diff options
Diffstat (limited to 'net/ipv4')
85 files changed, 5444 insertions, 3473 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6d2c97f8e9ef..b71c22475c51 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -425,7 +425,7 @@ config INET_DIAG tristate "INET: socket monitoring interface" default y help - Support for INET (TCP, DCCP, etc) socket monitoring interface used by + Support for INET (TCP, UDP, etc) socket monitoring interface used by native Linux tools such as ss. ss is included in iproute2, currently downloadable at: @@ -760,9 +760,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" - select CRYPTO - select CRYPTO_MD5 - select TCP_SIGPOOL + select CRYPTO_LIB_MD5 help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8095e82de808..08d811f11896 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -102,6 +102,7 @@ #include <net/gro.h> #include <net/gso.h> #include <net/tcp.h> +#include <net/psp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/ping.h> @@ -153,11 +154,12 @@ void inet_sock_destruct(struct sock *sk) WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); - WARN_ON_ONCE(sk_forward_alloc_get(sk)); + WARN_ON_ONCE(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); + psp_sk_assoc_free(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -439,7 +441,7 @@ int inet_release(struct socket *sock) } EXPORT_SYMBOL(inet_release); -int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; int err; @@ -462,13 +464,13 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) return __inet_bind(sk, uaddr, addr_len, flags); } -int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { return inet_bind_sk(sock->sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_bind); -int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, +int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; @@ -565,7 +567,7 @@ out: return err; } -int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; @@ -621,7 +623,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ -int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int __inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; @@ -739,7 +741,7 @@ sock_error: } EXPORT_SYMBOL(__inet_stream_connect); -int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { int err; @@ -753,6 +755,11 @@ EXPORT_SYMBOL(inet_stream_connect); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) { + if (mem_cgroup_sockets_enabled) { + mem_cgroup_sk_alloc(newsk); + __sk_charge(newsk, GFP_KERNEL); + } + sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | @@ -766,6 +773,7 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new newsock->state = SS_CONNECTED; } +EXPORT_SYMBOL_GPL(__inet_accept); /* * Accept a pending connection. The TCP layer now gives BSD semantics. @@ -811,7 +819,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + BPF_CGROUP_RUN_SA_PROG(sk, sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; @@ -819,7 +827,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + BPF_CGROUP_RUN_SA_PROG(sk, sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); @@ -1309,8 +1317,6 @@ int inet_sk_rebuild_header(struct sock *sk) { struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); - __be32 daddr; - struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; @@ -1319,17 +1325,9 @@ int inet_sk_rebuild_header(struct sock *sk) return 0; /* Reroute. */ - rcu_read_lock(); - inet_opt = rcu_dereference(inet->inet_opt); - daddr = inet->inet_daddr; - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; - rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; - rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, - inet->inet_dport, inet->inet_sport, - sk->sk_protocol, ip_sock_rt_tos(sk), - sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, fl4); + rt = ip_route_output_flow(sock_net(sk), fl4, sk); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); @@ -1338,10 +1336,7 @@ int inet_sk_rebuild_header(struct sock *sk) /* Routing failed... */ sk->sk_route_caps = 0; - /* - * Other protocols have to map its equivalent state to TCP_SYN_SENT. - * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme - */ + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || @@ -1406,14 +1401,10 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - if (!skb->encapsulation || encap) { - udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); - fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); + fixedid = !!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID << encap)); - /* fixed ID is invalid if DF bit is not set */ - if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) - goto out; - } + if (!skb->encapsulation || encap) + udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index cb9a7ed8abd3..7f3863daaa40 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -170,7 +170,7 @@ struct neigh_table arp_tbl = { [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, - [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, + [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, @@ -659,10 +659,12 @@ static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb */ void arp_xmit(struct sk_buff *skb) { + rcu_read_lock(); /* Send it off, maybe filter it using firewalling first. */ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, - dev_net(skb->dev), NULL, skb, NULL, skb->dev, + dev_net_rcu(skb->dev), NULL, skb, NULL, skb->dev, arp_xmit_finish); + rcu_read_unlock(); } EXPORT_SYMBOL(arp_xmit); @@ -862,7 +864,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && - pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { + pneigh_lookup(&arp_tbl, net, &tip, dev)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); @@ -964,6 +966,7 @@ static int arp_is_multicast(const void *pkey) static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason; const struct arphdr *arp; /* do not tweak dropwatch on an ARP we will ignore */ @@ -977,12 +980,15 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ - if (!pskb_may_pull(skb, arp_hdr_len(dev))) + drop_reason = pskb_may_pull_reason(skb, arp_hdr_len(dev)); + if (drop_reason != SKB_NOT_DROPPED_YET) goto freeskb; arp = arp_hdr(skb); - if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) + if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) { + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; goto freeskb; + } memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); @@ -994,7 +1000,7 @@ consumeskb: consume_skb(skb); return NET_RX_SUCCESS; freeskb: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); out_of_mem: return NET_RX_DROP; } @@ -1062,8 +1068,8 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } - if (__in_dev_get_rtnl(dev)) { - IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); + if (__in_dev_get_rtnl_net(dev)) { + IN_DEV_CONF_SET(__in_dev_get_rtnl_net(dev), PROXY_ARP, on); return 0; } return -ENXIO; @@ -1075,7 +1081,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; @@ -1083,9 +1089,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) - return -ENOBUFS; - return 0; + return pneigh_create(&arp_tbl, net, &ip, dev, 0, 0, false); } return arp_req_set_proxy(net, dev, 1); @@ -1185,7 +1189,7 @@ static int arp_req_get(struct net *net, struct arpreq *r) read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, - min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); + min(dev->addr_len, sizeof(r->arp_ha.sa_data))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); @@ -1213,10 +1217,10 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); } return err; @@ -1293,14 +1297,14 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCDARP: - rtnl_lock(); + rtnl_net_lock(net); err = arp_req_delete(net, &r); - rtnl_unlock(); + rtnl_net_unlock(net); break; case SIOCSARP: - rtnl_lock(); + rtnl_net_lock(net); err = arp_req_set(net, &r); - rtnl_unlock(); + rtnl_net_unlock(net); break; case SIOCGARP: rcu_read_lock(); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 554804774628..e01492234b0b 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -121,7 +121,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt) { /* bpf_tcp_ca prog cannot have NULL tp */ - __tcp_send_ack((struct sock *)tp, rcv_nxt); + __tcp_send_ack((struct sock *)tp, rcv_nxt, 0); return 0; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 740af8541d2f..709021197e1c 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1715,8 +1715,7 @@ validate_return: */ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { - unsigned char optbuf[sizeof(struct ip_options) + 40]; - struct ip_options *opt = (struct ip_options *)optbuf; + struct inet_skb_parm parm; int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) @@ -1727,19 +1726,19 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) * so we can not use icmp_send and IPCB here. */ - memset(opt, 0, sizeof(struct ip_options)); - opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + memset(&parm, 0, sizeof(parm)); + parm.opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + res = __ip_options_compile(dev_net(skb->dev), &parm.opt, skb, NULL); rcu_read_unlock(); if (res) return; if (gateway) - __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, &parm); else - __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, &parm); } /** diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index cc6d0bd7b0a9..1614593b6d72 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -16,7 +16,7 @@ #include <net/tcp_states.h> #include <net/sock_reuseport.h> -int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *) uaddr; @@ -61,15 +61,17 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len err = -EACCES; goto out; } + + /* Update addresses before rehashing */ + inet->inet_daddr = fl4->daddr; + inet->inet_dport = usin->sin_port; if (!inet->inet_saddr) - inet->inet_saddr = fl4->saddr; /* Update source address */ + inet->inet_saddr = fl4->saddr; if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = fl4->saddr; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } - inet->inet_daddr = fl4->daddr; - inet->inet_dport = usin->sin_port; reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); @@ -82,7 +84,7 @@ out: } EXPORT_SYMBOL(__ip4_datagram_connect); -int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { int res; @@ -100,8 +102,6 @@ EXPORT_SYMBOL(ip4_datagram_connect); void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const struct ip_options_rcu *inet_opt; - __be32 daddr = inet->inet_daddr; struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; @@ -109,18 +109,13 @@ void ip4_datagram_release_cb(struct sock *sk) rcu_read_lock(); dst = __sk_dst_get(sk); - if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, 0)) { rcu_read_unlock(); return; } - inet_opt = rcu_dereference(inet->inet_opt); - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; - rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, - inet->inet_saddr, inet->inet_dport, - inet->inet_sport, sk->sk_protocol, - ip_sock_rt_tos(sk), sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, &fl4); + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c8b3cf5fba4c..942a887bf089 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -46,6 +46,7 @@ #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> +#include "igmp_internal.h" #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL @@ -107,15 +108,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_PROTO] = { .type = NLA_U8 }, }; -struct inet_fill_args { - u32 portid; - u32 seq; - int event; - unsigned int flags; - int netnsid; - int ifindex; -}; - #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) @@ -289,7 +281,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) - dev_disable_lro(dev); + netif_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ @@ -348,14 +340,13 @@ static void inetdev_destroy(struct in_device *in_dev) static int __init inet_blackhole_dev_init(void) { - int err = 0; + struct in_device *in_dev; rtnl_lock(); - if (!inetdev_init(blackhole_netdev)) - err = -ENOMEM; + in_dev = inetdev_init(blackhole_netdev); rtnl_unlock(); - return err; + return PTR_ERR_OR_ZERO(in_dev); } late_initcall(inet_blackhole_dev_init); @@ -1371,10 +1362,11 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; - struct net *net = dev_net(dev); + struct net *net; int master_idx; rcu_read_lock(); + net = dev_net_rcu(dev); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; @@ -1799,12 +1791,12 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct ifaddrmsg *ifm; int err, i; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { + ifm = nlmsg_payload(nlh, sizeof(*ifm)); + if (!ifm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); return -EINVAL; } - ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); return -EINVAL; @@ -1846,9 +1838,38 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, return 0; } -static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, - struct netlink_callback *cb, int *s_ip_idx, - struct inet_fill_args *fillargs) +static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + struct ip_mc_list *im; + int ip_idx = 0; + int err; + + for (im = rcu_dereference(in_dev->mc_list); + im; + im = rcu_dereference(im->next_rcu)) { + if (ip_idx < *s_ip_idx) { + ip_idx++; + continue; + } + err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs); + if (err < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; + } + err = 0; + ip_idx = 0; +done: + *s_ip_idx = ip_idx; + return err; +} + +static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; @@ -1874,6 +1895,21 @@ done: return err; } +static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + switch (fillargs->event) { + case RTM_NEWADDR: + return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs); + case RTM_GETMULTICAST: + return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx, + fillargs); + default: + return -EINVAL; + } +} + /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) @@ -1889,13 +1925,14 @@ static u32 inet_base_seq(const struct net *net) return res; } -static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, + int event) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, - .event = RTM_NEWADDR, + .event = event, .flags = NLM_F_MULTI, .netnsid = -1, }; @@ -1949,6 +1986,16 @@ done: return err; } +static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_NEWADDR); +} + +static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_GETMULTICAST); +} + static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -2845,6 +2892,8 @@ static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, + {.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST, + .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index f3281312eb5e..2c922afadb8f 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -120,51 +120,20 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) } #ifdef CONFIG_INET_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); - sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4, - dport, x->props.saddr.a4, sport, 0); + sk = inet_lookup_established(net, x->id.daddr.a4, dport, + x->props.saddr.a4, sport, 0); if (!sk) return ERR_PTR(-ENOENT); @@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) sk = esp_find_tcp_sk(x); err = PTR_ERR_OR_ZERO(sk); - if (err) + if (err) { + kfree_skb(skb); goto out; + } bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -279,7 +238,7 @@ static void esp_output_done(void *data, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } } @@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); @@ -816,7 +777,8 @@ int esp_input_done2(struct sk_buff *skb, int err) } skb_pull_rcsum(skb, hlen); - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL || + x->props.mode == XFRM_MODE_IPTFS) skb_reset_transport_header(skb); else skb_set_transport_header(skb, -ihl); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index e0d94270da28..05828d4cb6cd 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6) - : htons(ETH_P_IP); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) + : htons(ETH_P_IP); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 272e42d81323..1dab44e13d3b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,6 +32,7 @@ #include <linux/list.h> #include <linux/slab.h> +#include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> @@ -293,7 +294,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb))), + .flowi4_dscp = ip4h_dscp(ip_hdr(skb)), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; @@ -358,7 +359,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; - fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); + fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; @@ -553,18 +554,16 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, const struct in_ifaddr *ifa; struct in_device *in_dev; - in_dev = __in_dev_get_rtnl(dev); + in_dev = __in_dev_get_rtnl_net(dev); if (!in_dev) return -ENODEV; *colon = ':'; - rcu_read_lock(); - in_dev_for_each_ifa_rcu(ifa, in_dev) { + in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } - rcu_read_unlock(); if (!ifa) return -ENODEV; @@ -635,7 +634,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - rtnl_lock(); + rtnl_net_lock(net); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; @@ -659,7 +658,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } - rtnl_unlock(); + rtnl_net_unlock(net); return err; } return -EINVAL; @@ -837,19 +836,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, } } + if (cfg->fc_dst_len > 32) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + err = -EINVAL; + goto errout; + } + + if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { + NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); + err = -EINVAL; + goto errout; + } + if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); - return -EINVAL; + err = -EINVAL; + goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - return -EINVAL; + err = -EINVAL; + goto errout; } if (!cfg->fc_table) @@ -872,20 +885,24 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; + rtnl_net_lock(net); + if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; - goto errout; + goto unlock; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; - goto errout; + goto unlock; } err = fib_table_delete(net, tb, &cfg, extack); +unlock: + rtnl_net_unlock(net); errout: return err; } @@ -902,15 +919,20 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; + rtnl_net_lock(net); + tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; - goto errout; + goto unlock; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; + +unlock: + rtnl_net_unlock(net); errout: return err; } @@ -927,12 +949,12 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, if (filter->rtnl_held) ASSERT_RTNL(); - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + rtm = nlmsg_payload(nlh, sizeof(*rtm)); + if (!rtm) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } - rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); @@ -1351,7 +1373,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, - .flowi4_tos = frn->fl_tos & INET_DSCP_MASK, + .flowi4_dscp = inet_dsfield_to_dscp(frn->fl_tos), .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; @@ -1450,7 +1472,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev)); + rt_cache_flush(net); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); @@ -1461,7 +1483,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, */ fib_disable_ip(dev, event, true); } else { - rt_cache_flush(dev_net(dev)); + rt_cache_flush(net); } break; } @@ -1503,7 +1525,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: - flags = dev_get_flags(dev); + flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else @@ -1575,7 +1597,7 @@ static void ip_fib_net_exit(struct net *net) { int i; - ASSERT_RTNL(); + ASSERT_RTNL_NET(net); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); @@ -1615,9 +1637,15 @@ static int __net_init fib_net_init(struct net *net) error = ip_fib_net_init(net); if (error < 0) goto out; + + error = fib4_semantics_init(net); + if (error) + goto out_semantics; + error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; + error = fib_proc_init(net); if (error < 0) goto out_proc; @@ -1627,9 +1655,11 @@ out: out_proc: nl_fib_lookup_exit(net); out_nlfl: - rtnl_lock(); + fib4_semantics_exit(net); +out_semantics: + rtnl_net_lock(net); ip_fib_net_exit(net); - rtnl_unlock(); + rtnl_net_unlock(net); goto out; } @@ -1644,10 +1674,15 @@ static void __net_exit fib_net_exit_batch(struct list_head *net_list) struct net *net; rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) + list_for_each_entry(net, net_list, exit_list) { + __rtnl_net_lock(net); ip_fib_net_exit(net); - + __rtnl_net_unlock(net); + } rtnl_unlock(); + + list_for_each_entry(net, net_list, exit_list) + fib4_semantics_exit(net); } static struct pernet_operations fib_net_ops = { @@ -1658,9 +1693,9 @@ static struct pernet_operations fib_net_ops = { static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWROUTE, - .doit = inet_rtm_newroute}, + .doit = inet_rtm_newroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELROUTE, - .doit = inet_rtm_delroute}, + .doit = inet_rtm_delroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETROUTE, .dumpit = inet_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 8325224ef072..51f0193092f0 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/export.h> +#include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> @@ -37,6 +38,7 @@ struct fib4_rule { u8 dst_len; u8 src_len; dscp_t dscp; + dscp_t dscp_mask; u8 dscp_full:1; /* DSCP or TOS selector */ __be32 src; __be32 srcmask; @@ -192,7 +194,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, * to mask the upper three DSCP bits prior to matching to maintain * legacy behavior. */ - if (r->dscp_full && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) + if (r->dscp_full && (r->dscp ^ fl4->flowi4_dscp) & r->dscp_mask) return 0; else if (!r->dscp_full && r->dscp && !fib_dscp_masked_match(r->dscp, fl4)) @@ -201,12 +203,12 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) return 0; - if (fib_rule_port_range_set(&rule->sport_range) && - !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport)) + if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, + fl4->fl4_sport)) return 0; - if (fib_rule_port_range_set(&rule->dport_range) && - !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport)) + if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, + fl4->fl4_dport)) return 0; return 1; @@ -235,19 +237,49 @@ static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4, } rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); + rule4->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK); rule4->dscp_full = true; return 0; } +static int fib4_nl2rule_dscp_mask(const struct nlattr *nla, + struct fib4_rule *rule4, + struct netlink_ext_ack *extack) +{ + dscp_t dscp_mask; + + if (!rule4->dscp_full) { + NL_SET_ERR_MSG_ATTR(extack, nla, + "Cannot specify DSCP mask without DSCP value"); + return -EINVAL; + } + + dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); + if (rule4->dscp & ~dscp_mask) { + NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask"); + return -EINVAL; + } + + rule4->dscp_mask = dscp_mask; + + return 0; +} + static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct net *net = sock_net(skb->sk); + struct fib4_rule *rule4 = (struct fib4_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct fib4_rule *rule4 = (struct fib4_rule *) rule; + + if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) { + NL_SET_ERR_MSG(extack, + "Flow label cannot be specified for IPv4 FIB rules"); + goto errout; + } if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, @@ -265,6 +297,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0) goto errout; + if (tb[FRA_DSCP_MASK] && + fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0) + goto errout; + /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) @@ -360,6 +396,14 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, return 0; } + if (tb[FRA_DSCP_MASK]) { + dscp_t dscp_mask; + + dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2); + if (!rule4->dscp_full || rule4->dscp_mask != dscp_mask) + return 0; + } + #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; @@ -385,7 +429,9 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, if (rule4->dscp_full) { frh->tos = 0; if (nla_put_u8(skb, FRA_DSCP, - inet_dscp_to_dsfield(rule4->dscp) >> 2)) + inet_dscp_to_dsfield(rule4->dscp) >> 2) || + nla_put_u8(skb, FRA_DSCP_MASK, + inet_dscp_to_dsfield(rule4->dscp_mask) >> 2)) goto nla_put_failure; } else { frh->tos = inet_dscp_to_dsfield(rule4->dscp); @@ -412,7 +458,8 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) return nla_total_size(4) /* dst */ + nla_total_size(4) /* src */ + nla_total_size(4) /* flow */ - + nla_total_size(1); /* dscp */ + + nla_total_size(1) /* dscp */ + + nla_total_size(1); /* dscp mask */ } static void fib4_rule_flush_cache(struct fib_rules_ops *ops) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d2cee5c314f5..a5f3c8459758 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -50,12 +50,6 @@ #include "fib_lookup.h" -static struct hlist_head *fib_info_hash; -static struct hlist_head *fib_info_laddrhash; -static unsigned int fib_info_hash_size; -static unsigned int fib_info_hash_bits; -static unsigned int fib_info_cnt; - /* for_nexthops and change_nexthops only used when nexthop object * is not set in a fib_info. The logic within can reference fib_nh. */ @@ -258,8 +252,7 @@ void fib_release_info(struct fib_info *fi) ASSERT_RTNL(); if (fi && refcount_dec_and_test(&fi->fib_treeref)) { hlist_del(&fi->fib_hash); - - fib_info_cnt--; + fi->fib_net->ipv4.fib_info_cnt--; if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); @@ -335,11 +328,12 @@ static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope, static unsigned int fib_info_hashfn_result(const struct net *net, unsigned int val) { - return hash_32(val ^ net_hash_mix(net), fib_info_hash_bits); + return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits); } -static inline unsigned int fib_info_hashfn(struct fib_info *fi) +static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi) { + struct net *net = fi->fib_net; unsigned int val; val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol, @@ -354,7 +348,70 @@ static inline unsigned int fib_info_hashfn(struct fib_info *fi) } endfor_nexthops(fi) } - return fib_info_hashfn_result(fi->fib_net, val); + return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)]; +} + +static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net, + __be32 val) +{ + unsigned int hash_bits = net->ipv4.fib_info_hash_bits; + u32 slot; + + slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits); + + return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot]; +} + +static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits) +{ + /* The second half is used for prefsrc */ + return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head), + GFP_KERNEL); +} + +static void fib_info_hash_free(struct hlist_head *head) +{ + kvfree(head); +} + +static void fib_info_hash_grow(struct net *net) +{ + unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits; + struct hlist_head *new_info_hash, *old_info_hash; + unsigned int i; + + if (net->ipv4.fib_info_cnt < old_size) + return; + + new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1); + if (!new_info_hash) + return; + + old_info_hash = net->ipv4.fib_info_hash; + net->ipv4.fib_info_hash = new_info_hash; + net->ipv4.fib_info_hash_bits += 1; + + for (i = 0; i < old_size; i++) { + struct hlist_head *head = &old_info_hash[i]; + struct hlist_node *n; + struct fib_info *fi; + + hlist_for_each_entry_safe(fi, n, head, fib_hash) + hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi)); + } + + for (i = 0; i < old_size; i++) { + struct hlist_head *lhead = &old_info_hash[old_size + i]; + struct hlist_node *n; + struct fib_info *fi; + + hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) + hlist_add_head(&fi->fib_lhash, + fib_info_laddrhash_bucket(fi->fib_net, + fi->fib_prefsrc)); + } + + fib_info_hash_free(old_info_hash); } /* no metrics, only nexthop id */ @@ -370,13 +427,12 @@ static struct fib_info *fib_find_info_nh(struct net *net, (__force u32)cfg->fc_prefsrc, cfg->fc_priority); hash = fib_info_hashfn_result(net, hash); - head = &fib_info_hash[hash]; + head = &net->ipv4.fib_info_hash[hash]; hlist_for_each_entry(fi, head, fib_hash) { - if (!net_eq(fi->fib_net, net)) - continue; if (!fi->nh || fi->nh->id != cfg->fc_nh_id) continue; + if (cfg->fc_protocol == fi->fib_protocol && cfg->fc_scope == fi->fib_scope && cfg->fc_prefsrc == fi->fib_prefsrc && @@ -392,18 +448,13 @@ static struct fib_info *fib_find_info_nh(struct net *net, static struct fib_info *fib_find_info(struct fib_info *nfi) { - struct hlist_head *head; + struct hlist_head *head = fib_info_hash_bucket(nfi); struct fib_info *fi; - unsigned int hash; - - hash = fib_info_hashfn(nfi); - head = &fib_info_hash[hash]; hlist_for_each_entry(fi, head, fib_hash) { - if (!net_eq(fi->fib_net, nfi->fib_net)) - continue; if (fi->fib_nhs != nfi->fib_nhs) continue; + if (nfi->fib_protocol == fi->fib_protocol && nfi->fib_scope == fi->fib_scope && nfi->fib_prefsrc == fi->fib_prefsrc && @@ -574,11 +625,6 @@ int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, if (encap) { struct lwtunnel_state *lwtstate; - if (encap_type == LWTUNNEL_ENCAP_NONE) { - NL_SET_ERR_MSG(extack, "LWT encap type not specified"); - err = -EINVAL; - goto lwt_failure; - } err = lwtunnel_build_state(net, encap_type, encap, nhc->nhc_family, cfg, &lwtstate, extack); @@ -1239,64 +1285,6 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, return err; } -static struct hlist_head * -fib_info_laddrhash_bucket(const struct net *net, __be32 val) -{ - u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val, - fib_info_hash_bits); - - return &fib_info_laddrhash[slot]; -} - -static void fib_info_hash_move(struct hlist_head *new_info_hash, - struct hlist_head *new_laddrhash, - unsigned int new_size) -{ - struct hlist_head *old_info_hash, *old_laddrhash; - unsigned int old_size = fib_info_hash_size; - unsigned int i; - - ASSERT_RTNL(); - old_info_hash = fib_info_hash; - old_laddrhash = fib_info_laddrhash; - fib_info_hash_size = new_size; - fib_info_hash_bits = ilog2(new_size); - - for (i = 0; i < old_size; i++) { - struct hlist_head *head = &fib_info_hash[i]; - struct hlist_node *n; - struct fib_info *fi; - - hlist_for_each_entry_safe(fi, n, head, fib_hash) { - struct hlist_head *dest; - unsigned int new_hash; - - new_hash = fib_info_hashfn(fi); - dest = &new_info_hash[new_hash]; - hlist_add_head(&fi->fib_hash, dest); - } - } - fib_info_hash = new_info_hash; - - fib_info_laddrhash = new_laddrhash; - for (i = 0; i < old_size; i++) { - struct hlist_head *lhead = &old_laddrhash[i]; - struct hlist_node *n; - struct fib_info *fi; - - hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) { - struct hlist_head *ldest; - - ldest = fib_info_laddrhash_bucket(fi->fib_net, - fi->fib_prefsrc); - hlist_add_head(&fi->fib_lhash, ldest); - } - } - - kvfree(old_info_hash); - kvfree(old_laddrhash); -} - __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { @@ -1409,32 +1397,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg, } #endif - err = -ENOBUFS; - - if (fib_info_cnt >= fib_info_hash_size) { - unsigned int new_size = fib_info_hash_size << 1; - struct hlist_head *new_info_hash; - struct hlist_head *new_laddrhash; - size_t bytes; - - if (!new_size) - new_size = 16; - bytes = (size_t)new_size * sizeof(struct hlist_head *); - new_info_hash = kvzalloc(bytes, GFP_KERNEL); - new_laddrhash = kvzalloc(bytes, GFP_KERNEL); - if (!new_info_hash || !new_laddrhash) { - kvfree(new_info_hash); - kvfree(new_laddrhash); - } else { - fib_info_hash_move(new_info_hash, new_laddrhash, new_size); - } - if (!fib_info_hash_size) - goto failure; - } + fib_info_hash_grow(net); fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); - if (!fi) + if (!fi) { + err = -ENOBUFS; goto failure; + } + fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(fi->fib_metrics)) { err = PTR_ERR(fi->fib_metrics); @@ -1571,9 +1541,9 @@ link_it: refcount_set(&fi->fib_treeref, 1); refcount_set(&fi->fib_clntref, 1); - fib_info_cnt++; - hlist_add_head(&fi->fib_hash, - &fib_info_hash[fib_info_hashfn(fi)]); + net->ipv4.fib_info_cnt++; + hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi)); + if (fi->fib_prefsrc) { struct hlist_head *head; @@ -1665,8 +1635,7 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex)) goto nla_put_failure; - if (nhc->nhc_lwtstate && - lwtunnel_fill_encap(skb, nhc->nhc_lwtstate, + if (lwtunnel_fill_encap(skb, nhc->nhc_lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; @@ -1855,7 +1824,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) struct fib_info *fi; int ret = 0; - if (!fib_info_laddrhash || local == 0) + if (!local) return 0; head = fib_info_laddrhash_bucket(net, local); @@ -2118,7 +2087,7 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags) return 0; if (nh_flags & RTNH_F_DEAD) { - unsigned int flags = dev_get_flags(dev); + unsigned int flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) nh_flags |= RTNH_F_LINKDOWN; @@ -2193,34 +2162,52 @@ static bool fib_good_nh(const struct fib_nh *nh) return !!(state & NUD_VALID); } -void fib_select_multipath(struct fib_result *res, int hash) +void fib_select_multipath(struct fib_result *res, int hash, + const struct flowi4 *fl4) { struct fib_info *fi = res->fi; struct net *net = fi->fib_net; - bool first = false; + bool found = false; + bool use_neigh; + __be32 saddr; if (unlikely(res->fi->nh)) { nexthop_path_fib_result(res, hash); return; } + use_neigh = READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh); + saddr = fl4 ? fl4->saddr : 0; + change_nexthops(fi) { - if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) { - if (!fib_good_nh(nexthop_nh)) - continue; - if (!first) { - res->nh_sel = nhsel; - res->nhc = &nexthop_nh->nh_common; - first = true; - } + int nh_upper_bound; + + /* Nexthops without a carrier are assigned an upper bound of + * minus one when "ignore_routes_with_linkdown" is set. + */ + nh_upper_bound = atomic_read(&nexthop_nh->fib_nh_upper_bound); + if (nh_upper_bound == -1 || + (use_neigh && !fib_good_nh(nexthop_nh))) + continue; + + if (!found) { + res->nh_sel = nhsel; + res->nhc = &nexthop_nh->nh_common; + found = !saddr || nexthop_nh->nh_saddr == saddr; } - if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound)) + if (hash > nh_upper_bound) continue; - res->nh_sel = nhsel; - res->nhc = &nexthop_nh->nh_common; - return; + if (!saddr || nexthop_nh->nh_saddr == saddr) { + res->nh_sel = nhsel; + res->nhc = &nexthop_nh->nh_common; + return; + } + + if (found) + return; + } endfor_nexthops(fi); } #endif @@ -2235,7 +2222,7 @@ void fib_select_path(struct net *net, struct fib_result *res, if (fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(net, fl4, skb, NULL); - fib_select_multipath(res, h); + fib_select_multipath(res, h, fl4); } else #endif @@ -2257,3 +2244,22 @@ check_saddr: fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK); } } + +int __net_init fib4_semantics_init(struct net *net) +{ + unsigned int hash_bits = 4; + + net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits); + if (!net->ipv4.fib_info_hash) + return -ENOMEM; + + net->ipv4.fib_info_hash_bits = hash_bits; + net->ipv4.fib_info_cnt = 0; + + return 0; +} + +void __net_exit fib4_semantics_exit(struct net *net) +{ + fib_info_hash_free(net->ipv4.fib_info_hash); +} diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 161f5526b86c..59a6f0a9638f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1187,22 +1187,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) -{ - if (plen > KEYLENGTH) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - return false; - } - - if ((plen < KEYLENGTH) && (key << plen)) { - NL_SET_ERR_MSG(extack, - "Invalid prefix for given prefix length"); - return false; - } - - return true; -} - static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); @@ -1223,9 +1207,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); @@ -1717,9 +1698,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; @@ -2999,7 +2977,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", + "%u\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, @@ -3011,7 +2989,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", + "%u\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 3e30745e2c09..3970b6b7ace5 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -228,21 +228,27 @@ drop: return 0; } +static const struct net_offload *fou_gro_ops(const struct sock *sk, + int proto) +{ + const struct net_offload __rcu **offloads; + + /* FOU doesn't allow IPv4 on IPv6 sockets. */ + offloads = sk->sk_family == AF_INET6 ? inet6_offloads : inet_offloads; + return rcu_dereference(offloads[proto]); +} + static struct sk_buff *fou_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { - const struct net_offload __rcu **offloads; struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; struct sk_buff *pp = NULL; - u8 proto; if (!fou) goto out; - proto = fou->protocol; - /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are simply @@ -254,8 +260,7 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; - offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[proto]); + ops = fou_gro_ops(sk, fou->protocol); if (!ops || !ops->callbacks.gro_receive) goto out; @@ -268,10 +273,8 @@ out: static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { - const struct net_offload __rcu **offloads; struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; - u8 proto; int err; if (!fou) { @@ -279,10 +282,7 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, goto out; } - proto = fou->protocol; - - offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[proto]); + ops = fou_gro_ops(sk, fou->protocol); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) { err = -ENOSYS; goto out; @@ -323,7 +323,6 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { - const struct net_offload __rcu **offloads; const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; @@ -450,8 +449,7 @@ next_proto: /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; - offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[proto]); + ops = fou_gro_ops(sk, proto); if (!ops || !ops->callbacks.gro_receive) goto out; @@ -467,7 +465,6 @@ out: static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); - const struct net_offload __rcu **offloads; const struct net_offload *ops; unsigned int guehlen = 0; u8 proto; @@ -494,8 +491,7 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) return err; } - offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[proto]); + ops = fou_gro_ops(sk, proto); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 3d9614609b2d..7a99639204b1 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> @@ -18,9 +19,9 @@ const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = { [FOU_ATTR_TYPE] = { .type = NLA_U8, }, [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .len = 16, }, + [FOU_ATTR_LOCAL_V6] = NLA_POLICY_EXACT_LEN(16), [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_PEER_V6] = { .len = 16, }, + [FOU_ATTR_PEER_V6] = NLA_POLICY_EXACT_LEN(16), [FOU_ATTR_PEER_PORT] = { .type = NLA_BE16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index 63a6c4ed803d..438342dc8507 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_FOU_GEN_H #define _LINUX_FOU_GEN_H diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 6701a98d9a9f..dafd68f3436a 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -199,7 +199,7 @@ static const struct net_protocol net_gre_protocol = { static int __init gre_init(void) { - pr_info("GRE over IPv4 demultiplexor driver\n"); + pr_info("GRE over IPv4 demultiplexer driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4f088fa1c2f2..4abbec2f47ef 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -72,6 +72,7 @@ #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> +#include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> @@ -311,23 +312,24 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; + struct net_device *dev; bool rc = true; - int vif; if (!apply_ratelimit) return true; /* No rate limit on loopback */ - if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) + rcu_read_lock(); + dev = dst_dev_rcu(dst); + if (dev && (dev->flags & IFF_LOOPBACK)) goto out; - vif = l3mdev_master_ifindex(dst->dev); - peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); + peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, + l3mdev_master_ifindex_rcu(dev)); rc = inet_peer_xrlim_allow(peer, READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); - if (peer) - inet_putpeer(peer); out: + rcu_read_unlock(); if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); else @@ -400,13 +402,12 @@ static void icmp_push_reply(struct sock *sk, static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { - struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->dst.dev); + struct net *net = dev_net_rcu(rt->dst.dev); bool apply_ratelimit = false; + struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; - struct inet_sock *inet; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; @@ -425,12 +426,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; - inet = inet_sk(sk); icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); - inet->tos = ip_hdr(skb)->tos; + ipc.tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -445,7 +445,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); - fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(skb))); + fl4.flowi4_dscp = ip4h_dscp(ip_hdr(skb)); fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); @@ -469,13 +469,13 @@ out_bh_enable: */ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) { - struct net_device *route_lookup_dev = NULL; + struct net_device *dev = skb->dev; + const struct dst_entry *dst; - if (skb->dev) - route_lookup_dev = skb->dev; - else if (skb_dst(skb)) - route_lookup_dev = skb_dst(skb)->dev; - return route_lookup_dev; + if (dev) + return dev; + dst = skb_dst(skb); + return dst ? dst_dev(dst) : NULL; } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, @@ -496,7 +496,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_uid = sock_net_uid(net, NULL); - fl4->flowi4_tos = inet_dscp_to_dsfield(dscp); + fl4->flowi4_dscp = dscp; fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; @@ -517,6 +517,9 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, if (!IS_ERR(dst)) { if (rt != rt2) return rt; + if (inet_addr_type_dev_table(net, route_lookup_dev, + fl4->daddr) == RTN_LOCAL) + return rt; } else if (PTR_ERR(dst) == -EPERM) { rt = NULL; } else { @@ -542,14 +545,15 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, goto relookup_failed; } /* Ugh! */ - orefdst = skb_in->_skb_refdst; /* save old refdst */ - skb_dst_set(skb_in, NULL); + orefdst = skb_dstref_steal(skb_in); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, dscp, rt2->dst.dev) ? -EINVAL : 0; dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); - skb_in->_skb_refdst = orefdst; /* restore old refdst */ + /* steal dst entry from skb_in, don't drop refcnt */ + skb_dstref_steal(skb_in); + skb_dstref_restore(skb_in, orefdst); } if (err) @@ -578,6 +582,185 @@ relookup_failed: return ERR_PTR(err); } +struct icmp_ext_iio_addr4_subobj { + __be16 afi; + __be16 reserved; + __be32 addr4; +}; + +static unsigned int icmp_ext_iio_len(void) +{ + return sizeof(struct icmp_extobj_hdr) + + /* ifIndex */ + sizeof(__be32) + + /* Interface Address Sub-Object */ + sizeof(struct icmp_ext_iio_addr4_subobj) + + /* Interface Name Sub-Object. Length must be a multiple of 4 + * bytes. + */ + ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) + + /* MTU */ + sizeof(__be32); +} + +static unsigned int icmp_ext_max_len(u8 ext_objs) +{ + unsigned int ext_max_len; + + ext_max_len = sizeof(struct icmp_ext_hdr); + + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + ext_max_len += icmp_ext_iio_len(); + + return ext_max_len; +} + +static __be32 icmp_ext_iio_addr4_find(const struct net_device *dev) +{ + struct in_device *in_dev; + struct in_ifaddr *ifa; + + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + return 0; + + /* It is unclear from RFC 5837 which IP address should be chosen, but + * it makes sense to choose a global unicast address. + */ + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) + continue; + if (ifa->ifa_scope != RT_SCOPE_UNIVERSE || + ipv4_is_multicast(ifa->ifa_address)) + continue; + return ifa->ifa_address; + } + + return 0; +} + +static void icmp_ext_iio_iif_append(struct net *net, struct sk_buff *skb, + int iif) +{ + struct icmp_ext_iio_name_subobj *name_subobj; + struct icmp_extobj_hdr *objh; + struct net_device *dev; + __be32 data; + + if (!iif) + return; + + /* Add the fields in the order specified by RFC 5837. */ + objh = skb_put(skb, sizeof(*objh)); + objh->class_num = ICMP_EXT_OBJ_CLASS_IIO; + objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF); + + data = htonl(iif); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, iif); + if (!dev) + goto out; + + data = icmp_ext_iio_addr4_find(dev); + if (data) { + struct icmp_ext_iio_addr4_subobj *addr4_subobj; + + addr4_subobj = skb_put_zero(skb, sizeof(*addr4_subobj)); + addr4_subobj->afi = htons(ICMP_AFI_IP); + addr4_subobj->addr4 = data; + objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR; + } + + name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4)); + name_subobj->len = ALIGN(sizeof(*name_subobj), 4); + netdev_copy_name(dev, name_subobj->name); + objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME; + + data = htonl(READ_ONCE(dev->mtu)); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU; + +out: + rcu_read_unlock(); + objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh); +} + +static void icmp_ext_objs_append(struct net *net, struct sk_buff *skb, + u8 ext_objs, int iif) +{ + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + icmp_ext_iio_iif_append(net, skb, iif); +} + +static struct sk_buff * +icmp_ext_append(struct net *net, struct sk_buff *skb_in, struct icmphdr *icmph, + unsigned int room, int iif) +{ + unsigned int payload_len, ext_max_len, ext_len; + struct icmp_ext_hdr *ext_hdr; + struct sk_buff *skb; + u8 ext_objs; + int nhoff; + + switch (icmph->type) { + case ICMP_DEST_UNREACH: + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + break; + default: + return NULL; + } + + ext_objs = READ_ONCE(net->ipv4.sysctl_icmp_errors_extension_mask); + if (!ext_objs) + return NULL; + + ext_max_len = icmp_ext_max_len(ext_objs); + if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room) + return NULL; + + skb = skb_clone(skb_in, GFP_ATOMIC); + if (!skb) + return NULL; + + nhoff = skb_network_offset(skb); + payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN); + + if (!pskb_network_may_pull(skb, payload_len)) + goto free_skb; + + if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) || + __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false)) + goto free_skb; + + if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC)) + goto free_skb; + + ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr)); + ext_hdr->version = ICMP_EXT_VERSION_2; + + icmp_ext_objs_append(net, skb, ext_objs, iif); + + /* Do not send an empty extension structure. */ + ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr; + if (ext_len == sizeof(*ext_hdr)) + goto free_skb; + + ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len); + /* The length of the original datagram in 32-bit words (RFC 4884). */ + icmph->un.reserved[1] = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u32); + + return skb; + +free_skb: + consume_skb(skb); + return NULL; +} + /* * Send an ICMP message in response to a situation * @@ -590,13 +773,14 @@ relookup_failed: */ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, - const struct ip_options *opt) + const struct inet_skb_parm *parm) { struct iphdr *iph; int room; struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); bool apply_ratelimit = false; + struct sk_buff *ext_skb; struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; @@ -606,12 +790,14 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, struct sock *sk; if (!rt) - goto out; + return; + + rcu_read_lock(); if (rt->dst.dev) - net = dev_net(rt->dst.dev); + net = dev_net_rcu(rt->dst.dev); else if (skb_in->dev) - net = dev_net(skb_in->dev); + net = dev_net_rcu(skb_in->dev); else goto out; @@ -704,7 +890,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) - dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); + dev = dev_get_by_index_rcu(net, parm->iif ? parm->iif : + inet_iif(skb_in)); if (dev) saddr = inet_select_addr(dev, iph->saddr, @@ -719,7 +906,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); - if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) + if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, + &parm->opt)) goto out_unlock; @@ -733,8 +921,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data.icmph.checksum = 0; icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); - inet_sk(sk)->tos = tos; ipcm_init(&ipc); + ipc.tos = tos; ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; ipc.sockc.mark = mark; @@ -762,7 +950,12 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (room <= (int)sizeof(struct iphdr)) goto ende; - icmp_param.data_len = skb_in->len - icmp_param.offset; + ext_skb = icmp_ext_append(net, skb_in, &icmp_param.data.icmph, room, + parm->iif); + if (ext_skb) + icmp_param.skb = ext_skb; + + icmp_param.data_len = icmp_param.skb->len - icmp_param.offset; if (icmp_param.data_len > room) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); @@ -777,13 +970,17 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, trace_icmp_send(skb_in, type, code); icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); + + if (ext_skb) + consume_skb(ext_skb); ende: ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); -out:; +out: + rcu_read_unlock(); } EXPORT_SYMBOL(__icmp_send); @@ -792,14 +989,16 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; - struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + struct inet_skb_parm parm; struct nf_conn *ct; __be32 orig_ip; + memset(&parm, 0, sizeof(parm)); ct = nf_ct_get(skb_in, &ctinfo); - if (!ct || !