grp_entry *nhge, *tmp; - list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) { - struct nh_group *nhg; - - list_del(&nhge->nh_list); - nhg = rtnl_dereference(nhge->nh_parent->nh_grp); - remove_nh_grp_entry(nhge, nhg, nlinfo); + list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) + remove_nh_grp_entry(net, nhge, nlinfo); - /* if this group has no more entries then remove it */ - if (!nhg->num_nh) - remove_nexthop(net, nhge->nh_parent, nlinfo); - } + /* make sure all see the newly published array before releasing rtnl */ + synchronize_rcu(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) @@ -759,10 +840,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) if (WARN_ON(!nhge->nh)) continue; - list_del(&nhge->nh_list); - nexthop_put(nhge->nh); - nhge->nh = NULL; - nhg->num_nh--; + list_del_init(&nhge->nh_list); } } @@ -773,6 +851,8 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) bool do_flush = false; struct fib_info *fi; + call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh); + list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; @@ -784,7 +864,8 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); - ipv6_stub->ip6_del_rt(net, f6i); + ipv6_stub->ip6_del_rt(net, f6i, + !net->ipv4.sysctl_nexthop_compat_mode); } } @@ -1041,7 +1122,7 @@ out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); - if (replace_notify) + if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } @@ -1085,6 +1166,7 @@ static struct nexthop *nexthop_create_group(struct net *net, { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); + u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int i; @@ -1095,12 +1177,21 @@ static struct nexthop *nexthop_create_group(struct net *net, nh->is_group = 1; - nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry)); + nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } + /* spare group used for removals */ + nhg->spare = nexthop_grp_alloc(num_nh); + if (!nhg->spare) { + kfree(nhg); + kfree(nh); + return ERR_PTR(-ENOMEM); + } + nhg->spare->spare = nhg; + for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; @@ -1124,6 +1215,9 @@ static struct nexthop *nexthop_create_group(struct net *net, nh_group_rebalance(nhg); } + if (cfg->nh_fdb) + nh->is_fdb_nh = 1; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -1132,6 +1226,7 @@ out_no_nh: for (; i >= 0; --i) nexthop_put(nhg->nh_entries[i].nh); + kfree(nhg->spare); kfree(nhg); kfree(nh); @@ -1151,7 +1246,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; - u32 tb_id = l3mdev_fib_table(cfg->dev); + u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); @@ -1160,6 +1255,9 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, goto out; } + if (nh->is_fdb_nh) + goto out; + /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { @@ -1185,6 +1283,7 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, .fc_flags = cfg->nh_flags, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, + .fc_is_fdb = cfg->nh_fdb, }; int err; @@ -1226,6 +1325,9 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; + if (cfg->nh_fdb) + nh->is_fdb_nh = 1; + if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; @@ -1247,7 +1349,8 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, } /* add the entry to the device based hash */ - nexthop_devhash_add(net, nhi); + if (!nh->is_fdb_nh) + nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); @@ -1351,6 +1454,19 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); + if (tb[NHA_FDB]) { + if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || + tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { + NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); + goto out; + } + if (nhm->nh_flags) { + NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); + goto out; + } + cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); + } + if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); @@ -1374,8 +1490,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || - tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { - NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway or oif"); + tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { + NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } @@ -1384,26 +1500,28 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } - if (!tb[NHA_OIF]) { - NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole nexthops"); + if (!cfg->nh_fdb && !tb[NHA_OIF]) { + NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } - cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); - if (cfg->nh_ifindex) - cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); + if (!cfg->nh_fdb && tb[NHA_OIF]) { + cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); + if (cfg->nh_ifindex) + cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); - if (!cfg->dev) { - NL_SET_ERR_MSG(extack, "Invalid device index"); - goto out; - } else if (!