(ct->status & IPS_SRC_NAT)) { - __icmp_send(skb_in, type, code, info, &opts); + if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) { + __icmp_send(skb_in, type, code, info, &parm); return; } @@ -813,8 +1012,9 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) goto out; orig_ip = ip_hdr(skb_in)->saddr; - ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - __icmp_send(skb_in, type, code, info, &opts); + dir = CTINFO2DIR(ctinfo); + ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip; + __icmp_send(skb_in, type, code, info, &parm); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); @@ -832,7 +1032,7 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) * avoid additional coding at protocol handlers. */ if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) { - __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); return; } @@ -866,7 +1066,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) struct net *net; u32 info = 0; - net = dev_net(skb_dst(skb)->dev); + net = skb_dst_dev_net_rcu(skb); /* * Incomplete header ? @@ -977,7 +1177,7 @@ out_err: static enum skb_drop_reason icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { - __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } @@ -1009,7 +1209,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) struct icmp_bxm icmp_param; struct net *net; - net = dev_net(skb_dst(skb)->dev); + net = skb_dst_dev_net_rcu(skb); /* should there be an ICMP stat for ignored echos? */ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; @@ -1038,9 +1238,9 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) { + struct net *net = dev_net_rcu(skb->dev); struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; - struct net *net = dev_net(skb->dev); struct inet6_dev *in6_dev; struct in_device *in_dev; struct net_device *dev; @@ -1179,7 +1379,7 @@ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) return SKB_NOT_DROPPED_YET; out_err: - __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(skb_dst_dev_net_rcu(skb), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } @@ -1196,7 +1396,7 @@ int icmp_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->dst.dev); + struct net *net = dev_net_rcu(rt->dst.dev); struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { @@ -1245,22 +1445,6 @@ int icmp_rcv(struct sk_buff *skb) goto reason_check; } - if (icmph->type == ICMP_EXT_ECHOREPLY) { - reason = ping_rcv(skb); - goto reason_check; - } - - /* - * 18 is the highest 'known' ICMP type. Anything else is a mystery - * - * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently - * discarded. - */ - if (icmph->type > NR_ICMP_TYPES) { - reason = SKB_DROP_REASON_UNHANDLED_PROTO; - goto error; - } - /* * Parse the ICMP message */ @@ -1287,6 +1471,23 @@ int icmp_rcv(struct sk_buff *skb) } } + if (icmph->type == ICMP_EXT_ECHOREPLY || + icmph->type == ICMP_ECHOREPLY) { + reason = ping_rcv(skb); + return reason ? NET_RX_DROP : NET_RX_SUCCESS; + } + + /* + * 18 is the highest 'known' ICMP type. Anything else is a mystery + * + * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently + * discarded. + */ + if (icmph->type > NR_ICMP_TYPES) { + reason = SKB_DROP_REASON_UNHANDLED_PROTO; + goto error; + } + reason = icmp_pointers[icmph->type].handler(skb); reason_check: if (!reason) { @@ -1369,9 +1570,9 @@ int icmp_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; int offset = iph->ihl<<2; struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset); + struct net *net = dev_net_rcu(skb->dev); int type = icmp_hdr(skb)->type; int code = icmp_hdr(skb)->code; - struct net *net = dev_net(skb->dev); /* * Use ping_err to handle all icmp errors except those @@ -1489,6 +1690,7 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; + net->ipv4.sysctl_icmp_errors_extension_mask = 0; net->ipv4.sysctl_icmp_msgs_per_sec = 1000; net->ipv4.sysctl_icmp_msgs_burst = 50; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6a238398acc9..7182f1419c2a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -81,6 +81,7 @@ #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> +#include "igmp_internal.h" #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> @@ -88,6 +89,8 @@ #include <linux/byteorder/generic.h> #include <net/net_namespace.h> +#include <net/netlink.h> +#include <net/addrconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> @@ -202,7 +205,7 @@ static void ip_sf_list_clear_all(struct ip_sf_list *psf) static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); - if (del_timer(&im->timer)) + if (timer_delete(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; @@ -248,7 +251,7 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; - if (del_timer(&im->timer)) { + if (timer_delete(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; @@ -424,7 +427,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); + return ip_local_out(skb_dst_dev_net(skb), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) @@ -798,7 +801,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, static void igmp_gq_timer_expire(struct timer_list *t) { - struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); + struct in_device *in_dev = timer_container_of(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); @@ -807,7 +810,7 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { - struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + struct in_device *in_dev = timer_container_of(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); @@ -837,7 +840,7 @@ static void igmp_ifc_event(struct in_device *in_dev) static void igmp_timer_expire(struct timer_list *t) { - struct ip_mc_list *im = from_timer(im, t, timer); + struct ip_mc_list *im = timer_container_of(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); @@ -971,7 +974,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); - if (del_timer(&in_dev->mr_ifc_timer)) + if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); @@ -1430,6 +1433,70 @@ static void ip_mc_hash_remove(struct in_device *in_dev, *mc_hash = im->next_hash; } +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args) +{ + struct ifa_cacheinfo ci; + struct ifaddrmsg *ifm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); + if (!nlh) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifa_family = AF_INET; + ifm->ifa_prefixlen = 32; + ifm->ifa_flags = IFA_F_PERMANENT; + ifm->ifa_scope = RT_SCOPE_UNIVERSE; + ifm->ifa_index = dev->ifindex; + + ci.cstamp = (READ_ONCE(im->mca_cstamp) - INITIAL_JIFFIES) * 100UL / HZ; + ci.tstamp = ci.cstamp; + ci.ifa_prefered = INFINITY_LIFE_TIME; + ci.ifa_valid = INFINITY_LIFE_TIME; + + if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || + nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + + nlmsg_end(skb, nlh); + return 0; +} + +static void inet_ifmcaddr_notify(struct net_device *dev, + const struct ip_mc_list *im, int event) +{ + struct inet_fill_args fillargs = { + .event = event, + }; + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOMEM; + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(sizeof(__be32)) + + nla_total_size(sizeof(struct ifa_cacheinfo)), + GFP_KERNEL); + if (!skb) + goto error; + + err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); + if (err < 0) { + WARN_ON_ONCE(err == -EMSGSIZE); + nlmsg_free(skb); + goto error; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MCADDR, NULL, GFP_KERNEL); + return; +error: + rtnl_set_sk_err(net, RTNLGRP_IPV4_MCADDR, err); +} /* * A socket has joined a multicast group on device dev. @@ -1473,6 +1540,8 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; + im->mca_cstamp = jiffies; + im->mca_tstamp = im->mca_cstamp; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; @@ -1492,6 +1561,7 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); + inet_ifmcaddr_notify(in_dev->dev, im, RTM_NEWMULTICAST); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: @@ -1705,6 +1775,8 @@ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); + inet_ifmcaddr_notify(in_dev->dev, i, + RTM_DELMULTICAST); ip_mc_clear_src(i); if (!in_dev->dead) @@ -1758,10 +1830,10 @@ void ip_mc_down(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); - if (del_timer(&in_dev->mr_ifc_timer)) + if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; - if (del_timer(&in_dev->mr_gq_timer)) + if (timer_delete(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif diff --git a/net/ipv4/igmp_internal.h b/net/ipv4/igmp_internal.h new file mode 100644 index 000000000000..0a1bcc8ec8e1 --- /dev/null +++ b/net/ipv4/igmp_internal.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IGMP_INTERNAL_H +#define _LINUX_IGMP_INTERNAL_H + +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; + int ifindex; +}; + +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args); +#endif diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 491c2c6b683e..97d57c52b9ad 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -157,12 +157,10 @@ static bool inet_use_bhash2_on_bind(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { - int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - - if (addr_type == IPV6_ADDR_ANY) + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) return false; - if (addr_type != IPV6_ADDR_MAPPED) + if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) return true; } #endif @@ -170,7 +168,7 @@ static bool inet_use_bhash2_on_bind(const struct sock *sk) } static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, - kuid_t sk_uid, bool relax, + kuid_t uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { int bound_dev_if2; @@ -187,12 +185,12 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, if (!relax || (!reuseport_ok && sk->sk_reuseport && sk2->sk_reuseport && reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || - uid_eq(sk_uid, sock_i_uid(sk2))))) + uid_eq(uid, sk_uid(sk2))))) return true; } else if (!reuseport_ok || !sk->sk_reuseport || !sk2->sk_reuseport || !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && - !uid_eq(sk_uid, sock_i_uid(sk2)))) { + !uid_eq(uid, sk_uid(sk2)))) { return true; } } @@ -200,7 +198,7 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, } static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, - kuid_t sk_uid, bool relax, + kuid_t uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { if (ipv6_only_sock(sk2)) { @@ -213,20 +211,20 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, #endif } - return inet_bind_conflict(sk, sk2, sk_uid, relax, + return inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok); } static bool inet_bhash2_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, - kuid_t sk_uid, + kuid_t uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { struct sock *sk2; sk_for_each_bound(sk2, &tb2->owners) { - if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, + if (__inet_bhash2_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok)) return true; } @@ -244,8 +242,8 @@ static int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, /* may be null */ bool relax, bool reuseport_ok) { - kuid_t uid = sock_i_uid((struct sock *)sk); struct sock_reuseport *reuseport_cb; + kuid_t uid = sk_uid(sk); bool reuseport_cb_ok; struct sock *sk2; @@ -289,11 +287,11 @@ static int inet_csk_bind_conflict(const struct sock *sk, static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l3mdev, bool relax, bool reuseport_ok) { - kuid_t uid = sock_i_uid((struct sock *)sk); const struct net *net = sock_net(sk); struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; + kuid_t uid = sk_uid(sk); bool conflict = false; bool reuseport_cb_ok; @@ -332,7 +330,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, struct inet_bind2_bucket **tb2_ret, struct inet_bind_hashbucket **head2_ret, int *port_ret) { - struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk); int i, low, high, attempt_half, port, l3mdev; struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); @@ -425,17 +423,15 @@ success: } static inline int sk_reuseport_match(struct inet_bind_bucket *tb, - struct sock *sk) + const struct sock *sk) { - kuid_t uid = sock_i_uid(sk); - if (tb->fastreuseport <= 0) return 0; if (!sk->sk_reuseport) return 0; if (rcu_access_pointer(sk->sk_reuseport_cb)) return 0; - if (!uid_eq(tb->fastuid, uid)) + if (!uid_eq(tb->fastuid, sk_uid(sk))) return 0; /* We only need to check the rcv_saddr if this tb was once marked * without fastreuseport and then was reset, as we can only know that @@ -457,17 +453,17 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, ipv6_only_sock(sk), true, false); } -void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, - struct sock *sk) +void inet_csk_update_fastreuse(const struct sock *sk, + struct inet_bind_bucket *tb, + struct inet_bind2_bucket *tb2) { - kuid_t uid = sock_i_uid(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; if (hlist_empty(&tb->bhash2)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; - tb->fastuid = uid; + tb->fastuid = sk_uid(sk); tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; @@ -494,7 +490,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, */ if (!sk_reuseport_match(tb, sk)) { tb->fastreuseport = FASTREUSEPORT_STRICT; - tb->fastuid = uid; + tb->fastuid = sk_uid(sk); tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; @@ -506,6 +502,9 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, tb->fastreuseport = 0; } } + + tb2->fastreuse = tb->fastreuse; + tb2->fastreuseport = tb->fastreuseport; } /* Obtain a reference to a local port for the given sock, @@ -514,10 +513,10 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, */ int inet_csk_get_port(struct sock *sk, unsigned short snum) { - struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; + struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk); int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; @@ -587,7 +586,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) } success: - inet_csk_update_fastreuse(tb, sk); + inet_csk_update_fastreuse(sk, tb, tb2); if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, tb2, port); @@ -600,7 +599,7 @@ fail_unlock: if (bhash2_created) inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2); if (bhash_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); + inet_bind_bucket_destroy(tb); } if (head2_lock_acquired) spin_unlock(&head2->lock); @@ -711,44 +710,18 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) spin_unlock_bh(&queue->fastopenq.lock); } -out: release_sock(sk); - if (newsk && mem_cgroup_sockets_enabled) { - gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; - int amt = 0; - - /* atomically get the memory usage, set and charge the - * newsk->sk_memcg. - */ - lock_sock(newsk); - mem_cgroup_sk_alloc(newsk); - if (newsk->sk_memcg) { - /* The socket has not been accepted yet, no need - * to look at newsk->sk_wmem_queued. - */ - amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&newsk->sk_rmem_alloc)); - } - - if (amt) - mem_cgroup_charge_skmem(newsk->sk_memcg, amt, gfp); - kmem_cache_charge(newsk, gfp); - - release_sock(newsk); - } if (req) reqsk_put(req); - if (newsk) - inet_init_csk_locks(newsk); - + inet_init_csk_locks(newsk); return newsk; + out_err: - newsk = NULL; - req = NULL; + release_sock(sk); arg->err = error; - goto out; + return NULL; } EXPORT_SYMBOL(inet_csk_accept); @@ -764,12 +737,11 @@ void inet_csk_init_xmit_timers(struct sock *sk, { struct inet_connection_sock *icsk = inet_csk(sk); - timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&sk->tcp_retransmit_timer, retransmit_handler, 0); timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); - timer_setup(&sk->sk_timer, keepalive_handler, 0); + timer_setup(&icsk->icsk_keepalive_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } -EXPORT_SYMBOL(inet_csk_init_xmit_timers); void inet_csk_clear_xmit_timers(struct sock *sk) { @@ -778,11 +750,10 @@ void inet_csk_clear_xmit_timers(struct sock *sk) smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer(sk, &sk->tcp_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer(sk, &icsk->icsk_keepalive_timer); } -EXPORT_SYMBOL(inet_csk_clear_xmit_timers); void inet_csk_clear_xmit_timers_sync(struct sock *sk) { @@ -794,22 +765,10 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk) smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); - sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &sk->tcp_retransmit_timer); sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); - sk_stop_timer_sync(sk, &sk->sk_timer); -} - -void inet_csk_delete_keepalive_timer(struct sock *sk) -{ - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer_sync(sk, &icsk->icsk_keepalive_timer); } -EXPORT_SYMBOL(inet_csk_delete_keepalive_timer); - -void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) -{ - sk_reset_timer(sk, &sk->sk_timer, jiffies + len); -} -EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, @@ -828,7 +787,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, - htons(ireq->ir_num), sk->sk_uid); + htons(ireq->ir_num), sk_uid(sk)); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -845,7 +804,6 @@ no_route: __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } -EXPORT_SYMBOL_GPL(inet_csk_route_req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, @@ -866,7 +824,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, - htons(ireq->ir_num), sk->sk_uid); + htons(ireq->ir_num), sk_uid(sk)); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -904,16 +862,6 @@ static void syn_ack_recalc(struct request_sock *req, req->num_timeout >= rskq_defer_accept - 1; } -int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) -{ - int err = req->rsk_ops->rtx_syn_ack(parent, req); - - if (!err) - req->num_retrans++; - return err; -} -EXPORT_SYMBOL(inet_rtx_syn_ack); - static struct request_sock * reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) @@ -937,7 +885,6 @@ reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; req->syncookie = 0; - req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; @@ -965,7 +912,6 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; - req->timeout = TCP_TIMEOUT_INIT; } return req; @@ -1040,9 +986,10 @@ static bool reqsk_queue_unlink(struct request_sock *req) bool found = false; if (sk_hashed(sk)) { - struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); - spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash); + struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk); + spinlock_t *lock; + lock = inet_ehash_lockp(hashinfo, req->rsk_hash); spin_lock(lock); found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); @@ -1072,18 +1019,17 @@ bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { return __inet_csk_reqsk_queue_drop(sk, req, false); } -EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_put(req); } -EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); +EXPORT_IPV6_MOD(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { - struct request_sock *req = from_timer(req, t, rsk_timer); + struct request_sock *req = timer_container_of(req, t, rsk_timer); struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; struct inet_connection_sock *icsk; @@ -1148,16 +1094,18 @@ static void reqsk_timer_handler(struct timer_list *t) young <<= 1; } } + syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); - req->rsk_ops->syn_ack_timeout(req); + tcp_syn_ack_timeout(req); + if (!expire && (!resend || - !inet_rtx_syn_ack(sk_listener, req) || + !tcp_rtx_synack(sk_listener, req) || inet_rsk(req)->acked)) { if (req->num_timeout++ == 0) atomic_dec(&queue->young); - mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); + mod_timer(&req->rsk_timer, jiffies + tcp_reqsk_timeout(req)); if (!nreq) return; @@ -1191,11 +1139,10 @@ no_ownership: drop: __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); - reqsk_put(req); + reqsk_put(oreq); } -static bool reqsk_queue_hash_req(struct request_sock *req, - unsigned long timeout) +static bool reqsk_queue_hash_req(struct request_sock *req) { bool found_dup_sk = false; @@ -1203,8 +1150,9 @@ static bool reqsk_queue_hash_req(struct request_sock *req, return false; /* The timer needs to be setup after a successful insertion. */ + req->timeout = tcp_timeout_init((struct sock *)req); timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); - mod_timer(&req->rsk_timer, jiffies + timeout); + mod_timer(&req->rsk_timer, jiffies + req->timeout); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. @@ -1214,16 +1162,14 @@ static bool reqsk_queue_hash_req(struct request_sock *req, return true; } -bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - unsigned long timeout) +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req) { - if (!reqsk_queue_hash_req(req, timeout)) + if (!reqsk_queue_hash_req(req)) return false; inet_csk_reqsk_queue_added(sk); return true; } -EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, const gfp_t priority) @@ -1249,42 +1195,61 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk = sk_clone_lock(sk, priority); + struct inet_connection_sock *newicsk; + struct inet_request_sock *ireq; + struct inet_sock *newinet; + + if (!newsk) + return NULL; + + newicsk = inet_csk(newsk); + newinet = inet_sk(newsk); + ireq = inet_rsk(req); + + newicsk->icsk_bind_hash = NULL; + newicsk->icsk_bind2_hash = NULL; - if (newsk) { - struct inet_connection_sock *newicsk = inet_csk(newsk); + newinet->inet_dport = ireq->ir_rmt_port; + newinet->inet_num = ireq->ir_num; + newinet->inet_sport = htons(ireq->ir_num); - inet_sk_set_state(newsk, TCP_SYN_RECV); - newicsk->icsk_bind_hash = NULL; - newicsk->icsk_bind2_hash = NULL; + newsk->sk_bound_dev_if = ireq->ir_iif; - inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; - inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; - inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); + newsk->sk_daddr = ireq->ir_rmt_addr; + newsk->sk_rcv_saddr = ireq->ir_loc_addr; + newinet->inet_saddr = ireq->ir_loc_addr; - /* listeners have SOCK_RCU_FREE, not the children */ - sock_reset_flag(newsk, SOCK_RCU_FREE); +#if IS_ENABLED(CONFIG_IPV6) + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; +#endif - inet_sk(newsk)->mc_list = NULL; + /* listeners have SOCK_RCU_FREE, not the children */ + sock_reset_flag(newsk, SOCK_RCU_FREE); - newsk->sk_mark = inet_rsk(req)->ir_mark; - atomic64_set(&newsk->sk_cookie, - atomic64_read(&inet_rsk(req)->ir_cookie)); + inet_sk(newsk)->mc_list = NULL; - newicsk->icsk_retransmits = 0; - newicsk->icsk_backoff = 0; - newicsk->icsk_probes_out = 0; - newicsk->icsk_probes_tstamp = 0; + newsk->sk_mark = inet_rsk(req)->ir_mark; + atomic64_set(&newsk->sk_cookie, + atomic64_read(&inet_rsk(req)->ir_cookie)); - /* Deinitialize accept_queue to trap illegal accesses. */ - memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + newicsk->icsk_retransmits = 0; + newicsk->icsk_backoff = 0; + newicsk->icsk_probes_out = 0; + newicsk->icsk_probes_tstamp = 0; - inet_clone_ulp(req, newsk, priority); + /* Deinitialize accept_queue to trap illegal accesses. */ + memset(&newicsk->icsk_accept_queue, 0, + sizeof(newicsk->icsk_accept_queue)); + + inet_sk_set_state(newsk, TCP_SYN_RECV); + + inet_clone_ulp(req, newsk, priority); + + security_inet_csk_clone(newsk, req); - security_inet_csk_clone(newsk, req); - } return newsk; } -EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this @@ -1309,14 +1274,21 @@ void inet_csk_destroy_sock(struct sock *sk) xfrm_sk_free_policy(sk); - this_cpu_dec(*sk->sk_prot->orphan_count); + tcp_orphan_count_dec(); sock_put(sk); } EXPORT_SYMBOL(inet_csk_destroy_sock); +void inet_csk_prepare_for_destroy_sock(struct sock *sk) +{ + /* The below has to be done to allow calling inet_csk_destroy_sock */ + sock_set_flag(sk, SOCK_DEAD); + tcp_orphan_count_inc(); +} + /* This function allows to force a closure of a socket after the call to - * tcp/dccp_create_openreq_child(). + * tcp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) __releases(&sk->sk_lock.slock) @@ -1374,7 +1346,6 @@ int inet_csk_listen_start(struct sock *sk) inet_sk_set_state(sk, TCP_CLOSE); return err; } -EXPORT_SYMBOL_GPL(inet_csk_listen_start); static void inet_child_forget(struct sock *sk, struct request_sock *req, struct sock *child) @@ -1383,7 +1354,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, sock_orphan(child); - this_cpu_inc(*sk->sk_prot->orphan_count); + tcp_orphan_count_inc(); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); @@ -1469,7 +1440,6 @@ child_put: sock_put(child); return NULL; } -EXPORT_SYMBOL(inet_csk_complete_hashdance); /* * This routine closes sockets which have been at least partially @@ -1547,34 +1517,16 @@ skip_child_forget: } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); -void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) -{ - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; - const struct inet_sock *inet = inet_sk(sk); - - sin->sin_family = AF_INET; - sin->sin_addr.s_addr = inet->inet_daddr; - sin->sin_port = inet->inet_dport; -} -EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); - static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) { const struct inet_sock *inet = inet_sk(sk); - const struct ip_options_rcu *inet_opt; - __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; rcu_read_lock(); - inet_opt = rcu_dereference(inet->inet_opt); - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; fl4 = &fl->u.ip4; - rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, - inet->inet_saddr, inet->inet_dport, - inet->inet_sport, sk->sk_protocol, - ip_sock_rt_tos(sk), sk->sk_bound_dev_if); + inet_sk_init_flowi4(inet, fl4); + rt = ip_route_output_flow(sock_net(sk), fl4, sk); if (IS_ERR(rt)) rt = NULL; if (rt) @@ -1602,4 +1554,3 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) out: return dst; } -EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 321acc8abf17..3f5b1418a610 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -20,9 +20,6 @@ #include <net/ipv6.h> #include <net/inet_common.h> #include <net/inet_connection_sock.h> -#include <net/inet_hashtables.h> -#include <net/inet_timewait_sock.h> -#include <net/inet6_hashtables.h> #include <net/bpf_sk_storage.h> #include <net/netlink.h> @@ -74,54 +71,29 @@ static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) { - r->idiag_family = sk->sk_family; + r->idiag_family = READ_ONCE(sk->sk_family); - r->id.idiag_sport = htons(sk->sk_num); - r->id.idiag_dport = sk->sk_dport; - r->id.idiag_if = sk->sk_bound_dev_if; + r->id.idiag_sport = htons(READ_ONCE(sk->sk_num)); + r->id.idiag_dport = READ_ONCE(sk->sk_dport); + r->id.idiag_if = READ_ONCE(sk->sk_bound_dev_if); sock_diag_save_cookie(sk, r->id.idiag_cookie); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - *(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr; - *(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr; + if (r->idiag_family == AF_INET6) { + data_race(*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr); + data_race(*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr); } else #endif { memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - r->id.idiag_src[0] = sk->sk_rcv_saddr; - r->id.idiag_dst[0] = sk->sk_daddr; + r->id.idiag_src[0] = READ_ONCE(sk->sk_rcv_saddr); + r->id.idiag_dst[0] = READ_ONCE(sk->sk_daddr); } } EXPORT_SYMBOL_GPL(inet_diag_msg_common_fill); -static size_t inet_sk_attr_size(struct sock *sk, - const struct inet_diag_req_v2 *req, - bool net_admin) -{ - const struct inet_diag_handler *handler; - size_t aux = 0; - - rcu_read_lock(); - handler = rcu_dereference(inet_diag_table[req->sdiag_protocol]); - DEBUG_NET_WARN_ON_ONCE(!handler); - if (handler && handler->idiag_get_aux_size) - aux = handler->idiag_get_aux_size(sk, net_admin); - rcu_read_unlock(); - - return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(sizeof(struct inet_diag_msg)) - + inet_diag_msg_attrs_size() - + nla_total_size(sizeof(struct inet_diag_meminfo)) - + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) - + nla_total_size(TCP_CA_NAME_MAX) - + nla_total_size(sizeof(struct tcpvegas_info)) - + aux - + 64; -} - int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, @@ -160,7 +132,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; -#ifdef CONFIG_SOCK_CGROUP_DATA +#ifdef CONFIG_CGROUP_NET_CLASSID classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif /* Fallback to socket priority if class id isn't set. @@ -181,7 +153,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, goto errout; #endif - r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); + r->idiag_uid = from_kuid_munged(user_ns, sk_uid(sk)); r->idiag_inode = sock_i_ino(sk); memset(&inet_sockopt, 0, sizeof(inet_sockopt)); @@ -282,7 +254,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), - .idiag_fmem = sk_forward_alloc_get(sk), + .idiag_fmem = READ_ONCE(sk->sk_forward_alloc), .idiag_tmem = sk_wmem_alloc_get(sk), }; @@ -313,19 +285,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { r->idiag_timer = 1; - r->idiag_retrans = icsk->icsk_retransmits; + r->idiag_retrans = READ_ONCE(icsk->icsk_retransmits); r->idiag_expires = - jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies); + jiffies_delta_to_msecs(tcp_timeout_expires(sk) - jiffies); } else if (icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; - r->idiag_retrans = icsk->icsk_probes_out; + r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out); r->idiag_expires = - jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies); - } else if (timer_pending(&sk->sk_timer)) { + jiffies_delta_to_msecs(tcp_timeout_expires(sk) - jiffies); + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { r->idiag_timer = 2; - r->idiag_retrans = icsk->icsk_probes_out; + r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out); r->idiag_expires = - jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); + jiffies_delta_to_msecs(icsk->icsk_keepalive_timer.expires - jiffies); } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { @@ -422,183 +394,6 @@ errout: } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); -static int inet_twsk_diag_fill(struct sock *sk, - struct sk_buff *skb, - struct netlink_callback *cb, - u16 nlmsg_flags, bool net_admin) -{ - struct inet_timewait_sock *tw = inet_twsk(sk); - struct inet_diag_msg *r; - struct nlmsghdr *nlh; - long tmo; - - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, - sizeof(*r), nlmsg_flags); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - BUG_ON(tw->tw_state != TCP_TIME_WAIT); - - inet_diag_msg_common_fill(r, sk); - r->idiag_retrans = 0; - - r->idiag_state = READ_ONCE(tw->tw_substate); - r->idiag_timer = 3; - tmo = tw->tw_timer.expires - jiffies; - r->idiag_expires = jiffies_delta_to_msecs(tmo); - r->idiag_rqueue = 0; - r->idiag_wqueue = 0; - r->idiag_uid = 0; - r->idiag_inode = 0; - - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - tw->tw_mark)) { - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; - } - - nlmsg_end(skb, nlh); - return 0; -} - -static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, - struct netlink_callback *cb, - u16 nlmsg_flags, bool net_admin) -{ - struct request_sock *reqsk = inet_reqsk(sk); - struct inet_diag_msg *r; - struct nlmsghdr *nlh; - long tmo; - - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - inet_diag_msg_common_fill(r, sk); - r->idiag_state = TCP_SYN_RECV; - r->idiag_timer = 1; - r->idiag_retrans = reqsk->num_retrans; - - BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != - offsetof(struct sock, sk_cookie)); - - tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; - r->idiag_expires = jiffies_delta_to_msecs(tmo); - r->idiag_rqueue = 0; - r->idiag_wqueue = 0; - r->idiag_uid = 0; - r->idiag_inode = 0; - - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) { - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; - } - - nlmsg_end(skb, nlh); - return 0; -} - -static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - u16 nlmsg_flags, bool net_admin) -{ - if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); - - if (sk->sk_state == TCP_NEW_SYN_RECV) - return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); - - return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags, - net_admin); -} - -struct sock *inet_diag_find_one_icsk(struct net *net, - struct inet_hashinfo *hashinfo, - const struct inet_diag_req_v2 *req) -{ - struct sock *sk; - - rcu_read_lock(); - if (req->sdiag_family == AF_INET) - sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0], - req->id.idiag_dport, req->id.idiag_src[0], - req->id.idiag_sport, req->id.idiag_if); -#if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) { - if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && - ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) - sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3], - req->id.idiag_dport, req->id.idiag_src[3], - req->id.idiag_sport, req->id.idiag_if); - else - sk = inet6_lookup(net, hashinfo, NULL, 0, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); - } -#endif - else { - rcu_read_unlock(); - return ERR_PTR(-EINVAL); - } - rcu_read_unlock(); - if (!sk) - return ERR_PTR(-ENOENT); - - if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { - sock_gen_put(sk); - return ERR_PTR(-ENOENT); - } - - return sk; -} -EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); - -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *req) -{ - struct sk_buff *in_skb = cb->skb; - bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); - struct net *net = sock_net(in_skb->sk); - struct sk_buff *rep; - struct sock *sk; - int err; - - sk = inet_diag_find_one_icsk(net, hashinfo, req); - if (IS_ERR(sk)) - return PTR_ERR(sk); - - rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL); - if (!rep) { - err = -ENOMEM; - goto out; - } - - err = sk_diag_fill(sk, rep, cb, req, 0, net_admin); - if (err < 0) { - WARN_ON(err == -EMSGSIZE); - nlmsg_free(rep); - goto out; - } - err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); - -out: - if (sk) - sock_gen_put(sk); - - return err; -} -EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); - static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, int hdrlen, @@ -785,7 +580,7 @@ static void entry_fill_addrs(struct inet_diag_entry *entry, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { + if (entry->family == AF_INET6) { entry->saddr = sk->sk_v6_rcv_saddr.s6_addr32; entry->daddr = sk->sk_v6_daddr.s6_addr32; } else @@ -796,31 +591,36 @@ static void entry_fill_addrs(struct inet_diag_entry *entry, } } -int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) +int inet_diag_bc_sk(const struct inet_diag_dump_data *cb_data, struct sock *sk) { - struct inet_sock *inet = inet_sk(sk); + const struct nlattr *bc = cb_data->inet_diag_nla_bc; + const struct inet_sock *inet = inet_sk(sk); struct inet_diag_entry entry; if (!bc) return 1; - entry.family = sk->sk_family; + entry.family = READ_ONCE(sk->sk_family); entry_fill_addrs(&entry, sk); - entry.sport = inet->inet_num; - entry.dport = ntohs(inet->inet_dport); - entry.ifindex = sk->sk_bound_dev_if; - entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; - if (sk_fullsock(sk)) - entry.mark = READ_ONCE(sk->sk_mark); - else if (sk->sk_state == TCP_NEW_SYN_RECV) - entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; - else if (sk->sk_state == TCP_TIME_WAIT) - entry.mark = inet_twsk(sk)->tw_mark; - else - entry.mark = 0; + entry.sport = READ_ONCE(inet->inet_num); + entry.dport = ntohs(READ_ONCE(inet->inet_dport)); + entry.ifindex = READ_ONCE(sk->sk_bound_dev_if); + if (cb_data->userlocks_needed) + entry.userlocks = sk_fullsock(sk) ? READ_ONCE(sk->sk_userlocks) : 0; + if (cb_data->mark_needed) { + if (sk_fullsock(sk)) + entry.mark = READ_ONCE(sk->sk_mark); + else if (sk->sk_state == TCP_NEW_SYN_RECV) + entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; + else if (sk->sk_state == TCP_TIME_WAIT) + entry.mark = inet_twsk(sk)->tw_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; + if (cb_data->cgroup_needed) + entry.cgroup_id = sk_fullsock(sk) ? + cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)) : 0; #endif return inet_diag_bc_run(bc, &entry); @@ -920,16 +720,21 @@ static bool valid_cgroupcond(const struct inet_diag_bc_op *op, int len, } #endif -static int inet_diag_bc_audit(const struct nlattr *attr, +static int inet_diag_bc_audit(struct inet_diag_dump_data *cb_data, const struct sk_buff *skb) { - bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN); + const struct nlattr *attr = cb_data->inet_diag_nla_bc; const void *bytecode, *bc; int bytecode_len, len; + bool net_admin; + + if (!attr) + return 0; - if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op)) + if (nla_len(attr) < sizeof(struct inet_diag_bc_op)) return -EINVAL; + net_admin = netlink_net_capable(skb, CAP_NET_ADMIN); bytecode = bc = nla_data(attr); len = bytecode_len = nla_len(attr); @@ -961,14 +766,18 @@ static int inet_diag_bc_audit(const struct nlattr *attr, return -EPERM; if (!valid_markcond(bc, len, &min_len)) return -EINVAL; + cb_data->mark_needed = true; break; #ifdef CONFIG_SOCK_CGROUP_DATA case INET_DIAG_BC_CGROUP_COND: if (!valid_cgroupcond(bc, len, &min_len)) return -EINVAL; + cb_data->cgroup_needed = true; break; #endif case INET_DIAG_BC_AUTO: + cb_data->userlocks_needed = true; + fallthrough; case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: break; @@ -992,280 +801,6 @@ static int inet_diag_bc_audit(const struct nlattr *attr, return len == 0 ? 0 : -EINVAL; } -static void twsk_build_assert(void) -{ - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != - offsetof(struct sock, sk_family)); - - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) != - offsetof(struct inet_sock, inet_num)); - - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) != - offsetof(struct inet_sock, inet_dport)); - - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) != - offsetof(struct inet_sock, inet_rcv_saddr)); - - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) != - offsetof(struct inet_sock, inet_daddr)); - -#if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) != - offsetof(struct sock, sk_v6_rcv_saddr)); - - BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) != - offsetof(struct sock, sk_v6_daddr)); -#endif -} - -void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r) -{ - bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); - struct inet_diag_dump_data *cb_data = cb->data; - struct net *net = sock_net(skb->sk); - u32 idiag_states = r->idiag_states; - int i, num, s_i, s_num; - struct nlattr *bc; - struct sock *sk; - - bc = cb_data->inet_diag_nla_bc; - if (idiag_states & TCPF_SYN_RECV) - idiag_states |= TCPF_NEW_SYN_RECV; - s_i = cb->args[1]; - s_num = num = cb->args[2]; - - if (cb->args[0] == 0) { - if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport) - goto skip_listen_ht; - - for (i = s_i; i <= hashinfo->lhash2_mask; i++) { - struct inet_listen_hashbucket *ilb; - struct hlist_nulls_node *node; - - num = 0; - ilb = &hashinfo->lhash2[i]; - - if (hlist_nulls_empty(&ilb->nulls_head)) { - s_num = 0; - continue; - } - spin_lock(&ilb->lock); - sk_nulls_for_each(sk, node, &ilb->nulls_head) { - struct inet_sock *inet = inet_sk(sk); - - if (!net_eq(sock_net(sk), net)) - continue; - - if (num < s_num) { - num++; - continue; - } - - if (r->sdiag_family != AF_UNSPEC && - sk->sk_family != r->sdiag_family) - goto next_listen; - - if (r->id.idiag_sport != inet->inet_sport && - r->id.idiag_sport) - goto next_listen; - - if (!inet_diag_bc_sk(bc, sk)) - goto next_listen; - - if (inet_sk_diag_fill(sk, inet_csk(sk), skb, - cb, r, NLM_F_MULTI, - net_admin) < 0) { - spin_unlock(&ilb->lock); - goto done; - } - -next_listen: - ++num; - } - spin_unlock(&ilb->lock); - - s_num = 0; - } -skip_listen_ht: - cb->args[0] = 1; - s_i = num = s_num = 0; - } - -/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets - * with bh disabled. - */ -#define SKARR_SZ 16 - - /* Dump bound but inactive (not listening, connecting, etc.) sockets */ - if (cb->args[0] == 1) { - if (!(idiag_states & TCPF_BOUND_INACTIVE)) - goto skip_bind_ht; - - for (i = s_i; i < hashinfo->bhash_size; i++) { - struct inet_bind_hashbucket *ibb; - struct inet_bind2_bucket *tb2; - struct sock *sk_arr[SKARR_SZ]; - int num_arr[SKARR_SZ]; - int idx, accum, res; - -resume_bind_walk: - num = 0; - accum = 0; - ibb = &hashinfo->bhash2[i]; - - if (hlist_empty(&ibb->chain)) { - s_num = 0; - continue; - } - spin_lock_bh(&ibb->lock); - inet_bind_bucket_for_each(tb2, &ibb->chain) { - if (!net_eq(ib2_net(tb2), net)) - continue; - - sk_for_each_bound(sk, &tb2->owners) { - struct inet_sock *inet = inet_sk(sk); - - if (num < s_num) - goto next_bind; - - if (sk->sk_state != TCP_CLOSE || - !inet->inet_num) - goto next_bind; - - if (r->sdiag_family != AF_UNSPEC && - r->sdiag_family != sk->sk_family) - goto next_bind; - - if (!inet_diag_bc_sk(bc, sk)) - goto next_bind; - - sock_hold(sk); - num_arr[accum] = num; - sk_arr[accum] = sk; - if (++accum == SKARR_SZ) - goto pause_bind_walk; -next_bind: - num++; - } - } -pause_bind_walk: - spin_unlock_bh(&ibb->lock); - - res = 0; - for (idx = 0; idx < accum; idx++) { - if (res >= 0) { - res = inet_sk_diag_fill(sk_arr[idx], - NULL, skb, cb, - r, NLM_F_MULTI, - net_admin); - if (res < 0) - num = num_arr[idx]; - } - sock_put(sk_arr[idx]); - } - if (res < 0) - goto done; - - cond_resched(); - - if (accum == SKARR_SZ) { - s_num = num + 1; - goto resume_bind_walk; - } - - s_num = 0; - } -skip_bind_ht: - cb->args[0] = 2; - s_i = num = s_num = 0; - } - - if (!(idiag_states & ~TCPF_LISTEN)) - goto out; - - for (i = s_i; i <= hashinfo->ehash_mask; i++) { - struct inet_ehash_bucket *head = &hashinfo->ehash[i]; - spinlock_t *lock = inet_ehash_lockp(hashinfo, i); - struct hlist_nulls_node *node; - struct sock *sk_arr[SKARR_SZ]; - int num_arr[SKARR_SZ]; - int idx, accum, res; - - if (hlist_nulls_empty(&head->chain)) - continue; - - if (i > s_i) - s_num = 0; - -next_chunk: - num = 0; - accum = 0; - spin_lock_bh(lock); - sk_nulls_for_each(sk, node, &head->chain) { - int state; - - if (!net_eq(sock_net(sk), net)) - continue; - if (num < s_num) - goto next_normal; - state = (sk->sk_state == TCP_TIME_WAIT) ? - READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; - if (!(idiag_states & (1 << state))) - goto next_normal; - if (r->sdiag_family != AF_UNSPEC && - sk->sk_family != r->sdiag_family) - goto next_normal; - if (r->id.idiag_sport != htons(sk->sk_num) && - r->id.idiag_sport) - goto next_normal; - if (r->id.idiag_dport != sk->sk_dport && - r->id.idiag_dport) - goto next_normal; - twsk_build_assert(); - - if (!inet_diag_bc_sk(bc, sk)) - goto next_normal; - - if (!refcount_inc_not_zero(&sk->sk_refcnt)) - goto next_normal; - - num_arr[accum] = num; - sk_arr[accum] = sk; - if (++accum == SKARR_SZ) - break; -next_normal: - ++num; - } - spin_unlock_bh(lock); - res = 0; - for (idx = 0; idx < accum; idx++) { - if (res >= 0) { - res = sk_diag_fill(sk_arr[idx], skb, cb, r, - NLM_F_MULTI, net_admin); - if (res < 0) - num = num_arr[idx]; - } - sock_gen_put(sk_arr[idx]); - } - if (res < 0) - break; - cond_resched(); - if (accum == SKARR_SZ) { - s_num = num + 1; - goto next_chunk; - } - } - -done: - cb->args[1] = i; - cb->args[2] = num; -out: - ; -} -EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); - static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { @@ -1319,13 +854,10 @@ static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) kfree(cb_data); return err; } - nla = cb_data->inet_diag_nla_bc; - if (nla) { - err = inet_diag_bc_audit(nla, skb); - if (err) { - kfree(cb_data); - return err; - } + err = inet_diag_bc_audit(cb_data, skb); + if (err) { + kfree(cb_data); + return err; } nla = cb_data->inet_diag_nla_bpf_stgs; @@ -1369,8 +901,6 @@ static int inet_diag_type2proto(int type) switch (type) { case TCPDIAG_GETSOCK: return IPPROTO_TCP; - case DCCPDIAG_GETSOCK: - return IPPROTO_DCCP; default: return 0; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d179a2c84222..025895eb6ec5 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -133,7 +133,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) struct inet_frag_queue *fq = ptr; int count; - count = del_timer_sync(&fq->timer) ? 1 : 0; + count = timer_delete_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); fq->flags |= INET_FRAG_DROP; @@ -145,8 +145,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) } spin_unlock_bh(&fq->lock); - if (refcount_sub_and_test(count, &fq->refcnt)) - inet_frag_destroy(fq); + inet_frag_putn(fq, count); } static LLIST_HEAD(fqdir_free_list); @@ -184,7 +183,7 @@ static void fqdir_work_fn(struct work_struct *work) rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) - queue_delayed_work(system_wq, &fqdir_free_work, HZ); + queue_delayed_work(system_percpu_wq, &fqdir_free_work, HZ); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) @@ -226,10 +225,10 @@ void fqdir_exit(struct fqdir *fqdir) } EXPORT_SYMBOL(fqdir_exit); -void inet_frag_kill(struct inet_frag_queue *fq) +void inet_frag_kill(struct inet_frag_queue *fq, int *refs) { - if (del_timer(&fq->timer)) - refcount_dec(&fq->refcnt); + if (timer_delete(&fq->timer)) + (*refs)++; if (!(fq->flags & INET_FRAG_COMPLETE)) { struct fqdir *fqdir = fq->fqdir; @@ -244,7 +243,7 @@ void inet_frag_kill(struct inet_frag_queue *fq) if (!READ_ONCE(fqdir->dead)) { rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, fqdir->f->rhash_params); - refcount_dec(&fq->refcnt); + (*refs)++; } else { fq->flags |= INET_FRAG_HASH_DEAD; } @@ -298,7 +297,7 @@ void inet_frag_destroy(struct inet_frag_queue *q) reason = (q->flags & INET_FRAG_DROP) ? SKB_DROP_REASON_FRAG_REASM_TIMEOUT : SKB_CONSUMED; - WARN_ON(del_timer(&q->timer) != 0); + WARN_ON(timer_delete(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; @@ -328,7 +327,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); - refcount_set(&q->refcnt, 3); + /* One reference for the timer, one for the hash table. */ + refcount_set(&q->refcnt, 2); return q; } @@ -350,15 +350,20 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { + /* We could not insert in the hash table, + * we need to cancel what inet_frag_alloc() + * anticipated. + */ + int refs = 1; + q->flags |= INET_FRAG_COMPLETE; - inet_frag_kill(q); - inet_frag_destroy(q); + inet_frag_kill(q, &refs); + inet_frag_putn(q, refs); return NULL; } return q; } -/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) { /* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */ @@ -368,17 +373,11 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) if (!high_thresh || frag_mem_limit(fqdir) > high_thresh) return NULL; - rcu_read_lock(); - prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (!IS_ERR_OR_NULL(prev)) { + if (!IS_ERR_OR_NULL(prev)) fq = prev; - if (!refcount_inc_not_zero(&fq->refcnt)) - fq = NULL; - } - rcu_read_unlock(); return fq; } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9bfcfd016e18..f5826ec4bcaa 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -23,11 +23,12 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/inet6_hashtables.h> #endif -#include <net/secure_seq.h> #include <net/hotdata.h> #include <net/ip.h> -#include <net/tcp.h> +#include <net/rps.h> +#include <net/secure_seq.h> #include <net/sock_reuseport.h> +#include <net/tcp.h> u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, @@ -35,8 +36,8 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr, { net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); - return __inet_ehashfn(laddr, lport, faddr, fport, - inet_ehash_secret + net_hash_mix(net)); + return lport + __inet_ehashfn(laddr, 0, faddr, fport, + inet_ehash_secret + net_hash_mix(net)); } EXPORT_SYMBOL_GPL(inet_ehashfn); @@ -57,6 +58,14 @@ static u32 sk_ehashfn(const struct sock *sk) sk->sk_daddr, sk->sk_dport); } +static bool sk_is_connect_bind(const struct sock *sk) +{ + if (sk->sk_state == TCP_TIME_WAIT) + return inet_twsk(sk)->tw_connect_bind; + else + return sk->sk_userlocks & SOCK_CONNECT_BIND; +} + /* * Allocate and initialize a new local port bind bucket. * The bindhash mutex for snum's hash chain must be held here. @@ -76,7 +85,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, tb->fastreuse = 0; tb->fastreuseport = 0; INIT_HLIST_HEAD(&tb->bhash2); - hlist_add_head(&tb->node, &head->chain); + hlist_add_head_rcu(&tb->node, &head->chain); } return tb; } @@ -84,12 +93,24 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, /* * Caller must hold hashbucket lock for this tb with local BH disabled */ -void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb) +void inet_bind_bucket_destroy(struct inet_bind_bucket *tb) { + const struct inet_bind2_bucket *tb2; + if (hlist_empty(&tb->bhash2)) { - __hlist_del(&tb->node); - kmem_cache_free(cachep, tb); + hlist_del_rcu(&tb->node); + kfree_rcu(tb, rcu); + return; + } + + if (tb->fastreuse == -1 && tb->fastreuseport == -1) + return; + hlist_for_each_entry(tb2, &tb->bhash2, bhash_node) { + if (tb2->fastreuse != -1 || tb2->fastreuseport != -1) + return; } + tb->fastreuse = -1; + tb->fastreuseport = -1; } bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net, @@ -120,6 +141,8 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2, #else tb2->rcv_saddr = sk->sk_rcv_saddr; #endif + tb2->fastreuse = 0; + tb2->fastreuseport = 0; INIT_HLIST_HEAD(&tb2->owners); hlist_add_head(&tb2->node, &head->chain); hlist_add_head(&tb2->bhash_node, &tb->bhash2); @@ -142,11 +165,23 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, /* Caller must hold hashbucket lock for this tb with local BH disabled */ void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) { + const struct sock *sk; + if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); __hlist_del(&tb->bhash_node); kmem_cache_free(cachep, tb); + return; } + + if (tb->fastreuse == -1 && tb->fastreuseport == -1) + return; + sk_for_each_bound(sk, &tb->owners) { + if (!sk_is_connect_bind(sk)) + return; + } + tb->fastreuse = -1; + tb->fastreuseport = -1; } static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, @@ -176,7 +211,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, */ static void __inet_put_port(struct sock *sk) { - struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk); struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); struct inet_bind_bucket *tb; @@ -190,6 +225,7 @@ static void __inet_put_port(struct sock *sk) tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; inet_sk(sk)->inet_num = 0; + sk->sk_userlocks &= ~SOCK_CONNECT_BIND; spin_lock(&head2->lock); if (inet_csk(sk)->icsk_bind2_hash) { @@ -201,7 +237,7 @@ static void __inet_put_port(struct sock *sk) } spin_unlock(&head2->lock); - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + inet_bind_bucket_destroy(tb); spin_unlock(&head->lock); } @@ -215,7 +251,7 @@ EXPORT_SYMBOL(inet_put_port); int __inet_inherit_port(const struct sock *sk, struct sock *child) { - struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *table = tcp_get_hashinfo(sk); unsigned short port = inet_sk(child)->inet_num; struct inet_bind_hashbucket *head, *head2; bool created_inet_bind_bucket = false; @@ -276,7 +312,7 @@ bhash2_find: } } if (update_fastreuse) - inet_csk_update_fastreuse(tb, child); + inet_csk_update_fastreuse(child, tb, tb2); inet_bind_hash(child, tb, tb2, port); spin_unlock(&head2->lock); spin_unlock(&head->lock); @@ -285,7 +321,7 @@ bhash2_find: error: if (created_inet_bind_bucket) - inet_bind_bucket_destroy(table->bind_bucket_cachep, tb); + inet_bind_bucket_destroy(tb); spin_unlock(&head2->lock); spin_unlock(&head->lock); return -ENOMEM; @@ -424,19 +460,18 @@ struct sock *inet_lookup_run_sk_lookup(const struct net *net, } struct sock *__inet_lookup_listener(const struct net *net, - struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { struct inet_listen_hashbucket *ilb2; + struct inet_hashinfo *hashinfo; struct sock *result = NULL; unsigned int hash2; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled) && - hashinfo == net->ipv4.tcp_death_row.hashinfo) { + if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, saddr, sport, daddr, hnum, dif, inet_ehashfn); @@ -444,6 +479,7 @@ struct sock *__inet_lookup_listener(const struct net *net, goto done; } + hashinfo = net->ipv4.tcp_death_row.hashinfo; hash2 = ipv4_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); @@ -489,21 +525,22 @@ void sock_edemux(struct sk_buff *skb) EXPORT_SYMBOL(sock_edemux); struct sock *__inet_lookup_established(const struct net *net, - struct inet_hashinfo *hashinfo, - const __be32 saddr, const __be16 sport, - const __be32 daddr, const u16 hnum, - const int dif, const int sdif) + const __be32 saddr, const __be16 sport, + const __be32 daddr, const u16 hnum, + const int dif, const int sdif) { - INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(sport, hnum); - struct sock *sk; + INET_ADDR_COOKIE(acookie, saddr, daddr); const struct hlist_nulls_node *node; - /* Optimize here for direct hit, only listening connections can - * have wildcards anyways. - */ - unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport); - unsigned int slot = hash & hashinfo->ehash_mask; - struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; + struct inet_ehash_bucket *head; + struct inet_hashinfo *hashinfo; + unsigned int hash, slot; + struct sock *sk; + + hashinfo = net->ipv4.tcp_death_row.hashinfo; + hash = inet_ehashfn(net, daddr, hnum, saddr, sport); + slot = hash & hashinfo->ehash_mask; + head = &hashinfo->ehash[slot]; begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { @@ -537,7 +574,9 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established); /* called with local bh disabled */ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, __u16 lport, - struct inet_timewait_sock **twp) + struct inet_timewait_sock **twp, + bool rcu_lookup, + u32 hash) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); @@ -548,14 +587,25 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, int sdif = l3mdev_master_ifindex_by_index(net, dif); INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); - unsigned int hash = inet_ehashfn(net, daddr, lport, - saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - spinlock_t *lock = inet_ehash_lockp(hinfo, hash); - struct sock *sk2; - const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; + const struct hlist_nulls_node *node; + struct sock *sk2; + spinlock_t *lock; + if (rcu_lookup) { + sk_nulls_for_each(sk2, node, &head->chain) { + if (sk2->sk_hash != hash || + !inet_match(net, sk2, acookie, ports, dif, sdif)) + continue; + if (sk2->sk_state == TCP_TIME_WAIT) + break; + return -EADDRNOTAVAIL; + } + return 0; + } + + lock = inet_ehash_lockp(hinfo, hash); spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { @@ -565,8 +615,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); - if (sk->sk_protocol == IPPROTO_TCP && - tcp_twsk_unique(sk, sk2, twp)) + if (tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; @@ -655,7 +704,7 @@ static bool inet_ehash_lookup_by_sk(struct sock *sk, */ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk); struct inet_ehash_bucket *head; struct hlist_nulls_head *list; spinlock_t *lock; @@ -671,8 +720,11 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_nulls_replace_node_init_rcu(osk, sk); + goto unlock; + } + + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -681,6 +733,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); +unlock: spin_unlock(lock); return ret; @@ -693,22 +746,22 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } else { - this_cpu_inc(*sk->sk_prot->orphan_count); + tcp_orphan_count_inc(); inet_sk_set_state(sk, TCP_CLOSE); sock_set_flag(sk, SOCK_DEAD); inet_csk_destroy_sock(sk); } return ok; } -EXPORT_SYMBOL_GPL(inet_ehash_nolisten); +EXPORT_IPV6_MOD(inet_ehash_nolisten); static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; const struct hlist_nulls_node *node; + kuid_t uid = sk_uid(sk); struct sock *sk2; - kuid_t uid = sock_i_uid(sk); sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && @@ -716,7 +769,7 @@ static int inet_reuseport_add_sock(struct sock *sk, ipv6_only_sock(sk2) == ipv6_only_sock(sk) && sk2->sk_bound_dev_if == sk->sk_bound_dev_if && inet_csk(sk2)->icsk_bind_hash == tb && - sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && + sk2->sk_reuseport && uid_eq(uid, sk_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) return reuseport_add_sock(sk, sk2, inet_rcv_saddr_any(sk)); @@ -725,15 +778,18 @@ static int inet_reuseport_add_sock(struct sock *sk, return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } -int __inet_hash(struct sock *sk, struct sock *osk) +int inet_hash(struct sock *sk) { - struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk); struct inet_listen_hashbucket *ilb2; int err = 0; + if (sk->sk_state == TCP_CLOSE) + return 0; + if (sk->sk_state != TCP_LISTEN) { local_bh_disable(); - inet_ehash_nolisten(sk, osk, NULL); + inet_ehash_nolisten(sk, NULL, NULL); local_bh_enable(); return 0; } @@ -758,26 +814,16 @@ unlock: return err; } -EXPORT_SYMBOL(__inet_hash); - -int inet_hash(struct sock *sk) -{ - int err = 0; - - if (sk->sk_state != TCP_CLOSE) - err = __inet_hash(sk, NULL); - - return err; -} -EXPORT_SYMBOL_GPL(inet_hash); +EXPORT_IPV6_MOD(inet_hash); void inet_unhash(struct sock *sk) { - struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk); if (sk_unhashed(sk)) return; + sock_rps_delete_flow(sk); if (sk->sk_state == TCP_LISTEN) { struct inet_listen_hashbucket *ilb2; @@ -786,11 +832,6 @@ void inet_unhash(struct sock *sk) * avoid circular locking dependency on PREEMPT_RT. */ spin_lock(&ilb2->lock); - if (sk_unhashed(sk)) { - spin_unlock(&ilb2->lock); - return; - } - if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_stop_listen_sock(sk); @@ -801,16 +842,12 @@ void inet_unhash(struct sock *sk) spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); spin_lock_bh(lock); - if (sk_unhashed(sk)) { - spin_unlock_bh(lock); - return; - } __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock_bh(lock); } } -EXPORT_SYMBOL_GPL(inet_unhash); +EXPORT_IPV6_MOD(inet_unhash); static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, @@ -861,7 +898,7 @@ inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port) { - struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk); u32 hash; #if IS_ENABLED(CONFIG_IPV6) @@ -889,7 +926,7 @@ static void inet_update_saddr(struct sock *sk, void *saddr, int family) static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { - struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk); struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); @@ -952,6 +989,10 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, if (!tb2) { tb2 = new_tb2; inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk); + if (sk_is_connect_bind(sk)) { + tb2->fastreuse = -1; + tb2->fastreuseport = -1; + } } inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); @@ -969,14 +1010,14 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) { return __inet_bhash2_update_saddr(sk, saddr, family, false); } -EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +EXPORT_IPV6_MOD(inet_bhash2_update_saddr); void inet_bhash2_reset_saddr(struct sock *sk) { if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) __inet_bhash2_update_saddr(sk, NULL, 0, true); } -EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); +EXPORT_IPV6_MOD(inet_bhash2_reset_saddr); /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') @@ -993,8 +1034,10 @@ static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, + u32 hash_port0, int (*check_established)(struct inet_timewait_death_row *, - struct sock *, __u16, struct inet_timewait_sock **)) + struct sock *, __u16, struct inet_timewait_sock **, + bool rcu_lookup, u32 hash)) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_bind_hashbucket *head, *head2; @@ -1012,7 +1055,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (port) { local_bh_disable(); - ret = check_established(death_row, sk, port, NULL); + ret = check_established(death_row, sk, port, NULL, false, + hash_port0 + port); local_bh_enable(); return ret; } @@ -1048,6 +1092,22 @@ other_parity_scan: continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; + rcu_read_lock(); + hlist_for_each_entry_rcu(tb, &head->chain, node) { + if (!inet_bind_bucket_match(tb, net, port, l3mdev)) + continue; + if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) { + rcu_read_unlock(); + goto next_port; + } + if (!check_established(death_row, sk, port, &tw, true, + hash_port0 + port)) + break; + rcu_read_unlock(); + goto next_port; + } + rcu_read_unlock(); + spin_lock_bh(&head->lock); /* Does not bother with rcv_saddr checks, because @@ -1057,12 +1117,13 @@ other_parity_scan: if (inet_bind_bucket_match(tb, net, port, l3mdev)) { if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) - goto next_port; + goto next_port_unlock; WARN_ON(hlist_empty(&tb->bhash2)); if (!check_established(death_row, sk, - port, &tw)) + port, &tw, false, + hash_port0 + port)) goto ok; - goto next_port; + goto next_port_unlock; } } @@ -1076,8 +1137,9 @@ other_parity_scan: tb->fastreuse = -1; tb->fastreuseport = -1; goto ok; -next_port: +next_port_unlock: spin_unlock_bh(&head->lock); +next_port: cond_resched(); } @@ -1101,6 +1163,8 @@ ok: head2, tb, sk); if (!tb2) goto error; + tb2->fastreuse = -1; + tb2->fastreuseport = -1; } /* Here we want to add a little bit of randomness to the next source @@ -1113,6 +1177,7 @@ ok: /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, tb2, port); + sk->sk_userlocks |= SOCK_CONNECT_BIND; if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); @@ -1149,7 +1214,7 @@ error: spin_unlock(&head2->lock); if (tb_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); + inet_bind_bucket_destroy(tb); spin_unlock(&head->lock); if (tw) @@ -1166,14 +1231,20 @@ error: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { + const struct inet_sock *inet = inet_sk(sk); + const struct net *net = sock_net(sk); u64 port_offset = 0; + u32 hash_port0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); - return __inet_hash_connect(death_row, sk, port_offset, + + hash_port0 = inet_ehashfn(net, inet->inet_rcv_saddr, 0, + inet->inet_daddr, inet->inet_dport); + + return __inet_hash_connect(death_row, sk, port_offset, hash_port0, __inet_check_established); } -EXPORT_SYMBOL_GPL(inet_hash_connect); static void init_hashinfo_lhash2(struct inet_hashinfo *h) { @@ -1224,32 +1295,45 @@ int inet_hashinfo2_init_mod(struct inet_hashinfo *h) init_hashinfo_lhash2(h); return 0; } -EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod); int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); unsigned int i, nblocks = 1; + spinlock_t *ptr = NULL; - if (locksz != 0) { - /* allocate 2 cache lines or at least one spinlock per cpu */ - nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U); - nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + if (locksz == 0) + goto set_mask; - /* no more locks than number of hash buckets */ - nblocks = min(nblocks, hashinfo->ehash_mask + 1); + /* Allocate 2 cache lines or at least one spinlock per cpu. */ + nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus(); - hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); - if (!hashinfo->ehash_locks) - return -ENOMEM; + /* At least one page per NUMA node. */ + nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz); + + nblocks = roundup_pow_of_two(nblocks); - for (i = 0; i < nblocks; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); + /* No more locks than number of hash buckets. */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); + + if (num_online_nodes() > 1) { + /* Use vmalloc() to allow NUMA policy to spread pages + * on all available nodes if desired. + */ + ptr = vmalloc_array(nblocks, locksz); + } + if (!ptr) { + ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL); + if (!ptr) + return -ENOMEM; } + for (i = 0; i < nblocks; i++) + spin_lock_init(&ptr[i]); + hashinfo->ehash_locks = ptr; +set_mask: hashinfo->ehash_locks_mask = nblocks - 1; return 0; } -EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc); struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo, unsigned int ehash_entries) @@ -1285,7 +1369,6 @@ free_hashinfo: err: return NULL; } -EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc); void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo) { @@ -1296,4 +1379,3 @@ void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo) vfree(hashinfo->ehash); kfree(hashinfo); } -EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 337390ba85b4..d4c781a0667f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -15,7 +15,8 @@ #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> - +#include <net/tcp.h> +#include <net/psp.h> /** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash @@ -39,7 +40,7 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, tw->tw_tb = NULL; tw->tw_tb2 = NULL; inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + inet_bind_bucket_destroy(tb); __sock_put((struct sock *)tw); } @@ -74,7 +75,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) void inet_twsk_free(struct inet_timewait_sock *tw) { struct module *owner = tw->tw_prot->owner; - twsk_destructor((struct sock *)tw); + + tcp_twsk_destructor((struct sock *)tw); kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); module_put(owner); } @@ -86,12 +88,6 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) -{ - hlist_nulls_add_head_rcu(&tw->tw_node, list); -} - static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, false); @@ -111,13 +107,12 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead, *bhead2; - /* Step 1: Put TW into bind hash. Original socket stays there too. - Note, that any socket with inet->num != 0 MUST be bound in - binding cache, even if it is closed. + /* Put TW into bind hash. Original socket stays there too. + * Note, that any socket with inet->num != 0 MUST be bound in + * binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; @@ -139,19 +134,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, spin_lock(lock); - /* Step 2: Hash TW into tcp ehash chain */ - inet_twsk_add_node_rcu(tw, &ehead->chain); - - /* Step 3: Remove SK from hash chain */ - if (__sk_nulls_del_node_init_rcu(sk)) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - - - /* Ensure above writes are committed into memory before updating the - * refcount. - * Provides ordering vs later refcount_inc(). - */ - smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. @@ -161,16 +143,24 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, */ refcount_set(&tw->tw_refcnt, 3); + /* Ensure tw_refcnt has been set before tw is published. + * smp_wmb() provides the necessary memory barrier to enforce this + * ordering. + */ + smp_wmb(); + + hlist_nulls_replace_init_rcu(&sk->sk_nulls_node, &tw->tw_node); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + inet_twsk_schedule(tw, timeo); spin_unlock(lock); local_bh_enable(); } -EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule); static void tw_timer_handler(struct timer_list *t) { - struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); + struct inet_timewait_sock *tw = timer_container_of(tw, t, tw_timer); inet_twsk_kill(tw); } @@ -207,10 +197,14 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); + tw->tw_connect_bind = !!(sk->sk_userlocks & SOCK_CONNECT_BIND); tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); timer_setup(&tw->tw_timer, tw_timer_handler, 0); +#ifdef CONFIG_SOCK_VALIDATE_XMIT + tw->tw_validate_xmit_skb = NULL; +#endif /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this @@ -219,11 +213,11 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, refcount_set(&tw->tw_refcnt, 0); __module_get(tw->tw_prot->owner); + psp_twsk_init(tw, sk); } return tw; } -EXPORT_SYMBOL_GPL(inet_twsk_alloc); /* These are always called from BH context. See callers in * tcp_input.c to verify this. @@ -306,7 +300,6 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } -EXPORT_SYMBOL_GPL(__inet_twsk_schedule); /* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo) @@ -332,13 +325,13 @@ restart: TCPF_NEW_SYN_RECV)) continue; - if (refcount_read(&sock_net(sk)->ns.count)) + if (check_net(sock_net(sk))) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (refcount_read(&sock_net(sk)->ns.count)) { + if (check_net(sock_net(sk))) { sock_gen_put(sk); goto restart; } @@ -365,4 +358,3 @@ restart: rcu_read_unlock(); } } -EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 5ab56f4cb529..7b1e0a2d6906 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -60,7 +60,7 @@ void inet_peer_base_init(struct inet_peer_base *bp) seqlock_init(&bp->lock); bp->total = 0; } -EXPORT_SYMBOL_GPL(inet_peer_base_init); +EXPORT_IPV6_MOD_GPL(inet_peer_base_init); #define PEER_MAX_GC 32 @@ -95,6 +95,7 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, { struct rb_node **pp, *parent, *next; struct inet_peer *p; + u32 now; pp = &base->rb_root.rb_node; parent = NULL; @@ -108,8 +109,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, p = rb_entry(parent, struct inet_peer, rb_node); cmp = inetpeer_addr_cmp(daddr, &p->daddr); if (cmp == 0) { - if (!refcount_inc_not_zero(&p->refcnt)) - break; + now = jiffies; + if (READ_ONCE(p->dtime) != now) + WRITE_ONCE(p->dtime, now); return p; } if (gc_stack) { @@ -150,9 +152,6 @@ static void inet_peer_gc(struct inet_peer_base *base, for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; - /* The READ_ONCE() pairs with the WRITE_ONCE() - * in inet_putpeer() - */ delta = (__u32)jiffies - READ_ONCE(p->dtime); if (delta < ttl || !refcount_dec_if_one(&p->refcnt)) @@ -168,31 +167,23 @@ static void inet_peer_gc(struct inet_peer_base *base, } } +/* Must be called under RCU : No refcount change is done here. */ struct inet_peer *inet_getpeer(struct inet_peer_base *base, - const struct inetpeer_addr *daddr, - int create) + const struct inetpeer_addr *daddr) { struct inet_peer *p, *gc_stack[PEER_MAX_GC]; struct rb_node **pp, *parent; unsigned int gc_cnt, seq; - int invalidated; /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ - rcu_read_lock(); seq = read_seqbegin(&base->lock); p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp); - invalidated = read_seqretry(&base->lock, seq); - rcu_read_unlock(); if (p) return p; - /* If no writer did a change during our lookup, we can return early. */ - if (!create && !invalidated) - return NULL; - /* retry an exact lookup, taking the lock before. * At least, nodes should be hot in our cache. */ @@ -201,12 +192,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, gc_cnt = 0; p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp); - if (!p && create) { + if (!p) { p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC); if (p) { p->daddr = *daddr; p->dtime = (__u32)jiffies; - refcount_set(&p->refcnt, 2); + refcount_set(&p->refcnt, 1); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -227,19 +218,13 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, return p; } -EXPORT_SYMBOL_GPL(inet_getpeer); +EXPORT_IPV6_MOD_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { - /* The WRITE_ONCE() pairs with itself (we run lockless) - * and the READ_ONCE() in inet_peer_gc() - */ - WRITE_ONCE(p->dtime, (__u32)jiffies); - if (refcount_dec_and_test(&p->refcnt)) kfree_rcu(p, rcu); } -EXPORT_SYMBOL_GPL(inet_putpeer); /* * Check transmit rate limitation for given message. @@ -261,26 +246,30 @@ EXPORT_SYMBOL_GPL(inet_putpeer); #define XRLIM_BURST_FACTOR 6 bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) { - unsigned long now, token; + unsigned long now, token, otoken, delta; bool rc = false; if (!peer) return true; - token = peer->rate_tokens; + token = otoken = READ_ONCE(peer->rate_tokens); now = jiffies; - token += now - peer->rate_last; - peer->rate_last = now; - if (token > XRLIM_BURST_FACTOR * timeout) - token = XRLIM_BURST_FACTOR * timeout; + delta = now - READ_ONCE(peer->rate_last); + if (delta) { + WRITE_ONCE(peer->rate_last, now); + token += delta; + if (token > XRLIM_BURST_FACTOR * timeout) + token = XRLIM_BURST_FACTOR * timeout; + } if (token >= timeout) { token -= timeout; rc = true; } - peer->rate_tokens = token; + if (token != otoken) + WRITE_ONCE(peer->rate_tokens, token); return rc; } -EXPORT_SYMBOL(inet_peer_xrlim_allow); +EXPORT_IPV6_MOD(inet_peer_xrlim_allow); void inetpeer_invalidate_tree(struct inet_peer_base *base) { @@ -297,4 +286,4 @@ void inetpeer_invalidate_tree(struct inet_peer_base *base) base->total = 0; } -EXPORT_SYMBOL(inetpeer_invalidate_tree); +EXPORT_IPV6_MOD(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 07036a2943c1..f7012479713b 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -76,21 +76,27 @@ static u8 ip4_frag_ecn(u8 tos) static struct inet_frags ip4_frags; static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, - struct sk_buff *prev_tail, struct net_device *dev); + struct sk_buff *prev_tail, struct net_device *dev, + int *refs); static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); - struct net *net = q->fqdir->net; - const struct frag_v4_compare_key *key = a; + struct net *net = q->fqdir->net; + struct inet_peer *p = NULL; q->key.v4 = *key; qp->ecn = 0; - qp->peer = q->fqdir->max_dist ? - inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : - NULL; + if (q->fqdir->max_dist) { + rcu_read_lock(); + p = inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif); + if (p && !refcount_inc_not_zero(&p->refcnt)) + p = NULL; + rcu_read_unlock(); + } + qp->peer = p; } static void ip4_frag_free(struct inet_frag_queue *q) @@ -102,22 +108,6 @@ static void ip4_frag_free(struct inet_frag_queue *q) inet_putpeer(qp->peer); } - -/* Destruction primitives. */ - -static void ipq_put(struct ipq *ipq) -{ - inet_frag_put(&ipq->q); -} - -/* Kill ipq entry. It is not destroyed immediately, - * because caller (and someone more) holds reference count. - */ -static void ipq_kill(struct ipq *ipq) -{ - inet_frag_kill(&ipq->q); -} - static bool frag_expire_skip_icmp(u32 user) { return user == IP_DEFRAG_AF_PACKET || @@ -133,11 +123,12 @@ static bool frag_expire_skip_icmp(u32 user) static void ip_expire(struct timer_list *t) { enum skb_drop_reason reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; - struct inet_frag_queue *frag = from_timer(frag, t, timer); + struct inet_frag_queue *frag = timer_container_of(frag, t, timer); const struct iphdr *iph; struct sk_buff *head = NULL; struct net *net; struct ipq *qp; + int refs = 1; qp = container_of(frag, struct ipq, q); net = qp->q.fqdir->net; @@ -154,7 +145,7 @@ static void ip_expire(struct timer_list *t) goto out; qp->q.flags |= INET_FRAG_DROP; - ipq_kill(qp); + inet_frag_kill(&qp->q, &refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -197,7 +188,7 @@ out: out_rcu_unlock: rcu_read_unlock(); kfree_skb_reason(head, reason); - ipq_put(qp); + inet_frag_putn(&qp->q, refs); } /* Find the correct entry in the "incomplete datagrams" queue for @@ -273,7 +264,7 @@ static int ip_frag_reinit(struct ipq *qp) } /* Add new segment to existing queue. */ -static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) +static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb, int *refs) { struct net *net = qp->q.fqdir->net; int ihl, end, flags, offset; @@ -293,7 +284,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && unlikely(err = ip_frag_reinit(qp))) { - ipq_kill(qp); + inet_frag_kill(&qp->q, refs); goto err; } @@ -377,10 +368,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - err = ip_frag_reasm(qp, skb, prev_tail, dev); + err = ip_frag_reasm(qp, skb, prev_tail, dev, refs); skb->_skb_refdst = orefdst; if (err) - inet_frag_kill(&qp->q); + inet_frag_kill(&qp->q, refs); return err; } @@ -397,7 +388,7 @@ insert_error: err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: - inet_frag_kill(&qp->q); + inet_frag_kill(&qp->q, refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb_reason(skb, reason); @@ -411,7 +402,8 @@ static bool ip_frag_coalesce_ok(const struct ipq *qp) /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, - struct sk_buff *prev_tail, struct net_device *dev) + struct sk_buff *prev_tail, struct net_device *dev, + int *refs) { struct net *net = qp->q.fqdir->net; struct iphdr *iph; @@ -419,7 +411,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, int len, err; u8 ecn; - ipq_kill(qp); + inet_frag_kill(&qp->q, refs); ecn = ip_frag_ecn_table[qp->ecn]; if (unlikely(ecn == 0xff)) { @@ -484,25 +476,30 @@ out_fail: /* Process an incoming IP datagram fragment. */ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { - struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; - int vif = l3mdev_master_ifindex_rcu(dev); + struct net_device *dev; struct ipq *qp; + int vif; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ + rcu_read_lock(); + dev = skb->dev ? : skb_dst_dev_rcu(skb); + vif = l3mdev_master_ifindex_rcu(dev); qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { - int ret; + int ret, refs = 0; spin_lock(&qp->q.lock); - ret = ip_frag_queue(qp, skb); + ret = ip_frag_queue(qp, skb, &refs); spin_unlock(&qp->q.lock); - ipq_put(qp); + rcu_read_unlock(); + inet_frag_putn(&qp->q, refs); return ret; } + rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); kfree_skb(skb); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f1f31ebfc793..761a53c6a89a 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -28,6 +28,7 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> +#include <net/flow.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> @@ -44,7 +45,6 @@ #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> -#include <net/inet_dscp.h> /* Problems & solutions @@ -141,7 +141,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info, const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) @@ -182,7 +181,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info, case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; - data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: @@ -190,10 +188,16 @@ static int ipgre_err(struct sk_buff *skb, u32 info, } #if IS_ENABLED(CONFIG_IPV6) - if (tpi->proto == htons(ETH_P_IPV6) && - !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, - type, data_len)) - return 0; + if (tpi->proto == htons(ETH_P_IPV6)) { + unsigned int data_len = 0; + + if (type == ICMP_TIME_EXCEEDED) + data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ + + if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, + type, data_len)) + return 0; + } #endif if (t->parms.iph.daddr == 0 || @@ -924,15 +928,18 @@ static int ipgre_open(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { - struct flowi4 fl4; + struct flowi4 fl4 = { + .flowi4_oif = t->parms.link, + .flowi4_dscp = ip4h_dscp(&t->parms.iph), + .flowi4_scope = RT_SCOPE_UNIVERSE, + .flowi4_proto = IPPROTO_GRE, + .saddr = t->parms.iph.saddr, + .daddr = t->parms.iph.daddr, + .fl4_gre_key = t->parms.o_key, + }; struct rtable *rt; - rt = ip_route_output_gre(t->net, &fl4, - t->parms.iph.daddr, - t->parms.iph.saddr, - t->parms.o_key, - t->parms.iph.tos & INET_DSCP_MASK, - t->parms.link); + rt = ip_route_output_key(t->net, &fl4); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; @@ -1059,16 +1066,15 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, - struct list_head *dev_to_kill) +static void __net_exit ipgre_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, - dev_to_kill); + ip_tunnel_delete_net(net, ipgre_net_id, &ipgre_link_ops, dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit_batch_rtnl = ipgre_exit_batch_rtnl, + .exit_rtnl = ipgre_exit_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1389,10 +1395,12 @@ ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) return 0; } -static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipgre_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1404,13 +1412,16 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } -static int erspan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int erspan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1422,7 +1433,8 @@ static int erspan_newlink(struct net *src_net, struct net_device *dev, err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], @@ -1690,6 +1702,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { + struct rtnl_newlink_params params = { .src_net = net }; struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); @@ -1697,6 +1710,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, int err; memset(&tb, 0, sizeof(tb)); + params.tb = tb; dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); @@ -1707,7 +1721,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t = netdev_priv(dev); t->collect_md = true; - err = ipgre_newlink(net, dev, tb, NULL, NULL); + err = ipgre_newlink(dev, ¶ms, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); @@ -1737,16 +1751,15 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, - struct list_head *dev_to_kill) +static void __net_exit ipgre_tap_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, - dev_to_kill); + ip_tunnel_delete_net(net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, + .exit_rtnl = ipgre_tap_exit_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1757,16 +1770,15 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, - struct list_head *dev_to_kill) +static void __net_exit erspan_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, - dev_to_kill); + ip_tunnel_delete_net(net, erspan_net_id, &erspan_link_ops, dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit_batch_rtnl = erspan_exit_batch_rtnl, + .exit_rtnl = erspan_exit_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f0a4dda246ab..19d3141dad1f 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -141,6 +141,8 @@ #include <linux/mroute.h> #include <linux/netlink.h> #include <net/dst_metadata.h> +#include <net/udp.h> +#include <net/tcp.h> /* * Process Router Attention IP option (RFC 2113) @@ -226,6 +228,12 @@ resubmit: static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { + __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); + kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); + return 0; + } + skb_clear_delivery_time(skb); __skb_pull(skb, skb_network_header_len(skb)); @@ -257,10 +265,11 @@ int ip_local_deliver(struct sk_buff *skb) } EXPORT_SYMBOL(ip_local_deliver); -static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) +static inline enum skb_drop_reason +ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { - struct ip_options *opt; const struct iphdr *iph; + struct ip_options *opt; /* It looks as overkill, because not all IP options require packet mangling. @@ -271,7 +280,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) */ if (skb_cow(skb, skb_headroom(skb))) { __IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INDISCARDS); - goto drop; + return SKB_DROP_REASON_NOMEM; } iph = ip_hdr(skb); @@ -280,7 +289,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) if (ip_options_compile(dev_net(dev), opt, skb)) { __IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INHDRERRORS); - goto drop; + return SKB_DROP_REASON_IP_INHDR; } if (unlikely(opt->srr)) { @@ -292,17 +301,15 @@ static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) net_info_ratelimited("source route option %pI4 -> %pI4\n", &iph->saddr, &iph->daddr); - goto drop; + return SKB_DROP_REASON_NOT_SPECIFIED; } } if (ip_options_rcv_srr(skb, dev)) - goto drop; + return SKB_DROP_REASON_NOT_SPECIFIED; } - return false; -drop: - return true; + return SKB_NOT_DROPPED_YET; } static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, @@ -312,15 +319,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -int tcp_v4_early_demux(struct sk_buff *skb); -int udp_v4_early_demux(struct sk_buff *skb); -static int ip_rcv_finish_core(struct net *net, struct sock *sk, +static int ip_rcv_finish_core(struct net *net, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int err, drop_reason; struct rtable *rt; + int drop_reason; if (ip_can_use_hint(skb, iph, hint)) { drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr, @@ -329,7 +334,6 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, goto drop_error; } - drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && @@ -345,8 +349,8 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, break; case IPPROTO_UDP: if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { - err = udp_v4_early_demux(skb); - if (unlikely(err)) + drop_reason = udp_v4_early_demux(skb); + if (unlikely(drop_reason)) goto drop_error; /* must reload iph, skb->head might have changed */ @@ -365,7 +369,6 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, ip4h_dscp(iph), dev); if (unlikely(drop_reason)) goto drop_error; - drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; } else { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -384,8 +387,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, } #endif - if (iph->ihl > 5 && ip_rcv_options(skb, dev)) - goto drop; + if (iph->ihl > 5) { + drop_reason = ip_rcv_options(skb, dev); + if (drop_reason) + goto drop; + } rt = skb_rtable(skb); if (rt->rt_type == RTN_MULTICAST) { @@ -442,7 +448,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb, dev, NULL); + ret = ip_rcv_finish_core(net, skb, dev, NULL); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -580,17 +586,20 @@ static void ip_sublist_rcv_finish(struct list_head *head) } static struct sk_buff *ip_extract_route_hint(const struct net *net, - struct sk_buff *skb, int rt_type) + struct sk_buff *skb) { - if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST || + const struct iphdr *iph = ip_hdr(skb); + + if (fib4_has_custom_rules(net) || + ipv4_is_lbcast(iph->daddr) || + ipv4_is_zeronet(iph->daddr) || IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; } -static void ip_list_rcv_finish(struct net *net, struct sock *sk, - struct list_head *head) +static void ip_list_rcv_finish(struct net *net, struct list_head *head) { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; @@ -607,13 +616,12 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP) + if (ip_rcv_finish_core(net, skb, dev, hint) == NET_RX_DROP) continue; dst = skb_dst(skb); if (curr_dst != dst) { - hint = ip_extract_route_hint(net, skb, - dst_rtable(dst)->rt_type); + hint = ip_extract_route_hint(net, skb); /* dispatch old sublist */ if (!list_empty(&sublist)) @@ -633,7 +641,7 @@ static void ip_sublist_rcv(struct list_head *head, struct net_device *dev, { NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, head, dev, NULL, ip_rcv_finish); - ip_list_rcv_finish(net, NULL, head); + ip_list_rcv_finish(net, head); } /* Receive a list of IP packets */ diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index e3321932bec0..be8815ce3ac2 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -615,14 +615,13 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) } memcpy(&nexthop, &optptr[srrptr-1], 4); - orefdst = skb->_skb_refdst; - skb_dst_set(skb, NULL); + orefdst = skb_dstref_steal(skb); err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph), dev) ? -EINVAL : 0; rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); - skb->_skb_refdst = orefdst; + skb_dstref_restore(skb, orefdst); return -EINVAL; } refdst_drop(orefdst); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0065b1996c94..ff11d3a85a36 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -63,6 +63,7 @@ #include <linux/stat.h> #include <linux/init.h> +#include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> @@ -75,7 +76,6 @@ #include <net/checksum.h> #include <net/gso.h> #include <net/inetpeer.h> -#include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <net/inet_dscp.h> #include <linux/bpf-cgroup.h> @@ -84,6 +84,7 @@ #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> +#include <net/psp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, @@ -117,7 +118,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, skb_dst(skb)->dev, + net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } @@ -200,7 +201,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; @@ -426,15 +427,20 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; + struct net_device *dev, *indev = skb->dev; + int ret_val; + rcu_read_lock(); + dev = skb_dst_dev_rcu(skb); skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, indev, dev, - ip_finish_output, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + ret_val = NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, indev, dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); + rcu_read_unlock(); + return ret_val; } EXPORT_SYMBOL(ip_output); @@ -478,24 +484,16 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* Make sure we can route this packet. */ rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { - __be32 daddr; + inet_sk_init_flowi4(inet, fl4); - /* Use correct destination address if we have options. */ - daddr = inet->inet_daddr; - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; + /* sctp_v4_xmit() uses its own DSCP value */ + fl4->flowi4_dscp = inet_dsfield_to_dscp(tos); /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(net, fl4, sk, - daddr, inet->inet_saddr, - inet->inet_dport, - inet->inet_sport, - sk->sk_protocol, - tos & INET_DSCP_MASK, - sk->sk_bound_dev_if); + rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); @@ -1023,7 +1021,8 @@ static int __ip_append_data(struct sock *sk, uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), + false); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ @@ -1169,7 +1168,10 @@ alloc_new_skb: /* [!] NOTE: copy will be negative if pagedlen>0 * because then the equation reduces to -fraggap. */ - if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { + if (copy > 0 && + INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, data + transhdrlen, offset, + copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; @@ -1213,8 +1215,9 @@ alloc_new_skb: unsigned int off; off = skb->len; - if (getfrag(from, skb_put(skb, copy), - offset, copy, off, skb) < 0) { + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, skb_put(skb, copy), + offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; @@ -1226,8 +1229,7 @@ alloc_new_skb: if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; - err = skb_splice_from_iter(skb, &msg->msg_iter, copy, - sk->sk_allocation); + err = skb_splice_from_iter(skb, &msg->msg_iter, copy); if (err < 0) goto error; copy = err; @@ -1252,7 +1254,8 @@ alloc_new_skb: get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (getfrag(from, + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; @@ -1328,7 +1331,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; - cork->priority = ipc->priority; + cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); @@ -1465,7 +1468,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_options_build(skb, opt, cork->addr, rt); } - skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); + skb->priority = cork->priority; skb->mark = cork->mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); @@ -1643,7 +1646,7 @@ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, if (IS_ERR(rt)) return; - inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; + inet_sk(sk)->tos = arg->tos; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; @@ -1663,8 +1666,10 @@ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - if (orig_sk) + if (orig_sk) { skb_set_owner_edemux(nskb, (struct sock *)orig_sk); + psp_reply_set_decrypted(orig_sk, nskb); + } if (transmit_time) nskb->tstamp_type = SKB_CLOCK_MONOTONIC; if (txhash) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cf377377b52d..6d9c5c20b1c4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -128,20 +128,20 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { - char *secdata; - u32 seclen, secid; + struct lsm_context ctx; + u32 secid; int err; err = security_socket_getpeersec_dgram(NULL, skb, &secid); if (err) return; - err = security_secid_to_secctx(secid, &secdata, &seclen); - if (err) + err = security_secid_to_secctx(secid, &ctx); + if (err < 0) return; - put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); + put_cmsg(msg, SOL_IP, SCM_SECURITY, ctx.len, ctx.context); + security_release_secctx(&ctx); } static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) @@ -315,7 +315,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; - ipc->priority = rt_tos2priority(ipc->tos); + ipc->sockc.priority = rt_tos2priority(ipc->tos); break; case IP_PROTOCOL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 25505f9b724c..158a30ae7c5f 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -40,6 +40,7 @@ #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/netdev_lock.h> #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> @@ -242,11 +243,11 @@ static struct net_device *__ip_tunnel_create(struct net *net, if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; - strscpy(name, parms->name, IFNAMSIZ); + strscpy(name, parms->name); } else { if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; - strcpy(name, ops->kind); + strscpy(name, ops->kind); strcat(name, "%d"); } @@ -294,7 +295,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - iph->tos & INET_DSCP_MASK, dev_net(dev), + iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); @@ -567,20 +568,6 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } -static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) -{ - /* we must cap headroom to some upperlimit, else pskb_expand_head - * will overflow header offsets in skb_headers_offset_update(). - */ - static const unsigned int max_allowed = 512; - - if (headroom > max_allowed) - headroom = max_allowed; - - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); -} - void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -611,7 +598,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, + tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) @@ -667,7 +654,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, - df, !net_eq(tunnel->net, dev_net(dev))); + df, !net_eq(tunnel->net, dev_net(dev)), 0); return; tx_error: DEV_STATS_INC(dev, tx_errors); @@ -774,7 +761,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, - dev_net(dev), READ_ONCE(tunnel->parms.link), + tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) @@ -856,7 +843,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, - df, !net_eq(tunnel->net, dev_net(dev))); + df, !net_eq(tunnel->net, dev_net(dev)), 0); return; #if IS_ENABLED(CONFIG_IPV6) @@ -1162,7 +1149,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { - itn->fb_tunnel_dev->netns_local = true; + itn->fb_tunnel_dev->netns_immutable = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; @@ -1173,13 +1160,16 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); -static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, - struct list_head *head, - struct rtnl_link_ops *ops) +void ip_tunnel_delete_net(struct net *net, unsigned int id, + struct rtnl_link_ops *ops, + struct list_head *head) { + struct ip_tunnel_net *itn = net_generic(net, id); struct net_device *dev, *aux; int h; + ASSERT_RTNL_NET(net); + for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == ops) unregister_netdevice_queue(dev, head); @@ -1197,27 +1187,13 @@ static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, unregister_netdevice_queue(t->dev, head); } } +EXPORT_SYMBOL_GPL(ip_tunnel_delete_net); -void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, - struct rtnl_link_ops *ops, - struct list_head *dev_to_kill) -{ - struct ip_tunnel_net *itn; - struct net *net; - - ASSERT_RTNL(); - list_for_each_entry(net, net_list, exit_list) { - itn = net_generic(net, id); - ip_tunnel_destroy(net, itn, dev_to_kill, ops); - } -} -EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); - -int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm_kern *p, __u32 fwmark) +int ip_tunnel_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct ip_tunnel_parm_kern *p, + __u32 fwmark) { struct ip_tunnel *nt; - struct net *net = dev_net(dev); struct ip_tunnel_net *itn; int mtu; int err; @@ -1326,7 +1302,6 @@ int ip_tunnel_init(struct net_device *dev) } tunnel->dev = dev; - tunnel->net = dev_net(dev); strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index a3676155be78..2e61ac137128 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -49,7 +49,8 @@ EXPORT_SYMBOL(ip6tun_encaps); void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, - __u8 tos, __u8 ttl, __be16 df, bool xnet) + __u8 tos, __u8 ttl, __be16 df, bool xnet, + u16 ipcb_flags) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); @@ -62,6 +63,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_clear_hash_if_not_l4(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + IPCB(skb)->flags = ipcb_flags; /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); @@ -204,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -298,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -416,7 +424,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, skb_dst_update_pmtu_no_confirm(skb, mtu); - if (!reply || skb->pkt_type == PACKET_HOST) + if (!reply) return 0; if (skb->protocol == htons(ETH_P_IP)) @@ -451,7 +459,7 @@ static const struct nla_policy geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, - [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index f0b4419cef34..95b6bb78fcd2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -229,7 +229,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error_icmp; } - tdev = dst->dev; + tdev = dst_dev(dst); if (tdev == dev) { dst_release(dst); @@ -259,7 +259,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; + skb->dev = skb_dst_dev(skb); err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) @@ -523,16 +523,15 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, - struct list_head *dev_to_kill) +static void __net_exit vti_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, - dev_to_kill); + ip_tunnel_delete_net(net, vti_net_id, &vti_link_ops, dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit_batch_rtnl = vti_exit_batch_rtnl, + .exit_rtnl = vti_exit_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -575,15 +574,18 @@ static void vti_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } -static int vti_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vti_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; struct ip_tunnel_parm_kern parms; + struct nlattr **tb = params->tb; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); - return ip_tunnel_newlink(dev, tb, &parms, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, + &parms, fwmark); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 5a4fb2539b08..9a45aed508d1 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -54,6 +54,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info) } /* We always hold one tunnel user reference to indicate a tunnel */ +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -62,6 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPIP; t->id.spi = x->props.saddr.a4; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index c56b6fe6f0d7..019408d3ca2c 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -274,9 +274,9 @@ static int __init ic_open_devs(void) /* wait for a carrier on at least one device */ start = jiffies; - next_msg = start + msecs_to_jiffies(20000); + next_msg = start + secs_to_jiffies(20); while (time_before(jiffies, start + - msecs_to_jiffies(carrier_timeout * 1000))) { + secs_to_jiffies(carrier_timeout))) { int wait, elapsed; rtnl_lock(); @@ -295,7 +295,7 @@ static int __init ic_open_devs(void) elapsed = jiffies_to_msecs(jiffies - start); wait = (carrier_timeout * 1000 - elapsed + 500) / 1000; pr_info("Waiting up to %d more seconds for network.\n", wait); - next_msg = jiffies + msecs_to_jiffies(20000); + next_msg = jiffies + secs_to_jiffies(20); } have_carrier: @@ -1690,7 +1690,8 @@ static int __init ic_proto_name(char *name) *v = 0; if (kstrtou8(client_id, 0, dhcp_client_identifier)) pr_debug("DHCP: Invalid client identifier type\n"); - strncpy(dhcp_client_identifier + 1, v + 1, 251); + strscpy(dhcp_client_identifier + 1, v + 1, + sizeof(dhcp_client_identifier) - 1); *v = ','; } return 1; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index dc0db5895e0e..ff95b1b9908e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -353,6 +353,30 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) return ip_tunnel_ctl(dev, p, cmd); } +static int ipip_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct ip_tunnel *tunnel = netdev_priv(ctx->dev); + const struct iphdr *tiph = &tunnel->parms.iph; + struct rtable *rt; + + rt = ip_route_output(dev_net(ctx->dev), tiph->daddr, 0, 0, 0, + RT_SCOPE_UNIVERSE); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + path->type = DEV_PATH_TUN; + path->tun.src_v4.s_addr = tiph->saddr; + path->tun.dst_v4.s_addr = tiph->daddr; + path->tun.l3_proto = IPPROTO_IPIP; + path->dev = ctx->dev; + + ctx->dev = rt->dst.dev; + ip_rt_put(rt); + + return 0; +} + static const struct net_device_ops ipip_netdev_ops = { .ndo_init = ipip_tunnel_init, .ndo_uninit = ip_tunnel_uninit, @@ -362,6 +386,7 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip_tunnel_ctl, + .ndo_fill_forward_path = ipip_fill_forward_path, }; #define IPIP_FEATURES (NETIF_F_SG | \ @@ -436,11 +461,13 @@ static void ipip_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } -static int ipip_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipip_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; @@ -453,7 +480,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, } ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], @@ -601,16 +629,15 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_batch_rtnl(struct list_head *list_net, - struct list_head *dev_to_kill) +static void __net_exit ipip_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops, - dev_to_kill); + ip_tunnel_delete_net(net, ipip_net_id, &ipip_link_ops, dev_to_kill); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit_batch_rtnl = ipip_exit_batch_rtnl, + .exit_rtnl = ipip_exit_rtnl, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c58dd78509a2..ca9eaee4c2ef 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -42,6 +42,7 @@ #include <linux/init.h> #include <linux/if_ether.h> #include <linux/slab.h> +#include <net/flow.