(cfg->dev->flags & IFF_UP)) { - NL_SET_ERR_MSG(extack, "Nexthop device is not up"); - err = -ENETDOWN; - goto out; - } else if (!netif_carrier_ok(cfg->dev)) { - NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); - err = -ENETDOWN; - goto out; + if (!cfg->dev) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + goto out; + } else if (!(cfg->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Nexthop device is not up"); + err = -ENETDOWN; + goto out; + } else if (!netif_carrier_ok(cfg->dev)) { + NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); + err = -ENETDOWN; + goto out; + } } err = -EINVAL; @@ -1632,7 +1750,7 @@ static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, int *master_idx, bool *group_filter, - struct netlink_callback *cb) + bool *fdb_filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NHA_MAX + 1]; @@ -1669,6 +1787,9 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, case NHA_GROUPS: *group_filter = true; break; + case NHA_FDB: + *fdb_filter = true; + break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; @@ -1687,17 +1808,17 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { + bool group_filter = false, fdb_filter = false; struct nhmsg *nhm = nlmsg_data(cb->nlh); int dev_filter_idx = 0, master_idx = 0; struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; - bool group_filter = false; struct rb_node *node; int idx = 0, s_idx; int err; err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, - &group_filter, cb); + &group_filter, &fdb_filter, cb); if (err < 0) return err; @@ -1782,6 +1903,19 @@ static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; +int register_nexthop_notifier(struct net *net, struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&net->nexthop.notifier_chain, nb); +} +EXPORT_SYMBOL(register_nexthop_notifier); + +int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&net->nexthop.notifier_chain, + nb); +} +EXPORT_SYMBOL(unregister_nexthop_notifier); + static void __net_exit nexthop_net_exit(struct net *net) { rtnl_lock(); @@ -1798,6 +1932,7 @@ static int __net_init nexthop_net_init(struct net *net) net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; + ATOMIC_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 788c69d9bfe0..1d7076b78e63 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -491,18 +491,16 @@ u32 ip_idents_reserve(u32 hash, int segs) atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; u32 old = READ_ONCE(*p_tstamp); u32 now = (u32)jiffies; - u32 new, delta = 0; + u32 delta = 0; if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - /* Do not use atomic_add_return() as it makes UBSAN unhappy */ - do { - old = (u32)atomic_read(p_id); - new = old + delta + segs; - } while (atomic_cmpxchg(p_id, old, new) != old); - - return new - segs; + /* If UBSAN reports an error there, please make sure your compiler + * supports -fno-strict-overflow before reporting it that was a bug + * in UBSAN, and it has been fixed in GCC-8. + */ + return atomic_add_return(segs + delta, p_id) - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -915,7 +913,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { @@ -3336,8 +3334,7 @@ static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 81b267e990a1..5653e3b011bf 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -71,8 +71,7 @@ static void set_local_port_range(struct net *net, int range[2]) /* Validate changes from /proc interface. */ static int ipv4_local_port_range(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.ip_local_ports.range); @@ -107,7 +106,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, /* Validate changes from /proc interface. */ static int ipv4_privileged_ports(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_ip_prot_sock); @@ -168,8 +167,7 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig /* Validate changes from /proc interface. */ static int ipv4_ping_group_range(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct user_namespace *user_ns = current_user_ns(); int ret; @@ -204,8 +202,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, } static int ipv4_fwd_update_priority(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; @@ -221,7 +218,7 @@ static int ipv4_fwd_update_priority(struct ctl_table *table, int write, } static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(ctl->data, struct net, ipv4.tcp_congestion_control); @@ -241,9 +238,8 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, } static int proc_tcp_available_congestion_control(struct ctl_table *ctl, - int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, }; int ret; @@ -258,9 +254,8 @@ static int proc_tcp_available_congestion_control(struct ctl_table *ctl, } static int proc_allowed_congestion_control(struct ctl_table *ctl, - int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; int ret; @@ -296,8 +291,7 @@ static int sscanf_key(char *buf, __le32 *key) } static int proc_tcp_fastopen_key(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen); @@ -399,7 +393,7 @@ static void proc_configure_early_demux(int enabled, int protocol) } static int proc_tcp_early_demux(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; @@ -415,7 +409,7 @@ static int proc_tcp_early_demux(struct ctl_table *table, int write, } static int proc_udp_early_demux(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; @@ -431,8 +425,7 @@ static int proc_udp_early_demux(struct ctl_table *table, int write, } static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, - int write, - void __user *buffer, + int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -447,8 +440,7 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, } static int proc_tcp_available_ulp(struct ctl_table *ctl, - int write, - void __user *buffer, size_t *lenp, + int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; @@ -466,7 +458,7 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, + void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -711,6 +703,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_tcp_early_demux }, { + .procname = "nexthop_compat_mode", + .data = &init_net.ipv4.sysctl_nexthop_compat_mode, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, .maxlen = sizeof(int), @@ -1321,6 +1322,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_doulongvec_minmax, }, { + .procname = "tcp_comp_sack_slack_ns", + .data = &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { .procname = "tcp_comp_sack_nr", .data = &init_net.ipv4.sysctl_tcp_comp_sack_nr, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6d87de434377..27716e4932bc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || - (sk->sk_prot->stream_memory_read ? - sk->sk_prot->stream_memory_read(sk) : false); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail > 0) { + if (avail >= target) + return true; + if (tcp_rmem_pressure(sk)) + return true; + } + if (sk->sk_prot->stream_memory_read) + return sk->sk_prot->stream_memory_read(sk); + return false; } /* @@ -1726,7 +1734,7 @@ int tcp_mmap(struct file *file, struct socket *sock, return -EPERM; vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); - /* Instruct vm_insert_page() to not down_read(mmap_sem) */ + /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vma->vm_flags |= VM_MIXEDMAP; vma->vm_ops = &tcp_vm_ops; @@ -1754,12 +1762,13 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); - ret = -EINVAL; vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) - goto out; + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + mmap_read_unlock(current->mm); + return -EINVAL; + } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); tp = tcp_sk(sk); @@ -1818,7 +1827,7 @@ static int tcp_zerocopy_receive(struct sock *sk, frags++; } out: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (length) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -2154,13 +2163,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); cmsg_flags |= 2; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) @@ -2790,6 +2801,163 @@ static void tcp_enable_tx_delay(void) } } +/* When set indicates to always queue non-full frames. Later the user clears + * this option and we transmit any pending partial frames in the queue. This is + * meant to be used alongside sendfile() to get properly filled frames when the + * user (for example) must write out headers with a write() call first and then + * use sendfile to send out the data parts. + * + * TCP_CORK can be set together with TCP_NODELAY and it is stronger than + * TCP_NODELAY. + */ +static void __tcp_sock_set_cork(struct sock *sk, bool on) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (on) { + tp->nonagle |= TCP_NAGLE_CORK; + } else { + tp->nonagle &= ~TCP_NAGLE_CORK; + if (tp->nonagle & TCP_NAGLE_OFF) + tp->nonagle |= TCP_NAGLE_PUSH; + tcp_push_pending_frames(sk); + } +} + +void tcp_sock_set_cork(struct sock *sk, bool on) +{ + lock_sock(sk); + __tcp_sock_set_cork(sk, on); + release_sock(sk); +} +EXPORT_SYMBOL(tcp_sock_set_cork); + +/* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is + * remembered, but it is not activated until cork is cleared. + * + * However, when TCP_NODELAY is set we make an explicit push, which overrides + * even TCP_CORK for currently queued segments. + */ +static void __tcp_sock_set_nodelay(struct sock *sk, bool on) +{ + if (on) { + tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; + tcp_push_pending_frames(sk); + } else { + tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; + } +} + +void tcp_sock_set_nodelay(struct sock *sk) +{ + lock_sock(sk); + __tcp_sock_set_nodelay(sk, true); + release_sock(sk); +} +EXPORT_SYMBOL(tcp_sock_set_nodelay); + +static void __tcp_sock_set_quickack(struct sock *sk, int val) +{ + if (!val) { + inet_csk_enter_pingpong_mode(sk); + return; + } + + inet_csk_exit_pingpong_mode(sk); + if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && + inet_csk_ack_scheduled(sk)) { + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; + tcp_cleanup_rbuf(sk, 1); + if (!(val & 1)) + inet_csk_enter_pingpong_mode(sk); + } +} + +void tcp_sock_set_quickack(struct sock *sk, int val) +{ + lock_sock(sk); + __tcp_sock_set_quickack(sk, val); + release_sock(sk); +} +EXPORT_SYMBOL(tcp_sock_set_quickack); + +int tcp_sock_set_syncnt(struct sock *sk, int val) +{ + if (val < 1 || val > MAX_TCP_SYNCNT) + return -EINVAL; + + lock_sock(sk); + inet_csk(sk)->icsk_syn_retries = val; + release_sock(sk); + return 0; +} +EXPORT_SYMBOL(tcp_sock_set_syncnt); + +void tcp_sock_set_user_timeout(struct sock *sk, u32 val) +{ + lock_sock(sk); + inet_csk(sk)->icsk_user_timeout = val; + release_sock(sk); +} +EXPORT_SYMBOL(tcp_sock_set_user_timeout); + +static int __tcp_sock_set_keepidle(struct sock *sk, int val) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (val < 1 || val > MAX_TCP_KEEPIDLE) + return -EINVAL; + + tp->keepalive_time = val * HZ; + if (sock_flag(sk, SOCK_KEEPOPEN) && + !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { + u32 elapsed = keepalive_time_elapsed(tp); + + if (tp->keepalive_time > elapsed) + elapsed = tp->keepalive_time - elapsed; + else + elapsed = 0; + inet_csk_reset_keepalive_timer(sk, elapsed); + } + + return 0; +} + +int tcp_sock_set_keepidle(struct sock *sk, int val) +{ + int err; + + lock_sock(sk); + err = __tcp_sock_set_keepidle(sk, val); + release_sock(sk); + return err; +} +EXPORT_SYMBOL(tcp_sock_set_keepidle); + +int tcp_sock_set_keepintvl(struct sock *sk, int val) +{ + if (val < 1 || val > MAX_TCP_KEEPINTVL) + return -EINVAL; + + lock_sock(sk); + tcp_sk(sk)->keepalive_intvl = val * HZ; + release_sock(sk); + return 0; +} +EXPORT_SYMBOL(tcp_sock_set_keepintvl); + +int tcp_sock_set_keepcnt(struct sock *sk, int val) +{ + if (val < 1 || val > MAX_TCP_KEEPCNT) + return -EINVAL; + + lock_sock(sk); + tcp_sk(sk)->keepalive_probes = val; + release_sock(sk); + return 0; +} +EXPORT_SYMBOL(tcp_sock_set_keepcnt); + /* * Socket option code for TCP. */ @@ -2887,20 +3055,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_NODELAY: - if (val) { - /* TCP_NODELAY is weaker than TCP_CORK, so that - * this option on corked socket is remembered, but - * it is not activated until cork is cleared. - * - * However, when TCP_NODELAY is set we make - * an explicit push, which overrides even TCP_CORK - * for currently queued segments. - */ - tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; - tcp_push_pending_frames(sk); - } else { - tp->nonagle &= ~TCP_NAGLE_OFF; - } + __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: @@ -2968,43 +3123,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_CORK: - /* When set indicates to always queue non-full frames. - * Later the user clears this option and we transmit - * any pending partial frames in the queue. This is - * meant to be used alongside sendfile() to get properly - * filled frames when the user (for example) must write - * out headers with a write() call first and then use - * sendfile to send out the data parts. - * - * TCP_CORK can be set together with TCP_NODELAY and it is - * stronger than TCP_NODELAY. - */ - if (val) { - tp->nonagle |= TCP_NAGLE_CORK; - } else { - tp->nonagle &= ~TCP_NAGLE_CORK; - if (tp->nonagle&TCP_NAGLE_OFF) - tp->nonagle |= TCP_NAGLE_PUSH; - tcp_push_pending_frames(sk); - } + __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: - if (val < 1 || val > MAX_TCP_KEEPIDLE) - err = -EINVAL; - else { - tp->keepalive_time = val * HZ; - if (sock_flag(sk, SOCK_KEEPOPEN) && - !