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -137,7 +138,7 @@ static struct mr_table *ipmr_mr_table_iter(struct net *net, return ret; } -static struct mr_table *ipmr_get_table(struct net *net, u32 id) +static struct mr_table *__ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; @@ -148,6 +149,16 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id) return NULL; } +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + + rcu_read_lock(); + mrt = __ipmr_get_table(net, id); + rcu_read_unlock(); + return mrt; +} + static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { @@ -189,7 +200,7 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, arg->table = fib_rule_get_table(rule, arg); - mrt = ipmr_get_table(rule->fr_net, arg->table); + mrt = __ipmr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; @@ -315,6 +326,8 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id) return net->ipv4.mrt; } +#define __ipmr_get_table ipmr_get_table + static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { @@ -403,7 +416,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) if (id != RT_TABLE_DEFAULT && id >= 1000000000) return ERR_PTR(-EINVAL); - mrt = ipmr_get_table(net, id); + mrt = __ipmr_get_table(net, id); if (mrt) return mrt; @@ -413,6 +426,10 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) static void ipmr_free_table(struct mr_table *mrt) { + struct net *net = read_pnet(&mrt->net); + + WARN_ON_ONCE(!mr_can_free_table(net)); + timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC); @@ -537,7 +554,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; - dev->netns_local = true; + dev->netns_immutable = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) @@ -749,7 +766,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) /* Timer process for the unresolved queue. */ static void ipmr_expire_process(struct timer_list *t) { - struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); + struct mr_table *mrt = timer_container_of(mrt, t, ipmr_expire_timer); struct mr_mfc *c, *next; unsigned long expires; unsigned long now; @@ -805,7 +822,7 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, cache->mfc_un.res.maxvif = vifi + 1; } } - cache->mfc_un.res.lastuse = jiffies; + WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int vif_add(struct net *net, struct mr_table *mrt, @@ -885,7 +902,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); - err = dev_get_port_parent_id(dev, &ppid, true); + err = netif_get_port_parent_id(dev, &ppid, true); if (err == 0) { memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); v->dev_parent_id.id_len = ppid.id_len; @@ -1263,7 +1280,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, } } if (list_empty(&mrt->mfc_unres_queue)) - del_timer(&mrt->ipmr_expire_timer); + timer_delete(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { @@ -1374,7 +1391,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, goto out_unlock; } - mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + mrt = __ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) { ret = -ENOENT; goto out_unlock; @@ -1655,9 +1672,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { - sr->pktcnt = c->_c.mfc_un.res.pkt; - sr->bytecnt = c->_c.mfc_un.res.bytes; - sr->wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } @@ -1727,9 +1744,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1837,20 +1854,19 @@ static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, /* Processing handlers for ipmr_forward, under rcu_read_lock() */ -static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, - int in_vifi, struct sk_buff *skb, int vifi) +static int ipmr_prepare_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; - struct net_device *dev; struct rtable *rt; struct flowi4 fl4; int encap = 0; vif_dev = vif_dev_read(vif); if (!vif_dev) - goto out_free; + return -1; if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); @@ -1858,12 +1874,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); - goto out_free; + return -1; } - if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) - goto out_free; - if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, @@ -1871,7 +1884,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) - goto out_free; + return -1; encap = sizeof(struct iphdr); } else { rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, @@ -1879,11 +1892,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) - goto out_free; + return -1; } - dev = rt->dst.dev; - if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not * allow to send ICMP, so that packets will disappear @@ -1891,14 +1902,14 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, */ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); - goto out_free; + return -1; } - encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; + encap += LL_RESERVED_SPACE(dst_dev_rcu(&rt->dst)) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); - goto out_free; + return -1; } WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); @@ -1918,6 +1929,22 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } + return 0; +} + +static void ipmr_queue_fwd_xmit(struct net *net, struct mr_table *mrt, + int in_vifi, struct sk_buff *skb, int vifi) +{ + struct rtable *rt; + + if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) + goto out_free; + + if (ipmr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; + + rt = skb_rtable(skb); + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally @@ -1931,7 +1958,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * result in receiving multiple packets. */ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, - net, NULL, skb, skb->dev, dev, + net, NULL, skb, skb->dev, dst_dev_rcu(&rt->dst), ipmr_forward_finish); return; @@ -1939,6 +1966,19 @@ out_free: kfree_skb(skb); } +static void ipmr_queue_output_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) +{ + if (ipmr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; + + ip_mc_output(net, NULL, skb); + return; + +out_free: + kfree_skb(skb); +} + /* Called with mrt_lock or rcu_read_lock() */ static int ipmr_find_vif(const struct mr_table *mrt, struct net_device *dev) { @@ -1962,9 +2002,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, int vif, ct; vif = c->_c.mfc_parent; - c->_c.mfc_un.res.pkt++; - c->_c.mfc_un.res.bytes += skb->len; - c->_c.mfc_un.res.lastuse = jiffies; + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; @@ -1995,7 +2035,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } - c->_c.mfc_un.res.wrong_if++; + atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2049,8 +2089,8 @@ forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, true_vifi, - skb2, psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, + skb2, psend); } psend = ct; } @@ -2061,10 +2101,10 @@ last_forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, true_vifi, skb2, - psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, skb2, + psend); } else { - ipmr_queue_xmit(net, mrt, true_vifi, skb, psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, skb, psend); return; } } @@ -2081,7 +2121,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), + .flowi4_dscp = ip4h_dscp(iph), .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? @@ -2198,6 +2238,110 @@ dont_forward: return 0; } +static void ip_mr_output_finish(struct net *net, struct mr_table *mrt, + struct net_device *dev, struct sk_buff *skb, + struct mfc_cache *c) +{ + int psend = -1; + int ct; + + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); + + /* Forward the frame */ + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (ip_hdr(skb)->ttl > + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = c->_c.mfc_parent; + goto last_xmit; + } + goto dont_xmit; + } + + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { + if (ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { + if (psend != -1) { + struct sk_buff *skb2; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) + ipmr_queue_output_xmit(net, mrt, + skb2, psend); + } + psend = ct; + } + } + +last_xmit: + if (psend != -1) { + ipmr_queue_output_xmit(net, mrt, skb, psend); + return; + } + +dont_xmit: + kfree_skb(skb); +} + +/* Multicast packets for forwarding arrive here + * Called with rcu_read_lock(); + */ +int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct rtable *rt = skb_rtable(skb); + struct mfc_cache *cache; + struct net_device *dev; + struct mr_table *mrt; + int vif; + + guard(rcu)(); + + dev = dst_dev_rcu(&rt->dst); + + if (IPCB(skb)->flags & IPSKB_FORWARDED) + goto mc_output; + if (!(IPCB(skb)->flags & IPSKB_MCROUTE)) + goto mc_output; + + skb->dev = dev; + + mrt = ipmr_rt_fib_lookup(net, skb); + if (IS_ERR(mrt)) + goto mc_output; + + cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (!cache) { + vif = ipmr_find_vif(mrt, dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } + + /* No usable cache entry */ + if (!cache) { + vif = ipmr_find_vif(mrt, dev); + if (vif >= 0) + return ipmr_cache_unresolved(mrt, vif, skb, dev); + goto mc_output; + } + + vif = cache->_c.mfc_parent; + if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) + goto mc_output; + + ip_mr_output_finish(net, mrt, dev, skb, cache); + return 0; + +mc_output: + return ip_mc_output(net, sk, skb); +} + #ifdef CONFIG_IP_PIMSM_V1 /* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) @@ -2262,11 +2406,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, struct mr_table *mrt; int err; - mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (!mrt) + rcu_read_lock(); + mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); + if (!mrt) { + rcu_read_unlock(); return -ENOENT; + } - rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); @@ -2483,7 +2629,8 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, struct rtmsg *rtm; int i, err; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + rtm = nlmsg_payload(nlh, sizeof(*rtm)); + if (!rtm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request"); return -EINVAL; } @@ -2492,7 +2639,6 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); - rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || @@ -2550,7 +2696,7 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, grp = nla_get_in_addr_default(tb[RTA_DST], 0); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); - mrt = ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); + mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); if (!mrt) { err = -ENOENT; goto errout_free; @@ -2604,7 +2750,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (filter.table_id) { struct mr_table *mrt; - mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id); + mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; @@ -2712,7 +2858,7 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh, break; } } - mrt = ipmr_get_table(net, tblid); + mrt = __ipmr_get_table(net, tblid); if (!mrt) { ret = -ENOENT; goto out; @@ -2808,7 +2954,8 @@ static int ipmr_valid_dumplink(const struct nlmsghdr *nlh, { struct ifinfomsg *ifm; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { + ifm = nlmsg_payload(nlh, sizeof(*ifm)); + if (!ifm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump"); return -EINVAL; } @@ -2818,7 +2965,6 @@ static int ipmr_valid_dumplink(const struct nlmsghdr *nlh, return -EINVAL; } - ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request"); @@ -2920,13 +3066,15 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) struct net *net = seq_file_net(seq); struct mr_table *mrt; - mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (!mrt) + rcu_read_lock(); + mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); + if (!mrt) { + rcu_read_unlock(); return ERR_PTR(-ENOENT); + } iter->mrt = mrt; - rcu_read_lock(); return mr_vif_seq_start(seq, pos); } @@ -2999,9 +3147,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->_c.mfc_un.res.pkt, - mfc->_c.mfc_un.res.bytes, - mfc->_c.mfc_un.res.wrong_if); + atomic_long_read(&mfc->_c.mfc_un.res.pkt), + atomic_long_read(&mfc->_c.mfc_un.res.bytes), + atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index f0af12a2f70b..28d77d454d44 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -263,9 +263,9 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, lastuse = READ_ONCE(c->mfc_un.res.lastuse); lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + mfcs.mfcs_packets = atomic_long_read(&c->mfc_un.res.pkt); + mfcs.mfcs_bytes = atomic_long_read(&c->mfc_un.res.bytes); + mfcs.mfcs_wrong_if = atomic_long_read(&c->mfc_un.res.wrong_if); if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) @@ -330,9 +330,6 @@ next_entry: list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; - if (filter->dev && - !mr_mfc_uses_dev(mrt, mfc, filter->dev)) - goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 08bc3f2c0078..ce310eb779e0 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -11,21 +11,21 @@ #include <linux/skbuff.h> #include <linux/gfp.h> #include <linux/export.h> +#include <net/flow.h> #include <net/route.h> #include <net/xfrm.h> #include <net/ip.h> -#include <net/inet_dscp.h> #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { + struct net_device *dev = skb_dst_dev(skb); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags; - struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; @@ -44,7 +44,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un */ fl4.daddr = iph->daddr; fl4.saddr = saddr; - fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); + fl4.flowi4_dscp = ip4h_dscp(iph); fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; @@ -65,7 +65,10 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && xfrm_decode_session(net, skb, flowi4_to_flowi(&fl4), AF_INET) == 0) { struct dst_entry *dst = skb_dst(skb); - skb_dst_set(skb, NULL); + /* ignore return value from skb_dstref_steal, xfrm_lookup takes + * care of dropping the refcnt if needed. + */ + skb_dstref_steal(skb); dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -74,7 +77,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un #endif /* Change in oif may mean change in hh_len. */ - hh_len = skb_dst(skb)->dev->hard_header_len; + hh_len = skb_dst_dev(skb)->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), 0, GFP_ATOMIC)) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ef8009281da5..7dc9772fe2d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -13,8 +13,9 @@ config NF_DEFRAG_IPV4 # old sockopt interface and eval loop config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" - default n - select NETFILTER_XTABLES + depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES + default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. This is not needed if you are using iptables over nftables @@ -182,8 +183,8 @@ config IP_NF_MATCH_TTL # `filter', generic and specific targets config IP_NF_FILTER tristate "Packet filtering" - default m if NETFILTER_ADVANCED=n - select IP_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -220,10 +221,10 @@ config IP_NF_TARGET_SYNPROXY config IP_NF_NAT tristate "iptables NAT support" depends on NF_CONNTRACK + depends on IP_NF_IPTABLES_LEGACY default m if NETFILTER_ADVANCED=n select NF_NAT select NETFILTER_XT_NAT - select IP_NF_IPTABLES_LEGACY help This enables the `nat' table in iptables. This allows masquerading, port forwarding and other forms of full Network Address Port @@ -263,8 +264,8 @@ endif # IP_NF_NAT # mangle + specific targets config IP_NF_MANGLE tristate "Packet mangling" - default m if NETFILTER_ADVANCED=n - select IP_NF_IPTABLES_LEGACY + default m if NETFILTER_ADVANCED=n || IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -299,7 +300,7 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - select IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -313,7 +314,7 @@ config IP_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED - select IP_NF_IPTABLES_LEGACY + depends on IP_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -325,8 +326,9 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" + depends on NETFILTER_XTABLES_LEGACY depends on NETFILTER_XTABLES - default n + default n help arptables is a legacy packet classifier. This is not needed if you are using arptables over nftables @@ -342,6 +344,7 @@ config IP_NF_ARPFILTER tristate "arptables-legacy packet filtering support" select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP + depends on NETFILTER_XTABLES_LEGACY depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 3d101613f27f..23c8deff8095 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -270,7 +270,7 @@ ipt_do_table(void *priv, * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) - jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); + jumpstack += private->stacksize * current->in_nf_duplicate; e = get_entry(table_base, private->hook_entry[hook]); diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index a27782d7653e..6d9bf5106868 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -8,8 +8,8 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netdevice.h> -#include <net/inet_dscp.h> #include <linux/ip.h> +#include <net/flow.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/route.h> @@ -76,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); + flow.flowi4_dscp = ip4h_dscp(iph); flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index 25e1e8eb18dd..9a773502f10a 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -12,10 +12,10 @@ #include <linux/skbuff.h> #include <linux/netfilter.h> #include <net/checksum.h> +#include <net/flow.h> #include <net/icmp.h> #include <net/ip.h> #include <net/route.h> -#include <net/inet_dscp.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> @@ -33,7 +33,7 @@ static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb, fl4.flowi4_oif = oif; fl4.daddr = gw->s_addr; - fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); + fl4.flowi4_dscp = ip4h_dscp(iph); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); @@ -54,7 +54,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, struct iphdr *iph; local_bh_disable(); - if (this_cpu_read(nf_skb_duplicated)) + if (current->in_nf_duplicate) goto out; /* * Copy the skb, and route the copy. Will later return %XT_CONTINUE for @@ -86,9 +86,9 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, --iph->ttl; if (nf_dup_ipv4_route(net, skb, gw, oif)) { - __this_cpu_write(nf_skb_duplicated, true); + current->in_nf_duplicate = true; ip_local_out(net, skb->sk, skb); - __this_cpu_write(nf_skb_duplicated, false); + current->in_nf_duplicate = false; } else { kfree_skb(skb); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 87fd945a0d27..fae4aa4a5f09 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -12,6 +12,15 @@ #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> +static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + __u8 protocol, int ttl); +static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, + const struct tcphdr *oth); +static const struct tcphdr * +nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, + struct tcphdr *_oth, int hook); + static int nf_reject_iphdr_validate(struct sk_buff *skb) { struct iphdr *iph; @@ -71,6 +80,27 @@ struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset); +static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + u8 *tp, _type; + int thoff; + + if (iph->protocol != IPPROTO_ICMP) + return false; + + thoff = skb_network_offset(skb) + sizeof(*iph); + + tp = skb_header_pointer(skb, + thoff + offsetof(struct icmphdr, type), + sizeof(_type), &_type); + + if (!tp) + return false; + + return *tp == ICMP_DEST_UNREACH; +} + struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, @@ -91,6 +121,10 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; + /* don't reply to ICMP_DEST_UNREACH with ICMP_DEST_UNREACH. */ + if (nf_skb_is_icmp_unreach(oldskb)) + return NULL; + /* RFC says return as much as we can without exceeding 576 bytes. */ len = min_t(unsigned int, 536, oldskb->len); @@ -136,8 +170,9 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach); -const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, - struct tcphdr *_oth, int hook) +static const struct tcphdr * +nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, + struct tcphdr *_oth, int hook) { const struct tcphdr *oth; @@ -163,11 +198,10 @@ const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, return oth; } -EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get); -struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, - const struct sk_buff *oldskb, - __u8 protocol, int ttl) +static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + __u8 protocol, int ttl) { struct iphdr *niph, *oiph = ip_hdr(oldskb); @@ -188,10 +222,9 @@ struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, return niph; } -EXPORT_SYMBOL_GPL(nf_reject_iphdr_put); -void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - const struct tcphdr *oth) +static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, + const struct tcphdr *oth) { struct iphdr *niph = ip_hdr(nskb); struct tcphdr *tcph; @@ -218,7 +251,6 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); } -EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) { @@ -247,8 +279,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (!oth) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(oldskb) < 0) + if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -321,8 +352,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index a1350fc25838..5080fa5fbf6a 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -71,8 +71,7 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, { switch (protocol) { case IPPROTO_TCP: - return inet_lookup(net, net->ipv4.tcp_death_row.hashinfo, - skb, doff, saddr, sport, daddr, dport, + return inet_lookup(net, skb, doff, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: return udp4_lib_lookup(net, saddr, sport, daddr, dport, diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 73e66a088e25..041c3f37f237 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -81,7 +81,6 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const struct net_device *in, const enum nf_tproxy_lookup_t lookup_type) { - struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; struct sock *sk; switch (protocol) { @@ -95,7 +94,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, hinfo, skb, + sk = inet_lookup_listener(net, skb, ip_hdrlen(skb) + __tcp_hdrlen(hp), saddr, sport, daddr, dport, in->ifindex, 0); @@ -109,7 +108,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, */ break; case NF_TPROXY_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, hinfo, saddr, sport, + sk = inet_lookup_established(net, saddr, sport, daddr, dport, in->ifindex); break; default: diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 625adbc42037..82af6cd76d13 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -10,7 +10,7 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> -#include <net/inet_dscp.h> +#include <net/flow.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/route.h> @@ -50,7 +50,12 @@ void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, else addr = iph->saddr; - *dst = inet_dev_addr_type(nft_net(pkt), dev, addr); + if (priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) { + *dst = inet_dev_addr_type(nft_net(pkt), dev, addr); + return; + } + + *dst = inet_addr_type_dev_table(nft_net(pkt), pkt->skb->dev, addr); } EXPORT_SYMBOL_GPL(nft_fib4_eval_type); @@ -65,12 +70,17 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_proto = pkt->tprot, .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), - .flowi4_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)), }; const struct net_device *oif; const struct net_device *found; + if (nft_fib_can_skip(pkt)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } + /* * Do not set flowi4_oif, it restricts results (for example, asking * for oif 3 will get RTN_UNICAST result even if the daddr exits @@ -85,11 +95,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; - } + fl4.flowi4_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, oif); iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { @@ -108,7 +114,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); + fl4.flowi4_dscp = ip4h_dscp(iph); if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 09a3d73b45ba..7b9d70f9b31c 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -541,6 +541,7 @@ static struct nexthop *nexthop_alloc(void) INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); INIT_LIST_HEAD(&nh->fdb_list); + spin_lock_init(&nh->lock); } return nh; } @@ -984,8 +985,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, break; } - if (nhi->fib_nhc.nhc_lwtstate && - lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, + if (lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, NHA_ENCAP, NHA_ENCAP_TYPE) < 0) goto nla_put_failure; @@ -1272,10 +1272,8 @@ static int nh_check_attr_group(struct net *net, u16 nh_grp_type, 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 || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, @@ -1307,10 +1305,41 @@ static int nh_check_attr_group(struct net *net, } } - if (tb[NHA_FDB]) - nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); - for (i = 0; i < len; ++i) { + for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { + if (!tb[i]) + continue; + switch (i) { + case NHA_HW_STATS_ENABLE: + case NHA_FDB: + continue; + case NHA_RES_GROUP: + if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) + continue; + break; + } + NL_SET_ERR_MSG(extack, + "No other attributes can be set in nexthop groups"); + return -EINVAL; + } + + return 0; +} + +static int nh_check_attr_group_rtnl(struct net *net, struct nlattr *tb[], + struct netlink_ext_ack *extack) +{ + u8 nh_family = AF_UNSPEC; + struct nexthop_grp *nhg; + unsigned int len; + unsigned int i; + u8 nhg_fdb; + + len = nla_len(tb[NHA_GROUP]) / sizeof(*nhg); + nhg = nla_data(tb[NHA_GROUP]); + nhg_fdb = !!tb[NHA_FDB]; + + for (i = 0; i < len; i++) { struct nexthop *nh; bool is_fdb_nh; @@ -1330,22 +1359,6 @@ static int nh_check_attr_group(struct net *net, return -EINVAL; } } - for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { - if (!tb[i]) - continue; - switch (i) { - case NHA_HW_STATS_ENABLE: - case NHA_FDB: - continue; - case NHA_RES_GROUP: - if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) - continue; - break; - } - NL_SET_ERR_MSG(extack, - "No other attributes can be set in nexthop groups"); - return -EINVAL; - } return 0; } @@ -1542,12 +1555,12 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, if (nh->is_group) { struct nh_group *nhg; - nhg = rtnl_dereference(nh->nh_grp); + nhg = rcu_dereference_rtnl(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; is_fdb_nh = nhg->fdb_nh; } else { - nhi = rtnl_dereference(nh->nh_info); + nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; is_fdb_nh = nhi->fdb_nh; @@ -2074,6 +2087,12 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, { struct nh_grp_entry *nhge, *tmp; + /* If there is nothing to do, let's avoid the costly call to + * synchronize_net() + */ + if (list_empty(&nh->grp_list)) + return; + list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) remove_nh_grp_entry(net, nhge, nlinfo); @@ -2105,7 +2124,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) /* not called for nexthop replace */ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) { - struct fib6_info *f6i, *tmp; + struct fib6_info *f6i; bool do_flush = false; struct fib_info *fi; @@ -2116,13 +2135,24 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) if (do_flush) fib_flush(net); - /* ip6_del_rt removes the entry from this list hence the _safe */ - list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { + spin_lock_bh(&nh->lock); + + nh->dead = true; + + while (!list_empty(&nh->f6i_list)) { + f6i = list_first_entry(&nh->f6i_list, typeof(*f6i), nh_list); + /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); + + spin_unlock_bh(&nh->lock); ipv6_stub->ip6_del_rt(net, f6i, !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); + + spin_lock_bh(&nh->lock); } + + spin_unlock_bh(&nh->lock); } static void __remove_nexthop(struct net *net, struct nexthop *nh, @@ -2375,6 +2405,13 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, return -EINVAL; } + if (!list_empty(&old->grp_list) && + rtnl_dereference(new->nh_info)->fdb_nh != + rtnl_dereference(old->nh_info)->fdb_nh) { + NL_SET_ERR_MSG(extack, "Cannot change nexthop FDB status while in a group"); + return -EINVAL; + } + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; @@ -2679,9 +2716,6 @@ static struct nexthop *nexthop_create_group(struct net *net, int err; int i; - if (WARN_ON(!num_nh)) - return ERR_PTR(-EINVAL); - nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); @@ -2915,11 +2949,6 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct nexthop *nh; int err; - if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { - NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); - return ERR_PTR(-EINVAL); - } - if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { @@ -3016,19 +3045,13 @@ static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nh_config *cfg, + struct nlmsghdr *nlh, struct nlattr **tb, + struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; int err; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, - ARRAY_SIZE(rtm_nh_policy_new) - 1, - rtm_nh_policy_new, extack); - if (err < 0) - return err; - err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); @@ -3093,7 +3116,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } - err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), + + err = nh_check_attr_group(net, tb, ARRAY_SIZE(rtm_nh_policy_new), cfg->nh_grp_type, extack); if (err) goto out; @@ -3126,25 +3150,6 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } - 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; - } - } - err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; @@ -3206,22 +3211,76 @@ out: return err; } +static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb, + struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + if (tb[NHA_GROUP]) + return nh_check_attr_group_rtnl(net, tb, extack); + + if (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"); + return -EINVAL; + } + + if (!(cfg->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Nexthop device is not up"); + return -ENETDOWN; + } + + if (!netif_carrier_ok(cfg->dev)) { + NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); + return -ENETDOWN; + } + } + + return 0; +} + /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; - err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); - if (!err) { - nh = nexthop_add(net, &cfg, extack); - if (IS_ERR(nh)) - err = PTR_ERR(nh); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_new) - 1, + rtm_nh_policy_new, extack); + if (err < 0) + goto out; + + err = rtm_to_nh_config(net, skb, nlh, tb, &cfg, extack); + if (err) + goto out; + + if (cfg.nlflags & NLM_F_REPLACE && !cfg.nh_id) { + NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); + err = -EINVAL; + goto out; } + rtnl_net_lock(net); + + err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack); + if (err) + goto unlock; + + nh = nexthop_add(net, &cfg, extack); + if (IS_ERR(nh)) + err = PTR_ERR(nh); + +unlock: + rtnl_net_unlock(net); +out: return err; } @@ -3278,13 +3337,17 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + rtnl_net_lock(net); + nh = nexthop_find_by_id(net, id); - if (!nh) - return -ENOENT; + if (nh) + remove_nexthop(net, nh, &nlinfo); + else + err = -ENOENT; - remove_nexthop(net, nh, &nlinfo); + rtnl_net_unlock(net); - return 0; + return err; } /* rtnl */ @@ -3461,12 +3524,42 @@ static int rtm_dump_walk_nexthops(struct sk_buff *skb, int err; s_idx = ctx->idx; - for (node = rb_first(root); node; node = rb_next(node)) { + + /* If this is not the first invocation, ctx->idx will contain the id of + * the last nexthop we processed. Instead of starting from the very + * first element of the red/black tree again and linearly skipping the + * (potentially large) set of nodes with an id smaller than s_idx, walk + * the tree and find the left-most node whose id is >= s_idx. This + * provides an efficient O(log n) starting point for the dump + * continuation. + */ + if (s_idx != 0) { + struct rb_node *tmp = root->rb_node; + + node = NULL; + while (tmp) { + struct nexthop *nh; + + nh = rb_entry(tmp, struct nexthop, rb_node); + if (nh->id < s_idx) { + tmp = tmp->rb_right; + } else { + /* Track current candidate and keep looking on + * the left side to find the left-most + * (smallest id) that is still >= s_idx. + */ + node = tmp; + tmp = tmp->rb_left; + } + } + } else { + node = rb_first(root); + } + + for (; node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); - if (nh->id < s_idx) - continue; ctx->idx = nh->id; err = nh_cb(skb, cb, nh, data); @@ -3834,7 +3927,7 @@ static int nh_netdev_event(struct notifier_block *this, nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: - if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) + if (!(netif_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: @@ -4000,14 +4093,11 @@ out: } EXPORT_SYMBOL(nexthop_res_grp_activity_update); -static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, - struct list_head *dev_to_kill) +static void __net_exit nexthop_net_exit_rtnl(struct net *net, + struct list_head *dev_to_kill) { - struct net *net; - - ASSERT_RTNL(); - list_for_each_entry(net, net_list, exit_list) - flush_all_nexthops(net); + ASSERT_RTNL_NET(net); + flush_all_nexthops(net); } static void __net_exit nexthop_net_exit(struct net *net) @@ -4032,22 +4122,24 @@ static int __net_init nexthop_net_init(struct net *net) static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, .exit = nexthop_net_exit, - .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, + .exit_rtnl = nexthop_net_exit_rtnl, }; static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = { - {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop}, - {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop}, + {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, + .flags = RTNL_FLAG_DOIT_PERNET}, + {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop, + .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop, .dumpit = rtm_dump_nexthop}, {.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket, .dumpit = rtm_dump_nexthop_bucket}, {.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP, - .doit = rtm_new_nexthop}, + .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, {.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP, - .doit = rtm_new_nexthop}, + .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, }; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 619ddc087957..ad56588107cc 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -56,9 +56,7 @@ struct ping_table { static struct ping_table ping_table; struct pingv6_ops pingv6_ops; -EXPORT_SYMBOL_GPL(pingv6_ops); - -static u16 ping_port_rover; +EXPORT_IPV6_MOD_GPL(pingv6_ops); static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) { @@ -67,7 +65,6 @@ static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) pr_debug("hash(%u) = %u\n", num, res); return res; } -EXPORT_SYMBOL_GPL(ping_hash); static inline struct hlist_head *ping_hashslot(struct ping_table *table, struct net *net, unsigned int num) @@ -77,6 +74,7 @@ static inline struct hlist_head *ping_hashslot(struct ping_table *table, int ping_get_port(struct sock *sk, unsigned short ident) { + struct net *net = sock_net(sk); struct inet_sock *isk, *isk2; struct hlist_head *hlist; struct sock *sk2 = NULL; @@ -84,15 +82,16 @@ int ping_get_port(struct sock *sk, unsigned short ident) isk = inet_sk(sk); spin_lock(&ping_table.lock); if (ident == 0) { + u16 result = net->ipv4.ping_port_rover + 1; u32 i; - u16 result = ping_port_rover + 1; for (i = 0; i < (1L << 16); i++, result++) { if (!result) - result++; /* avoid zero */ - hlist = ping_hashslot(&ping_table, sock_net(sk), - result); + continue; /* avoid zero */ + hlist = ping_hashslot(&ping_table, net, result); sk_for_each(sk2, hlist) { + if (!net_eq(sock_net(sk2), net)) + continue; isk2 = inet_sk(sk2); if (isk2->inet_num == result) @@ -100,7 +99,7 @@ int ping_get_port(struct sock *sk, unsigned short ident) } /* found */ - ping_port_rover = ident = result; + net->ipv4.ping_port_rover = ident = result; break; next_port: ; @@ -108,8 +107,10 @@ next_port: if (i >= (1L << 16)) goto fail; } else { - hlist = ping_hashslot(&ping_table, sock_net(sk), ident); + hlist = ping_hashslot(&ping_table, net, ident); sk_for_each(sk2, hlist) { + if (!net_eq(sock_net(sk2), net)) + continue; isk2 = inet_sk(sk2); /* BUG? Why is this reuse and not reuseaddr? ping.c @@ -129,7 +130,7 @@ next_port: pr_debug("was not hashed\n"); sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + sock_prot_inuse_add(net, sk->sk_prot, 1); } spin_unlock(&ping_table.lock); return 0; @@ -138,15 +139,7 @@ fail: spin_unlock(&ping_table.lock); return -EADDRINUSE; } -EXPORT_SYMBOL_GPL(ping_get_port); - -int ping_hash(struct sock *sk) -{ - pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); - BUG(); /* "Please do not press this button again." */ - - return 0; -} +EXPORT_IPV6_MOD_GPL(ping_get_port); void ping_unhash(struct sock *sk) { @@ -161,7 +154,7 @@ void ping_unhash(struct sock *sk) } spin_unlock(&ping_table.lock); } -EXPORT_SYMBOL_GPL(ping_unhash); +EXPORT_IPV6_MOD_GPL(ping_unhash); /* Called under rcu_read_lock() */ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) @@ -188,6 +181,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) } sk_for_each_rcu(sk, hslot) { + if (!net_eq(sock_net(sk), net)) + continue; isk = inet_sk(sk); pr_debug("iterate\n"); @@ -279,7 +274,7 @@ out_release_group: put_group_info(group_info); return ret; } -EXPORT_SYMBOL_GPL(ping_init_sock); +EXPORT_IPV6_MOD_GPL(ping_init_sock); void ping_close(struct sock *sk, long timeout) { @@ -289,9 +284,9 @@ void ping_close(struct sock *sk, long timeout) sk_common_release(sk); } -EXPORT_SYMBOL_GPL(ping_close); +EXPORT_IPV6_MOD_GPL(ping_close); -static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int ping_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from __ip4_datagram_connect() and @@ -306,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, - struct sockaddr *uaddr, int addr_len) + struct sockaddr_unsized *uaddr, int addr_len) { struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { @@ -392,7 +387,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return 0; } -static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) +static void ping_set_saddr(struct sock *sk, struct sockaddr_unsized *saddr) { if (saddr->sa_family == AF_INET) { struct inet_sock *isk = inet_sk(sk); @@ -412,7 +407,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) * Moreover, we don't allow binding to multi- and broadcast addresses. */ -int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *isk = inet_sk(sk); unsigned short snum; @@ -467,7 +462,7 @@ out: pr_debug("ping_v4_bind -> %d\n", err); return err; } -EXPORT_SYMBOL_GPL(ping_bind); +EXPORT_IPV6_MOD_GPL(ping_bind); /* * Is this a supported type of ICMP message? @@ -600,7 +595,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) out: return; } -EXPORT_SYMBOL_GPL(ping_err); +EXPORT_IPV6_MOD_GPL(ping_err); /* * Copy and checksum an ICMP Echo packet from user space into a buffer @@ -630,7 +625,7 @@ int ping_getfrag(void *from, char *to, return 0; } -EXPORT_SYMBOL_GPL(ping_getfrag); +EXPORT_IPV6_MOD_GPL(ping_getfrag); static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, struct flowi4 *fl4) @@ -691,7 +686,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, return 0; } -EXPORT_SYMBOL_GPL(ping_common_sendmsg); +EXPORT_IPV6_MOD_GPL(ping_common_sendmsg); static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { @@ -705,7 +700,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ip_options_data opt_copy; int free = 0; __be32 saddr, daddr, faddr; - u8 tos, scope; + u8 scope; int err; pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); @@ -768,7 +763,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } faddr = ipc.opt->opt.faddr; } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); if (ipv4_is_multicast(daddr)) { @@ -779,9 +773,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) ipc.oif = READ_ONCE(inet->uc_index); - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, - saddr, 0, 0, sk->sk_uid); + saddr, 0, 0, sk_uid(sk)); fl4.fl4_icmp_type = user_icmph.type; fl4.fl4_icmp_code = user_icmph.code; @@ -936,7 +931,7 @@ out: pr_debug("ping_recvmsg -> %d\n", err); return err; } -EXPORT_SYMBOL_GPL(ping_recvmsg); +EXPORT_IPV6_MOD_GPL(ping_recvmsg); static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) @@ -957,7 +952,7 @@ int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { return __ping_queue_rcv_skb(sk, skb) ? -1 : 0; } -EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); +EXPORT_IPV6_MOD_GPL(ping_queue_rcv_skb); /* @@ -966,10 +961,9 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); enum skb_drop_reason ping_rcv(struct sk_buff *skb) { - enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET; - struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + struct sock *sk; /* We assume the packet has already been checked by icmp_rcv */ @@ -980,22 +974,13 @@ enum skb_drop_reason ping_rcv(struct sk_buff *skb) skb_push(skb, skb->data - (u8 *)icmph); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); - if (sk) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - - pr_debug("rcv on socket %p\n", sk); - if (skb2) - reason = __ping_queue_rcv_skb(sk, skb2); - else - reason = SKB_DROP_REASON_NOMEM; - } - - if (reason) - pr_debug("no socket, dropping\n"); + if (sk) + return __ping_queue_rcv_skb(sk, skb); - return reason; + kfree_skb_reason(skb, SKB_DROP_REASON_NO_SOCKET); + return SKB_DROP_REASON_NO_SOCKET; } -EXPORT_SYMBOL_GPL(ping_rcv); +EXPORT_IPV6_MOD_GPL(ping_rcv); struct proto ping_prot = { .name = "PING", @@ -1012,13 +997,12 @@ struct proto ping_prot = { .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .release_cb = ip4_datagram_release_cb, - .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .put_port = ping_unhash, .obj_size = sizeof(struct inet_sock), }; -EXPORT_SYMBOL(ping_prot); +EXPORT_IPV6_MOD(ping_prot); #ifdef CONFIG_PROC_FS @@ -1083,7 +1067,7 @@ void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } -EXPORT_SYMBOL_GPL(ping_seq_start); +EXPORT_IPV6_MOD_GPL(ping_seq_start); static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos) { @@ -1102,14 +1086,14 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } -EXPORT_SYMBOL_GPL(ping_seq_next); +EXPORT_IPV6_MOD_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) __releases(ping_table.lock) { spin_unlock(&ping_table.lock); } -EXPORT_SYMBOL_GPL(ping_seq_stop); +EXPORT_IPV6_MOD_GPL(ping_seq_stop); static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, int bucket) @@ -1126,10 +1110,10 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + from_kuid_munged(seq_user_ns(f), sk_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops)); + sk_drops_read(sp)); } static int ping_v4_seq_show(struct seq_file *seq, void *v) @@ -1160,6 +1144,8 @@ static int __net_init ping_v4_proc_init_net(struct net *net) if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; + + net->ipv4.ping_port_rover = get_random_u16(); return 0; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 40053a02bae1..974afc4ecbe2 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -95,7 +95,6 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS), SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES), SNMP_MIB_ITEM("OutTransmits", IPSTATS_MIB_OUTPKTS), - SNMP_MIB_SENTINEL }; /* Following items are displayed in /proc/net/netstat */ @@ -119,7 +118,6 @@ static const struct snmp_mib snmp4_ipextstats_list[] = { SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS), SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS), - SNMP_MIB_SENTINEL }; static const struct { @@ -157,7 +155,6 @@ static const struct snmp_mib snmp4_tcp_list[] = { SNMP_MIB_ITEM("InErrs", TCP_MIB_INERRS), SNMP_MIB_ITEM("OutRsts", TCP_MIB_OUTRSTS), SNMP_MIB_ITEM("InCsumErrors", TCP_MIB_CSUMERRORS), - SNMP_MIB_SENTINEL }; static const struct snmp_mib snmp4_udp_list[] = { @@ -170,7 +167,6 @@ static const struct snmp_mib snmp4_udp_list[] = { SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS), SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI), SNMP_MIB_ITEM("MemErrors", UDP_MIB_MEMERRORS), - SNMP_MIB_SENTINEL }; static const struct snmp_mib snmp4_net_list[] = { @@ -189,6 +185,10 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), + SNMP_MIB_ITEM("BeyondWindow", LINUX_MIB_BEYOND_WINDOW), + SNMP_MIB_ITEM("TSEcrRejected", LINUX_MIB_TSECRREJECTED), + SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK), + SNMP_MIB_ITEM("PAWSTimewait", LINUX_MIB_PAWS_TW_REJECTED), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED), SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), @@ -305,7 +305,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAOKeyNotFound", LINUX_MIB_TCPAOKEYNOTFOUND), SNMP_MIB_ITEM("TCPAOGood", LINUX_MIB_TCPAOGOOD), SNMP_MIB_ITEM("TCPAODroppedIcmps", LINUX_MIB_TCPAODROPPEDICMPS), - SNMP_MIB_SENTINEL }; static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals, @@ -385,14 +384,15 @@ static void icmp_put(struct seq_file *seq) */ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) { + const int cnt = ARRAY_SIZE(snmp4_ipstats_list); + u64 buff64[ARRAY_SIZE(snmp4_ipstats_list)]; struct net *net = seq->private; - u64 buff64[IPSTATS_MIB_MAX]; int i; - memset(buff64, 0, IPSTATS_MIB_MAX * sizeof(u64)); + memset(buff64, 0, sizeof(buff64)); seq_puts(seq, "Ip: Forwarding DefaultTTL"); - for (i = 0; snmp4_ipstats_list[i].name; i++) + for (i = 0; i < cnt; i++) seq_printf(seq, " %s", snmp4_ipstats_list[i].name); seq_printf(seq, "\nIp: %d %d", @@ -400,10 +400,10 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); - snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list, - net->mib.ip_statistics, - offsetof(struct ipstats_mib, syncp)); - for (i = 0; snmp4_ipstats_list[i].name; i++) + snmp_get_cpu_field64_batch_cnt(buff64, snmp4_ipstats_list, cnt, + net->mib.ip_statistics, + offsetof(struct ipstats_mib, syncp)); + for (i = 0; i < cnt; i++) seq_printf(seq, " %llu", buff64[i]); return 0; @@ -411,20 +411,23 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v) { + const int udp_cnt = ARRAY_SIZE(snmp4_udp_list); + const int tcp_cnt = ARRAY_SIZE(snmp4_tcp_list); unsigned long buff[TCPUDP_MIB_MAX]; struct net *net = seq->private; int i; - memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long)); + memset(buff, 0, tcp_cnt * sizeof(unsigned long)); seq_puts(seq, "\nTcp:"); - for (i = 0; snmp4_tcp_list[i].name; i++) + for (i = 0; i < tcp_cnt; i++) seq_printf(seq, " %s", snmp4_tcp_list[i].name); seq_puts(seq, "\nTcp:"); - snmp_get_cpu_field_batch(buff, snmp4_tcp_list, - net->mib.tcp_statistics); - for (i = 0; snmp4_tcp_list[i].name; i++) { + snmp_get_cpu_field_batch_cnt(buff, snmp4_tcp_list, + tcp_cnt, + net->mib.tcp_statistics); + for (i = 0; i < tcp_cnt; i++) { /* MaxConn field is signed, RFC 2012 */ if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN) seq_printf(seq, " %ld", buff[i]); @@ -432,27 +435,29 @@ static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v) seq_printf(seq, " %lu", buff[i]); } - memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long)); + memset(buff, 0, udp_cnt * sizeof(unsigned long)); - snmp_get_cpu_field_batch(buff, snmp4_udp_list, - net->mib.udp_statistics); + snmp_get_cpu_field_batch_cnt(buff, snmp4_udp_list, + udp_cnt, + net->mib.udp_statistics); seq_puts(seq, "\nUdp:"); - for (i = 0; snmp4_udp_list[i].name; i++) + for (i = 0; i < udp_cnt; i++) seq_printf(seq, " %s", snmp4_udp_list[i].name); seq_puts(seq, "\nUdp:"); - for (i = 0; snmp4_udp_list[i].name; i++) + for (i = 0; i < udp_cnt; i++) seq_printf(seq, " %lu", buff[i]); - memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long)); + memset(buff, 0, udp_cnt * sizeof(unsigned long)); /* the UDP and UDP-Lite MIBs are the same */ seq_puts(seq, "\nUdpLite:"); - snmp_get_cpu_field_batch(buff, snmp4_udp_list, - net->mib.udplite_statistics); - for (i = 0; snmp4_udp_list[i].name; i++) + snmp_get_cpu_field_batch_cnt(buff, snmp4_udp_list, + udp_cnt, + net->mib.udplite_statistics); + for (i = 0; i < udp_cnt; i++) seq_printf(seq, " %s", snmp4_udp_list[i].name); seq_puts(seq, "\nUdpLite:"); - for (i = 0; snmp4_udp_list[i].name; i++) + for (i = 0; i < udp_cnt; i++) seq_printf(seq, " %lu", buff[i]); seq_putc(seq, '\n'); @@ -476,8 +481,8 @@ static int snmp_seq_show(struct seq_file *seq, void *v) */ static int netstat_seq_show(struct seq_file *seq, void *v) { - const int ip_cnt = ARRAY_SIZE(snmp4_ipextstats_list) - 1; - const int tcp_cnt = ARRAY_SIZE(snmp4_net_list) - 1; + const int ip_cnt = ARRAY_SIZE(snmp4_ipextstats_list); + const int tcp_cnt = ARRAY_SIZE(snmp4_net_list); struct net *net = seq->private; unsigned long *buff; int i; @@ -490,8 +495,8 @@ static int netstat_seq_show(struct seq_file *seq, void *v) buff = kzalloc(max(tcp_cnt * sizeof(long), ip_cnt * sizeof(u64)), GFP_KERNEL); if (buff) { - snmp_get_cpu_field_batch(buff, snmp4_net_list, - net->mib.net_statistics); + snmp_get_cpu_field_batch_cnt(buff, snmp4_net_list, tcp_cnt, + net->mib.net_statistics); for (i = 0; i < tcp_cnt; i++) seq_printf(seq, " %lu", buff[i]); } else { @@ -509,7 +514,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v) u64 *buff64 = (u64 *)buff; memset(buff64, 0, ip_cnt * sizeof(u64)); - snmp_get_cpu_field64_batch(buff64, snmp4_ipextstats_list, + snmp_get_cpu_field64_batch_cnt(buff64, snmp4_ipextstats_list, ip_cnt, net->mib.ip_statistics, offsetof(struct ipstats_mib, syncp)); for (i = 0; i < ip_cnt; i++) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0e9e01967ec9..5998c4cc6f47 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -178,7 +178,7 @@ static int raw_v4_input(struct net *net, struct sk_buff *skb, if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { - atomic_inc(&sk->sk_drops); + sk_drops_inc(sk); continue; } @@ -311,7 +311,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { - atomic_inc(&sk->sk_drops); + sk_drops_inc(sk); sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } @@ -358,7 +358,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IP); - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); @@ -486,7 +486,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm_cookie ipc; struct rtable *rt = NULL; struct flowi4 fl4; - u8 tos, scope; + u8 scope; int free = 0; __be32 daddr; __be32 saddr; @@ -581,7 +581,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = ipc.opt->opt.faddr; } } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); uc_index = READ_ONCE(inet->uc_index); @@ -606,11 +605,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), - daddr, saddr, 0, 0, sk->sk_uid); + daddr, saddr, 0, 0, sk_uid(sk)); fl4.fl4_icmp_type = 0; fl4.fl4_icmp_code = 0; @@ -697,7 +697,8 @@ static void raw_destroy(struct sock *sk) } /* This gets rid of all the nasties in af_inet. -DaveM */ -static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int raw_bind(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; @@ -793,6 +794,7 @@ static int raw_sk_init(struct sock *sk) { struct raw_sock *rp = raw_sk(sk); + sk->sk_drop_counters = &rp->drop_counters; if (inet_sk(sk)->inet_num == IPPROTO_ICMP) memset(&rp->filter, 0, sizeof(rp->filter)); return 0; @@ -1043,9 +1045,9 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + from_kuid_munged(seq_user_ns(seq), sk_uid(sp)), 0, sock_i_ino(sp), - refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); + refcount_read(&sp->sk_refcnt), sp, sk_drops_read(sp)); } static int raw_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index cc793bd8de25..943e5998e0ad 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -126,9 +126,9 @@ static int raw_diag_dump_one(struct netlink_callback *cb, static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - struct nlattr *bc, bool net_admin) + bool net_admin) { - if (!inet_diag_bc_sk(bc, sk)) + if (!inet_diag_bc_sk(cb->data, sk)) return 0; return inet_sk_diag_fill(sk, NULL, skb, cb, r, NLM_F_MULTI, net_admin); @@ -140,17 +140,13 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); - struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; struct hlist_head *hlist; struct sock *sk = NULL; - struct nlattr *bc; if (IS_ERR(hashinfo)) return; - cb_data = cb->data; - bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; @@ -174,7 +170,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) + if (sk_diag_dump(sk, skb, cb, r, net_admin) < 0) goto out_unlock; next: num++; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e5603e84b20d..b549d6a57307 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -84,6 +84,7 @@ #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <net/flow.h> #include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> @@ -189,7 +190,11 @@ const __u8 ip_tos2prio[16] = { EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); +#ifndef CONFIG_PREEMPT_RT #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) +#else +#define RT_CACHE_STAT_INC(field) this_cpu_inc(rt_cache_stat.field) +#endif #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) @@ -390,7 +395,13 @@ static inline int ip_rt_proc_init(void) static inline bool rt_is_expired(const struct rtable *rth) { - return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); + bool res; + + rcu_read_lock(); + res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev)); + rcu_read_unlock(); + + return res; } void rt_cache_flush(struct net *net) @@ -403,11 +414,11 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net_device *dev = dst->dev; + struct net_device *dev; struct neighbour *n; rcu_read_lock(); - + dev = dst_dev_rcu(dst); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { @@ -430,7 +441,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); - struct net_device *dev = dst->dev; + struct net_device *dev = dst_dev(dst); const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { @@ -546,7 +557,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), - daddr, inet->inet_saddr, 0, 0, sk->sk_uid); + daddr, inet->inet_saddr, 0, 0, + sk_uid(sk)); rcu_read_unlock(); } @@ -595,6 +607,11 @@ static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) oldest_p = fnhe_p; } } + + /* Clear oldest->fnhe_daddr to prevent this fnhe from being + * rebound with new dsts in rt_bind_exception(). + */ + oldest->fnhe_daddr = 0; fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); @@ -706,7 +723,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); for_each_possible_cpu(i) { struct rtable __rcu **prt; @@ -714,7 +731,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); } } @@ -786,7 +803,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow jiffies + ip_rt_gc_timeout); } if (kill_route) - rt->dst.obsolete = DST_OBSOLETE_KILL; + WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); @@ -831,9 +848,9 @@ static void ipv4_negative_advice(struct sock *sk, { struct rtable *rt = dst_rtable(dst); - if ((dst->obsolete > 0) || + if ((READ_ONCE(dst->obsolete) > 0) || (rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) + READ_ONCE(rt->dst.expires)) sk_dst_reset(sk); } @@ -870,11 +887,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); - rcu_read_unlock(); net = dev_net(rt->dst.dev); - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif); if (!peer) { + rcu_read_unlock(); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; @@ -893,7 +910,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; - goto out_put_peer; + goto out_unlock; } /* Check for load limit; set rate_last to the latest sent @@ -914,8 +931,8 @@ void ip_rt_send_redirect(struct sk_buff *skb) &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } -out_put_peer: - inet_putpeer(peer); +out_unlock: + rcu_read_unlock(); } static int ip_error(struct sk_buff *skb) @@ -975,9 +992,9 @@ static int ip_error(struct sk_buff *skb) break; } + rcu_read_lock(); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, - l3mdev_master_ifindex(skb->dev), 1); - + l3mdev_master_ifindex_rcu(skb->dev)); send = true; if (peer) { now = jiffies; @@ -989,8 +1006,9 @@ static int ip_error(struct sk_buff *skb) peer->rate_tokens -= ip_rt_error_cost; else send = false; - inet_putpeer(peer); } + rcu_read_unlock(); + if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); @@ -1001,9 +1019,9 @@ out: kfree_skb_reason(skb, reason); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; - struct net *net = dev_net(dst->dev); struct fib_result res; bool lock = false; + struct net *net; u32 old_mtu; if (ip_mtu_locked(dst)) @@ -1013,16 +1031,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (old_mtu < mtu) return; + rcu_read_lock(); + net = dst_dev_net_rcu(dst); if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && - time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) - return; + time_before(jiffies, READ_ONCE(dst->expires) - + net->ipv4.ip_rt_mtu_expires / 2)) + goto out; - rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; @@ -1036,14 +1056,14 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } - rcu_read_unlock(); - return; + goto out; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } +out: rcu_read_unlock(); } @@ -1123,7 +1143,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = dst_rtable(odst); - if (odst->obsolete && !odst->ops->check(odst, 0)) { + if (READ_ONCE(odst->obsolete) && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1198,7 +1218,8 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ - if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) + if (READ_ONCE(dst->obsolete) != DST_OBSOLETE_FORCE_CHK || + rt_is_expired(rt)) return NULL; return dst; } @@ -1206,8 +1227,8 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct inet_skb_parm parm; struct net_device *dev; - struct ip_options opt; int res; /* Recompile ip options since IPCB may not be valid anymore. @@ -1217,21 +1238,21 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; - memset(&opt, 0, sizeof(opt)); + memset(&parm, 0, sizeof(parm)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; - opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + parm.opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; - res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); + res = __ip_options_compile(dev_net(dev), &parm.opt, skb, NULL); rcu_read_unlock(); if (res) return; } - __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &parm); } static void ipv4_link_failure(struct sk_buff *skb) @@ -1276,7 +1297,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), + .flowi4_dscp = ip4h_dscp(iph), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, @@ -1306,10 +1327,15 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { - struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); - unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, - net->ipv4.ip_rt_min_advmss); + unsigned int advmss; + struct net *net; + + rcu_read_lock(); + net = dst_dev_net_rcu(dst); + advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, + net->ipv4.ip_rt_min_advmss); + rcu_read_unlock(); return min(advmss, IPV4_MAX_PMTU - header_size); } @@ -1553,7 +1579,7 @@ void rt_flush_dev(struct net_device *dev) static bool rt_cache_valid(const struct rtable *rt) { return rt && - rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } @@ -1667,8 +1693,8 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; - new_rt->dst.input = rt->dst.input; - new_rt->dst.output = rt->dst.output; + new_rt->dst.input = READ_ONCE(rt->dst.input); + new_rt->dst.output = READ_ONCE(rt->dst.output); new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); @@ -2024,8 +2050,12 @@ static u32 fib_multipath_custom_hash_fl4(const struct net *net, hash_keys.addrs.v4addrs.dst = fl4->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl4->flowi4_proto; - if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) - hash_keys.ports.src = fl4->fl4_sport; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) { + if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT) + hash_keys.ports.src = (__force __be16)get_random_u16(); + else + hash_keys.ports.src = fl4->fl4_sport; + } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; @@ -2080,7 +2110,10 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; - hash_keys.ports.src = fl4->fl4_sport; + if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT) + hash_keys.ports.src = (__force __be16)get_random_u16(); + else + hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } @@ -2141,7 +2174,7 @@ ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); - fib_select_multipath(res, h); + fib_select_multipath(res, h, NULL); IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif @@ -2183,7 +2216,7 @@ ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto martian_source; } - if (rt->rt_type != RTN_LOCAL) + if (!(rt->rt_flags & RTCF_LOCAL)) goto skip_validate_source; reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, @@ -2304,7 +2337,7 @@ ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; - fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); + fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; @@ -2445,6 +2478,7 @@ martian_destination: net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif + goto out; e_nobufs: reason = SKB_DROP_REASON_NOMEM; @@ -2478,7 +2512,8 @@ ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, int our = 0; if (!in_dev) - return -EINVAL; + return reason; + our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); @@ -2546,12 +2581,16 @@ static struct rtable *__mkroute_output(const struct fib_result *res, !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); - if (ipv4_is_lbcast(fl4->daddr)) + if (ipv4_is_lbcast(fl4->daddr)) { type = RTN_BROADCAST; - else if (ipv4_is_multicast(fl4->daddr)) + + /* reset fi to prevent gateway resolution */ + fi = NULL; + } else if (ipv4_is_multicast(fl4->daddr)) { type = RTN_MULTICAST; - else if (ipv4_is_zeronet(fl4->daddr)) + } else if (ipv4_is_zeronet(fl4->daddr)) { return ERR_PTR(-EINVAL); + } if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; @@ -2559,7 +2598,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; - fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, @@ -2634,7 +2672,7 @@ add: if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; - rth->dst.output = ip_mc_output; + rth->dst.output = ip_mr_output; } } #endif @@ -2662,7 +2700,6 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - fl4->flowi4_tos &= INET_DSCP_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); @@ -2684,8 +2721,7 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || - ipv4_is_lbcast(fl4->saddr) || - ipv4_is_zeronet(fl4->saddr)) { + ipv4_is_lbcast(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } @@ -2952,8 +2988,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; - if (rt->dst.lwtstate && - lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) + if (lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && @@ -2984,7 +3019,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } - expires = rt->dst.expires; + expires = READ_ONCE(rt->dst.expires); if (expires) { unsigned long now = jiffies; @@ -3191,7 +3226,8 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb, struct rtmsg *rtm; int i, err; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + rtm = nlmsg_payload(nlh, sizeof(*rtm)); + if (!rtm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; @@ -3201,7 +3237,6 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb, return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); - rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || @@ -3267,6 +3302,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; + dscp_t dscp; kuid_t uid; u32 iif; int err; @@ -3281,6 +3317,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, dst = nla_get_in_addr_default(tb[RTA_DST], 0); iif = nla_get_u32_default(tb[RTA_IIF], 0); mark = nla_get_u32_default(tb[RTA_MARK], 0); + dscp = inet_dsfield_to_dscp(rtm->rtm_tos); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else @@ -3305,7 +3342,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; + fl4.flowi4_dscp = dscp; fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3329,9 +3366,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, - inet_dsfield_to_dscp(rtm->rtm_tos), - dev, &res) ? -EINVAL : 0; + err = ip_route_input_rcu(skb, dst, src, dscp, dev, + &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 1948d15f1f28..569befcf021b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -12,6 +12,7 @@ #include <linux/export.h> #include <net/secure_seq.h> #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/route.h> static siphash_aligned_key_t syncookie_secret[2]; @@ -222,7 +223,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, return NULL; } -EXPORT_SYMBOL(tcp_get_cookie_sock); +EXPORT_IPV6_MOD(tcp_get_cookie_sock); /* * when syncookies are in effect and tcp timestamps are enabled we stored @@ -259,7 +260,7 @@ bool cookie_timestamp_decode(const struct net *net, return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } -EXPORT_SYMBOL(cookie_timestamp_decode); +EXPORT_IPV6_MOD(cookie_timestamp_decode); static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, struct request_sock *req) @@ -279,6 +280,7 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, ireq->smc_ok = 0; treq->snt_synack = 0; + treq->snt_tsval_first = 0; treq->tfo_listener = false; treq->txhash = net_tx_rndhash(); treq->rcv_isn = ntohl(th->seq) - 1; @@ -310,7 +312,7 @@ struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) return req; } -EXPORT_SYMBOL_GPL(cookie_bpf_check); +EXPORT_IPV6_MOD_GPL(cookie_bpf_check); #endif struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, @@ -351,7 +353,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return req; } -EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc); +EXPORT_IPV6_MOD_GPL(cookie_tcp_reqsk_alloc); static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -402,6 +404,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_request_sock *ireq; struct net *net = sock_net(sk); + struct tcp_request_sock *treq; struct request_sock *req; struct sock *ret = sk; struct flowi4 fl4; @@ -427,6 +430,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } ireq = inet_rsk(req); + treq = tcp_rsk(req); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); @@ -453,7 +457,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, - ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid); + ireq->ir_loc_addr, th->source, th->dest, + sk_uid(sk)); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { @@ -481,6 +486,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); + treq->accecn_ok = ireq->ecn_ok && cookie_accecn_ok(th); ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a79b2a52ce01..a1a50a5c80dc 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -28,6 +28,7 @@ static int tcp_adv_win_scale_max = 31; static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; +static int tcp_rto_max_max = TCP_RTO_MAX_SEC * MSEC_PER_SEC; static int ip_privileged_port_min; static int ip_privileged_port_max = 65535; static int ip_ttl_min = 1; @@ -45,6 +46,10 @@ static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; +static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; +static int tcp_ecn_mode_max = 2; +static u32 icmp_errors_extension_mask_all = + GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0); /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -672,6 +677,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = SYSCTL_ONE }, { + .procname = "icmp_errors_extension_mask", + .data = &init_net.ipv4.sysctl_icmp_errors_extension_mask, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &icmp_errors_extension_mask_all, + }, + { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), @@ -726,9 +740,27 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_ecn_mode_max, + }, + { + .procname = "tcp_ecn_option", + .data = &init_net.ipv4.sysctl_tcp_ecn_option, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { + .procname = "tcp_ecn_option_beacon", + .data = &init_net.ipv4.sysctl_tcp_ecn_option_beacon, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_THREE, + }, + { .procname = "tcp_ecn_fallback", .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, .maxlen = sizeof(u8), @@ -1066,6 +1098,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = SYSCTL_TWO, }, { + .procname = "tcp_tw_reuse_delay", + .data = &init_net.ipv4.sysctl_tcp_tw_reuse_delay, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &tcp_tw_reuse_delay_max, + }, + { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), @@ -1302,6 +1343,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, }, { + .procname = "tcp_rcvbuf_low_rtt", + .data = &init_net.ipv4.sysctl_tcp_rcvbuf_low_rtt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, .maxlen = sizeof(u8), @@ -1411,6 +1461,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_doulongvec_minmax, }, { + .procname = "tcp_comp_sack_rtt_percent", + .data = &init_net.ipv4.sysctl_tcp_comp_sack_rtt_percent, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE_THOUSAND, + }, + { .procname = "tcp_comp_sack_slack_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns, .maxlen = sizeof(unsigned long), @@ -1573,6 +1632,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, + { + .procname = "tcp_rto_max_ms", + .data = &init_net.ipv4.sysctl_tcp_rto_max_ms, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE_THOUSAND, + .extra2 = &tcp_rto_max_max, + }, }; static __net_init int ipv4_sysctl_init_net(struct net *net) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d704bda6c41..f035440c475a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -243,7 +243,7 @@ #define pr_fmt(fmt) "TCP: " fmt -#include <crypto/hash.h> +#include <crypto/md5.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -253,7 +253,6 @@ #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> -#include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> @@ -270,11 +269,14 @@ #include <net/icmp.h> #include <net/inet_common.h> +#include <net/inet_ecn.h> #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> +#include <net/psp.h> #include <net/sock.h> #include <net/rstreason.h> @@ -300,10 +302,8 @@ DEFINE_PER_CPU(u32, tcp_tw_isn); EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_tcp_mem); +EXPORT_IPV6_MOD(sysctl_tcp_mem); -atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ -EXPORT_SYMBOL(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); @@ -316,7 +316,7 @@ EXPORT_SYMBOL(tcp_have_smc); * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; -EXPORT_SYMBOL(tcp_sockets_allocated); +EXPORT_IPV6_MOD(tcp_sockets_allocated); /* * TCP splice context @@ -349,7 +349,7 @@ void tcp_enter_memory_pressure(struct sock *sk) if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } -EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); +EXPORT_IPV6_MOD_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { @@ -362,7 +362,7 @@ void tcp_leave_memory_pressure(struct sock *sk) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } -EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); +EXPORT_IPV6_MOD_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) @@ -414,6 +414,21 @@ static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) return rate64; } +#ifdef CONFIG_TCP_MD5SIG +void tcp_md5_destruct_sock(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->md5sig_info) { + + tcp_clear_md5_list(sk); + kfree(rcu_replace_pointer(tp->md5sig_info, NULL, 1)); + static_branch_slow_dec_deferred(&tcp_md5_needed); + } +} +EXPORT_IPV6_MOD_GPL(tcp_md5_destruct_sock); +#endif + /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to @@ -423,7 +438,7 @@ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int rto_min_us; + int rto_min_us, rto_max_ms; tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; @@ -432,6 +447,10 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + + rto_max_ms = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_max_ms); + icsk->icsk_rto_max = msecs_to_jiffies(rto_max_ms); + rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us); icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us); icsk->icsk_delack_max = TCP_DELACK_MAX; @@ -475,7 +494,7 @@ void tcp_init_sock(struct sock *sk) sk_sockets_allocated_inc(sk); xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } -EXPORT_SYMBOL(tcp_init_sock); +EXPORT_IPV6_MOD(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) { @@ -488,10 +507,14 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) sock_tx_timestamp(sk, sockc, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) - tcb->txstamp_ack = 1; + tcb->txstamp_ack |= TSTAMP_ACK_SK; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } + + if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && + SK_BPF_CB_FLAG_TEST(sk, SK_BPF_CB_TX_TIMESTAMPING) && skb) + bpf_skops_tx_timestamping(sk, skb, BPF_SOCK_OPS_TSTAMP_SENDMSG_CB); } static bool tcp_stream_is_readable(struct sock *sk, int target) @@ -660,7 +683,7 @@ int tcp_ioctl(struct sock *sk, int cmd, int *karg) *karg = answ; return 0; } -EXPORT_SYMBOL(tcp_ioctl); +EXPORT_IPV6_MOD(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { @@ -681,6 +704,7 @@ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); + psp_enqueue_set_decrypted(sk, skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); @@ -876,7 +900,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, return ret; } -EXPORT_SYMBOL(tcp_splice_read); +EXPORT_IPV6_MOD(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) @@ -902,7 +926,8 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, } __kfree_skb(skb); } else { - sk->sk_prot->enter_memory_pressure(sk); + if (!sk->sk_bypass_prot_mem) + tcp_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; @@ -1036,7 +1061,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; - err = __inet_stream_connect(sk->sk_socket, uaddr, + err = __inet_stream_connect(sk->sk_socket, (struct sockaddr_unsized *)uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst @@ -1051,6 +1076,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { + struct net_devmem_dmabuf_binding *binding = NULL; struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; @@ -1058,11 +1084,20 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; + int sockc_err = 0; int zc = 0; long timeo; flags = msg->msg_flags; + sockc = (struct sockcm_cookie){ .tsflags = READ_ONCE(sk->sk_tsflags) }; + if (msg->msg_controllen) { + sockc_err = sock_cmsg_send(sk, msg, &sockc); + /* Don't return error until MSG_FASTOPEN has been processed; + * that may succeed even if the cmsg is invalid. + */ + } + if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; @@ -1070,7 +1105,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); - uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb), + !sockc_err && sockc.dmabuf_id); if (!uarg) { err = -ENOBUFS; goto out_err; @@ -1079,12 +1115,27 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; + + if (!sockc_err && sockc.dmabuf_id) { + binding = net_devmem_get_binding(sk, sockc.dmabuf_id); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + binding = NULL; + goto out_err; + } + } } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } + if (!sockc_err && sockc.dmabuf_id && + (!(flags & MSG_ZEROCOPY) || !sock_flag(sk, SOCK_ZEROCOPY))) { + err = -EINVAL; + goto out_err; + } + if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { @@ -1123,13 +1174,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } - sockcm_init(&sockc, sk); - if (msg->msg_controllen) { - err = sock_cmsg_send(sk, msg, &sockc); - if (unlikely(err)) { - err = -EINVAL; - goto out_err; - } + if (sockc_err) { + err = sockc_err; + goto out_err; } /* This should be in poll */ @@ -1146,12 +1193,14 @@ restart: goto do_error; while (msg_data_left(msg)) { - ssize_t copy = 0; + int copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; + trace_tcp_sendmsg_locked(sk, msg, skb, size_goal); + if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; @@ -1248,7 +1297,8 @@ new_segment: goto wait_for_space; } - err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg, + binding); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; @@ -1264,8 +1314,7 @@ new_segment: if (!copy) goto wait_for_space; - err = skb_splice_from_iter(skb, &msg->msg_iter, copy, - sk->sk_allocation); + err = skb_splice_from_iter(skb, &msg->msg_iter, copy); if (err < 0) { if (err == -EMSGSIZE) { tcp_mark_push(tp, skb); @@ -1329,6 +1378,8 @@ out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); + if (binding) + net_devmem_dmabuf_binding_put(binding); return copied + copied_syn; do_error: @@ -1346,6 +1397,9 @@ out_err: sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } + if (binding) + net_devmem_dmabuf_binding_put(binding); + return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); @@ -1376,7 +1430,7 @@ void tcp_splice_eof(struct socket *sock) tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } -EXPORT_SYMBOL_GPL(tcp_splice_eof); +EXPORT_IPV6_MOD_GPL(tcp_splice_eof); /* * Handle reading urgent data. BSD has very simple semantics for @@ -1502,8 +1556,10 @@ void __tcp_cleanup_rbuf(struct sock *sk, int copied) time_to_ack = true; } } - if (time_to_ack) + if (time_to_ack) { + tcp_mstamp_refresh(tp); tcp_send_ack(sk); + } } void tcp_cleanup_rbuf(struct sock *sk, int copied) @@ -1565,12 +1621,13 @@ EXPORT_SYMBOL(tcp_recv_skb); * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ -int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; + u32 seq = *copied_seq; u32 offset; int copied = 0; @@ -1624,9 +1681,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_eat_recv_skb(sk, skb); if (!desc->count) break; - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); } - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); + + if (noack) + goto out; tcp_rcv_space_adjust(sk); @@ -1635,10 +1695,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } +out: return copied; } + +int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + return __tcp_read_sock(sk, desc, recv_actor, false, + &tcp_sk(sk)->copied_seq); +} EXPORT_SYMBOL(tcp_read_sock); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) +{ + return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq); +} + int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; @@ -1667,7 +1742,7 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) } return copied; } -EXPORT_SYMBOL(tcp_read_skb); +EXPORT_IPV6_MOD(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { @@ -1712,11 +1787,12 @@ int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } -EXPORT_SYMBOL(tcp_peek_len); +EXPORT_IPV6_MOD(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { + struct tcp_sock *tp = tcp_sk(sk); int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) @@ -1735,11 +1811,13 @@ int tcp_set_rcvlowat(struct sock *sk, int val) space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); - WRITE_ONCE(tcp_sk(sk)->window_clamp, val); + + if (tp->window_clamp && tp->window_clamp < val) + WRITE_ONCE(tp->window_clamp, val); } return 0; } -EXPORT_SYMBOL(tcp_set_rcvlowat); +EXPORT_IPV6_MOD(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) @@ -1772,7 +1850,7 @@ int tcp_mmap(struct file *file, struct socket *sock, vma->vm_ops = &tcp_vm_ops; return 0; } -EXPORT_SYMBOL(tcp_mmap); +EXPORT_IPV6_MOD(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) @@ -2438,14 +2516,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; - err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, - sizeof(dmabuf_cmsg), &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } sent += copy; @@ -2476,6 +2552,11 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, } niov = skb_frag_net_iov(frag); + if (!net_is_devmem_iov(niov)) { + err = -ENODEV; + goto out; + } + end = start + skb_frag_size(frag); copy = end - offset; @@ -2494,23 +2575,19 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, /* Will perform the exchange later */ dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; - dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + dmabuf_cmsg.dmabuf_id = net_devmem_iov_binding_id(niov); offset += copy; remaining_len -= copy; - err = put_cmsg(msg, SOL_SOCKET, - SO_DEVMEM_DMABUF, - sizeof(dmabuf_cmsg), - &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } - atomic_long_inc(&niov->pp_ref_count); + atomic_long_inc(&niov->desc.pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); sent += copy; @@ -2765,9 +2842,9 @@ found_ok_skb: err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, used); - if (err <= 0) { + if (err < 0) { if (!copied) - copied = -EFAULT; + copied = err; break; } @@ -2864,7 +2941,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, } return ret; } -EXPORT_SYMBOL(tcp_recvmsg); +EXPORT_IPV6_MOD(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { @@ -2994,7 +3071,7 @@ void tcp_shutdown(struct sock *sk, int how) tcp_send_fin(sk); } } -EXPORT_SYMBOL(tcp_shutdown); +EXPORT_IPV6_MOD(tcp_shutdown); int tcp_orphan_count_sum(void) { @@ -3046,8 +3123,8 @@ bool tcp_check_oom(const struct sock *sk, int shift) void __tcp_close(struct sock *sk, long timeout) { + bool data_was_unread = false; struct sk_buff *skb; - int data_was_unread = 0; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); @@ -3065,13 +3142,14 @@ void __tcp_close(struct sock *sk, long timeout) * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { - u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq; + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { + u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - len--; - data_was_unread += len; - __kfree_skb(skb); + end_seq--; + if (after(end_seq, tcp_sk(sk)->copied_seq)) + data_was_unread = true; + tcp_eat_recv_skb(sk, skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ @@ -3142,7 +3220,7 @@ adjudge_to_death: /* remove backlog if any, without releasing ownership. */ __release_sock(sk); - this_cpu_inc(tcp_orphan_count); + tcp_orphan_count_inc(); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) @@ -3174,7 +3252,7 @@ adjudge_to_death: const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { - inet_csk_reset_keepalive_timer(sk, + tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); @@ -3274,6 +3352,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + struct request_sock *req; u32 seq; if (old_state != TCP_CLOSE) @@ -3323,11 +3402,11 @@ int tcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; - icsk->icsk_probes_out = 0; + WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; - icsk->icsk_rto_min = TCP_RTO_MIN; - icsk->icsk_delack_max = TCP_DELACK_MAX; + WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN); + WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX); tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; @@ -3336,6 +3415,11 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; + tp->accecn_fail_mode = 0; + tp->saw_accecn_opt = TCP_ACCECN_OPT_NOT_SEEN; + tcp_accecn_init_counters(tp); + tp->prev_ecnfield = 0; + tp->accecn_opt_tstamp = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -3381,6 +3465,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; + tp->syn_fastopen_child = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; @@ -3388,6 +3473,10 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) + reqsk_fastopen_remove(sk, req, false); tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; @@ -3493,11 +3582,14 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); -EXPORT_SYMBOL(tcp_tx_delay_enabled); +EXPORT_IPV6_MOD(tcp_tx_delay_enabled); -static void tcp_enable_tx_delay(void) +static void tcp_enable_tx_delay(struct sock *sk, int val) { - if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { + struct tcp_sock *tp = tcp_sk(sk); + s32 delta = (val - tp->tcp_tx_delay) << 3; + + if (val && !static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { @@ -3505,6 +3597,22 @@ static void tcp_enable_tx_delay(void) pr_info("TCP_TX_DELAY enabled\n"); } } + /* If we change tcp_tx_delay on a live flow, adjust tp->srtt_us, + * tp->rtt_min, icsk_rto and sk->sk_pacing_rate. + * This is best effort. + */ + if (delta && sk->sk_state == TCP_ESTABLISHED) { + s64 srtt = (s64)tp->srtt_us + delta; + + tp->srtt_us = clamp_t(s64, srtt, 1, ~0U); + + /* Note: does not deal with non zero icsk_backoff */ + tcp_set_rto(sk); + + minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); + + tcp_update_pacing_rate(sk); + } } /* When set indicates to always queue non-full frames. Later the user clears @@ -3627,7 +3735,7 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; - inet_csk_reset_keepalive_timer(sk, elapsed); + tcp_reset_keepalive_timer(sk, elapsed); } return 0; @@ -3667,36 +3775,49 @@ EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { + u32 old_window_clamp, new_window_clamp, new_rcv_ssthresh; struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; WRITE_ONCE(tp->window_clamp, 0); - } else { - u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; - u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; + return 0; + } - if (new_window_clamp == old_window_clamp) - return 0; + old_window_clamp = tp->window_clamp; + new_window_clamp = max_t(int, SOCK_MIN_RCVBUF / 2, val); - WRITE_ONCE(tp->window_clamp, new_window_clamp); - if (new_window_clamp < old_window_clamp) { - /* need to apply the reserved mem provisioning only - * when shrinking the window clamp - */ - __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); + if (new_window_clamp == old_window_clamp) + return 0; - } else { - new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); - tp->rcv_ssthresh = max(new_rcv_ssthresh, - tp->rcv_ssthresh); - } + WRITE_ONCE(tp->window_clamp, new_window_clamp); + + /* Need to apply the reserved mem provisioning only + * when shrinking the window clamp. + */ + if (new_window_clamp < old_window_clamp) { + __tcp_adjust_rcv_ssthresh(sk, new_window_clamp); + } else { + new_rcv_ssthresh = min(tp->rcv_wnd, new_window_clamp); + tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } return 0; } +int tcp_sock_set_maxseg(struct sock *sk, int val) +{ + /* Values greater than interface MTU won't take effect. However + * at the point when this call is done we typically don't yet + * know which interface is going to be used + */ + if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) + return -EINVAL; + + WRITE_ONCE(tcp_sk(sk)->rx_opt.user_mss, val); + return 0; +} + /* * Socket option code for TCP. */ @@ -3802,23 +3923,34 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); return 0; + case TCP_RTO_MAX_MS: + if (val < MSEC_PER_SEC || val > TCP_RTO_MAX_SEC * MSEC_PER_SEC) + return -EINVAL; + WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val)); + return 0; + case TCP_RTO_MIN_US: { + int rto_min = usecs_to_jiffies(val); + + if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN) + return -EINVAL; + WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min); + return 0; + } + case TCP_DELACK_MAX_US: { + int delack_max = usecs_to_jiffies(val); + + if (delack_max > TCP_DELACK_MAX || delack_max < TCP_TIMEOUT_MIN) + return -EINVAL; + WRITE_ONCE(inet_csk(sk)->icsk_delack_max, delack_max); + return 0; + } + case TCP_MAXSEG: + return tcp_sock_set_maxseg(sk, val); } sockopt_lock_sock(sk); switch (optname) { - case TCP_MAXSEG: - /* Values greater than interface MTU won't take effect. However - * at the point when this call is done we typically don't yet - * know which interface is going to be used - */ - if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { - err = -EINVAL; - break; - } - tp->rx_opt.user_mss = val; - break; - case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; @@ -4007,8 +4139,12 @@ ao_parse: tp->recvmsg_inq = val; break; case TCP_TX_DELAY: - if (val) - tcp_enable_tx_delay(); + /* tp->srtt_us is u32, and is shifted by 3 */ + if (val < 0 || val >= (1U << (31 - 3))) { + err = -EINVAL; + break; + } + tcp_enable_tx_delay(sk, val); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: @@ -4031,7 +4167,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } -EXPORT_SYMBOL(tcp_setsockopt); +EXPORT_IPV6_MOD(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) @@ -4057,6 +4193,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); + const u8 ect1_idx = INET_ECN_ECT_1 - 1; + const u8 ect0_idx = INET_ECN_ECT_0 - 1; + const u8 ce_idx = INET_ECN_CE - 1; unsigned long rate; u32 now; u64 rate64; @@ -4107,7 +4246,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } - if (tp->ecn_flags & TCP_ECN_OK) + if (tcp_ecn_mode_any(tp)) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; @@ -4115,6 +4254,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; + if (tp->syn_fastopen_child) + info->tcpi_options |= TCPI_OPT_TFO_CHILD; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, @@ -4181,6 +4322,16 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; + info->tcpi_accecn_fail_mode = tp->accecn_fail_mode; + info->tcpi_accecn_opt_seen = tp->saw_accecn_opt; + info->tcpi_received_ce = tp->received_ce; + info->tcpi_delivered_e1_bytes = tp->delivered_ecn_bytes[ect1_idx]; + info->tcpi_delivered_e0_bytes = tp->delivered_ecn_bytes[ect0_idx]; + info->tcpi_delivered_ce_bytes = tp->delivered_ecn_bytes[ce_idx]; + info->tcpi_received_e1_bytes = tp->received_ecn_bytes[ect1_idx]; + info->tcpi_received_e0_bytes = tp->received_ecn_bytes[ect0_idx]; + info->tcpi_received_ce_bytes = tp->received_ecn_bytes[ce_idx]; + unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -4266,7 +4417,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); - nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); + nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, + READ_ONCE(inet_csk(sk)->icsk_retransmits)); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); @@ -4301,6 +4453,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); + int user_mss; int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) @@ -4314,9 +4467,10 @@ int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (tp->rx_opt.user_mss && + user_mss = READ_ONCE(tp->rx_opt.user_mss); + if (user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) - val = tp->rx_opt.user_mss; + val = user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; @@ -4638,6 +4792,15 @@ zerocopy_rcv_out: case TCP_IS_MPTCP: val = 0; break; + case TCP_RTO_MAX_MS: + val = jiffies_to_msecs(tcp_rto_max(sk)); + break; + case TCP_RTO_MIN_US: + val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min)); + break; + case TCP_DELACK_MAX_US: + val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_delack_max)); + break; default: return -ENOPROTOOPT; } @@ -4659,7 +4822,7 @@ bool tcp_bpf_bypass_getsockopt(int level, int optname) return false; } -EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); +EXPORT_IPV6_MOD(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -4673,57 +4836,50 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } -EXPORT_SYMBOL(tcp_getsockopt); +EXPORT_IPV6_MOD(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG -int tcp_md5_sigpool_id = -1; -EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); - -int tcp_md5_alloc_sigpool(void) +void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb, + unsigned int header_len) { - size_t scratch_size; - int ret; + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; + const struct skb_shared_info *shi = skb_shinfo(skb); + struct sk_buff *frag_iter; + unsigned int i; - scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); - ret = tcp_sigpool_alloc_ahash("md5", scratch_size); - if (ret >= 0) { - /* As long as any md5 sigpool was allocated, the return - * id would stay the same. Re-write the id only for the case - * when previously all MD5 keys were deleted and this call - * allocates the first MD5 key, which may return a different - * sigpool id than was used previously. - */ - WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ - return 0; - } - return ret; -} + md5_update(ctx, (const u8 *)tcp_hdr(skb) + header_len, head_data_len); -void tcp_md5_release_sigpool(void) -{ - tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); -} + for (i = 0; i < shi->nr_frags; ++i) { + const skb_frag_t *f = &shi->frags[i]; + u32 p_off, p_len, copied; + const void *vaddr; + struct page *p; -void tcp_md5_add_sigpool(void) -{ - tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); + skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), + p, p_off, p_len, copied) { + vaddr = kmap_local_page(p); + md5_update(ctx, vaddr + p_off, p_len); + kunmap_local(vaddr); + } + } + + skb_walk_frags(skb, frag_iter) + tcp_md5_hash_skb_data(ctx, frag_iter, 0); } +EXPORT_IPV6_MOD(tcp_md5_hash_skb_data); -int tcp_md5_hash_key(struct tcp_sigpool *hp, - const struct tcp_md5sig_key *key) +void tcp_md5_hash_key(struct md5_ctx *ctx, + const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ - struct scatterlist sg; - - sg_init_one(&sg, key->key, keylen); - ahash_request_set_crypt(hp->req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ - return data_race(crypto_ahash_update(hp->req)); + data_race(({ md5_update(ctx, key->key, keylen), 0; })); } -EXPORT_SYMBOL(tcp_md5_hash_key); +EXPORT_IPV6_MOD(tcp_md5_hash_key); /* Called with rcu_read_lock() */ static enum skb_drop_reason @@ -4732,19 +4888,16 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. - * We have 3 drop cases: - * o No MD5 hash and one expected. - * o MD5 hash and we're not expecting one. - * o MD5 hash and its wrong. + * We have 2 drop cases: + * o An MD5 signature is present, but we're not expecting one. + * o The MD5 signature is wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; - int genhash; key = tcp_md5_do_lookup(sk, l3index, saddr, family); - - if (!key && hash_location) { + if (!key) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; @@ -4755,11 +4908,10 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, * IPv4-mapped case. */ if (family == AF_INET) - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); + tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else - genhash = tp->af_specific->calc_md5_hash(newhash, key, - NULL, skb); - if (genhash || memcmp(hash_location, newhash, 16) != 0) { + tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); + if (memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; @@ -4843,7 +4995,7 @@ tcp_inbound_hash(struct sock *sk, const struct request_sock *req, return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, l3index, md5_location); } -EXPORT_SYMBOL_GPL(tcp_inbound_hash); +EXPORT_IPV6_MOD_GPL(tcp_inbound_hash); void tcp_done(struct sock *sk) { @@ -4964,9 +5116,10 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); +#if IS_ENABLED(CONFIG_TLS_DEVICE) + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, tcp_clean_acked); +#endif /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); @@ -4977,11 +5130,9 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); @@ -4992,7 +5143,6 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); /* TX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); @@ -5006,11 +5156,11 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, accecn_opt_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); @@ -5025,15 +5175,13 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ce); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ecn_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); - /* 32bit arches with 8byte alignment on u64 fields might need padding - * before tcp_clock_cache. - */ - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4); - /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); @@ -5044,12 +5192,12 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); } void __init tcp_init(void) @@ -5133,7 +5281,7 @@ void __init tcp_init(void) /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); - max_rshare = min(6UL*1024*1024, limit); + max_rshare = min(32UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; @@ -5149,6 +5297,6 @@ void __init tcp_init(void) tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); - tcp_tasklet_init(); + tcp_tsq_work_init(); mptcp_init(); } diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index bbb8d5f0eae7..34b8450829d0 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -268,9 +268,8 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head) kfree_sensitive(key); } -static void tcp_ao_info_free_rcu(struct rcu_head *head) +static void tcp_ao_info_free(struct tcp_ao_info *ao) { - struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu); struct tcp_ao_key *key; struct hlist_node *n; @@ -310,7 +309,7 @@ void tcp_ao_destroy_sock(struct sock *sk, bool twsk) if (!twsk) tcp_ao_sk_omem_free(sk, ao); - call_rcu(&ao->rcu, tcp_ao_info_free_rcu); + tcp_ao_info_free(ao); } void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) @@ -1178,7 +1177,9 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) if (!ao) return; - WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); ao->rcv_sne = 0; hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 370993c03d31..a268e1595b22 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; - if (!sk_wmem_schedule(sk, size)) { + if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); @@ -406,8 +408,11 @@ more_data: if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); - if (!psock->cork) + if (!psock->cork) { + sk_msg_free(sk, msg); + *copied = 0; return -ENOMEM; + } } memcpy(psock->cork, msg, sizeof(*msg)); return 0; @@ -441,7 +446,6 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, tosend); release_sock(sk); origsize = msg->sg.size; @@ -453,8 +457,9 @@ more_data: sock_put(sk_redir); lock_sock(sk); + sk_mem_uncharge(sk, sent); if (unlikely(ret < 0)) { - int free = sk_msg_free_nocharge(sk, msg); + int free = sk_msg_free(sk, msg); if (!cork) *copied -= free; @@ -468,7 +473,7 @@ more_data: break; case __SK_DROP: default: - sk_msg_free_partial(sk, msg, tosend); + sk_msg_free(sk, msg); sk_msg_apply_bytes(psock, tosend); *copied -= (tosend + delta); return -EACCES; @@ -484,11 +489,8 @@ more_data: } if (msg && msg->sg.data[msg->sg.start].page_link && - msg->sg.data[msg->sg.start].length) { - if (eval == __SK_REDIRECT) - sk_mem_charge(sk, tosend - sent); + msg->sg.data[msg->sg.start].length) goto more_data; - } } return ret; } @@ -496,7 +498,7 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int copied = 0, err = 0; + int copied = 0, err = 0, ret = 0; struct sk_psock *psock; long timeo; int flags; @@ -539,14 +541,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = msg_tx->sg.size - osize; } - err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); - if (err < 0) { + if (ret < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } - copied += copy; + copied += ret; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; @@ -647,6 +649,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops) ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct sock *sk = strp->sk; + struct sk_psock *psock; + struct tcp_sock *tp; + int copied = 0; + + tp = tcp_sk(sk); + rcu_read_lock(); + psock = sk_psock(sk); + if (WARN_ON_ONCE(!psock)) { + desc->error = -EINVAL; + goto out; + } + + psock->ingress_bytes = 0; + copied = tcp_read_sock_noack(sk, desc, recv_actor, true, + &psock->copied_seq); + if (copied < 0) + goto out; + /* recv_actor may redirect skb to another socket (SK_REDIRECT) or + * just put skb into ingress queue of current socket (SK_PASS). + * For SK_REDIRECT, we need to ack the frame immediately but for + * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser(). + */ + tp->copied_seq = psock->copied_seq - psock->ingress_bytes; + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes); +out: + rcu_read_unlock(); + return copied; +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index ba4d98e510e0..fbad6c35dee9 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -379,7 +379,7 @@ static void tcp_cdg_init(struct sock *sk) /* We silently fall back to window = 1 if allocation fails. */ if (window > 1) ca->gradients = kcalloc(window, sizeof(ca->gradients[0]), - GFP_NOWAIT | __GFP_NOWARN); + GFP_NOWAIT); ca->rtt_seq = tp->snd_nxt; ca->shadow_wnd = tcp_snd_cwnd(tp); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5dbed91c6178..76c23675ae50 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -392,6 +392,10 @@ static void hystart_update(struct sock *sk, u32 delay) if (after(tp->snd_una, ca->end_seq)) bictcp_hystart_reset(sk); + /* hystart triggers when cwnd is larger than some threshold */ + if (tcp_snd_cwnd(tp) < hystart_low_window) + return; + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); @@ -467,9 +471,7 @@ __bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; - /* hystart triggers when cwnd is larger than some threshold */ - if (!ca->found && tcp_in_slow_start(tp) && hystart && - tcp_snd_cwnd(tp) >= hystart_low_window) + if (!ca->found && tcp_in_slow_start(tp) && hystart) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 8a45a4aea933..03abe0848420 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -90,7 +90,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - if ((tp->ecn_flags & TCP_ECN_OK) || + if (tcp_ecn_mode_any(tp) || (sk->sk_state == TCP_LISTEN || sk->sk_state == TCP_CLOSE)) { struct dctcp *ca = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_dctcp.h b/net/ipv4/tcp_dctcp.h index d69a77cbd0c7..4b0259111d81 100644 --- a/net/ipv4/tcp_dctcp.h +++ b/net/ipv4/tcp_dctcp.h @@ -28,7 +28,7 @@ static inline void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, */ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { dctcp_ece_ack_cwr(sk, *ce_state); - __tcp_send_ack(sk, *prior_rcv_nxt); + __tcp_send_ack(sk, *prior_rcv_nxt, 0); } inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index f428ecf9120f..d83efd91f461 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -12,6 +12,9 @@ #include <linux/tcp.h> +#include <net/inet_hashtables.h> +#include <net/inet6_hashtables.h> +#include <net/inet_timewait_sock.h> #include <net/netlink.h> #include <net/tcp.h> @@ -83,7 +86,7 @@ static int tcp_diag_put_md5sig(struct sk_buff *skb, #endif static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk, - const struct tcp_ulp_ops *ulp_ops) + const struct tcp_ulp_ops *ulp_ops, bool net_admin) { struct nlattr *nest; int err; @@ -97,7 +100,7 @@ static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk, goto nla_failure; if (ulp_ops->get_info) - err = ulp_ops->get_info(sk, skb); + err = ulp_ops->get_info(sk, skb, net_admin); if (err) goto nla_failure; @@ -113,6 +116,7 @@ static int tcp_diag_get_aux(struct sock *sk, bool net_admin, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_ulp_ops *ulp_ops; int err = 0; #ifdef CONFIG_TCP_MD5SIG @@ -129,15 +133,13 @@ static int tcp_diag_get_aux(struct sock *sk, bool net_admin, } #endif - if (net_admin) { - const struct tcp_ulp_ops *ulp_ops; - - ulp_ops = icsk->icsk_ulp_ops; - if (ulp_ops) - err = tcp_diag_put_ulp(skb, sk, ulp_ops); - if (err) + ulp_ops = icsk->icsk_ulp_ops; + if (ulp_ops) { + err = tcp_diag_put_ulp(skb, sk, ulp_ops, net_admin); + if (err < 0) return err; } + return 0; } @@ -164,7 +166,7 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) } #endif - if (net_admin && sk_fullsock(sk)) { + if (sk_fullsock(sk)) { const struct tcp_ulp_ops *ulp_ops; ulp_ops = icsk->icsk_ulp_ops; @@ -172,30 +174,468 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) size += nla_total_size(0) + nla_total_size(TCP_ULP_NAME_MAX); if (ulp_ops->get_info_size) - size += ulp_ops->get_info_size(sk); + size += ulp_ops->get_info_size(sk, net_admin); } } - return size; + + return size + + nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + +static int tcp_twsk_diag_fill(struct sock *sk, + struct sk_buff *skb, + struct netlink_callback *cb, + u16 nlmsg_flags, bool net_admin) +{ + struct inet_timewait_sock *tw = inet_twsk(sk); + struct inet_diag_msg *r; + struct nlmsghdr *nlh; + long tmo; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, + sizeof(*r), nlmsg_flags); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); + DEBUG_NET_WARN_ON_ONCE(tw->tw_state != TCP_TIME_WAIT); + + inet_diag_msg_common_fill(r, sk); + r->idiag_retrans = 0; + + r->idiag_state = READ_ONCE(tw->tw_substate); + r->idiag_timer = 3; + tmo = tw->tw_timer.expires - jiffies; + r->idiag_expires = jiffies_delta_to_msecs(tmo); + r->idiag_rqueue = 0; + r->idiag_wqueue = 0; + r->idiag_uid = 0; + r->idiag_inode = 0; + + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + tw->tw_mark)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + + nlmsg_end(skb, nlh); + return 0; +} + +static int tcp_req_diag_fill(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + u16 nlmsg_flags, bool net_admin) +{ + struct request_sock *reqsk = inet_reqsk(sk); + struct inet_diag_msg *r; + struct nlmsghdr *nlh; + long tmo; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); + inet_diag_msg_common_fill(r, sk); + r->idiag_state = TCP_SYN_RECV; + r->idiag_timer = 1; + r->idiag_retrans = READ_ONCE(reqsk->num_retrans); + + BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != + offsetof(struct sock, sk_cookie)); + + tmo = READ_ONCE(inet_reqsk(sk)->rsk_timer.expires) - jiffies; + r->idiag_expires = jiffies_delta_to_msecs(tmo); + r->idiag_rqueue = 0; + r->idiag_wqueue = 0; + r->idiag_uid = 0; + r->idiag_inode = 0; + + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + + nlmsg_end(skb, nlh); + return 0; +} + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, + u16 nlmsg_flags, bool net_admin) +{ + if (sk->sk_state == TCP_TIME_WAIT) + return tcp_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); + + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); + + return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags, + net_admin); +} + +static void twsk_build_assert(void) +{ + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != + offsetof(struct sock, sk_family)); + + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) != + offsetof(struct inet_sock, inet_num)); + + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) != + offsetof(struct inet_sock, inet_dport)); + + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) != + offsetof(struct inet_sock, inet_rcv_saddr)); + + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) != + offsetof(struct inet_sock, inet_daddr)); + +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) != + offsetof(struct sock, sk_v6_rcv_saddr)); + + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) != + offsetof(struct sock, sk_v6_daddr)); +#endif } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { - struct inet_hashinfo *hinfo; + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); + struct inet_diag_dump_data *cb_data = cb->data; + struct net *net = sock_net(skb->sk); + u32 idiag_states = r->idiag_states; + struct inet_hashinfo *hashinfo; + int i, num, s_i, s_num; + struct sock *sk; + + hashinfo = net->ipv4.tcp_death_row.hashinfo; + if (idiag_states & TCPF_SYN_RECV) + idiag_states |= TCPF_NEW_SYN_RECV; + s_i = cb->args[1]; + s_num = num = cb->args[2]; + + if (cb->args[0] == 0) { + if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport) + goto skip_listen_ht; + + for (i = s_i; i <= hashinfo->lhash2_mask; i++) { + struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; + + num = 0; + ilb = &hashinfo->lhash2[i]; + + if (hlist_nulls_empty(&ilb->nulls_head)) { + s_num = 0; + continue; + } + spin_lock(&ilb->lock); + sk_nulls_for_each(sk, node, &ilb->nulls_head) { + struct inet_sock *inet = inet_sk(sk); + + if (!net_eq(sock_net(sk), net)) + continue; + + if (num < s_num) { + num++; + continue; + } + + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next_listen; + + if (r->id.idiag_sport != inet->inet_sport && + r->id.idiag_sport) + goto next_listen; + + if (!inet_diag_bc_sk(cb_data, sk)) + goto next_listen; + + if (inet_sk_diag_fill(sk, inet_csk(sk), skb, + cb, r, NLM_F_MULTI, + net_admin) < 0) { + spin_unlock(&ilb->lock); + goto done; + } + +next_listen: + ++num; + } + spin_unlock(&ilb->lock); + + s_num = 0; + } +skip_listen_ht: + cb->args[0] = 1; + s_i = num = s_num = 0; + } + +/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets + * with bh disabled. + */ +#define SKARR_SZ 16 + + /* Dump bound but inactive (not listening, connecting, etc.) sockets */ + if (cb->args[0] == 1) { + if (!(idiag_states & TCPF_BOUND_INACTIVE)) + goto skip_bind_ht; + + for (i = s_i; i < hashinfo->bhash_size; i++) { + struct inet_bind_hashbucket *ibb; + struct inet_bind2_bucket *tb2; + struct sock *sk_arr[SKARR_SZ]; + int num_arr[SKARR_SZ]; + int idx, accum, res; + +resume_bind_walk: + num = 0; + accum = 0; + ibb = &hashinfo->bhash2[i]; + + if (hlist_empty(&ibb->chain)) { + s_num = 0; + continue; + } + spin_lock_bh(&ibb->lock); + inet_bind_bucket_for_each(tb2, &ibb->chain) { + if (!net_eq(ib2_net(tb2), net)) + continue; + + sk_for_each_bound(sk, &tb2->owners) { + struct inet_sock *inet = inet_sk(sk); + + if (num < s_num) + goto next_bind; + + if (sk->sk_state != TCP_CLOSE || + !inet->inet_num) + goto next_bind; + + if (r->sdiag_family != AF_UNSPEC && + r->sdiag_family != sk->sk_family) + goto next_bind; + + if (!inet_diag_bc_sk(cb_data, sk)) + goto next_bind; + + sock_hold(sk); + num_arr[accum] = num; + sk_arr[accum] = sk; + if (++accum == SKARR_SZ) + goto pause_bind_walk; +next_bind: + num++; + } + } +pause_bind_walk: + spin_unlock_bh(&ibb->lock); + + res = 0; + for (idx = 0; idx < accum; idx++) { + if (res >= 0) { + res = inet_sk_diag_fill(sk_arr[idx], + NULL, skb, cb, + r, NLM_F_MULTI, + net_admin); + if (res < 0) + num = num_arr[idx]; + } + sock_put(sk_arr[idx]); + } + if (res < 0) + goto done; + + cond_resched(); + + if (accum == SKARR_SZ) { + s_num = num + 1; + goto resume_bind_walk; + } + + s_num = 0; + } +skip_bind_ht: + cb->args[0] = 2; + s_i = num = s_num = 0; + } + + if (!(idiag_states & ~TCPF_LISTEN)) + goto out; + + for (i = s_i; i <= hashinfo->ehash_mask; i++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[i]; + spinlock_t *lock = inet_ehash_lockp(hashinfo, i); + struct hlist_nulls_node *node; + struct sock *sk_arr[SKARR_SZ]; + int num_arr[SKARR_SZ]; + int idx, accum, res; + + if (hlist_nulls_empty(&head->chain)) + continue; + + if (i > s_i) + s_num = 0; + +next_chunk: + num = 0; + accum = 0; + spin_lock_bh(lock); + sk_nulls_for_each(sk, node, &head->chain) { + int state; + + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) + goto next_normal; + state = (sk->sk_state == TCP_TIME_WAIT) ? + READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; + if (!(idiag_states & (1 << state))) + goto next_normal; + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next_normal; + if (r->id.idiag_sport != htons(sk->sk_num) && + r->id.idiag_sport) + goto next_normal; + if (r->id.idiag_dport != sk->sk_dport && + r->id.idiag_dport) + goto next_normal; + twsk_build_assert(); + + if (!inet_diag_bc_sk(cb_data, sk)) + goto next_normal; + + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + goto next_normal; + + num_arr[accum] = num; + sk_arr[accum] = sk; + if (++accum == SKARR_SZ) + break; +next_normal: + ++num; + } + spin_unlock_bh(lock); + + res = 0; + for (idx = 0; idx < accum; idx++) { + if (res >= 0) { + res = sk_diag_fill(sk_arr[idx], skb, cb, r, + NLM_F_MULTI, net_admin); + if (res < 0) + num = num_arr[idx]; + } + sock_gen_put(sk_arr[idx]); + } + if (res < 0) + break; + + cond_resched(); + + if (accum == SKARR_SZ) { + s_num = num + 1; + goto next_chunk; + } + } + +done: + cb->args[1] = i; + cb->args[2] = num; +out: + ; +} + +static struct sock *tcp_diag_find_one_icsk(struct net *net, + const struct inet_diag_req_v2 *req) +{ + struct sock *sk; + + rcu_read_lock(); + if (req->sdiag_family == AF_INET) { + sk = inet_lookup(net, NULL, 0, req->id.idiag_dst[0], + req->id.idiag_dport, req->id.idiag_src[0], + req->id.idiag_sport, req->id.idiag_if); +#if IS_ENABLED(CONFIG_IPV6) + } else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, NULL, 0, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, NULL, 0, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); +#endif + } else { + rcu_read_unlock(); + return ERR_PTR(-EINVAL); + } + rcu_read_unlock(); + if (!sk) + return ERR_PTR(-ENOENT); - hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; + if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { + sock_gen_put(sk); + return ERR_PTR(-ENOENT); + } - inet_diag_dump_icsk(hinfo, skb, cb, r); + return sk; } static int tcp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - struct inet_hashinfo *hinfo; + struct sk_buff *in_skb = cb->skb; + struct sk_buff *rep; + struct sock *sk; + struct net *net; + bool net_admin; + int err; + + net = sock_net(in_skb->sk); + sk = tcp_diag_find_one_icsk(net, req); + if (IS_ERR(sk)) + return PTR_ERR(sk); + + net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); + rep = nlmsg_new(tcp_diag_get_aux_size(sk, net_admin), GFP_KERNEL); + if (!rep) { + err = -ENOMEM; + goto out; + } + + err = sk_diag_fill(sk, rep, cb, req, 0, net_admin); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + nlmsg_free(rep); + goto out; + } + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); - hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; +out: + if (sk) + sock_gen_put(sk); - return inet_diag_dump_one_icsk(hinfo, cb, req); + return err; } #ifdef CONFIG_INET_DIAG_DESTROY @@ -203,13 +643,10 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { struct net *net = sock_net(in_skb->sk); - struct inet_hashinfo *hinfo; struct sock *sk; int err; - hinfo = net->ipv4.tcp_death_row.hashinfo; - sk = inet_diag_find_one_icsk(net, hinfo, req); - + sk = tcp_diag_find_one_icsk(net, req); if (IS_ERR(sk)) return PTR_ERR(sk); @@ -227,7 +664,6 @@ static const struct inet_diag_handler tcp_diag_handler = { .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_get_aux = tcp_diag_get_aux, - .idiag_get_aux_size = tcp_diag_get_aux_size, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), #ifdef CONFIG_INET_DIAG_DESTROY diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 0f523cbfe329..7d945a527daf 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -3,6 +3,7 @@ #include <linux/tcp.h> #include <linux/rcupdate.h> #include <net/tcp.h> +#include <net/busy_poll.h> void tcp_fastopen_init_key_once(struct net *net) { @@ -178,7 +179,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) if (!skb) return; - skb_dst_drop(skb); + tcp_cleanup_skb(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects @@ -195,7 +196,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, @@ -274,11 +275,13 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, * because it's been added to the accept queue directly. */ req->timeout = tcp_timeout_init(child); - inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, - req->timeout, TCP_RTO_MAX); + tcp_reset_xmit_timer(child, ICSK_TIME_RETRANS, + req->timeout, false); refcount_set(&req->rsk_refcnt, 2); + sk_mark_napi_id_set(child, skb); + /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); @@ -401,6 +404,7 @@ fastopen: } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); + tcp_sk(child)->syn_fastopen_child = 1; return child; } NET_INC_STATS(sock_net(sk), @@ -468,7 +472,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) } return false; } -EXPORT_SYMBOL(tcp_fastopen_defer_connect); +EXPORT_IPV6_MOD(tcp_fastopen_defer_connect); /* * The following code block is to deal with middle box issues with TFO: @@ -555,6 +559,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net_device *dev; struct dst_entry *dst; struct sk_buff *skb; @@ -571,10 +576,12 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) } } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { - dst = sk_dst_get(sk); - if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) + rcu_read_lock(); + dst = __sk_dst_get(sk); + dev = dst ? dst_dev_rcu(dst) : NULL; + if (!(dev && (dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); - dst_release(dst); + rcu_read_unlock(); } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5bdf13ac26ef..198f8a0d37be 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -70,8 +70,10 @@ #include <linux/sysctl.h> #include <linux/kernel.h> #include <linux/prefetch.h> +#include <linux/bitops.h> #include <net/dst.h> #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/proto_memory.h> #include <net/inet_common.h> #include <linux/ipsec.h> @@ -102,6 +104,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE; #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ #define FLAG_ACK_MAYBE_DELAYED 0x10000 /* Likely a delayed ACK */ #define FLAG_DSACK_TLP 0x20000 /* DSACK for tail loss probe */ +#define FLAG_TS_PROGRESS 0x40000 /* Positive timestamp delta */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -118,18 +121,18 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE; #if IS_ENABLED(CONFIG_TLS_DEVICE) static DEFINE_STATIC_KEY_DEFERRED_FALSE(clean_acked_data_enabled, HZ); -void clean_acked_data_enable(struct inet_connection_sock *icsk, +void clean_acked_data_enable(struct tcp_sock *tp, void (*cad)(struct sock *sk, u32 ack_seq)) { - icsk->icsk_clean_acked = cad; + tp->tcp_clean_acked = cad; static_branch_deferred_inc(&clean_acked_data_enabled); } EXPORT_SYMBOL_GPL(clean_acked_data_enable); -void clean_acked_data_disable(struct inet_connection_sock *icsk) +void clean_acked_data_disable(struct tcp_sock *tp) { static_branch_slow_dec_deferred(&clean_acked_data_enabled); - icsk->icsk_clean_acked = NULL; + tp->tcp_clean_acked = NULL; } EXPORT_SYMBOL_GPL(clean_acked_data_disable); @@ -169,6 +172,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB; sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); @@ -185,6 +189,7 @@ static void bpf_skops_established(struct sock *sk, int bpf_op, memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = bpf_op; sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ if (skb) @@ -243,9 +248,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; - if (old_ratio != tcp_sk(sk)->scaling_ratio) - WRITE_ONCE(tcp_sk(sk)->window_clamp, - tcp_win_from_space(sk, sk->sk_rcvbuf)); + if (old_ratio != tcp_sk(sk)->scaling_ratio) { + struct tcp_sock *tp = tcp_sk(sk); + + val = tcp_win_from_space(sk, sk->sk_rcvbuf); + tcp_set_window_clamp(sk, val); + + if (tp->window_clamp < tp->rcvq_space.space) + tp->rcvq_space.space = tp->window_clamp; + } } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -325,41 +336,18 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); - const struct dst_entry *dst = __sk_dst_get(sk); - return (dst && dst_metric(dst, RTAX_QUICKACK)) || + return icsk->icsk_ack.dst_quick_ack || (icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk)); } -static void tcp_ecn_queue_cwr(struct tcp_sock *tp) -{ - if (tp->ecn_flags & TCP_ECN_OK) - tp->ecn_flags |= TCP_ECN_QUEUE_CWR; -} - -static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) -{ - if (tcp_hdr(skb)->cwr) { - tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - - /* If the sender is telling us it has entered CWR, then its - * cwnd may be very low (even just 1 packet), so we should ACK - * immediately. - */ - if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; - } -} - -static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) -{ - tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; -} - -static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) +static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + if (tcp_ecn_disabled(tp)) + return; + switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) { case INET_ECN_NOT_ECT: /* Funny extension: if ECT is not set on a segment, @@ -373,44 +361,222 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) if (tcp_ca_needs_ecn(sk)) tcp_ca_event(sk, CA_EVENT_ECN_IS_CE); - if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { + if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR) && + tcp_ecn_mode_rfc3168(tp)) { /* Better not delay acks, sender can have a very low cwnd */ tcp_enter_quickack_mode(sk, 2); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } + /* As for RFC3168 ECN, the TCP_ECN_SEEN flag is set by + * tcp_data_ecn_check() when the ECN codepoint of + * received TCP data contains ECT(0), ECT(1), or CE. + */ + if (!tcp_ecn_mode_rfc3168(tp)) + break; tp->ecn_flags |= TCP_ECN_SEEN; break; default: if (tcp_ca_needs_ecn(sk)) tcp_ca_event(sk, CA_EVENT_ECN_NO_CE); + if (!tcp_ecn_mode_rfc3168(tp)) + break; tp->ecn_flags |= TCP_ECN_SEEN; break; } } -static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) +/* Returns true if the byte counters can be used */ +static bool tcp_accecn_process_option(struct tcp_sock *tp, + const struct sk_buff *skb, + u32 delivered_bytes, int flag) { - if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK) - __tcp_ecn_check_ce(sk, skb); + u8 estimate_ecnfield = tp->est_ecnfield; + bool ambiguous_ecn_bytes_incr = false; + bool first_changed = false; + unsigned int optlen; + bool order1, res; + unsigned int i; + u8 *ptr; + + if (tcp_accecn_opt_fail_recv(tp)) + return false; + + if (!(flag & FLAG_SLOWPATH) || !tp->rx_opt.accecn) { + if (!tp->saw_accecn_opt) { + /* Too late to enable after this point due to + * potential counter wraps + */ + if (tp->bytes_sent >= (1 << 23) - 1) { + u8 saw_opt = TCP_ACCECN_OPT_FAIL_SEEN; + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + } + return false; + } + + if (estimate_ecnfield) { + u8 ecnfield = estimate_ecnfield - 1; + + tp->delivered_ecn_bytes[ecnfield] += delivered_bytes; + return true; + } + return false; + } + + ptr = skb_transport_header(skb) + tp->rx_opt.accecn; + optlen = ptr[1] - 2; + if (WARN_ON_ONCE(ptr[0] != TCPOPT_ACCECN0 && ptr[0] != TCPOPT_ACCECN1)) + return false; + order1 = (ptr[0] == TCPOPT_ACCECN1); + ptr += 2; + + if (tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + tp->saw_accecn_opt = tcp_accecn_option_init(skb, + tp->rx_opt.accecn); + if (tp->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_OPT_FAIL_RECV); + } + + res = !!estimate_ecnfield; + for (i = 0; i < 3; i++) { + u32 init_offset; + u8 ecnfield; + s32 delta; + u32 *cnt; + + if (optlen < TCPOLEN_ACCECN_PERFIELD) + break; + + ecnfield = tcp_accecn_optfield_to_ecnfield(i, order1); + init_offset = tcp_accecn_field_init_offset(ecnfield); + cnt = &tp->delivered_ecn_bytes[ecnfield - 1]; + delta = tcp_update_ecn_bytes(cnt, ptr, init_offset); + if (delta && delta < 0) { + res = false; + ambiguous_ecn_bytes_incr = true; + } + if (delta && ecnfield != estimate_ecnfield) { + if (!first_changed) { + tp->est_ecnfield = ecnfield; + first_changed = true; + } else { + res = false; + ambiguous_ecn_bytes_incr = true; + } + } + + optlen -= TCPOLEN_ACCECN_PERFIELD; + ptr += TCPOLEN_ACCECN_PERFIELD; + } + if (ambiguous_ecn_bytes_incr) + tp->est_ecnfield = 0; + + return res; } -static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th) +static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count) { - if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr)) - tp->ecn_flags &= ~TCP_ECN_OK; + tp->delivered_ce += ecn_count; } -static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th) +/* Updates the delivered and delivered_ce counts */ +static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, + bool ece_ack) { - if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr)) - tp->ecn_flags &= ~TCP_ECN_OK; + tp->delivered += delivered; + if (tcp_ecn_mode_rfc3168(tp) && ece_ack) + tcp_count_delivered_ce(tp, delivered); } -static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th) +/* Returns the ECN CE delta */ +static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, + u32 delivered_pkts, u32 delivered_bytes, + int flag) { - if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK)) - return true; - return false; + u32 old_ceb = tcp_sk(sk)->delivered_ecn_bytes[INET_ECN_CE - 1]; + const struct tcphdr *th = tcp_hdr(skb); + struct tcp_sock *tp = tcp_sk(sk); + u32 delta, safe_delta, d_ceb; + bool opt_deltas_valid; + u32 corrected_ace; + + /* Reordered ACK or uncertain due to lack of data to send and ts */ + if (!(flag & (FLAG_FORWARD_PROGRESS | FLAG_TS_PROGRESS))) + return 0; + + opt_deltas_valid = tcp_accecn_process_option(tp, skb, + delivered_bytes, flag); + + if (!(flag & FLAG_SLOWPATH)) { + /* AccECN counter might overflow on large ACKs */ + if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK) + return 0; + } + + /* ACE field is not available during handshake */ + if (flag & FLAG_SYN_ACKED) + return 0; + + if (tp->received_ce_pending >= TCP_ACCECN_ACE_MAX_DELTA) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + + corrected_ace = tcp_accecn_ace(th) - TCP_ACCECN_CEP_INIT_OFFSET; + delta = (corrected_ace - tp->delivered_ce) & TCP_ACCECN_CEP_ACE_MASK; + if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK) + return delta; + + safe_delta = delivered_pkts - + ((delivered_pkts - delta) & TCP_ACCECN_CEP_ACE_MASK); + + if (opt_deltas_valid) { + d_ceb = tp->delivered_ecn_bytes[INET_ECN_CE - 1] - old_ceb; + if (!d_ceb) + return delta; + + if ((delivered_pkts >= (TCP_ACCECN_CEP_ACE_MASK + 1) * 2) && + (tcp_is_sack(tp) || + ((1 << inet_csk(sk)->icsk_ca_state) & + (TCPF_CA_Open | TCPF_CA_CWR)))) { + u32 est_d_cep; + + if (delivered_bytes <= d_ceb) + return safe_delta; + + est_d_cep = DIV_ROUND_UP_ULL((u64)d_ceb * + delivered_pkts, + delivered_bytes); + return min(safe_delta, + delta + + (est_d_cep & ~TCP_ACCECN_CEP_ACE_MASK)); + } + + if (d_ceb > delta * tp->mss_cache) + return safe_delta; + if (d_ceb < + safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT) + return delta; + } + + return safe_delta; +} + +static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, + u32 delivered_pkts, u32 delivered_bytes, + int *flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + u32 delta; + + delta = __tcp_accecn_process(sk, skb, delivered_pkts, + delivered_bytes, *flag); + if (delta > 0) { + tcp_count_delivered_ce(tp, delta); + *flag |= FLAG_ECE; + /* Recalculate header predictor */ + if (tp->pred_flags) + tcp_fast_path_on(tp); + } + return delta; } /* Buffer size and advertised window tuning. @@ -630,7 +796,7 @@ void tcp_initialize_rcv_mss(struct sock *sk) inet_csk(sk)->icsk_ack.rcv_mss = hint; } -EXPORT_SYMBOL(tcp_initialize_rcv_mss); +EXPORT_IPV6_MOD(tcp_initialize_rcv_mss); /* Receiver "autotuning" code. * @@ -645,10 +811,12 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss); */ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) { - u32 new_sample = tp->rcv_rtt_est.rtt_us; - long m = sample; + u32 new_sample, old_sample = tp->rcv_rtt_est.rtt_us; + long m = sample << 3; - if (new_sample != 0) { + if (old_sample == 0 || m < old_sample) { + new_sample = m; + } else { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially * with chatty applications or bulk transfer apps which @@ -659,17 +827,12 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) * else with timestamps disabled convergence takes too * long. */ - if (!win_dep) { - m -= (new_sample >> 3); - new_sample += m; - } else { - m <<= 3; - if (m < new_sample) - new_sample = m; - } - } else { - /* No previous measure. */ - new_sample = m << 3; + if (win_dep) + return; + /* Do not use this sample if receive queue is not empty. */ + if (tp->rcv_nxt != tp->copied_seq) + return; + new_sample = old_sample - (old_sample >> 3) + sample; } tp->rcv_rtt_est.rtt_us = new_sample; @@ -693,7 +856,7 @@ new_measure: tp->rcv_rtt_est.time = tp->tcp_mstamp; } -static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp) +static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp, u32 min_delta) { u32 delta, delta_us; @@ -703,7 +866,7 @@ static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp) if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { if (!delta) - delta = 1; + delta = min_delta; delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); return delta_us; } @@ -721,13 +884,58 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, if (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { - s32 delta = tcp_rtt_tsopt_us(tp); + s32 delta = tcp_rtt_tsopt_us(tp, 0); - if (delta >= 0) + if (delta > 0) tcp_rcv_rtt_update(tp, delta, 0); } } +void tcp_rcvbuf_grow(struct sock *sk, u32 newval) +{ + const struct net *net = sock_net(sk); + struct tcp_sock *tp = tcp_sk(sk); + u32 rcvwin, rcvbuf, cap, oldval; + u32 rtt_threshold, rtt_us; + u64 grow; + + oldval = tp->rcvq_space.space; + tp->rcvq_space.space = newval; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || + (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) + return; + + /* DRS is always one RTT late. */ + rcvwin = newval << 1; + + rtt_us = tp->rcv_rtt_est.rtt_us >> 3; + rtt_threshold = READ_ONCE(net->ipv4.sysctl_tcp_rcvbuf_low_rtt); + if (rtt_us < rtt_threshold) { + /* For small RTT, we set @grow to rcvwin * rtt_us/rtt_threshold. + * It might take few additional ms to reach 'line rate', + * but will avoid sk_rcvbuf inflation and poor cache use. + */ + grow = div_u64((u64)rcvwin * rtt_us, rtt_threshold); + } else { + /* slow start: allow the sender to double its rate. */ + grow = div_u64(((u64)rcvwin << 1) * (newval - oldval), oldval); + } + rcvwin += grow; + + if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) + rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt; + + cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]); + + rcvbuf = min_t(u32, tcp_space_from_win(sk, rcvwin), cap); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); + } +} /* * This function should be called every time data is copied to user space. * It calculates the appropriate TCP receive buffer space. @@ -735,56 +943,32 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, void tcp_rcv_space_adjust(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - u32 copied; - int time; + int time, inq, copied; trace_tcp_rcv_space_adjust(sk); - tcp_mstamp_refresh(tp); + if (unlikely(!tp->rcv_rtt_est.rtt_us)) + return; + + /* We do not refresh tp->tcp_mstamp here. + * Some platforms have expensive ktime_get() implementations. + * Using the last cached value is enough for DRS. + */ time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); - if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) + if (time < (tp->rcv_rtt_est.rtt_us >> 3)) return; /* Number of bytes copied to user in last RTT */ copied = tp->copied_seq - tp->rcvq_space.seq; + /* Number of bytes in receive queue. */ + inq = tp->rcv_nxt - tp->copied_seq; + copied -= inq; if (copied <= tp->rcvq_space.space) goto new_measure; - /* A bit of theory : - * copied = bytes received in previous RTT, our base window - * To cope with packet losses, we need a 2x factor - * To cope with slow start, and sender growing its cwin by 100 % - * every RTT, we need a 4x factor, because the ACK we are sending - * now is for the next RTT, not the current one : - * <prev RTT . ><current RTT .. ><next RTT .... > - */ - - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && - !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - u64 rcvwin, grow; - int rcvbuf; + trace_tcp_rcvbuf_grow(sk, time); - /* minimal window to cope with packet losses, assuming - * steady state. Add some cushion because of small variations. - */ - rcvwin = ((u64)copied << 1) + 16 * tp->advmss; - - /* Accommodate for sender rate increase (eg. slow start) */ - grow = rcvwin * (copied - tp->rcvq_space.space); - do_div(grow, tp->rcvq_space.space); - rcvwin += (grow << 1); - - rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); - } - } - tp->rcvq_space.space = copied; + tcp_rcvbuf_grow(sk, copied); new_measure: tp->rcvq_space.seq = tp->copied_seq; @@ -851,7 +1035,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) icsk->icsk_ack.lrcvtime = now; tcp_save_lrcv_flowlabel(sk, skb); - tcp_ecn_check_ce(sk, skb); + tcp_data_ecn_check(sk, skb); if (skb->len >= 128) tcp_grow_window(sk, skb, true); @@ -934,7 +1118,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->srtt_us = max(1U, srtt); } -static void tcp_update_pacing_rate(struct sock *sk) +void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; @@ -971,7 +1155,7 @@ static void tcp_update_pacing_rate(struct sock *sk) /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -static void tcp_set_rto(struct sock *sk) +void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) @@ -1016,6 +1200,7 @@ struct tcp_sacktag_state { u64 last_sackt; u32 reord; u32 sack_delivered; + u32 delivered_bytes; int flag; unsigned int mss_now; struct rate_sample *rate; @@ -1148,15 +1333,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -/* Updates the delivered and delivered_ce counts */ -static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, - bool ece_ack) -{ - tp->delivered += delivered; - if (ece_ack) - tp->delivered_ce += delivered; -} - /* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). @@ -1386,7 +1562,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount, + int dup_sack, int pcount, u32 plen, u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); @@ -1446,11 +1622,7 @@ static u8 tcp_sacktag_one(struct sock *sk, tp->sacked_out += pcount; /* Out-of-order packets delivered */ state->sack_delivered += pcount; - - /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (tp->lost_skb_hint && - before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) - tp->lost_cnt_hint += pcount; + state->delivered_bytes += plen; } /* D-SACK. We can detect redundant retransmission in S|R and plain R @@ -1487,13 +1659,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, * tcp_highest_sack_seq() when skb is highest_sack. */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, - start_seq, end_seq, dup_sack, pcount, + start_seq, end_seq, dup_sack, pcount, skb->len, tcp_skb_timestamp_us(skb)); tcp_rate_skb_delivered(sk, skb, state->rate); - if (skb == tp->lost_skb_hint) - tp->lost_cnt_hint += pcount; - TCP_SKB_CB(prev)->end_seq += shifted; TCP_SKB_CB(skb)->seq += shifted; @@ -1526,10 +1695,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, if (skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = prev; - if (skb == tp->lost_skb_hint) { - tp->lost_skb_hint = prev; - tp->lost_cnt_hint -= tcp_skb_pcount(prev); - } TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor; @@ -1779,6 +1944,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), + skb->len, tcp_skb_timestamp_us(skb)); tcp_rate_skb_delivered(sk, skb, state->rate); if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) @@ -2146,12 +2312,6 @@ static inline void tcp_init_undo(struct tcp_sock *tp) tp->undo_retrans = -1; } -static bool tcp_is_rack(const struct sock *sk) -{ - return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & - TCP_RACK_LOSS_DETECTION; -} - /* If we detect SACK reneging, forget all SACK information * and reset tags completely, otherwise preserve SACKs. If receiver * dropped its ofo queue, we will know this due to reneging detection. @@ -2177,8 +2337,7 @@ static void tcp_timeout_mark_lost(struct sock *sk) skb_rbtree_walk_from(skb) { if (is_reneg) TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; - else if (tcp_is_rack(sk) && skb != head && - tcp_rack_skb_timeout(tp, skb, 0) > 0) + else if (skb != head && tcp_rack_skb_timeout(tp, skb, 0) > 0) continue; /* Don't mark recently sent ones lost yet */ tcp_mark_skb_lost(sk, skb); } @@ -2252,30 +2411,13 @@ static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - delay, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, false); *ack_flag &= ~FLAG_SET_XMIT_TIMER; return true; } return false; } -/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs - * counter when SACK is enabled (without SACK, sacked_out is used for - * that purpose). - * - * With reordering, holes may still be in flight, so RFC3517 recovery - * uses pure sacked_out (total number of SACKed segments) even though - * it violates the RFC that uses duplicate ACKs, often these are equal - * but when e.g. out-of-window ACKs or packet duplication occurs, - * they differ. Since neither occurs due to loss, TCP should really - * ignore them. - */ -static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) -{ - return tp->sacked_out + 1; -} - /* Linux NewReno/SACK/ECN state machine. * -------------------------------------- * @@ -2328,13 +2470,7 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * * If the receiver supports SACK: * - * RFC6675/3517: It is the conventional algorithm. A packet is - * considered lost if the number of higher sequence packets - * SACKed is greater than or equal the DUPACK thoreshold - * (reordering). This is implemented in tcp_mark_head_lost and - * tcp_update_scoreboard. - * - * RACK (draft-ietf-tcpm-rack-01): it is a newer algorithm + * RACK (RFC8985): RACK is a newer loss detection algorithm * (2017-) that checks timing instead of counting DUPACKs. * Essentially a packet is considered lost if it's not S/ACKed * after RTT + reordering_window, where both metrics are @@ -2349,8 +2485,8 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * is lost (NewReno). This heuristics are the same in NewReno * and SACK. * - * Really tricky (and requiring careful tuning) part of algorithm - * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue(). + * The really tricky (and requiring careful tuning) part of the algorithm + * is hidden in the RACK code in tcp_recovery.c and tcp_xmit_retransmit_queue(). * The first determines the moment _when_ we should reduce CWND and, * hence, slow down forward transmission. In fact, it determines the moment * when we decide that hole is caused by loss, rather than by a reorder. @@ -2373,83 +2509,10 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * Main question: may we further continue forward transmission * with the same cwnd? */ -static bool tcp_time_to_recover(struct sock *sk, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - - /* Trick#1: The loss is proven. */ - if (tp->lost_out) - return true; - - /* Not-A-Trick#2 : Classic rule... */ - if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering) - return true; - - return false; -} - -/* Detect loss in event "A" above by marking head of queue up as lost. - * 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. - */ -static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) +static bool tcp_time_to_recover(const struct tcp_sock *tp) { - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int cnt; - /* Use SACK to deduce losses of new sequences sent during recovery */ - const u32 loss_high = tp->snd_nxt; - - WARN_ON(packets > tp->packets_out); - skb = tp->lost_skb_hint; - if (skb) { - /* Head already handled? */ - if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) - return; - cnt = tp->lost_cnt_hint; - } else { - skb = tcp_rtx_queue_head(sk); - cnt = 0; - } - - skb_rbtree_walk_from(skb) { - /* TODO: do this better */ - /* this is not the most efficient way to do this... */ - tp->lost_skb_hint = skb; - tp->lost_cnt_hint = cnt; - - if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) - break; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - cnt += tcp_skb_pcount(skb); - - if (cnt > packets) - break; - - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST)) - tcp_mark_skb_lost(sk, skb); - - if (mark_head) - break; - } - tcp_verify_left_out(tp); -} - -/* Account newly detected lost packet(s) */ - -static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tcp_is_sack(tp)) { - int sacked_upto = tp->sacked_out - tp->reordering; - if (sacked_upto >= 0) - tcp_mark_head_lost(sk, sacked_upto, 0); - else if (fast_rexmit) - tcp_mark_head_lost(sk, 1, 1); - } + /* Has loss detection marked at least one packet lost? */ + return tp->lost_out != 0; } static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when) @@ -2475,20 +2538,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { const struct sock *sk = (const struct sock *)tp; - if (tp->retrans_stamp && - tcp_tsopt_ecr_before(tp, tp->retrans_stamp)) - return true; /* got echoed TS before first retransmission */ + /* Received an echoed timestamp before the first retransmission? */ + if (tp->retrans_stamp) + return tcp_tsopt_ecr_before(tp, tp->retrans_stamp); + + /* We set tp->retrans_stamp upon the first retransmission of a loss + * recovery episode, so normally if tp->retrans_stamp is 0 then no + * retransmission has happened yet (likely due to TSQ, which can cause + * fast retransmits to be delayed). So if snd_una advanced while + * (tp->retrans_stamp is 0 then apparently a packet was merely delayed, + * not lost. But there are exceptions where we retransmit but then + * clear tp->retrans_stamp, so we check for those exceptions. + */ - /* Check if nothing was retransmitted (retrans_stamp==0), which may - * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp - * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear - * retrans_stamp even if we had retransmitted the SYN. + /* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen() + * clears tp->retrans_stamp when snd_una == high_seq. */ - if (!tp->retrans_stamp && /* no record of a retransmit/SYN? */ - sk->sk_state != TCP_SYN_SENT) /* not the FLAG_SYN_ACKED case? */ - return true; /* nothing was retransmitted */ + if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq)) + return false; - return false; + /* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp + * when setting FLAG_SYN_ACKED is set, even if the SYN was + * retransmitted. + */ + if (sk->sk_state == TCP_SYN_SENT) + return false; + + return true; /* tp->retrans_stamp is zero; no retransmit yet */ } /* Undo procedures. */ @@ -2666,7 +2742,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) if (frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); - inet_csk(sk)->icsk_retransmits = 0; + WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0); if (tcp_is_non_sack_preventing_reopen(sk)) return true; if (frto_undo || tcp_is_sack(tp)) { @@ -2710,6 +2786,8 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) return; + trace_tcp_cwnd_reduction_tp(sk, newly_acked_sacked, newly_lost, flag); + tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + @@ -2875,8 +2953,6 @@ void tcp_simple_retransmit(struct sock *sk) tcp_mark_skb_lost(sk, skb); } - tcp_clear_retrans_hints_partial(tp); - if (!tp->lost_out) return; @@ -2892,7 +2968,7 @@ void tcp_simple_retransmit(struct sock *sk) */ tcp_non_congestion_loss_retransmit(sk); } -EXPORT_SYMBOL(tcp_simple_retransmit); +EXPORT_IPV6_MOD(tcp_simple_retransmit); void tcp_enter_recovery(struct sock *sk, bool ece_ack) { @@ -2984,17 +3060,8 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; } -static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, - bool *do_lost) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); @@ -3019,9 +3086,6 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - } else { - /* Partial ACK arrived. Force fast retransmit. */ - *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -3035,7 +3099,7 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) if (unlikely(tcp_is_reno(tp))) { tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED); - } else if (tcp_is_rack(sk)) { + } else { u32 prior_retrans = tp->retrans_out; if (tcp_rack_mark_lost(sk)) @@ -3062,10 +3126,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int fast_rexmit = 0, flag = *ack_flag; + int flag = *ack_flag; bool ece_ack = flag & FLAG_ECE; - bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) && - tcp_force_fast_retransmit(sk)); if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; @@ -3114,7 +3176,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) + } else if (tcp_try_undo_partial(sk, prior_snd_una)) return; if (tcp_try_undo_dsack(sk)) @@ -3122,7 +3184,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tcp_identify_packet_loss(sk, ack_flag); if (icsk->icsk_ca_state != TCP_CA_Recovery) { - if (!tcp_time_to_recover(sk, flag)) + if (!tcp_time_to_recover(tp)) return; /* Undo reverts the recovery state. If loss is evident, * starts a new recovery (e.g. reordering then loss); @@ -3151,7 +3213,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tcp_try_undo_dsack(sk); tcp_identify_packet_loss(sk, ack_flag); - if (!tcp_time_to_recover(sk, flag)) { + if (!tcp_time_to_recover(tp)) { tcp_try_to_open(sk, flag); return; } @@ -3169,11 +3231,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, /* Otherwise enter Recovery state */ tcp_enter_recovery(sk, ece_ack); - fast_rexmit = 1; } - if (!tcp_is_rack(sk) && do_lost) - tcp_update_scoreboard(sk, fast_rexmit); *rexmit = REXMIT_LOST; } @@ -3215,7 +3274,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp); + seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp, 1); rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) @@ -3282,8 +3341,7 @@ 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_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, true); } } @@ -3395,6 +3453,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, if (sacked & TCPCB_SACKED_ACKED) { tp->sacked_out -= acked_pcount; + /* snd_una delta covers these skbs */ + sack->delivered_bytes -= skb->len; } else if (tcp_is_sack(tp)) { tcp_count_delivered(tp, acked_pcount, ece_ack); if (!tcp_skb_spurious_retrans(tp, skb)) @@ -3430,8 +3490,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; - if (unlikely(skb == tp->lost_skb_hint)) - tp->lost_skb_hint = NULL; tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } @@ -3489,15 +3547,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, if (flag & FLAG_RETRANS_DATA_ACKED) flag &= ~FLAG_ORIG_SACK_ACKED; } else { - int delta; - /* Non-retransmitted hole got filled? That's reordering */ if (before(reord, prior_fack)) tcp_check_sack_reordering(sk, reord, 0); - - delta = prior_sacked - tp->sacked_out; - tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } + + sack->delivered_bytes = (skb ? + TCP_SKB_CB(skb)->seq : tp->snd_una) - + prior_snd_una; } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb))) { @@ -3560,10 +3617,10 @@ static void tcp_ack_probe(struct sock *sk) * This function is not for random using! */ } else { - unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); + unsigned long when = tcp_probe0_when(sk, tcp_rto_max(sk)); when = tcp_clamp_probe0_to_user_timeout(sk, when); - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, true); } } @@ -3767,8 +3824,18 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } +static void tcp_send_ack_reflect_ect(struct sock *sk, bool accecn_reflector) +{ + struct tcp_sock *tp = tcp_sk(sk); + u16 flags = 0; + + if (accecn_reflector) + flags = tcp_accecn_reflector_flags(tp->syn_ect_rcv); + __tcp_send_ack(sk, tp->rcv_nxt, flags); +} + /* RFC 5961 7 [ACK Throttling] */ -static void tcp_send_challenge_ack(struct sock *sk) +static void tcp_send_challenge_ack(struct sock *sk, bool accecn_reflector) { struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); @@ -3798,7 +3865,7 @@ static void tcp_send_challenge_ack(struct sock *sk) WRITE_ONCE(net->ipv4.tcp_challenge_count, count - 1); send_ack: NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK); - tcp_send_ack(sk); + tcp_send_ack_reflect_ect(sk, accecn_reflector); } } @@ -3808,8 +3875,16 @@ static void tcp_store_ts_recent(struct tcp_sock *tp) tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); } -static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) +static int __tcp_replace_ts_recent(struct tcp_sock *tp, s32 tstamp_delta) +{ + tcp_store_ts_recent(tp); + return tstamp_delta > 0 ? FLAG_TS_PROGRESS : 0; +} + +static int tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) { + s32 delta; + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { /* PAWS bug workaround wrt. ACK frames, the PAWS discard * extra check below makes sure this can only happen @@ -3818,13 +3893,17 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) * Not only, also it occurs for expired timestamps. */ - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); + if (tcp_paws_check(&tp->rx_opt, 0)) { + delta = tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent; + return __tcp_replace_ts_recent(tp, delta); + } } + + return 0; } /* This routine deals with acks during a TLP episode and ends an episode by - * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack + * resetting tlp_high_seq. Ref: TLP algorithm in RFC8985 */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3856,12 +3935,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) } } -static inline void tcp_in_ack_event(struct sock *sk, u32 flags) +static void tcp_in_ack_event(struct sock *sk, int flag) { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_ca_ops->in_ack_event) - icsk->icsk_ca_ops->in_ack_event(sk, flags); + if (icsk->icsk_ca_ops->in_ack_event) { + u32 ack_ev_flags = 0; + + if (flag & FLAG_WIN_UPDATE) + ack_ev_flags |= CA_ACK_WIN_UPDATE; + if (flag & FLAG_SLOWPATH) { + ack_ev_flags |= CA_ACK_SLOWPATH; + if (flag & FLAG_ECE) + ack_ev_flags |= CA_ACK_ECE; + } + + icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags); + } } /* Congestion control has updated the cwnd already. So if we're in @@ -3886,7 +3976,8 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit) } /* Returns the number of packets newly acked or sacked by the current ACK */ -static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag) +static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, + u32 ecn_count, int flag) { const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3894,8 +3985,12 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag) delivered = tp->delivered - prior_delivered; NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered); - if (flag & FLAG_ECE) - NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered); + + if (flag & FLAG_ECE) { + if (tcp_ecn_mode_rfc3168(tp)) + ecn_count = delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, ecn_count); + } return delivered; } @@ -3916,11 +4011,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 delivered = tp->delivered; u32 lost = tp->lost; int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ + u32 ecn_count = 0; /* Did we receive ECE/an AccECN ACE update? */ u32 prior_fack; sack_state.first_sackt = 0; sack_state.rate = &rs; sack_state.sack_delivered = 0; + sack_state.delivered_bytes = 0; /* We very likely will need to access rtx queue. */ prefetch(sk->tcp_rtx_queue.rb_node); @@ -3936,7 +4033,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) - tcp_send_challenge_ack(sk); + tcp_send_challenge_ack(sk, false); return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; } goto old_ack; @@ -3950,12 +4047,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; - icsk->icsk_retransmits = 0; + WRITE_ONCE(icsk->icsk_retransmits, 0); #if IS_ENABLED(CONFIG_TLS_DEVICE) if (static_branch_unlikely(&clean_acked_data_enabled.key)) - if (icsk->icsk_clean_acked) - icsk->icsk_clean_acked(sk, ack); + if (tp->tcp_clean_acked) + tp->tcp_clean_acked(sk, ack); #endif } @@ -3966,7 +4063,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * is in window. */ if (flag & FLAG_UPDATE_TS_RECENT) - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + flag |= tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) == FLAG_SND_UNA_ADVANCED) { @@ -3978,12 +4075,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; - tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { - u32 ack_ev_flags = CA_ACK_SLOWPATH; - if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else @@ -3995,19 +4088,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); - if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { + if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; - ack_ev_flags |= CA_ACK_ECE; - } if (sack_state.sack_delivered) tcp_count_delivered(tp, sack_state.sack_delivered, flag & FLAG_ECE); - - if (flag & FLAG_WIN_UPDATE) - ack_ev_flags |= CA_ACK_WIN_UPDATE; - - tcp_in_ack_event(sk, ack_ev_flags); } /* This is a deviation from RFC3168 since it states that: @@ -4022,8 +4108,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* We passed data and got it acked, remove any soft error * log. Something worked... */ - WRITE_ONCE(sk->sk_err_soft, 0); - icsk->icsk_probes_out = 0; + if (READ_ONCE(sk->sk_err_soft)) + WRITE_ONCE(sk->sk_err_soft, 0); + WRITE_ONCE(icsk->icsk_probes_out, 0); tp->rcv_tstamp = tcp_jiffies32; if (!prior_packets) goto no_queue; @@ -4034,6 +4121,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_rack_update_reo_wnd(sk, &rs); + if (tcp_ecn_mode_accecn(tp)) + ecn_count = tcp_accecn_process(sk, skb, + tp->delivered - delivered, + sack_state.delivered_bytes, + &flag); + + tcp_in_ack_event(sk, flag); + if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -4056,7 +4151,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - delivered = tcp_newly_delivered(sk, delivered, flag); + delivered = tcp_newly_delivered(sk, delivered, ecn_count, flag); + lost = tp->lost - lost; /* freshly marked lost */ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED); tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate); @@ -4065,11 +4161,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + if (tcp_ecn_mode_accecn(tp)) + ecn_count = tcp_accecn_process(sk, skb, + tp->delivered - delivered, + sack_state.delivered_bytes, + &flag); + tcp_in_ack_event(sk, flag); /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, &rexmit); - tcp_newly_delivered(sk, delivered, flag); + tcp_newly_delivered(sk, delivered, ecn_count, flag); } /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than @@ -4090,7 +4192,7 @@ old_ack: &sack_state); tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, &rexmit); - tcp_newly_delivered(sk, delivered, flag); + tcp_newly_delivered(sk, delivered, ecn_count, flag); tcp_xmit_recovery(sk, rexmit); } @@ -4174,7 +4276,6 @@ u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) } return mss; } -EXPORT_SYMBOL_GPL(tcp_parse_mss_option); /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when @@ -4191,6 +4292,7 @@ void tcp_parse_options(const struct net *net, ptr = (const unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; + opt_rx->accecn = 0; opt_rx->saw_unknown = 0; while (length > 0) { @@ -4282,6 +4384,12 @@ void tcp_parse_options(const struct net *net, ptr, th->syn, foc, false); break; + case TCPOPT_ACCECN0: + case TCPOPT_ACCECN1: + /* Save offset of AccECN option in TCP header */ + opt_rx->accecn = (ptr - 2) - (__u8 *)th; + break; + case TCPOPT_EXP: /* Fast Open option shares code 254 using a * 16 bits magic number. @@ -4342,11 +4450,14 @@ static bool tcp_fast_parse_options(const struct net *net, */ if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; + tp->rx_opt.accecn = 0; return false; } else if (tp->rx_opt.tstamp_ok && th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { - if (tcp_parse_aligned_timestamp(tp, th)) + if (tcp_parse_aligned_timestamp(tp, th)) { + tp->rx_opt.accecn = 0; return true; + } } tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL); @@ -4450,34 +4561,40 @@ static u32 tcp_tsval_replay(const struct sock *sk) return inet_csk(sk)->icsk_rto * 1200 / HZ; } -static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) +static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk, + const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); const struct tcphdr *th = tcp_hdr(skb); - u32 seq = TCP_SKB_CB(skb)->seq; + SKB_DR_INIT(reason, TCP_RFC7323_PAWS); u32 ack = TCP_SKB_CB(skb)->ack_seq; + u32 seq = TCP_SKB_CB(skb)->seq; - return /* 1. Pure ACK with correct sequence number. */ - (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && + /* 1. Is this not a pure ACK ? */ + if (!th->ack || seq != TCP_SKB_CB(skb)->end_seq) + return reason; - /* 2. ... and duplicate ACK. */ - ack == tp->snd_una && + /* 2. Is its sequence not the expected one ? */ + if (seq != tp->rcv_nxt) + return before(seq, tp->rcv_nxt) ? + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK : + reason; - /* 3. ... and does not update window. */ - !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && + /* 3. Is this not a duplicate ACK ? */ + if (ack != tp->snd_una) + return reason; - /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= - tcp_tsval_replay(sk); -} + /* 4. Is this updating the window ? */ + if (tcp_may_update_window(tp, ack, seq, ntohs(th->window) << + tp->rx_opt.snd_wscale)) + return reason; -static inline bool tcp_paws_discard(const struct sock *sk, - const struct sk_buff *skb) -{ - const struct tcp_sock *tp = tcp_sk(sk); + /* 5. Is this not in the replay window ? */ + if ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > + tcp_tsval_replay(sk)) + return reason; - return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) && - !tcp_disordered_ack(sk, skb); + return 0; } /* Check segment sequence number for validity. @@ -4493,14 +4610,22 @@ static inline bool tcp_paws_discard(const struct sock *sk, * (borrowed from freebsd) */ -static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, +static enum skb_drop_reason tcp_sequence(const struct sock *sk, u32 seq, u32 end_seq) { + const struct tcp_sock *tp = tcp_sk(sk); + if (before(end_seq, tp->rcv_wup)) return SKB_DROP_REASON_TCP_OLD_SEQUENCE; - if (after(seq, tp->rcv_nxt + tcp_receive_window(tp))) - return SKB_DROP_REASON_TCP_INVALID_SEQUENCE; + if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) { + if (after(seq, tp->rcv_nxt + tcp_receive_window(tp))) + return SKB_DROP_REASON_TCP_INVALID_SEQUENCE; + + /* Only accept this packet if receive queue is empty. */ + if (skb_queue_len(&sk->sk_receive_queue)) + return SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE; + } return SKB_NOT_DROPPED_YET; } @@ -4518,7 +4643,7 @@ void tcp_done_with_error(struct sock *sk, int err) if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } -EXPORT_SYMBOL(tcp_done_with_error); +EXPORT_IPV6_MOD(tcp_done_with_error); /* When we get a reset we do this. */ void tcp_reset(struct sock *sk, struct sk_buff *skb) @@ -4924,7 +5049,7 @@ static bool tcp_ooo_try_coalesce(struct sock *sk, noinline_for_tracing static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { - sk_drops_add(sk, skb); + sk_drops_skbadd(sk, skb); sk_skb_reason_drop(sk, skb, reason); } @@ -4947,8 +5072,9 @@ static void tcp_ofo_queue(struct sock *sk) if (before(TCP_SKB_CB(skb)->seq, dsack_high)) { __u32 dsack = dsack_high; + if (before(TCP_SKB_CB(skb)->end_seq, dsack_high)) - dsack_high = TCP_SKB_CB(skb)->end_seq; + dsack = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } p = rb_next(p); @@ -4964,7 +5090,7 @@ static void tcp_ofo_queue(struct sock *sk) tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); else kfree_skb_partial(skb, fragstolen); @@ -4981,10 +5107,31 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); -static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, +/* Check if this incoming skb can be added to socket receive queues + * while satisfying sk->sk_rcvbuf limit. + * + * In theory we should use skb->truesize, but this can cause problems + * when applications use too small SO_RCVBUF values. + * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio, + * allowing RWIN to be close to available space. + * Whenever the receive queue gets full, we can receive a small packet + * filling RWIN, but with a high skb->truesize, because most NIC use 4K page + * plus sk_buff metadata even when receiving less than 1500 bytes of payload. + * + * Note that we use skb->len to decide to accept or drop this packet, + * but sk->sk_rmem_alloc is the sum of all skb->truesize. + */ +static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb) +{ + unsigned int rmem = atomic_read(&sk->sk_rmem_alloc); + + return rmem + skb->len <= sk->sk_rcvbuf; +} + +static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb, unsigned int size) { - if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || + if (!tcp_can_ingest(sk, skb) || !