((1 << sk->sk_state) & - (TCPF_CLOSE | TCPF_LISTEN))) { - u32 elapsed = keepalive_time_elapsed(tp); - if (tp->keepalive_time > elapsed) - elapsed = tp->keepalive_time - elapsed; - else - elapsed = 0; - inet_csk_reset_keepalive_timer(sk, elapsed); - } - } + err = __tcp_sock_set_keepidle(sk, val); break; case TCP_KEEPINTVL: if (val < 1 || val > MAX_TCP_KEEPINTVL) @@ -3035,8 +3158,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_LINGER2: if (val < 0) tp->linger2 = -1; - else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ) - tp->linger2 = 0; + else if (val > TCP_FIN_TIMEOUT_MAX / HZ) + tp->linger2 = TCP_FIN_TIMEOUT_MAX; else tp->linger2 = val * HZ; break; @@ -3061,19 +3184,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_QUICKACK: - if (!val) { - inet_csk_enter_pingpong_mode(sk); - } else { - inet_csk_exit_pingpong_mode(sk); - if ((1 << sk->sk_state) & - (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && - inet_csk_ack_scheduled(sk)) { - icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; - tcp_cleanup_rbuf(sk, 1); - if (!(val & 1)) - inet_csk_enter_pingpong_mode(sk); - } - } + __tcp_sock_set_quickack(sk, val); break; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5a05327f97c1..629aaa9a1eb9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk_psock_data_ready(sk, psock); } else { @@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bf4ced9273e8..83330a6cb242 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -437,7 +437,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* 3. Try to fixup all. It is made immediately after connection enters * established state. */ -void tcp_init_buffer_space(struct sock *sk) +static void tcp_init_buffer_space(struct sock *sk) { int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win; struct tcp_sock *tp = tcp_sk(sk); @@ -2183,8 +2183,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) } /* Detect loss in event "A" above by marking head of queue up as lost. - * For non-SACK(Reno) senders, the first "packets" number of segments - * are considered lost. For RFC3517 SACK, a segment is considered lost if it + * For RFC3517 SACK, a segment is considered lost if it * has at least tp->reordering SACKed seqments above it; "packets" refers to * the maximum SACKed segments to pass before reaching this limit. */ @@ -2192,10 +2191,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt, lost; - unsigned int mss; + int cnt; /* Use SACK to deduce losses of new sequences sent during recovery */ - const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; + const u32 loss_high = tp->snd_nxt; WARN_ON(packets > tp->packets_out); skb = tp->lost_skb_hint; @@ -2218,26 +2216,11 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) break; - oldcnt = cnt; - if (tcp_is_reno(tp) || - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) cnt += tcp_skb_pcount(skb); - if (cnt > packets) { - if (tcp_is_sack(tp) || - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || - (oldcnt >= packets)) - break; - - mss = tcp_skb_mss(skb); - /* If needed, chop off the prefix to mark as lost. */ - lost = (packets - oldcnt) * mss; - if (lost < skb->len && - tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, - lost, mss, GFP_ATOMIC) < 0) - break; - cnt = packets; - } + if (cnt > packets) + break; tcp_skb_mark_lost(tp, skb); @@ -2849,8 +2832,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (tcp_try_undo_partial(sk, prior_snd_una)) return; /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_is_reno(tp) || - tcp_force_fast_retransmit(sk); + do_lost = tcp_force_fast_retransmit(sk); } if (tcp_try_undo_dsack(sk)) { tcp_try_keep_open(sk); @@ -3014,7 +2996,7 @@ void tcp_rearm_rto(struct sock *sk) rto = usecs_to_jiffies(max_t(int, delta_us, 1)); } tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, - TCP_RTO_MAX, tcp_rtx_queue_head(sk)); + TCP_RTO_MAX); } } @@ -3291,7 +3273,7 @@ static void tcp_ack_probe(struct sock *sk) unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - when, TCP_RTO_MAX, NULL); + when, TCP_RTO_MAX); } } @@ -3926,10 +3908,6 @@ void tcp_parse_options(const struct net *net, */ break; #endif - case TCPOPT_MPTCP: - mptcp_parse_option(skb, ptr, opsize, opt_rx); - break; - case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4327,6 +4305,33 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } +static void tcp_sack_compress_send_ack(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->compressed_ack) + return; + + if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) + __sock_put(sk); + + /* Since we have to send one ack finally, + * substract one from tp->compressed_ack to keep + * LINUX_MIB_TCPACKCOMPRESSED accurate. + */ + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, + tp->compressed_ack - 1); + + tp->compressed_ack = 0; + tcp_send_ack(sk); +} + +/* Reasonable amount of sack blocks included in TCP SACK option + * The max is 4, but this