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk, skb) < 0) @@ -5007,7 +5154,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) bool fragstolen; tcp_save_lrcv_flowlabel(sk, skb); - tcp_ecn_check_ce(sk, skb); + tcp_data_ecn_check(sk, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); @@ -5016,6 +5163,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) return; } + tcp_measure_rcv_mss(sk, skb); /* Disable header prediction. */ tp->pred_flags = 0; inet_csk_schedule_ack(sk); @@ -5143,6 +5291,9 @@ end: skb_condense(skb); skb_set_owner_r(skb, sk); } + /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ + if (sk->sk_socket) + tcp_rcvbuf_grow(sk, tp->rcvq_space.space); } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, @@ -5156,7 +5307,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); skb_set_owner_r(skb, sk); } return eaten; @@ -5239,7 +5390,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); return; } - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -5596,7 +5747,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb) tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); tp->ooo_last_skb = rb_to_skb(prev); if (!prev || goal <= 0) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + if (tcp_can_ingest(sk, in_skb) && !tcp_under_memory_pressure(sk)) break; goal = sk->sk_rcvbuf >> 3; @@ -5628,14 +5779,18 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); + /* Do nothing if our queues are empty. */ + if (!atomic_read(&sk->sk_rmem_alloc)) + return -1; + NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED); - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + if (!tcp_can_ingest(sk, in_skb)) tcp_clamp_window(sk); else if (tcp_under_memory_pressure(sk)) tcp_adjust_rcv_ssthresh(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + if (tcp_can_ingest(sk, in_skb)) return 0; tcp_collapse_ofo_queue(sk); @@ -5645,7 +5800,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) NULL, tp->copied_seq, tp->rcv_nxt); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + if (tcp_can_ingest(sk, in_skb)) return 0; /* Collapsing did not help, destructive actions follow. @@ -5653,7 +5808,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) tcp_prune_ofo_queue(sk, in_skb); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + if (tcp_can_ingest(sk, in_skb)) return 0; /* If we are really being abused, tell the caller to silently @@ -5748,7 +5903,9 @@ static inline void tcp_data_snd_check(struct sock *sk) static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) { struct tcp_sock *tp = tcp_sk(sk); - unsigned long rtt, delay; + struct net *net = sock_net(sk); + unsigned long rtt; + u64 delay; /* More than one full frame received... */ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && @@ -5767,7 +5924,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) * Defer the ack until tcp_release_cb(). */ if (sock_owned_by_user_nocheck(sk) && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_backlog_ack_defer)) { + READ_ONCE(net->ipv4.sysctl_tcp_backlog_ack_defer)) { set_bit(TCP_ACK_DEFERRED, &sk->sk_tsq_flags); return; } @@ -5782,7 +5939,7 @@ send_now: } if (!tcp_is_sack(tp) || - tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)) + tp->compressed_ack >= READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_nr)) goto send_now; if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { @@ -5797,18 +5954,26 @@ send_now: if (hrtimer_is_queued(&tp->compressed_ack_timer)) return; - /* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */ + /* compress ack timer : comp_sack_rtt_percent of rtt, + * but no more than tcp_comp_sack_delay_ns. + */ rtt = tp->rcv_rtt_est.rtt_us; if (tp->srtt_us && tp->srtt_us < rtt) rtt = tp->srtt_us; - delay = min_t(unsigned long, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns), - rtt * (NSEC_PER_USEC >> 3)/20); + /* delay = (rtt >> 3) * NSEC_PER_USEC * comp_sack_rtt_percent / 100 + * -> + * delay = rtt * 1.25 * comp_sack_rtt_percent + */ + delay = (u64)(rtt + (rtt >> 2)) * + READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_rtt_percent); + + delay = min(delay, READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_delay_ns)); + sock_hold(sk); hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay), - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns), + READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_slack_ns), HRTIMER_MODE_REL_PINNED_SOFT); } @@ -5946,28 +6111,41 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { struct tcp_sock *tp = tcp_sk(sk); + bool accecn_reflector = false; SKB_DR(reason); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && - tp->rx_opt.saw_tstamp && - tcp_paws_discard(sk, skb)) { - if (!th->rst) { - if (unlikely(th->syn)) - goto syn_challenge; - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); - if (!tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDPAWS, - &tp->last_oow_ack_time)) - tcp_send_dupack(sk, skb); - SKB_DR_SET(reason, TCP_RFC7323_PAWS); - goto discard; - } - /* Reset is accepted even if it did not pass PAWS. */ + if (!tcp_fast_parse_options(sock_net(sk), skb, th, tp) || + !tp->rx_opt.saw_tstamp || + tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW)) + goto step1; + + reason = tcp_disordered_ack_check(sk, skb); + if (!reason) + goto step1; + /* Reset is accepted even if it did not pass PAWS. */ + if (th->rst) + goto step1; + if (unlikely(th->syn)) + goto syn_challenge; + + /* Old ACK are common, increment PAWS_OLD_ACK + * and do not send a dupack. + */ + if (reason == SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWS_OLD_ACK); + goto discard; } + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + if (!tcp_oow_rate_limited(sock_net(sk), skb, + LINUX_MIB_TCPACKSKIPPEDPAWS, + &tp->last_oow_ack_time)) + tcp_send_dupack(sk, skb); + goto discard; +step1: /* Step 1: check sequence number */ - reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); if (reason) { /* RFC793, page 37: "In all states except SYN-SENT, all reset * (RST) segments are validated by checking their SEQ-fields." @@ -5978,6 +6156,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (!th->rst) { if (th->syn) goto syn_challenge; + + if (reason == SKB_DROP_REASON_TCP_INVALID_SEQUENCE || + reason == SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_BEYOND_WINDOW); if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSEQ, &tp->last_oow_ack_time)) @@ -6026,7 +6209,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (tp->syn_fastopen && !tp->data_segs_in && sk->sk_state == TCP_ESTABLISHED) tcp_fastopen_active_disable(sk); - tcp_send_challenge_ack(sk); + tcp_send_challenge_ack(sk, false); SKB_DR_SET(reason, TCP_RESET); goto discard; } @@ -6037,6 +6220,16 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, * RFC 5961 4.2 : Send a challenge ack */ if (th->syn) { + if (tcp_ecn_mode_accecn(tp)) { + accecn_reflector = true; + if (tp->rx_opt.accecn && + tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + tcp_accecn_opt_demand_min(sk, 1); + } + } if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack && TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq && TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt && @@ -6046,7 +6239,7 @@ syn_challenge: if (syn_inerr) TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); - tcp_send_challenge_ack(sk); + tcp_send_challenge_ack(sk, accecn_reflector); SKB_DR_SET(reason, TCP_INVALID_SYN); goto discard; } @@ -6118,6 +6311,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) */ tp->rx_opt.saw_tstamp = 0; + tp->rx_opt.accecn = 0; /* pred_flags is 0xS?10 << 16 + snd_wnd * if header_prediction is to be made @@ -6132,6 +6326,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->seq == tp->rcv_nxt && !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) { int tcp_header_len = tp->tcp_header_len; + s32 delta = 0; + int flag = 0; /* Timestamp header prediction: tcp_header_len * is automatically equal to th->doff*4 due to pred_flags @@ -6144,8 +6340,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) if (!tcp_parse_aligned_timestamp(tp, th)) goto slow_path; + delta = tp->rx_opt.rcv_tsval - + tp->rx_opt.ts_recent; /* If PAWS failed, check it more carefully in slow path */ - if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0) + if (delta < 0) goto slow_path; /* DO NOT update ts_recent here, if checksum fails @@ -6165,12 +6363,15 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) if (tcp_header_len == (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && tp->rcv_nxt == tp->rcv_wup) - tcp_store_ts_recent(tp); + flag |= __tcp_replace_ts_recent(tp, + delta); + + tcp_ecn_received_counters(sk, skb, 0); /* We know that such packets are checksummed * on entry. */ - tcp_ack(sk, skb, 0); + tcp_ack(sk, skb, flag); __kfree_skb(skb); tcp_data_snd_check(sk); /* When receiving pure ack in fast path, update @@ -6191,6 +6392,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) if (tcp_checksum_complete(skb)) goto csum_error; + if (after(TCP_SKB_CB(skb)->end_seq, + tp->rcv_nxt + tcp_receive_window(tp))) + goto validate; + if ((int)skb->truesize > sk->sk_forward_alloc) goto step5; @@ -6201,22 +6406,25 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) if (tcp_header_len == (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && tp->rcv_nxt == tp->rcv_wup) - tcp_store_ts_recent(tp); + flag |= __tcp_replace_ts_recent(tp, + delta); tcp_rcv_rtt_measure_ts(sk, skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_header_len); + tcp_ecn_received_counters(sk, skb, + len - tcp_header_len); eaten = tcp_queue_rcv(sk, skb, &fragstolen); tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) { /* Well, only one small jumplet in fast path... */ - tcp_ack(sk, skb, FLAG_DATA); + tcp_ack(sk, skb, flag | FLAG_DATA); tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; @@ -6245,11 +6453,13 @@ slow_path: /* * Standard slow path. */ - +validate: if (!tcp_validate_incoming(sk, skb, th, 1)) return; step5: + tcp_ecn_received_counters_payload(sk, skb); + reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT); if ((int)reason < 0) { reason = -reason; @@ -6276,7 +6486,7 @@ csum_error: discard: tcp_drop_reason(sk, skb, reason); } -EXPORT_SYMBOL(tcp_rcv_established); +EXPORT_IPV6_MOD(tcp_rcv_established); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) { @@ -6329,7 +6539,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tp->lsndtime = tcp_jiffies32; if (sock_flag(sk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); + tcp_reset_keepalive_timer(sk, keepalive_time_when(tp)); if (!tp->rx_opt.snd_wscale) __tcp_fast_path_on(tp, tp->snd_wnd); @@ -6345,7 +6555,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; - if (mss == tp->rx_opt.user_mss) { + if (mss == READ_ONCE(tp->rx_opt.user_mss)) { struct tcp_options_received opt; /* Get original SYNACK MSS value if user MSS sets mss_clamp */ @@ -6452,9 +6662,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) { /* Previous FIN/ACK or RST/ACK might be ignored. */ if (icsk->icsk_retransmits == 0) - inet_csk_reset_xmit_timer(sk, - ICSK_TIME_RETRANS, - TCP_TIMEOUT_MIN, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_TIMEOUT_MIN, false); SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE); goto reset_and_undo; } @@ -6501,7 +6710,9 @@ consume: * state to ESTABLISHED..." */ - tcp_ecn_rcv_synack(tp, th); + if (tcp_ecn_mode_any(tp)) + tcp_ecn_rcv_synack(sk, skb, th, + TCP_SKB_CB(skb)->ip_dsfield); tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); tcp_try_undo_spurious_syn(sk); @@ -6569,11 +6780,11 @@ consume: */ inet_csk_schedule_ack(sk); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - TCP_DELACK_MAX, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_DACK, + TCP_DELACK_MAX, false); goto consume; } - tcp_send_ack(sk); + tcp_send_ack_reflect_ect(sk, tcp_ecn_mode_accecn(tp)); return -1; } @@ -6632,7 +6843,7 @@ consume: tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd; - tcp_ecn_rcv_syn(tp, th); + tcp_ecn_rcv_syn(tp, th, skb); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -6685,7 +6896,7 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) tcp_try_undo_recovery(sk); tcp_update_rto_time(tp); - inet_csk(sk)->icsk_retransmits = 0; + WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0); /* In tcp_fastopen_synack_timer() on the first SYNACK RTO we set * retrans_stamp but don't enter CA_Loss, so in case that happened we * need to zero retrans_stamp here to prevent spurious @@ -6788,10 +6999,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (!tcp_check_req(sk, skb, req, true, &req_stolen)) { - SKB_DR_SET(reason, TCP_FASTOPEN); + SKB_DR_SET(reason, TCP_FASTOPEN); + if (!tcp_check_req(sk, skb, req, true, &req_stolen, &reason)) goto discard; - } } if (!th->ack && !th->rst && !th->syn) { @@ -6815,7 +7025,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } /* accept old ack during closing */ if ((int)reason < 0) { - tcp_send_challenge_ack(sk); + tcp_send_challenge_ack(sk, false); reason = -reason; goto discard; } @@ -6827,6 +7037,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); + if (tp->rx_opt.tstamp_ok) + tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; + if (req) { tcp_rcv_synrecv_state_fastopen(sk); } else { @@ -6852,9 +7065,6 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - if (tp->rx_opt.tstamp_ok) - tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); @@ -6862,9 +7072,12 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); + if (tcp_ecn_mode_accecn(tp)) + tcp_accecn_third_ack(sk, skb, tp->syn_ect_snt); tcp_fast_path_on(tp); if (sk->sk_shutdown & SEND_SHUTDOWN) tcp_shutdown(sk, SEND_SHUTDOWN); + break; case TCP_FIN_WAIT1: { @@ -6904,7 +7117,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { - inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); + tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else if (th->fin || sock_owned_by_user(sk)) { /* Bad case. We could lose such FIN otherwise. * It is not a big problem, but it looks confusing @@ -6912,7 +7125,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * if it spins in bh_lock_sock(), but it is really * marginal case. */ - inet_csk_reset_keepalive_timer(sk, tmo); + tcp_reset_keepalive_timer(sk, tmo); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto consume; @@ -6990,7 +7203,7 @@ consume: __kfree_skb(skb); return 0; } -EXPORT_SYMBOL(tcp_rcv_state_process); +EXPORT_IPV6_MOD(tcp_rcv_state_process); static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) { @@ -7034,6 +7247,15 @@ static void tcp_ecn_create_request(struct request_sock *req, bool ect, ecn_ok; u32 ecn_ok_dst; + if (tcp_accecn_syn_requested(th) && + READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3) { + inet_rsk(req)->ecn_ok = 1; + tcp_rsk(req)->accecn_ok = 1; + tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; + return; + } + if (!th_ecn) return; @@ -7041,7 +7263,8 @@ static void tcp_ecn_create_request(struct request_sock *req, ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst; - if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || + if (((!ect || th->res1 || th->ae) && ecn_ok) || + tcp_ca_needs_ecn(listen_sk) || (ecn_ok_dst & DST_FEATURE_ECN_CA) || tcp_bpf_ca_needs_ecn((struct sock *)req)) inet_rsk(req)->ecn_ok = 1; @@ -7057,7 +7280,13 @@ static void tcp_openreq_init(struct request_sock *req, tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tcp_rsk(req)->snt_synack = 0; + tcp_rsk(req)->snt_tsval_first = 0; tcp_rsk(req)->last_oow_ack_time = 0; + tcp_rsk(req)->accecn_ok = 0; + tcp_rsk(req)->saw_accecn_opt = TCP_ACCECN_OPT_NOT_SEEN; + tcp_rsk(req)->accecn_fail_mode = 0; + tcp_rsk(req)->syn_ect_rcv = 0; + tcp_rsk(req)->syn_ect_snt = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; ireq->tstamp_ok = rx_opt->tstamp_ok; @@ -7097,8 +7326,8 @@ static bool tcp_syn_flood_action(struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!READ_ONCE(queue->synflood_warned) && syncookies != 2 && - xchg(&queue->synflood_warned, 1) == 0) { + if (syncookies != 2 && !READ_ONCE(queue->synflood_warned)) { + WRITE_ONCE(queue->synflood_warned, 1); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_family == AF_INET6) { net_info_ratelimited("%s: Possible SYN flooding on port [%pI6c]:%u. %s.\n", proto, inet6_rcv_saddr(sk), @@ -7166,13 +7395,13 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, return 0; } - mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss); + mss = tcp_parse_mss_option(th, READ_ONCE(tp->rx_opt.user_mss)); if (!mss) mss = af_ops->mss_clamp; return mss; } -EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss); +EXPORT_IPV6_MOD_GPL(tcp_get_syncookie_mss); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, @@ -7180,7 +7409,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, { struct tcp_fastopen_cookie foc = { .len = -1 }; struct tcp_options_received tmp_opt; - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; struct request_sock *req; @@ -7231,7 +7460,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; - tmp_opt.user_mss = tp->rx_opt.user_mss; + tmp_opt.user_mss = READ_ONCE(tp->rx_opt.user_mss); tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, want_cookie ? NULL : &foc); @@ -7313,7 +7542,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, &foc, TCP_SYNACK_FASTOPEN, skb); /* Add the child socket directly into the accept queue */ if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { - reqsk_fastopen_remove(fastopen_sk, req, false); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); goto drop_and_free; @@ -7323,14 +7551,11 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; - if (!want_cookie) { - req->timeout = tcp_timeout_init((struct sock *)req); - if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, - req->timeout))) { - reqsk_free(req); - return 0; - } - + if (!want_cookie && + unlikely(!inet_csk_reqsk_queue_hash_add(sk, req))) { + reqsk_free(req); + dst_release(dst); + return 0; } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : @@ -7352,4 +7577,4 @@ drop: tcp_listendrop(sk); return 0; } -EXPORT_SYMBOL(tcp_conn_request); +EXPORT_IPV6_MOD(tcp_conn_request); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a38c8b1f44db..f8a9596e8f4d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -53,24 +53,30 @@ #include <linux/module.h> #include <linux/random.h> #include <linux/cache.h> +#include <linux/fips.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sock_diag.h> +#include <net/aligned_data.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/transp_v6.h> #include <net/ipv6.h> #include <net/inet_common.h> +#include <net/inet_ecn.h> #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <net/rstreason.h> +#include <net/psp.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -81,18 +87,16 @@ #include <linux/btf_ids.h> #include <linux/skbuff_ref.h> -#include <crypto/hash.h> -#include <linux/scatterlist.h> +#include <crypto/md5.h> #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG -static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, const struct tcphdr *th); +static void tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; -EXPORT_SYMBOL(tcp_hashinfo); static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), @@ -120,6 +124,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; + u32 reuse_thresh; if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) reuse = 0; @@ -162,9 +167,10 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); + reuse_thresh = READ_ONCE(tw->tw_entry_stamp) + + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse_delay); if (ts_recent_stamp && - (!twp || (reuse && time_after32(ktime_get_seconds(), - ts_recent_stamp)))) { + (!twp || (reuse && time_after32(tcp_clock_ms(), reuse_thresh)))) { /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ @@ -197,9 +203,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) return 0; } -EXPORT_SYMBOL_GPL(tcp_twsk_unique); +EXPORT_IPV6_MOD_GPL(tcp_twsk_unique); -static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to @@ -215,7 +221,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, } /* This will initiate an outgoing connection. */ -int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; @@ -288,9 +294,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); - inet_csk(sk)->icsk_ext_hdr_len = 0; + inet_csk(sk)->icsk_ext_hdr_len = psp_sk_overhead(sk); if (inet_opt) - inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; + inet_csk(sk)->icsk_ext_hdr_len += inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; @@ -357,7 +363,7 @@ failure: inet->inet_dport = 0; return err; } -EXPORT_SYMBOL(tcp_v4_connect); +EXPORT_IPV6_MOD(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. @@ -398,7 +404,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } -EXPORT_SYMBOL(tcp_v4_mtu_reduced); +EXPORT_IPV6_MOD(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -432,7 +438,7 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort) } reqsk_put(req); } -EXPORT_SYMBOL(tcp_req_err); +EXPORT_IPV6_MOD(tcp_req_err); /* TCP-LD (RFC 6069) logic */ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) @@ -456,15 +462,14 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) 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); + icsk->icsk_rto = inet_csk_rto_backoff(icsk, tcp_rto_max(sk)); 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); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, false); } else { /* RTO revert clocked out retransmission. * Will retransmit now. @@ -472,7 +477,7 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) tcp_retransmit_timer(sk); } } -EXPORT_SYMBOL(tcp_ld_RTO_revert); +EXPORT_IPV6_MOD(tcp_ld_RTO_revert); /* * This routine is called by the ICMP module when it gets some @@ -494,17 +499,16 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); - struct tcp_sock *tp; + struct net *net = dev_net_rcu(skb->dev); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - struct sock *sk; struct request_sock *fastopen; + struct tcp_sock *tp; u32 seq, snd_una; + struct sock *sk; int err; - struct net *net = dev_net(skb->dev); - sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, - iph->daddr, th->dest, iph->saddr, + sk = __inet_lookup_established(net, iph->daddr, th->dest, iph->saddr, ntohs(th->source), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); @@ -674,7 +678,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } -EXPORT_SYMBOL(tcp_v4_send_check); +EXPORT_IPV6_MOD(tcp_v4_send_check); #define REPLY_OPTIONS_LEN (MAX_TCP_OPTION_SPACE / sizeof(__be32)) @@ -750,7 +754,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, struct tcp_md5sig_key *key = NULL; unsigned char newhash[16]; struct sock *sk1 = NULL; - int genhash; #endif u64 transmit_time = 0; struct sock *ctl_sk; @@ -786,7 +789,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); + net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh)) @@ -820,8 +823,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ - sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, - NULL, 0, ip_hdr(skb)->saddr, + sk1 = __inet_lookup_listener(net, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ @@ -837,11 +839,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, if (!key) goto out; - - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) + tcp_v4_md5_hash_skb(newhash, key, NULL, skb); + if (memcmp(md5_hash_location, newhash, 16) != 0) goto out; - } if (key) { @@ -887,7 +887,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); - arg.tos = ip_hdr(skb)->tos; + /* ECN bits of TW reset are cleared */ + arg.tos = ip_hdr(skb)->tos & ~INET_ECN_MASK; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); @@ -896,7 +897,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); @@ -1033,11 +1034,21 @@ static void tcp_v4_send_ack(const struct sock *sk, local_bh_enable(); } -static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) +static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb, + enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); struct tcp_key key = {}; + u8 tos = tw->tw_tos; + + /* Cleaning only ECN bits of TW ACKs of oow data or is paws_reject, + * while not cleaning ECN bits of other TW ACKs to avoid these ACKs + * being placed in a different service queues (Classic rather than L4S) + */ + if (tw_status == TCP_TW_ACK_OOW) + tos &= ~INET_ECN_MASK; + #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; @@ -1081,7 +1092,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, - tw->tw_tos, + tos, tw->tw_txhash); inet_twsk_put(tw); @@ -1151,14 +1162,15 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, key.type = TCP_KEY_MD5; } + /* Cleaning ECN bits of TW ACKs of oow data or is paws_reject */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), - READ_ONCE(req->ts_recent), + req->ts_recent, 0, &key, inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, + ip_hdr(skb)->tos & ~INET_ECN_MASK, READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); @@ -1176,7 +1188,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { - const struct inet_request_sock *ireq = inet_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; @@ -1189,6 +1201,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { + tcp_rsk(req)->syn_ect_snt = inet_sk(sk)->tos & INET_ECN_MASK; __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = READ_ONCE(inet_sk(sk)->tos); @@ -1229,7 +1242,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) */ DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); -EXPORT_SYMBOL(tcp_md5_needed); +EXPORT_IPV6_MOD(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) { @@ -1288,7 +1301,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, } return best_match; } -EXPORT_SYMBOL(__tcp_md5_do_lookup); +EXPORT_IPV6_MOD(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, @@ -1335,7 +1348,7 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } -EXPORT_SYMBOL(tcp_v4_md5_lookup); +EXPORT_IPV6_MOD(tcp_v4_md5_lookup); static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) { @@ -1409,13 +1422,13 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - if (tcp_md5_alloc_sigpool()) - return -ENOMEM; + if (fips_enabled) { + pr_warn_once("TCP-MD5 support is disabled due to FIPS\n"); + return -EOPNOTSUPP; + } - if (tcp_md5sig_info_add(sk, GFP_KERNEL)) { - tcp_md5_release_sigpool(); + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) return -ENOMEM; - } if (!static_branch_inc(&tcp_md5_needed.key)) { struct tcp_md5sig_info *md5sig; @@ -1423,7 +1436,6 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); - tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1431,7 +1443,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, newkey, newkeylen, GFP_KERNEL); } -EXPORT_SYMBOL(tcp_md5_do_add); +EXPORT_IPV6_MOD(tcp_md5_do_add); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, @@ -1440,12 +1452,9 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - tcp_md5_add_sigpool(); - if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) { - tcp_md5_release_sigpool(); + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) return -ENOMEM; - } if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { struct tcp_md5sig_info *md5sig; @@ -1454,7 +1463,6 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); - tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1463,7 +1471,7 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } -EXPORT_SYMBOL(tcp_md5_key_copy); +EXPORT_IPV6_MOD(tcp_md5_key_copy); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) @@ -1478,7 +1486,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, kfree_rcu(key, rcu); return 0; } -EXPORT_SYMBOL(tcp_md5_do_del); +EXPORT_IPV6_MOD(tcp_md5_do_del); void tcp_clear_md5_list(struct sock *sk) { @@ -1490,9 +1498,9 @@ void tcp_clear_md5_list(struct sock *sk) md5sig = rcu_dereference_protected(tp->md5sig_info, 1); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { - hlist_del_rcu(&key->node); + hlist_del(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); - kfree_rcu(key, rcu); + kfree(key); } } @@ -1562,66 +1570,44 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, cmd.tcpm_key, cmd.tcpm_keylen); } -static int tcp_v4_md5_hash_headers(struct tcp_sigpool *hp, - __be32 daddr, __be32 saddr, - const struct tcphdr *th, int nbytes) +static void tcp_v4_md5_hash_headers(struct md5_ctx *ctx, + __be32 daddr, __be32 saddr, + const struct tcphdr *th, int nbytes) { - struct tcp4_pseudohdr *bp; - struct scatterlist sg; - struct tcphdr *_th; - - bp = hp->scratch; - bp->saddr = saddr; - bp->daddr = daddr; - bp->pad = 0; - bp->protocol = IPPROTO_TCP; - bp->len = cpu_to_be16(nbytes); - - _th = (struct tcphdr *)(bp + 1); - memcpy(_th, th, sizeof(*th)); - _th->check = 0; + struct { + struct tcp4_pseudohdr ip; + struct tcphdr tcp; + } h; - sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); - ahash_request_set_crypt(hp->req, &sg, NULL, - sizeof(*bp) + sizeof(*th)); - return crypto_ahash_update(hp->req); + h.ip.saddr = saddr; + h.ip.daddr = daddr; + h.ip.pad = 0; + h.ip.protocol = IPPROTO_TCP; + h.ip.len = cpu_to_be16(nbytes); + h.tcp = *th; + h.tcp.check = 0; + md5_update(ctx, (const u8 *)&h, sizeof(h.ip) + sizeof(h.tcp)); } -static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, const struct tcphdr *th) +static noinline_for_stack void +tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th) { - struct tcp_sigpool hp; - - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; + struct md5_ctx ctx; -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v4_md5_hash_headers(&ctx, daddr, saddr, th, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } -int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, - const struct sock *sk, - const struct sk_buff *skb) +noinline_for_stack void +tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); - struct tcp_sigpool hp; __be32 saddr, daddr; + struct md5_ctx ctx; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; @@ -1632,32 +1618,13 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, daddr = iph->daddr; } - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - - if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) - goto clear_hash; - if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; - -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v4_md5_hash_headers(&ctx, daddr, saddr, th, skb->len); + tcp_md5_hash_skb_data(&ctx, skb, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } -EXPORT_SYMBOL(tcp_v4_md5_hash_skb); +EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb); #endif @@ -1690,11 +1657,9 @@ static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { @@ -1730,7 +1695,7 @@ drop: tcp_listendrop(sk); return 0; } -EXPORT_SYMBOL(tcp_v4_conn_request); +EXPORT_IPV6_MOD(tcp_v4_conn_request); /* @@ -1768,10 +1733,6 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - sk_daddr_set(newsk, ireq->ir_rmt_addr); - sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); - newsk->sk_bound_dev_if = ireq->ir_iif; - newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); @@ -1854,7 +1815,7 @@ put_and_exit: tcp_done(newsk); goto exit; } -EXPORT_SYMBOL(tcp_v4_syn_recv_sock); +EXPORT_IPV6_MOD(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { @@ -1897,6 +1858,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) enum skb_drop_reason reason; struct sock *rsk; + reason = psp_sk_rx_policy_check(sk, skb); + if (reason) + goto err_discard; + if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1958,6 +1923,7 @@ csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); +err_discard: TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } @@ -1965,7 +1931,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; @@ -1982,8 +1948,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) if (th->doff < sizeof(struct tcphdr) / 4) return 0; - sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, - iph->saddr, th->source, + sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { @@ -2016,6 +1981,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, u32 gso_size; u64 limit; int delta; + int err; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. @@ -2025,7 +1991,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ skb_condense(skb); - skb_dst_drop(skb); + tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); @@ -2055,10 +2021,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, !((TCP_SKB_CB(tail)->tcp_flags & TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ - TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || + TCP_SKB_CB(skb)->tcp_flags) & + (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)) || !tcp_skb_can_collapse_rx(tail, skb) || thtail->doff != th->doff || - memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) + memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)) || + /* prior to PSP Rx policy check, retain exact PSP metadata */ + psp_skb_coalesce_diff(tail, skb)) goto no_coalesce; __skb_pull(skb, hdrlen); @@ -2125,23 +2094,29 @@ no_coalesce: limit = min_t(u64, limit, UINT_MAX); - if (unlikely(sk_add_backlog(sk, skb, limit))) { + err = sk_add_backlog(sk, skb, limit); + if (unlikely(err)) { bh_unlock_sock(sk); - *reason = SKB_DROP_REASON_SOCKET_BACKLOG; - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + if (err == -ENOMEM) { + *reason = SKB_DROP_REASON_PFMEMALLOC; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); + } else { + *reason = SKB_DROP_REASON_SOCKET_BACKLOG; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + } return true; } return false; } -EXPORT_SYMBOL(tcp_add_backlog); +EXPORT_IPV6_MOD(tcp_add_backlog); -int tcp_filter(struct sock *sk, struct sk_buff *skb) +int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { struct tcphdr *th = (struct tcphdr *)skb->data; - return sk_filter_trim_cap(sk, skb, th->doff * 4); + return sk_filter_trim_cap(sk, skb, th->doff * 4, reason); } -EXPORT_SYMBOL(tcp_filter); +EXPORT_IPV6_MOD(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { @@ -2163,7 +2138,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = @@ -2176,8 +2151,9 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, int tcp_v4_rcv(struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; + enum tcp_tw_status tw_status; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; @@ -2217,8 +2193,7 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: - sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo, - skb, __tcp_hdrlen(th), th->source, + sk = __inet_lookup_skb(skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; @@ -2239,7 +2214,7 @@ lookup: &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (unlikely(drop_reason)) { - sk_drops_add(sk, skb); + sk_drops_skbadd(sk, skb); reqsk_put(req); goto discard_it; } @@ -2265,13 +2240,12 @@ lookup: } refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) { + if (!tcp_filter(sk, skb, &drop_reason)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); - nsk = tcp_check_req(sk, skb, req, false, &req_stolen); - } else { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + nsk = tcp_check_req(sk, skb, req, false, &req_stolen, + &drop_reason); } if (!nsk) { reqsk_put(req); @@ -2327,10 +2301,9 @@ process: nf_reset_ct(skb); - if (tcp_filter(sk, skb)) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (tcp_filter(sk, skb, &drop_reason)) goto discard_and_relse; - } + th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); @@ -2386,7 +2359,7 @@ discard_it: return 0; discard_and_relse: - sk_drops_add(sk, skb); + sk_drops_skbadd(sk, skb); if (refcounted) sock_put(sk); goto discard_it; @@ -2404,11 +2377,12 @@ do_time_wait: inet_twsk_put(inet_twsk(sk)); goto csum_error; } - switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) { + + tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn, + &drop_reason); + switch (tw_status) { case TCP_TW_SYN: { - struct sock *sk2 = inet_lookup_listener(net, - net->ipv4.tcp_death_row.hashinfo, - skb, __tcp_hdrlen(th), + struct sock *sk2 = inet_lookup_listener(net, skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), @@ -2421,11 +2395,16 @@ do_time_wait: __this_cpu_write(tcp_tw_isn, isn); goto process; } + + drop_reason = psp_twsk_rx_policy_check(inet_twsk(sk), skb); + if (drop_reason) + break; } /* to ACK */ fallthrough; case TCP_TW_ACK: - tcp_v4_timewait_ack(sk, skb); + case TCP_TW_ACK_OOW: + tcp_v4_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); @@ -2438,7 +2417,6 @@ do_time_wait: static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_destructor= tcp_twsk_destructor, }; void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) @@ -2450,7 +2428,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) sk->sk_rx_dst_ifindex = skb->skb_iif; } } -EXPORT_SYMBOL(inet_sk_rx_dst_set); +EXPORT_IPV6_MOD(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, @@ -2462,11 +2440,9 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, - .addr2sockaddr = inet_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in), .mtu_reduced = tcp_v4_mtu_reduced, }; -EXPORT_SYMBOL(ipv4_specific); +EXPORT_IPV6_MOD(ipv4_specific); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { @@ -2482,6 +2458,13 @@ static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; + +static void tcp4_destruct_sock(struct sock *sk) +{ + tcp_md5_destruct_sock(sk); + tcp_ao_destroy_sock(sk, false); + inet_sock_destruct(sk); +} #endif /* NOTE: A lot of things set to zero explicitly by call to @@ -2497,23 +2480,12 @@ static int tcp_v4_init_sock(struct sock *sk) #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; + sk->sk_destruct = tcp4_destruct_sock; #endif return 0; } -#ifdef CONFIG_TCP_MD5SIG -static void tcp_md5sig_info_free_rcu(struct rcu_head *head) -{ - struct tcp_md5sig_info *md5sig; - - md5sig = container_of(head, struct tcp_md5sig_info, rcu); - kfree(md5sig); - static_branch_slow_dec_deferred(&tcp_md5_needed); - tcp_md5_release_sigpool(); -} -#endif - static void tcp_release_user_frags(struct sock *sk) { #ifdef CONFIG_PAGE_POOL @@ -2550,19 +2522,6 @@ void tcp_v4_destroy_sock(struct sock *sk) /* Cleans up our, hopefully empty, out_of_order_queue. */ skb_rbtree_purge(&tp->out_of_order_queue); -#ifdef CONFIG_TCP_MD5SIG - /* Clean up the MD5 key list, if any */ - if (tp->md5sig_info) { - struct tcp_md5sig_info *md5sig; - - md5sig = rcu_dereference_protected(tp->md5sig_info, 1); - tcp_clear_md5_list(sk); - call_rcu(&md5sig->rcu, tcp_md5sig_info_free_rcu); - rcu_assign_pointer(tp->md5sig_info, NULL); - } -#endif - tcp_ao_destroy_sock(sk, false); - /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); @@ -2576,7 +2535,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk_sockets_allocated_dec(sk); } -EXPORT_SYMBOL(tcp_v4_destroy_sock); +EXPORT_IPV6_MOD(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ @@ -2812,7 +2771,7 @@ out: st->last_pos = *pos; return rc; } -EXPORT_SYMBOL(tcp_seq_start); +EXPORT_IPV6_MOD(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { @@ -2843,7 +2802,7 @@ out: st->last_pos = *pos; return rc; } -EXPORT_SYMBOL(tcp_seq_next); +EXPORT_IPV6_MOD(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { @@ -2861,7 +2820,7 @@ void tcp_seq_stop(struct seq_file *seq, void *v) break; } } -EXPORT_SYMBOL(tcp_seq_stop); +EXPORT_IPV6_MOD(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) @@ -2882,7 +2841,7 @@ static void get_openreq4(const struct request_sock *req, jiffies_delta_to_clock_t(delta), req->num_timeout, from_kuid_munged(seq_user_ns(f), - sock_i_uid(req->rsk_listener)), + sk_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, @@ -2910,13 +2869,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_timeout; + timer_expires = tcp_timeout_expires(sk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_timeout; - } else if (timer_pending(&sk->sk_timer)) { + timer_expires = tcp_timeout_expires(sk); + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sk->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = jiffies; @@ -2939,9 +2898,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), - icsk->icsk_retransmits, - from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), - icsk->icsk_probes_out, + READ_ONCE(icsk->icsk_retransmits), + from_kuid_munged(seq_user_ns(f), sk_uid(sk)), + READ_ONCE(icsk->icsk_probes_out), sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), @@ -3000,13 +2959,17 @@ out: } #ifdef CONFIG_BPF_SYSCALL +union bpf_tcp_iter_batch_item { + struct sock *sk; + __u64 cookie; +}; + struct bpf_tcp_iter_state { struct tcp_iter_state state; unsigned int cur_sk; unsigned int end_sk; unsigned int max_sk; - struct sock **batch; - bool st_bucket_done; + union bpf_tcp_iter_batch_item *batch; }; struct bpf_iter__tcp { @@ -3029,21 +2992,32 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { - while (iter->cur_sk < iter->end_sk) - sock_gen_put(iter->batch[iter->cur_sk++]); + union bpf_tcp_iter_batch_item *item; + unsigned int cur_sk = iter->cur_sk; + __u64 cookie; + + /* Remember the cookies of the sockets we haven't seen yet, so we can + * pick up where we left off next time around. + */ + while (cur_sk < iter->end_sk) { + item = &iter->batch[cur_sk++]; + cookie = sock_gen_cookie(item->sk); + sock_gen_put(item->sk); + item->cookie = cookie; + } } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, - unsigned int new_batch_sz) + unsigned int new_batch_sz, gfp_t flags) { - struct sock **new_batch; + union bpf_tcp_iter_batch_item *new_batch; new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, - GFP_USER | __GFP_NOWARN); + flags | __GFP_NOWARN); if (!new_batch) return -ENOMEM; - bpf_iter_tcp_put_batch(iter); + memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk); kvfree(iter->batch); iter->batch = new_batch; iter->max_sk = new_batch_sz; @@ -3051,112 +3025,234 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, return 0; } -static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, - struct sock *start_sk) +static struct sock *bpf_iter_tcp_resume_bucket(struct sock *first_sk, + union bpf_tcp_iter_batch_item *cookies, + int n_cookies) +{ + struct hlist_nulls_node *node; + struct sock *sk; + int i; + + for (i = 0; i < n_cookies; i++) { + sk = first_sk; + sk_nulls_for_each_from(sk, node) + if (cookies[i].cookie == atomic64_read(&sk->sk_cookie)) + return sk; + } + + return NULL; +} + +static struct sock *bpf_iter_tcp_resume_listening(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; + unsigned int find_cookie = iter->cur_sk; + unsigned int end_cookie = iter->end_sk; + int resume_bucket = st->bucket; + struct sock *sk; + + if (end_cookie && find_cookie == end_cookie) + ++st->bucket; + + sk = listening_get_first(seq); + iter->cur_sk = 0; + iter->end_sk = 0; + + if (sk && st->bucket == resume_bucket && end_cookie) { + sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); + if (!sk) { + spin_unlock(&hinfo->lhash2[st->bucket].lock); + ++st->bucket; + sk = listening_get_first(seq); + } + } + + return sk; +} + +static struct sock *bpf_iter_tcp_resume_established(struct seq_file *seq) +{ + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + unsigned int find_cookie = iter->cur_sk; + unsigned int end_cookie = iter->end_sk; + int resume_bucket = st->bucket; + struct sock *sk; + + if (end_cookie && find_cookie == end_cookie) + ++st->bucket; + + sk = established_get_first(seq); + iter->cur_sk = 0; + iter->end_sk = 0; + + if (sk && st->bucket == resume_bucket && end_cookie) { + sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); + if (!sk) { + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); + ++st->bucket; + sk = established_get_first(seq); + } + } + + return sk; +} + +static struct sock *bpf_iter_tcp_resume(struct seq_file *seq) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + struct sock *sk = NULL; + + switch (st->state) { + case TCP_SEQ_STATE_LISTENING: + sk = bpf_iter_tcp_resume_listening(seq); + if (sk) + break; + st->bucket = 0; + st->state = TCP_SEQ_STATE_ESTABLISHED; + fallthrough; + case TCP_SEQ_STATE_ESTABLISHED: + sk = bpf_iter_tcp_resume_established(seq); + break; + } + + return sk; +} + +static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, + struct sock **start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; - sock_hold(start_sk); - iter->batch[iter->end_sk++] = start_sk; + sock_hold(*start_sk); + iter->batch[iter->end_sk++].sk = *start_sk; - sk = sk_nulls_next(start_sk); + sk = sk_nulls_next(*start_sk); + *start_sk = NULL; sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); - iter->batch[iter->end_sk++] = sk; + iter->batch[iter->end_sk++].sk = sk; + } else if (!*start_sk) { + /* Remember where we left off. */ + *start_sk = sk; } expected++; } } - spin_unlock(&hinfo->lhash2[st->bucket].lock); return expected; } static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, - struct sock *start_sk) + struct sock **start_sk) { - struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; - struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; - sock_hold(start_sk); - iter->batch[iter->end_sk++] = start_sk; + sock_hold(*start_sk); + iter->batch[iter->end_sk++].sk = *start_sk; - sk = sk_nulls_next(start_sk); + sk = sk_nulls_next(*start_sk); + *start_sk = NULL; sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); - iter->batch[iter->end_sk++] = sk; + iter->batch[iter->end_sk++].sk = sk; + } else if (!*start_sk) { + /* Remember where we left off. */ + *start_sk = sk; } expected++; } } - spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); return expected; } -static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) +static unsigned int bpf_iter_fill_batch(struct seq_file *seq, + struct sock **start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + + if (st->state == TCP_SEQ_STATE_LISTENING) + return bpf_iter_tcp_listening_batch(seq, start_sk); + else + return bpf_iter_tcp_established_batch(seq, start_sk); +} + +static void bpf_iter_tcp_unlock_bucket(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; + + if (st->state == TCP_SEQ_STATE_LISTENING) + spin_unlock(&hinfo->lhash2[st->bucket].lock); + else + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); +} + +static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) +{ + struct bpf_tcp_iter_state *iter = seq->private; unsigned int expected; - bool resized = false; struct sock *sk; + int err; - /* The st->bucket is done. Directly advance to the next - * bucket instead of having the tcp_seek_last_pos() to skip - * one by one in the current bucket and eventually find out - * it has to advance to the next bucket. - */ - if (iter->st_bucket_done) { - st->offset = 0; - st->bucket++; - if (st->state == TCP_SEQ_STATE_LISTENING && - st->bucket > hinfo->lhash2_mask) { - st->state = TCP_SEQ_STATE_ESTABLISHED; - st->bucket = 0; - } - } + sk = bpf_iter_tcp_resume(seq); + if (!sk) + return NULL; /* Done */ -again: - /* Get a new batch */ - iter->cur_sk = 0; - iter->end_sk = 0; - iter->st_bucket_done = false; + expected = bpf_iter_fill_batch(seq, &sk); + if (likely(iter->end_sk == expected)) + goto done; - sk = tcp_seek_last_pos(seq); + /* Batch size was too small. */ + bpf_iter_tcp_unlock_bucket(seq); + bpf_iter_tcp_put_batch(iter); + err = bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2, + GFP_USER); + if (err) + return ERR_PTR(err); + + sk = bpf_iter_tcp_resume(seq); if (!sk) return NULL; /* Done */ - if (st->state == TCP_SEQ_STATE_LISTENING) - expected = bpf_iter_tcp_listening_batch(seq, sk); - else - expected = bpf_iter_tcp_established_batch(seq, sk); - - if (iter->end_sk == expected) { - iter->st_bucket_done = true; - return sk; - } + expected = bpf_iter_fill_batch(seq, &sk); + if (likely(iter->end_sk == expected)) + goto done; - if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) { - resized = true; - goto again; + /* Batch size was still too small. Hold onto the lock while we try + * again with a larger batch to make sure the current bucket's size + * does not change in the meantime. + */ + err = bpf_iter_tcp_realloc_batch(iter, expected, GFP_NOWAIT); + if (err) { + bpf_iter_tcp_unlock_bucket(seq); + return ERR_PTR(err); } - return sk; + expected = bpf_iter_fill_batch(seq, &sk); + WARN_ON_ONCE(iter->end_sk != expected); +done: + bpf_iter_tcp_unlock_bucket(seq); + return iter->batch[0].sk; } static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos) @@ -3186,16 +3282,11 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * meta.seq_num is used instead. */ st->num++; - /* Move st->offset to the next sk in the bucket such that - * the future start() will resume at st->offset in - * st->bucket. See tcp_seek_last_pos(). - */ - st->offset++; - sock_gen_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++].sk); } if (iter->cur_sk < iter->end_sk) - sk = iter->batch[iter->cur_sk]; + sk = iter->batch[iter->cur_sk].sk; else sk = bpf_iter_tcp_batch(seq); @@ -3232,9 +3323,9 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) const struct request_sock *req = v; uid = from_kuid_munged(seq_user_ns(seq), - sock_i_uid(req->rsk_listener)); + sk_uid(req->rsk_listener)); } else { - uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk)); } meta.seq = seq; @@ -3261,10 +3352,8 @@ static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) (void)tcp_prog_seq_show(prog, &meta, v, 0); } - if (iter->cur_sk < iter->end_sk) { + if (iter->cur_sk < iter->end_sk) bpf_iter_tcp_put_batch(iter); - iter->st_bucket_done = false; - } } static const struct seq_operations bpf_iter_tcp_seq_ops = { @@ -3375,9 +3464,8 @@ struct proto tcp_prot = { .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, - .orphan_count = &tcp_orphan_count, - .memory_allocated = &tcp_memory_allocated, + .