becomes 3 if TCP timestamps are there. + * Given that SACK packets might be lost, be conservative and use 2. + */ +#define TCP_SACK_BLOCKS_EXPECTED 2 + static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); @@ -4339,6 +4344,8 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) { if (tcp_sack_extend(sp, seq, end_seq)) { + if (this_sack >= TCP_SACK_BLOCKS_EXPECTED) + tcp_sack_compress_send_ack(sk); /* Rotate this_sack to the first one. */ for (; this_sack > 0; this_sack--, sp--) swap(*sp, *(sp - 1)); @@ -4348,6 +4355,9 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) } } + if (this_sack >= TCP_SACK_BLOCKS_EXPECTED) + tcp_sack_compress_send_ack(sk); + /* Could not find an adjacent existing SACK, build a new one, * put it at the front, and shift everyone else down. We * always know there is at least one SACK present already here. @@ -4355,8 +4365,6 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) * If the sack array is full, forget about the last one. */ if (this_sack >= TCP_NUM_SACKS) { - if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) - tcp_send_ack(sk); this_sack--; tp->rx_opt.num_sacks--; sp--; @@ -4761,7 +4769,8 @@ void tcp_data_ready(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int avail = tp->rcv_nxt - tp->copied_seq; - if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && + !sock_flag(sk, SOCK_DONE)) return; sk->sk_data_ready(sk); @@ -5275,15 +5284,13 @@ send_now: if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { tp->compressed_ack_rcv_nxt = tp->rcv_nxt; - if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) - NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, - tp->compressed_ack - TCP_FASTRETRANS_THRESH); - tp->compressed_ack = 0; + tp->dup_ack_counter = 0; } - - if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH) + if (tp->dup_ack_counter < TCP_FASTRETRANS_THRESH) { + tp->dup_ack_counter++; goto send_now; - + } + tp->compressed_ack++; if (hrtimer_is_queued(&tp->compressed_ack_timer)) return; @@ -5296,8 +5303,9 @@ send_now: delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns, rtt * (NSEC_PER_USEC >> 3)/20); sock_hold(sk); - hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay), - HRTIMER_MODE_REL_PINNED_SOFT); + hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay), + sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns, + HRTIMER_MODE_REL_PINNED_SOFT); } static inline void tcp_ack_snd_check(struct sock *sk) @@ -5990,9 +5998,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); - if (sk_is_mptcp(sk)) - mptcp_rcv_synsent(sk); - /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 83a5d24e13b8..ad6435ba6d72 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -403,6 +403,46 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort) } EXPORT_SYMBOL(tcp_req_err); +/* TCP-LD (RFC 6069) logic */ +void tcp_ld_RTO_revert(struct sock *sk, u32 seq) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + s32 remaining; + u32 delta_us; + + if (sock_owned_by_user(sk)) + return; + + if (seq != tp->snd_una || !icsk->icsk_retransmits || + !icsk->icsk_backoff) + return; + + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + return; + + icsk->icsk_backoff--; + icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; + icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); + + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); + remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); + + if (remaining > 0) { + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + remaining, TCP_RTO_MAX); + } else { + /* RTO revert clocked out retransmission. + * Will retransmit now. + */ + tcp_retransmit_timer(sk); + } +} +EXPORT_SYMBOL(tcp_ld_RTO_revert); + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -419,27 +459,23 @@ EXPORT_SYMBOL(tcp_req_err); * */ -int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) +int tcp_v4_err(struct sk_buff *skb, u32 info) { - const struct iphdr *iph = (const struct iphdr *)icmp_skb->data; - struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); - struct inet_connection_sock *icsk; + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct tcp_sock *tp; struct inet_sock *inet; - const int type = icmp_hdr(icmp_skb)->type; - const int code = icmp_hdr(icmp_skb)->code; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; struct sock *sk; - struct sk_buff *skb; struct request_sock *fastopen; u32 seq, snd_una; - s32 remaining; - u32 delta_us; int err; - struct net *net = dev_net(icmp_skb->dev); + struct net *net = dev_net(skb->dev); sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), - inet_iif(icmp_skb), 0); + inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; @@ -476,7 +512,6 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; } - icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); @@ -490,7 +525,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) - do_redirect(icmp_skb, sk); + do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ @@ -521,41 +556,12 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } err = icmp_err_convert[code].errno; - /* check if icmp_skb allows revert of backoff - * (see draft-zimmermann-tcp-lcd) */ - if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH) - break; - if (seq != tp->snd_una || !icsk->icsk_retransmits || - !icsk->icsk_backoff || fastopen) - break; - - if (sock_owned_by_user(sk)) - break; - - skb = tcp_rtx_queue_head(sk); - if (WARN_ON_ONCE(!skb)) - break; - - icsk->icsk_backoff--; - icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : - TCP_TIMEOUT_INIT; - icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - - - tcp_mstamp_refresh(tp); - delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); - remaining = icsk->icsk_rto - - usecs_to_jiffies(delta_us); - - if (remaining > 0) { - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - remaining, TCP_RTO_MAX); - } else { - /* RTO revert clocked out retransmission. - * Will retransmit now */ - tcp_retransmit_timer(sk); - } - + /* check if this ICMP message allows revert of backoff. + * (see RFC 6069) + */ + if (!fastopen && + (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH)) + tcp_ld_RTO_revert(sk, seq); break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; @@ -573,6 +579,8 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (fastopen && !fastopen->sk) break; + ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); + if (!sock_owned_by_user(sk)) { sk->sk_err = err; @@ -2780,6 +2788,7 @@ static int __net_init tcp_sk_init(struct net *net) sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; + net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7e40322cc5ec..495dda2449fe 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -774,7 +774,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; - if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) { + if (own_req && rsk_drop_req(req)) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); inet_csk_reqsk_queue_drop_and_put(sk, req); return child; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2f45cde168c4..a50e1990a845 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -184,10 +184,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, { struct tcp_sock *tp = tcp_sk(sk); - if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) { + if (unlikely(tp->compressed_ack)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, - tp->compressed_ack - TCP_FASTRETRANS_THRESH); - tp->compressed_ack = TCP_FASTRETRANS_THRESH; + tp->compressed_ack); + tp->compressed_ack = 0; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } @@ -2593,8 +2593,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); - tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, - TCP_RTO_MAX, NULL); + tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); return true; } @@ -2772,8 +2771,12 @@ u32 __tcp_select_window(struct sock *sk) int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); - int full_space = min_t(int, tp->window_clamp, allowed_space); - int window; + int full_space, window; + + if (sk_is_mptcp(sk)) + mptcp_space(sk, &free_space, &allowed_space); + + full_space = min_t(int, tp->window_clamp, allowed_space); if (unlikely(mss > full_space)) { mss = full_space; @@ -3109,6 +3112,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); + bool rearm_timer = false; u32 max_segs; int mib_idx; @@ -3131,7 +3135,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) segs = tp->snd_cwnd - tcp_packets_in_flight(tp); if (segs <= 0) - return; + break; sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets @@ -3156,10 +3160,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk) continue; if (tcp_small_queue_check(sk, skb, 1)) - return; + break; if (tcp_retransmit_skb(sk, skb, segs)) - return; + break; NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); @@ -3168,11 +3172,13 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) - tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX, - skb); + rearm_timer = true; + } + if (rearm_timer) + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, + TCP_RTO_MAX); } /* We allow to exceed memory limits for FIN packets to expedite @@ -3903,7 +3909,7 @@ void tcp_send_probe0(struct sock *sk) */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c3f26dcd6704..ada046f425d2 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -753,8 +753,14 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) + if (tp->compressed_ack) { + /* Since we have to send one ack finally, + * substract one from tp->compressed_ack to keep + * LINUX_MIB_TCPACKCOMPRESSED accurate. + */ + tp->compressed_ack--; tcp_send_ack(sk); + } } else { if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32564b350823..1b7ebbcae497 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -112,6 +112,9 @@ #include <net/sock_reuseport.h> #include <net/addrconf.h> #include <net/udp_tunnel.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6_stubs.h> +#endif struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); @@ -2563,7 +2566,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: - up->encap_rcv = xfrm4_udp_encap_rcv; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + up->encap_rcv = ipv6_stub->xfrm6_udp_encap_rcv; + else +#endif + up->encap_rcv = xfrm4_udp_encap_rcv; #endif fallthrough; case UDP_ENCAP_L2TPINUDP: diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 150e6f0fdbf5..3eecba0874aa 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -22,9 +22,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, goto error; if (cfg->bind_ifindex) { - err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTOIFINDEX, - (void *)&cfg->bind_ifindex, - sizeof(cfg->bind_ifindex)); + err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index f8de2482a529..ad2afeef4f10 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -18,11 +18,6 @@ #include <net/ip.h> #include <net/xfrm.h> -int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) -{ - return xfrm4_extract_header(skb); -} - static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk, struct sk_buff *skb) { diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 89ba7c87de5d..3cff51ba72bb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -14,79 +14,18 @@ #include <net/xfrm.h> #include <net/icmp.h> -static int xfrm4_tunnel_check_size(struct sk_buff *skb) -{ - int mtu, ret = 0; - - if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE) - goto out; - - if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df) - goto out; - - mtu = dst_mtu(skb_dst(skb)); - if ((!skb_is_gso(skb) && skb->len > mtu) || - (skb_is_gso(skb) && - !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { - skb->protocol = htons(ETH_P_IP); - - if (skb->sk) - xfrm_local_error(skb, mtu); - else - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); - ret = -EMSGSIZE; - } -out: - return ret; -} - -int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb) -{ - int err; - - err = xfrm4_tunnel_check_size(skb); - if (err) - return err; - - XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol; - - return xfrm4_extract_header(skb); -} - -int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) -{ - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - -#ifdef CONFIG_NETFILTER - IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; -#endif - - return xfrm_output(sk, skb); -} - static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { +#ifdef CONFIG_NETFILTER struct xfrm_state *x = skb_dst(skb)->xfrm; - const struct xfrm_state_afinfo *afinfo; - int ret = -EAFNOSUPPORT; -#ifdef CONFIG_NETFILTER if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif - rcu_read_lock(); - afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family); - if (likely(afinfo)) - ret = afinfo->output_finish(sk, skb); - else - kfree_skb(skb); - rcu_read_unlock(); - - return ret; + return xfrm_output(sk, skb); } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index f8ed3c3bb928..87d4db591488 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -8,36 +8,12 @@ * */ -#include <net/ip.h> #include <net/xfrm.h> -#include <linux/pfkeyv2.h> -#include <linux/ipsec.h> -#include <linux/netfilter_ipv4.h> -#include <linux/export.h> - -int xfrm4_extract_header(struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); - XFRM_MODE_SKB_CB(skb)->id = iph->id; - XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off; - XFRM_MODE_SKB_CB(skb)->tos = iph->tos; - XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl; - XFRM_MODE_SKB_CB(skb)->optlen = iph->ihl * 4 - sizeof(*iph); - memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0, - sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); - - return 0; -} static struct xfrm_state_afinfo xfrm4_state_afinfo = { .family = AF_INET, .proto = IPPROTO_IPIP, .output = xfrm4_output, - .output_finish = xfrm4_output_finish, - .extract_input = xfrm4_extract_input, - .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, .local_error = xfrm4_local_error, }; |