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, @@ -3434,7 +3522,9 @@ fallback: static int __net_init tcp_sk_init(struct net *net) { - net->ipv4.sysctl_tcp_ecn = 2; + net->ipv4.sysctl_tcp_ecn = TCP_ECN_IN_ECN_OUT_NOECN; + net->ipv4.sysctl_tcp_ecn_option = TCP_ACCECN_OPTION_FULL; + net->ipv4.sysctl_tcp_ecn_option_beacon = TCP_ACCECN_OPTION_BEACON; net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; @@ -3457,6 +3547,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; + net->ipv4.sysctl_tcp_tw_reuse_delay = 1 * MSEC_PER_SEC; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); @@ -3475,13 +3566,14 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; + net->ipv4.sysctl_tcp_rcvbuf_low_rtt = USEC_PER_MSEC; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ net->ipv4.sysctl_tcp_tso_win_divisor = 3; - /* Default TSQ limit of 16 TSO segments */ - net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536; + /* Default TSQ limit of 4 MB */ + net->ipv4.sysctl_tcp_limit_output_bytes = 4 << 20; /* rfc5961 challenge ack rate limiting, per net-ns, disabled by default. */ net->ipv4.sysctl_tcp_challenge_ack_limit = INT_MAX; @@ -3502,8 +3594,9 @@ 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_slack_ns = 10 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; + net->ipv4.sysctl_tcp_comp_sack_rtt_percent = 33; net->ipv4.sysctl_tcp_backlog_ack_defer = 1; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; @@ -3530,6 +3623,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_pingpong_thresh = 1; net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN); + net->ipv4.sysctl_tcp_rto_max_ms = TCP_RTO_MAX_SEC * MSEC_PER_SEC; return 0; } @@ -3580,7 +3674,7 @@ static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) if (err) return err; - err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ); + err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER); if (err) { bpf_iter_fini_seq_net(priv_data); return err; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 52fe17167460..976b56644a8a 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -23,9 +23,9 @@ * Original Author: * Aleksandar Kuzmanovic <akuzma@northwestern.edu> * Available from: - * http://www.ece.rice.edu/~akuzma/Doc/akuzma/TCP-LP.pdf + * https://users.cs.northwestern.edu/~akuzma/doc/TCP-LP-ToN.pdf * Original implementation for 2.4.19: - * http://www-ece.rice.edu/networks/TCP-LP/ + * https://users.cs.northwestern.edu/~akuzma/rice/TCP-LP/linux/tcp-lp-linux.htm * * 2.6.x module Authors: * Wong Hoi Sing, Edison <hswong3i@gmail.com> @@ -113,6 +113,8 @@ static void tcp_lp_init(struct sock *sk) /** * tcp_lp_cong_avoid * @sk: socket to avoid congesting + * @ack: current ack sequence number + * @acked: number of ACKed packets * * Implementation of cong_avoid. * Will only call newReno CA when away from inference. @@ -261,6 +263,7 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt) /** * tcp_lp_pkts_acked * @sk: socket requiring congestion avoidance calculations + * @sample: ACK sample containing timing and rate information * * Implementation of pkts_acked. * Deal with active drop under Early Congestion Indication. diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 95669935494e..45b6ecd16412 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -166,11 +166,11 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, unsigned int hash) { struct tcp_metrics_block *tm; - struct net *net; bool reclaim = false; + struct net *net; spin_lock_bh(&tcp_metrics_lock); - net = dev_net(dst->dev); + net = dst_dev_net_rcu(dst); /* While waiting for the spin-lock the cache might have been populated * with this entry and so we have to check again. @@ -273,7 +273,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, return NULL; } - net = dev_net(dst->dev); + net = dst_dev_net_rcu(dst); hash ^= net_hash_mix(net); hash = hash_32(hash, tcp_metrics_hash_log); @@ -318,7 +318,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, else return NULL; - net = dev_net(dst->dev); + net = dst_dev_net_rcu(dst); hash ^= net_hash_mix(net); hash = hash_32(hash, tcp_metrics_hash_log); @@ -912,7 +912,7 @@ static void tcp_metrics_flush_all(struct net *net) spin_lock_bh(&tcp_metrics_lock); for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { match = net ? net_eq(tm_net(tm), net) : - !refcount_read(&tm_net(tm)->ns.count); + !check_net(tm_net(tm)); if (match) { rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bb1fe1ba867a..bd5462154f97 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -20,9 +20,11 @@ */ #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/xfrm.h> #include <net/busy_poll.h> #include <net/rstreason.h> +#include <net/psp.h> static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { @@ -44,7 +46,7 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw, /* Send ACK. Note, we do not put the bucket, * it will be released by caller. */ - return TCP_TW_ACK; + return TCP_TW_ACK_OOW; } /* We are rate-limiting, so just release the tw sock and drop skb. */ @@ -97,14 +99,22 @@ static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq, */ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th, u32 *tw_isn) + const struct tcphdr *th, u32 *tw_isn, + enum skb_drop_reason *drop_reason) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt); struct tcp_options_received tmp_opt; + enum skb_drop_reason psp_drop; bool paws_reject = false; int ts_recent_stamp; + /* Instead of dropping immediately, wait to see what value is + * returned. We will accept a non psp-encapsulated syn in the + * case where TCP_TW_SYN is returned. + */ + psp_drop = psp_twsk_rx_policy_check(tw, skb); + tmp_opt.saw_tstamp = 0; ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) { @@ -122,6 +132,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) { /* Just repeat all the checks of tcp_rcv_state_process() */ + if (psp_drop) + goto out_put; + /* Out of window, send ACK */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, @@ -157,8 +170,11 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, rcv_nxt); if (tmp_opt.saw_tstamp) { + u64 ts = tcp_clock_ms(); + + WRITE_ONCE(tw->tw_entry_stamp, ts); WRITE_ONCE(tcptw->tw_ts_recent_stamp, - ktime_get_seconds()); + div_u64(ts, MSEC_PER_SEC)); WRITE_ONCE(tcptw->tw_ts_recent, tmp_opt.rcv_tsval); } @@ -189,6 +205,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) { /* In window segment, it may be only reset or bare ack. */ + if (psp_drop) + goto out_put; + if (th->rst) { /* This is TIME_WAIT assassination, in two flavors. * Oh well... nobody has a sufficient solution to this @@ -242,8 +261,13 @@ kill: return TCP_TW_SYN; } - if (paws_reject) - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED); + if (psp_drop) + goto out_put; + + if (paws_reject) { + *drop_reason = SKB_DROP_REASON_TCP_RFC7323_TW_PAWS; + __NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWS_TW_REJECTED); + } if (!th->rst) { /* In this case we must reset the TIMEWAIT timer. @@ -258,10 +282,12 @@ kill: return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); } + +out_put: inet_twsk_put(tw); return TCP_TW_SUCCESS; } -EXPORT_SYMBOL(tcp_timewait_state_process); +EXPORT_IPV6_MOD(tcp_timewait_state_process); static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) { @@ -286,7 +312,6 @@ static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) return; if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) goto out_free; - tcp_md5_add_sigpool(); } return; out_free: @@ -312,10 +337,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); - tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_mark = sk->sk_mark; tw->tw_priority = READ_ONCE(sk->sk_priority); tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; + /* refreshed when we enter true TIME-WAIT state */ + tw->tw_entry_stamp = tcp_time_stamp_ms(tp); tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; tcptw->tw_rcv_wnd = tcp_receive_window(tp); @@ -326,6 +352,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_last_oow_ack_time = 0; tcptw->tw_tx_delay = tp->tcp_tx_delay; tw->tw_txhash = sk->sk_txhash; + tw->tw_tx_queue_mapping = sk->sk_tx_queue_mapping; +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING + tw->tw_rx_queue_mapping = sk->sk_rx_queue_mapping; +#endif #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -365,31 +395,21 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } EXPORT_SYMBOL(tcp_time_wait); -#ifdef CONFIG_TCP_MD5SIG -static void tcp_md5_twsk_free_rcu(struct rcu_head *head) -{ - struct tcp_md5sig_key *key; - - key = container_of(head, struct tcp_md5sig_key, rcu); - kfree(key); - static_branch_slow_dec_deferred(&tcp_md5_needed); - tcp_md5_release_sigpool(); -} -#endif - void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) - call_rcu(&twsk->tw_md5_key->rcu, tcp_md5_twsk_free_rcu); + if (twsk->tw_md5_key) { + kfree(twsk->tw_md5_key); + static_branch_slow_dec_deferred(&tcp_md5_needed); + } } #endif tcp_ao_destroy_sock(sk, true); + psp_twsk_assoc_free(inet_twsk(sk)); } -EXPORT_SYMBOL_GPL(tcp_twsk_destructor); void tcp_twsk_purge(struct list_head *net_exit_list) { @@ -448,12 +468,27 @@ void tcp_openreq_init_rwin(struct request_sock *req, rcv_wnd); ireq->rcv_wscale = rcv_wscale; } -EXPORT_SYMBOL(tcp_openreq_init_rwin); -static void tcp_ecn_openreq_child(struct tcp_sock *tp, - const struct request_sock *req) +static void tcp_ecn_openreq_child(struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb) { - tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0; + const struct tcp_request_sock *treq = tcp_rsk(req); + struct tcp_sock *tp = tcp_sk(sk); + + if (treq->accecn_ok) { + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_snt = treq->syn_ect_snt; + tcp_accecn_third_ack(sk, skb, treq->syn_ect_snt); + tp->saw_accecn_opt = treq->saw_accecn_opt; + tp->prev_ecnfield = treq->syn_ect_rcv; + tp->accecn_opt_demand = 1; + tcp_ecn_received_counters_payload(sk, skb); + } else { + tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ? + TCP_ECN_MODE_RFC3168 : + TCP_ECN_DISABLED); + } } void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) @@ -483,7 +518,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) tcp_set_ca_state(sk, TCP_CA_Open); } -EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); +EXPORT_IPV6_MOD_GPL(tcp_ca_openreq_child); static void smc_check_reset_syn_req(const struct tcp_sock *oldtp, struct request_sock *req, @@ -557,8 +592,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(newsk, - keepalive_time_when(newtp)); + tcp_reset_keepalive_timer(newsk, keepalive_time_when(newtp)); newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; newtp->rx_opt.sack_ok = ireq->sack_ok; @@ -578,7 +612,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, if (newtp->rx_opt.tstamp_ok) { newtp->tcp_usec_ts = treq->req_usec_ts; - newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); + newtp->rx_opt.ts_recent = req->ts_recent; newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +653,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; - tcp_ecn_openreq_child(newtp, req); + tcp_ecn_openreq_child(newsk, req, skb); newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); @@ -650,28 +684,37 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - bool fastopen, bool *req_stolen) + bool fastopen, bool *req_stolen, + enum skb_drop_reason *drop_reason) { struct tcp_options_received tmp_opt; struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); + bool tsecr_reject = false; bool paws_reject = false; bool own_req; tmp_opt.saw_tstamp = 0; + tmp_opt.accecn = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = READ_ONCE(req->ts_recent); - if (tmp_opt.rcv_tsecr) + tmp_opt.ts_recent = req->ts_recent; + if (tmp_opt.rcv_tsecr) { + if (inet_rsk(req)->tstamp_ok && !fastopen) + tsecr_reject = !between(tmp_opt.rcv_tsecr, + tcp_rsk(req)->snt_tsval_first, + READ_ONCE(tcp_rsk(req)->snt_tsval_last)); tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; + } /* We do not store true stamp, but it is not required, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ; + tmp_opt.ts_recent_stamp = ktime_get_seconds() - + tcp_reqsk_timeout(req) / HZ; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -707,10 +750,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, &tcp_rsk(req)->last_oow_ack_time) && - !inet_rtx_syn_ack(sk, req)) { + !tcp_rtx_synack(sk, req)) { unsigned long expires = jiffies; - expires += reqsk_timeout(req, TCP_RTO_MAX); + expires += tcp_reqsk_timeout(req); if (!fastopen) mod_timer_pending(&req->rsk_timer, expires); else @@ -781,37 +824,34 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1)) return sk; - /* Also, it would be not so bad idea to check rcv_tsecr, which - * is essentially ACK extension and too early or too late values - * should cause reset in unsynchronized states. - */ - /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, - tcp_rsk(req)->rcv_nxt + - tcp_synack_window(req))) { + if (paws_reject || tsecr_reject || + !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, &tcp_rsk(req)->last_oow_ack_time)) req->rsk_ops->send_ack(sk, skb, req); - if (paws_reject) + if (paws_reject) { + SKB_DR_SET(*drop_reason, TCP_RFC7323_PAWS); NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + } else if (tsecr_reject) { + SKB_DR_SET(*drop_reason, TCP_RFC7323_TSECR); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TSECRREJECTED); + } else { + SKB_DR_SET(*drop_reason, TCP_OVERWINDOW); + } return NULL; } /* In sequence, PAWS is OK. */ - /* TODO: We probably should defer ts_recent change once - * we take ownership of @req. - */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); - if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting at tcp_rsk(req)->rcv_isn + 1. */ @@ -835,6 +875,18 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + if (tcp_rsk(req)->accecn_ok && tmp_opt.accecn && + tcp_rsk(req)->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tmp_opt.accecn); + + tcp_rsk(req)->saw_accecn_opt = saw_opt; + if (tcp_rsk(req)->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN) { + u8 fail_mode = TCP_ACCECN_OPT_FAIL_RECV; + + tcp_rsk(req)->accecn_fail_mode |= fail_mode; + } + } + /* For Fast Open no more processing is needed (sk is the * child socket). */ @@ -860,6 +912,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + if (own_req && tmp_opt.saw_tstamp && + !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) + tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval; + if (own_req && rsk_drop_req(req)) { reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); @@ -872,6 +928,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: + SKB_DR_SET(*drop_reason, TCP_LISTEN_OVERFLOW); if (sk != req->rsk_listener) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); @@ -901,7 +958,7 @@ embryonic_reset: } return NULL; } -EXPORT_SYMBOL(tcp_check_req); +EXPORT_IPV6_MOD(tcp_check_req); /* * Queue segment on the new socket if the new socket is active, @@ -943,4 +1000,4 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, sock_put(child); return reason; } -EXPORT_SYMBOL(tcp_child_process); +EXPORT_IPV6_MOD(tcp_child_process); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 2308665b51c5..fdda18b1abda 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -13,12 +13,15 @@ #include <net/tcp.h> #include <net/protocol.h> -static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, +static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb, unsigned int seq, unsigned int mss) { + u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP; + u32 ts_seq = skb_shinfo(gso_skb)->tskey; + while (skb) { if (before(ts_seq, seq + mss)) { - skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP; + skb_shinfo(skb)->tx_flags |= flags; skb_shinfo(skb)->tskey = ts_seq; return; } @@ -139,6 +142,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, struct sk_buff *gso_skb = skb; __sum16 newcheck; bool ooo_okay, copy_destructor; + bool ecn_cwr_mask; __wsum delta; th = tcp_hdr(skb); @@ -193,11 +197,13 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th = tcp_hdr(skb); seq = ntohl(th->seq); - if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) - tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); + if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP)) + tcp_gso_tstamp(segs, gso_skb, seq, mss); newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta)); + ecn_cwr_mask = !!(skb_shinfo(gso_skb)->gso_type & SKB_GSO_TCP_ACCECN); + while (skb->next) { th->fin = th->psh = 0; th->check = newcheck; @@ -217,7 +223,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th = tcp_hdr(skb); th->seq = htonl(seq); - th->cwr = 0; + + th->cwr &= ecn_cwr_mask; } /* Following permits TCP Small Queues to work well with GSO : @@ -275,33 +282,6 @@ struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th) return NULL; } -struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) -{ - unsigned int thlen, hlen, off; - struct tcphdr *th; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*th); - th = skb_gro_header(skb, hlen, off); - if (unlikely(!th)) - return NULL; - - thlen = th->doff * 4; - if (thlen < sizeof(*th)) - return NULL; - - hlen = off + thlen; - if (!skb_gro_may_pull(skb, hlen)) { - th = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!th)) - return NULL; - } - - skb_gro_pull(skb, thlen); - - return th; -} - struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th) { @@ -325,7 +305,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, th2 = tcp_hdr(p); flush = (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & - ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); + ~(TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ @@ -352,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) mss = 1; @@ -401,7 +382,7 @@ void tcp_gro_complete(struct sk_buff *skb) shinfo->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) - shinfo->gso_type |= SKB_GSO_TCP_ECN; + shinfo->gso_type |= SKB_GSO_TCP_ACCECN; } EXPORT_SYMBOL(tcp_gro_complete); @@ -425,14 +406,13 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, inet_get_iif_sdif(skb, &iif, &sdif); iph = skb_gro_network_header(skb); - net = dev_net(skb->dev); - sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, - iph->saddr, th->source, + net = dev_net_rcu(skb->dev); + sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); NAPI_GRO_CB(skb)->is_flist = !sk; if (sk) - sock_put(sk); + sock_gen_put(sk); } INDIRECT_CALLABLE_SCOPE @@ -477,6 +457,7 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); + BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID << 1 != SKB_GSO_TCP_FIXEDID_INNER); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | (NAPI_GRO_CB(skb)->ip_fixedid * SKB_GSO_TCP_FIXEDID); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5485a70b5fe5..479afb714bdf 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -38,8 +38,11 @@ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> +#include <net/tcp_ecn.h> #include <net/mptcp.h> +#include <net/smc.h> #include <net/proto_memory.h> +#include <net/psp.h> #include <linux/compiler.h> #include <linux/gfp.h> @@ -250,7 +253,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, WRITE_ONCE(*__window_clamp, min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } -EXPORT_SYMBOL(tcp_select_initial_window); +EXPORT_IPV6_MOD(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return @@ -265,11 +268,14 @@ static u16 tcp_select_window(struct sock *sk) u32 cur_win, new_win; /* Make the window 0 if we failed to queue the data because we - * are out of memory. The window is temporary, so we don't store - * it on the socket. + * are out of memory. */ - if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) { + tp->pred_flags = 0; + tp->rcv_wnd = 0; + tp->rcv_wup = tp->rcv_nxt; return 0; + } cur_win = tcp_receive_window(tp); new_win = __tcp_select_window(sk); @@ -316,60 +322,6 @@ static u16 tcp_select_window(struct sock *sk) return new_win; } -/* Packet ECN state for a SYN-ACK */ -static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) -{ - const struct tcp_sock *tp = tcp_sk(sk); - - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; - if (!(tp->ecn_flags & TCP_ECN_OK)) - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; - else if (tcp_ca_needs_ecn(sk) || - tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); -} - -/* Packet ECN state for a SYN. */ -static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); - bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || - tcp_ca_needs_ecn(sk) || bpf_needs_ecn; - - if (!use_ecn) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) - use_ecn = true; - } - - tp->ecn_flags = 0; - - if (use_ecn) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; - tp->ecn_flags = TCP_ECN_OK; - if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); - } -} - -static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) -{ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) - /* tp->ecn_flags are cleared at a later point in time when - * SYN ACK is ultimatively being received. - */ - TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); -} - -static void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) -{ - if (inet_rsk(req)->ecn_ok) - th->ece = 1; -} - /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ @@ -378,7 +330,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - if (tp->ecn_flags & TCP_ECN_OK) { + if (!tcp_ecn_mode_any(tp)) + return; + + if (tcp_ecn_mode_accecn(tp)) { + if (!tcp_accecn_ace_fail_recv(tp)) + INET_ECN_xmit(sk); + tcp_accecn_set_ace(tp, skb, th); + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; + } else { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { @@ -400,13 +360,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ -static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) +static void tcp_init_nondata_skb(struct sk_buff *skb, struct sock *sk, + u32 seq, u16 flags) { skb->ip_summed = CHECKSUM_PARTIAL; TCP_SKB_CB(skb)->tcp_flags = flags; tcp_skb_pcount_set(skb, 1); + psp_enqueue_set_decrypted(sk, skb); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) @@ -427,6 +389,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) #define OPTION_AO BIT(11) +#define OPTION_ACCECN BIT(12) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -448,6 +411,8 @@ struct tcp_out_options { u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 num_accecn_fields:7, /* number of AccECN fields needed */ + use_synack_ecn_bytes:1; /* Use synack_ecn_bytes or not */ u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ @@ -522,6 +487,7 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk); sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; } @@ -567,6 +533,7 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, sock_owned_by_me(sk); sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_ops.sk = sk; } @@ -643,6 +610,11 @@ static __be32 *process_tcp_ao_options(struct tcp_sock *tp, return ptr; } +/* Initial values for AccECN option, ordered is based on ECN field bits + * similar to received_ecn_bytes. Used for SYN/ACK AccECN option. + */ +static const u32 synack_ecn_bytes[3] = { 0, 0, 0 }; + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -661,6 +633,8 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, struct tcp_out_options *opts, struct tcp_key *key) { + u8 leftover_highbyte = TCPOPT_NOP; /* replace 1st NOP if avail */ + u8 leftover_lowbyte = TCPOPT_NOP; /* replace 2nd NOP in succession */ __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ @@ -696,15 +670,75 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, *ptr++ = htonl(opts->tsecr); } + if (OPTION_ACCECN & options) { + const u32 *ecn_bytes = opts->use_synack_ecn_bytes ? + synack_ecn_bytes : + tp->received_ecn_bytes; + const u8 ect0_idx = INET_ECN_ECT_0 - 1; + const u8 ect1_idx = INET_ECN_ECT_1 - 1; + const u8 ce_idx = INET_ECN_CE - 1; + u32 e0b; + u32 e1b; + u32 ceb; + u8 len; + + e0b = ecn_bytes[ect0_idx] + TCP_ACCECN_E0B_INIT_OFFSET; + e1b = ecn_bytes[ect1_idx] + TCP_ACCECN_E1B_INIT_OFFSET; + ceb = ecn_bytes[ce_idx] + TCP_ACCECN_CEB_INIT_OFFSET; + len = TCPOLEN_ACCECN_BASE + + opts->num_accecn_fields * TCPOLEN_ACCECN_PERFIELD; + + if (opts->num_accecn_fields == 2) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + *ptr++ = htonl(((e1b & 0xff) << 24) | + (ceb & 0xffffff)); + } else if (opts->num_accecn_fields == 1) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + leftover_highbyte = e1b & 0xff; + leftover_lowbyte = TCPOPT_NOP; + } else if (opts->num_accecn_fields == 0) { + leftover_highbyte = TCPOPT_ACCECN1; + leftover_lowbyte = len; + } else if (opts->num_accecn_fields == 3) { + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) | + ((e1b >> 8) & 0xffff)); + *ptr++ = htonl(((e1b & 0xff) << 24) | + (ceb & 0xffffff)); + *ptr++ = htonl(((e0b & 0xffffff) << 8) | + TCPOPT_NOP); + } + if (tp) { + tp->accecn_minlen = 0; + tp->accecn_opt_tstamp = tp->tcp_mstamp; + if (tp->accecn_opt_demand) + tp->accecn_opt_demand--; + } + } + if (unlikely(OPTION_SACK_ADVERTISE & options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; } if (unlikely(OPTION_WSCALE & options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | + u8 highbyte = TCPOPT_NOP; + + /* Do not split the leftover 2-byte to fit into a single + * NOP, i.e., replace this NOP only when 1 byte is leftover + * within leftover_highbyte. + */ + if (unlikely(leftover_highbyte != TCPOPT_NOP && + leftover_lowbyte == TCPOPT_NOP)) { + highbyte = leftover_highbyte; + leftover_highbyte = TCPOPT_NOP; + } + *ptr++ = htonl((highbyte << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); @@ -715,11 +749,13 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, tp->duplicate_sack : tp->selective_acks; int this_sack; - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { @@ -728,6 +764,14 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, } tp->rx_opt.dsack = 0; + } else if (unlikely(leftover_highbyte != TCPOPT_NOP || + leftover_lowbyte != TCPOPT_NOP)) { + *ptr++ = htonl((leftover_highbyte << 24) | + (leftover_lowbyte << 16) | + (TCPOPT_NOP << 8) | + TCPOPT_NOP); + leftover_highbyte = TCPOPT_NOP; + leftover_lowbyte = TCPOPT_NOP; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { @@ -759,34 +803,36 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, mptcp_options_write(th, ptr, tp, opts); } -static void smc_set_option(const struct tcp_sock *tp, +static void smc_set_option(struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc) { + tp->syn_smc = !!smc_call_hsbpf(1, tp, syn_option); + /* re-check syn_smc */ + if (tp->syn_smc && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, - const struct inet_request_sock *ireq, + struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc && ireq->smc_ok) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc && ireq->smc_ok) { + ireq->smc_ok = !!smc_call_hsbpf(1, tp, synack_option, ireq); + /* re-check smc_ok */ + if (ireq->smc_ok && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif @@ -808,6 +854,80 @@ static void mptcp_set_option_cond(const struct request_sock *req, } } +static u32 tcp_synack_options_combine_saving(struct tcp_out_options *opts) +{ + /* How much there's room for combining with the alignment padding? */ + if ((opts->options & (OPTION_SACK_ADVERTISE | OPTION_TS)) == + OPTION_SACK_ADVERTISE) + return 2; + else if (opts->options & OPTION_WSCALE) + return 1; + return 0; +} + +/* Calculates how long AccECN option will fit to @remaining option space. + * + * AccECN option can sometimes replace NOPs used for alignment of other + * TCP options (up to @max_combine_saving available). + * + * Only solutions with at least @required AccECN fields are accepted. + * + * Returns: The size of the AccECN option excluding space repurposed from + * the alignment of the other options. + */ +static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required, + int remaining) +{ + int size = TCP_ACCECN_MAXSIZE; + int sack_blocks_reduce = 0; + int max_combine_saving; + int rem = remaining; + int align_size; + + if (opts->use_synack_ecn_bytes) + max_combine_saving = tcp_synack_options_combine_saving(opts); + else + max_combine_saving = opts->num_sack_blocks > 0 ? 2 : 0; + opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS; + while (opts->num_accecn_fields >= required) { + /* Pad to dword if cannot combine */ + if ((size & 0x3) > max_combine_saving) + align_size = ALIGN(size, 4); + else + align_size = ALIGN_DOWN(size, 4); + + if (rem >= align_size) { + size = align_size; + break; + } else if (opts->num_accecn_fields == required && + opts->num_sack_blocks > 2 && + required > 0) { + /* Try to fit the option by removing one SACK block */ + opts->num_sack_blocks--; + sack_blocks_reduce++; + rem = rem + TCPOLEN_SACK_PERBLOCK; + + opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS; + size = TCP_ACCECN_MAXSIZE; + continue; + } + + opts->num_accecn_fields--; + size -= TCPOLEN_ACCECN_PERFIELD; + } + if (sack_blocks_reduce > 0) { + if (opts->num_accecn_fields >= required) + size -= sack_blocks_reduce * TCPOLEN_SACK_PERBLOCK; + else + opts->num_sack_blocks += sack_blocks_reduce; + } + if (opts->num_accecn_fields < required) + return 0; + + opts->options |= OPTION_ACCECN; + return size; +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ @@ -883,11 +1003,27 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { - opts->options |= OPTION_MPTCP; - remaining -= size; + if (remaining >= size) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } } } + /* Simultaneous open SYN/ACK needs AccECN option but not SYN. + * It is attempted to negotiate the use of AccECN also on the first + * retransmitted SYN, as mentioned in "3.1.4.1. Retransmitted SYNs" + * of AccECN draft. + */ + if (unlikely((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) && + tcp_ecn_mode_accecn(tp) && + inet_csk(sk)->icsk_retransmits < 2 && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && + remaining >= TCPOLEN_ACCECN_BASE)) { + opts->use_synack_ecn_bytes = 1; + remaining -= tcp_options_fit_accecn(opts, 0, remaining); + } + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; @@ -905,6 +1041,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; + struct tcp_request_sock *treq = tcp_rsk(req); if (tcp_key_is_md5(key)) { opts->options |= OPTION_MD5; @@ -936,7 +1073,13 @@ static unsigned int tcp_synack_options(const struct sock *sk, opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + tcp_rsk(req)->ts_off; - opts->tsecr = READ_ONCE(req->ts_recent); + if (!tcp_rsk(req)->snt_tsval_first) { + if (!opts->tsval) + opts->tsval = ~0U; + tcp_rsk(req)->snt_tsval_first = opts->tsval; + } + WRITE_ONCE(tcp_rsk(req)->snt_tsval_last, opts->tsval); + opts->tsecr = req->ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { @@ -961,6 +1104,13 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + if (treq->accecn_ok && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && + req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) { + opts->use_synack_ecn_bytes = 1; + remaining -= tcp_options_fit_accecn(opts, 0, remaining); + } + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); @@ -1017,17 +1167,32 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; - if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + - TCPOLEN_SACK_PERBLOCK)) - return size; + if (likely(remaining >= TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) { + opts->num_sack_blocks = + min_t(unsigned int, eff_sacks, + (remaining - TCPOLEN_SACK_BASE_ALIGNED) / + TCPOLEN_SACK_PERBLOCK); + + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + } else { + opts->num_sack_blocks = 0; + } + } else { + opts->num_sack_blocks = 0; + } - opts->num_sack_blocks = - min_t(unsigned int, eff_sacks, - (remaining - TCPOLEN_SACK_BASE_ALIGNED) / - TCPOLEN_SACK_PERBLOCK); + if (tcp_ecn_mode_accecn(tp)) { + int ecn_opt = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (ecn_opt && tp->saw_accecn_opt && !tcp_accecn_opt_fail_send(tp) && + (ecn_opt >= TCP_ACCECN_OPTION_FULL || tp->accecn_opt_demand || + tcp_accecn_option_beacon_check(sk))) { + opts->use_synack_ecn_bytes = 0; + size += tcp_options_fit_accecn(opts, tp->accecn_minlen, + MAX_TCP_OPTION_SPACE - size); + } } if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, @@ -1053,15 +1218,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * - * Since transmit from skb destructor is forbidden, we use a tasklet + * Since transmit from skb destructor is forbidden, we use a BH work item * to process all sockets that eventually need to send more skbs. - * We use one tasklet per cpu, with its own queue of sockets. + * We use one work item per cpu, with its own queue of sockets. */ -struct tsq_tasklet { - struct tasklet_struct tasklet; +struct tsq_work { + struct work_struct work; struct list_head head; /* queue of tcp sockets */ }; -static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); +static DEFINE_PER_CPU(struct tsq_work, tsq_work); static void tcp_tsq_write(struct sock *sk) { @@ -1091,14 +1256,14 @@ static void tcp_tsq_handler(struct sock *sk) bh_unlock_sock(sk); } /* - * One tasklet per cpu tries to send more skbs. - * We run in tasklet context but need to disable irqs when + * One work item per cpu tries to send more skbs. + * We run in BH context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ -static void tcp_tasklet_func(struct tasklet_struct *t) +static void tcp_tsq_workfn(struct work_struct *work) { - struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet); + struct tsq_work *tsq = container_of(work, struct tsq_work, work); LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; @@ -1166,17 +1331,17 @@ void tcp_release_cb(struct sock *sk) if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk)) tcp_send_ack(sk); } -EXPORT_SYMBOL(tcp_release_cb); +EXPORT_IPV6_MOD(tcp_release_cb); -void __init tcp_tasklet_init(void) +void __init tcp_tsq_work_init(void) { int i; for_each_possible_cpu(i) { - struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + struct tsq_work *tsq = &per_cpu(tsq_work, i); INIT_LIST_HEAD(&tsq->head); - tasklet_setup(&tsq->tasklet, tcp_tasklet_func); + INIT_WORK(&tsq->work, tcp_tsq_workfn); } } @@ -1190,11 +1355,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - struct tsq_tasklet *tsq; + struct tsq_work *tsq; bool empty; /* Keep one reference on sk_wmem_alloc. - * Will be released by sk_free() from here or tcp_tasklet_func() + * Will be released by sk_free() from here or tcp_tsq_workfn() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); @@ -1216,13 +1381,13 @@ void tcp_wfree(struct sk_buff *skb) nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); - /* queue this socket to tasklet queue */ + /* queue this socket to BH workqueue */ local_irq_save(flags); - tsq = this_cpu_ptr(&tsq_tasklet); + tsq = this_cpu_ptr(&tsq_work); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) - tasklet_schedule(&tsq->tasklet); + queue_work(system_bh_wq, &tsq->work); local_irq_restore(flags); return; out: @@ -1382,7 +1547,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | - tcb->tcp_flags); + (tcb->tcp_flags & TCPHDR_FLAGS_MASK)); th->check = 0; th->urg_ptr = 0; @@ -1424,7 +1589,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th, opts.hash_location); if (err) { - kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED); return -ENOMEM; } } @@ -1497,6 +1662,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) /* Advance write_seq and place onto the write_queue. */ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); + psp_enqueue_set_decrypted(sk, skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); @@ -1541,11 +1707,6 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); - if (tp->lost_skb_hint && - before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) - tp->lost_cnt_hint -= decr; - tcp_verify_left_out(tp); } @@ -1603,8 +1764,8 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *buff; int old_factor; long limit; + u16 flags; int nlen; - u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; @@ -1778,7 +1939,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } -EXPORT_SYMBOL(tcp_mtu_to_mss); +EXPORT_IPV6_MOD(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) @@ -1808,7 +1969,6 @@ void tcp_mtup_init(struct sock *sk) if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } -EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. @@ -1852,7 +2012,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) return mss_now; } -EXPORT_SYMBOL(tcp_sync_mss); +EXPORT_IPV6_MOD(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. @@ -2159,7 +2319,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, { int nlen = skb->len - len; struct sk_buff *buff; - u8 flags; + u16 flags; /* All of a TSO frame must be composed of paged data. */ DEBUG_NET_WARN_ON_ONCE(skb->len != skb->data_len); @@ -2212,7 +2372,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); - u32 send_win, cong_win, limit, in_flight; + u32 send_win, cong_win, limit, in_flight, threshold; + u64 srtt_in_ns, expected_ack, how_far_is_the_ack; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; @@ -2274,9 +2435,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, head = tcp_rtx_queue_head(sk); if (!head) goto send_now; - delta = tp->tcp_clock_cache - head->tstamp; - /* If next ACK is likely to come too late (half srtt), do not defer */ - if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0) + + srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us; + /* When is the ACK expected ? */ + expected_ack = head->tstamp + srtt_in_ns; + /* How far from now is the ACK expected ? */ + how_far_is_the_ack = expected_ack - tp->tcp_clock_cache; + + /* If next ACK is likely to come too late, + * ie in more than min(1ms, half srtt), do not defer. + */ + threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC); + + if ((s64)(how_far_is_the_ack - threshold) > 0) goto send_now; /* Ok, it looks like it is advisable to defer. @@ -2607,9 +2778,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift)); - if (sk->sk_pacing_status == SK_PACING_NONE) - limit = min_t(unsigned long, limit, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); + limit = min_t(unsigned long, limit, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && @@ -2628,7 +2798,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, - * after softirq/tasklet schedule. + * after softirq schedule. * This helps when TX completions are delayed too much. */ if (tcp_rtx_queue_empty_or_single_skb(sk)) @@ -2744,6 +2914,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, sent_pkts = 0; tcp_mstamp_refresh(tp); + + /* AccECN option beacon depends on mstamp, it may change mss */ + if (tcp_ecn_mode_accecn(tp) && tcp_accecn_option_beacon_check(sk)) + mss_now = tcp_current_mss(sk); + if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); @@ -2906,7 +3081,7 @@ 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); + tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, true); return true; } @@ -3241,7 +3416,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ - tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; @@ -3325,8 +3499,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; - if (skb_still_in_host_queue(sk, skb)) - return -EBUSY; + if (skb_still_in_host_queue(sk, skb)) { + err = -EBUSY; + goto out; + } start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { @@ -3337,14 +3513,19 @@ start: } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); - return -EINVAL; + err = -EINVAL; + goto out; + } + if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) { + err = -ENOMEM; + goto out; } - if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) - return -ENOMEM; } - if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) - return -EHOSTUNREACH; /* Routing failure or similar. */ + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) { + err = -EHOSTUNREACH; /* Routing failure or similar. */ + goto out; + } cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; @@ -3355,8 +3536,10 @@ start: * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { - if (TCP_SKB_CB(skb)->seq != tp->snd_una) - return -EAGAIN; + if (TCP_SKB_CB(skb)->seq != tp->snd_una) { + err = -EAGAIN; + goto out; + } avail_wnd = cur_mss; } @@ -3368,11 +3551,15 @@ start: } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, - cur_mss, GFP_ATOMIC)) - return -ENOMEM; /* We'll try again later. */ + cur_mss, GFP_ATOMIC)) { + err = -ENOMEM; /* We'll try again later. */ + goto out; + } } else { - if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) - return -ENOMEM; + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) { + err = -ENOMEM; + goto out; + } diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); @@ -3384,7 +3571,10 @@ start: tcp_retrans_try_collapse(sk, skb, avail_wnd); } - /* RFC3168, section 6.1.1.1. ECN fallback */ + /* RFC3168, section 6.1.1.1. ECN fallback + * As AccECN uses the same SYN flags (+ AE), this check covers both + * cases. + */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); @@ -3426,17 +3616,16 @@ start: tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); - if (likely(!err)) { - trace_tcp_retransmit_skb(sk, skb); - } else if (err != -EBUSY) { + if (unlikely(err) && err != -EBUSY) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); - } /* To avoid taking spuriously low RTT samples based on a timestamp * for a transmit that never happened, always mark EVER_RETRANS */ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; +out: + trace_tcp_retransmit_skb(sk, skb, err); return err; } @@ -3540,8 +3729,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) } if (rearm_timer) tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX); + inet_csk(sk)->icsk_rto, true); } /* We allow to exceed memory limits for FIN packets to expedite @@ -3558,13 +3746,17 @@ void sk_forced_mem_schedule(struct sock *sk, int size) delta = size - sk->sk_forward_alloc; if (delta <= 0) return; + amt = sk_mem_pages(delta); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); - sk_memory_allocated_add(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_memcg) - mem_cgroup_charge_skmem(sk->sk_memcg, amt, - gfp_memcg_charge() | __GFP_NOFAIL); + if (mem_cgroup_sk_enabled(sk)) + mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge() | __GFP_NOFAIL); + + if (sk->sk_bypass_prot_mem) + return; + + sk_memory_allocated_add(sk, amt); } /* Send a FIN. The caller locks the socket for us. @@ -3609,7 +3801,7 @@ void tcp_send_fin(struct sock *sk) skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ - tcp_init_nondata_skb(skb, tp->write_seq, + tcp_init_nondata_skb(skb, sk, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } @@ -3637,7 +3829,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority, /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); - tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), + tcp_init_nondata_skb(skb, sk, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ @@ -3848,7 +4040,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, return skb; } -EXPORT_SYMBOL(tcp_make_synack); +EXPORT_IPV6_MOD(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { @@ -3875,6 +4067,7 @@ static void tcp_connect_init(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; + u16 user_mss; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. @@ -3887,8 +4080,9 @@ static void tcp_connect_init(struct sock *sk) tcp_ao_connect_init(sk); /* If user gave his TCP_MAXSEG, record it to clamp */ - if (tp->rx_opt.user_mss) - tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; + user_mss = READ_ONCE(tp->rx_opt.user_mss); + if (user_mss) + tp->rx_opt.mss_clamp = user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); @@ -3939,7 +4133,7 @@ static void tcp_connect_init(struct sock *sk) WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); - inet_csk(sk)->icsk_retransmits = 0; + WRITE_ONCE(inet_csk(sk)->icsk_retransmits, 0); tcp_clear_retrans(tp); } @@ -4132,7 +4326,7 @@ int tcp_connect(struct sock *sk) /* SYN eats a sequence byte, write_seq updated by * tcp_connect_queue_skb(). */ - tcp_init_nondata_skb(buff, tp->write_seq, TCPHDR_SYN); + tcp_init_nondata_skb(buff, sk, tp->write_seq, TCPHDR_SYN); tcp_mstamp_refresh(tp); tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); @@ -4158,8 +4352,8 @@ int tcp_connect(struct sock *sk) TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, false); return 0; } EXPORT_SYMBOL(tcp_connect); @@ -4168,7 +4362,7 @@ u32 tcp_delack_max(const struct sock *sk) { u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1; - return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min); + return min(READ_ONCE(inet_csk(sk)->icsk_delack_max), delack_from_rto_min); } /* Send out a delayed ack, the caller does the policy checking @@ -4214,22 +4408,21 @@ void tcp_send_delayed_ack(struct sock *sk) /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer is about to expire, send ACK now. */ - if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { + if (time_before_eq(icsk_delack_timeout(icsk), jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } - if (!time_before(timeout, icsk->icsk_ack.timeout)) - timeout = icsk->icsk_ack.timeout; + if (!time_before(timeout, icsk_delack_timeout(icsk))) + timeout = icsk_delack_timeout(icsk); } smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER); - icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ -void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags) { struct sk_buff *buff; @@ -4248,17 +4441,18 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) unsigned long delay; delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; - if (delay < TCP_RTO_MAX) + if (delay < tcp_rto_max(sk)) icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, false); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); + tcp_init_nondata_skb(buff, sk, + tcp_acceptable_seq(sk), TCPHDR_ACK | flags); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. @@ -4273,7 +4467,7 @@ EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { - __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt, 0); } /* This routine sends a packet with an out of date sequence @@ -4304,7 +4498,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) * end to send an ack. Don't queue or clone SKB, just * send it. */ - tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); + tcp_init_nondata_skb(skb, sk, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } @@ -4378,17 +4572,17 @@ void tcp_send_probe0(struct sock *sk) if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ - icsk->icsk_probes_out = 0; + WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_backoff = 0; icsk->icsk_probes_tstamp = 0; return; } - icsk->icsk_probes_out++; + WRITE_ONCE(icsk->icsk_probes_out, icsk->icsk_probes_out + 1); if (err <= 0) { if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; - timeout = tcp_probe0_when(sk, TCP_RTO_MAX); + timeout = tcp_probe0_when(sk, tcp_rto_max(sk)); } else { /* If packet was not sent due to local congestion, * Let senders fight for local resources conservatively. @@ -4397,7 +4591,7 @@ void tcp_send_probe0(struct sock *sk) } timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, true); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) @@ -4422,7 +4616,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) tcp_sk_rw(sk)->total_retrans++; } trace_tcp_retransmit_synack(sk, req); + WRITE_ONCE(req->num_retrans, req->num_retrans + 1); } return res; } -EXPORT_SYMBOL(tcp_rtx_synack); +EXPORT_IPV6_MOD(tcp_rtx_synack); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index bba10110fbbc..c52fd3254b6e 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -35,7 +35,7 @@ s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd) tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb)); } -/* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): +/* RACK loss detection (IETF RFC8985): * * Marks a packet lost, if some packet sent later has been (s)acked. * The underlying idea is similar to the traditional dupthresh and FACK diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b412ed88ccd9..160080c9021d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -109,7 +109,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ @@ -189,12 +189,12 @@ static unsigned int tcp_model_timeout(struct sock *sk, { unsigned int linear_backoff_thresh, timeout; - linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base); + linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base); if (boundary <= linear_backoff_thresh) timeout = ((2 << boundary) - 1) * rto_base; else timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + (boundary - linear_backoff_thresh) * tcp_rto_max(sk); return jiffies_to_msecs(timeout); } /** @@ -268,7 +268,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { - const bool alive = icsk->icsk_rto < TCP_RTO_MAX; + const bool alive = icsk->icsk_rto < tcp_rto_max(sk); retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || @@ -322,8 +322,9 @@ void tcp_delack_timer_handler(struct sock *sk) if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; - if (time_after(icsk->icsk_ack.timeout, jiffies)) { - sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); + if (time_after(icsk_delack_timeout(icsk), jiffies)) { + sk_reset_timer(sk, &icsk->icsk_delack_timer, + icsk_delack_timeout(icsk)); return; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; @@ -358,7 +359,7 @@ void tcp_delack_timer_handler(struct sock *sk) static void tcp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = - from_timer(icsk, t, icsk_delack_timer); + timer_container_of(icsk, t, icsk_delack_timer); struct sock *sk = &icsk->icsk_inet.sk; /* Avoid taking socket spinlock if there is no ACK to send. @@ -391,7 +392,7 @@ static void tcp_probe_timer(struct sock *sk) int max_probes; if (tp->packets_out || !skb) { - icsk->icsk_probes_out = 0; + WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_probes_tstamp = 0; return; } @@ -416,7 +417,8 @@ static void tcp_probe_timer(struct sock *sk) } max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { - const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; + unsigned int rto_max = tcp_rto_max(sk); + const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) @@ -442,7 +444,7 @@ static void tcp_update_rto_stats(struct sock *sk) tp->total_rto_recoveries++; tp->rto_stamp = tcp_time_stamp_ms(tp); } - icsk->icsk_retransmits++; + WRITE_ONCE(icsk->icsk_retransmits, icsk->icsk_retransmits + 1); tp->total_rto++; } @@ -456,7 +458,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) struct tcp_sock *tp = tcp_sk(sk); int max_retries; - req->rsk_ops->syn_ack_timeout(req); + tcp_syn_ack_timeout(req); /* Add one more retry for fastopen. * Paired with WRITE_ONCE() in tcp_sock_set_syncnt() @@ -476,13 +478,13 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ - inet_rtx_syn_ack(sk, req); + tcp_rtx_synack(sk, req); req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp_ts(tp); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - req->timeout << req->num_timeout, TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + req->timeout << req->num_timeout, false); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, @@ -492,7 +494,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct inet_connection_sock *icsk = inet_csk(sk); u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - int timeout = TCP_RTO_MAX * 2; + int timeout = tcp_rto_max(sk) * 2; s32 rcv_delta; if (user_timeout) { @@ -508,7 +510,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; + rcv_delta = tcp_timeout_expires(sk) - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; @@ -626,9 +628,9 @@ void tcp_retransmit_timer(struct sock *sk) /* Retransmission failed because of local congestion, * Let senders fight for local resources conservatively. */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - TCP_RESOURCE_PROBE_INTERVAL, - TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_RESOURCE_PROBE_INTERVAL, + false); goto out; } @@ -665,7 +667,7 @@ out_reset_timer: icsk->icsk_backoff = 0; icsk->icsk_rto = clamp(__tcp_set_rto(tp), tcp_rto_min(sk), - TCP_RTO_MAX); + tcp_rto_max(sk)); } else if (sk->sk_state != TCP_SYN_SENT || tp->total_rto > READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) { @@ -673,10 +675,10 @@ out_reset_timer: * activated. */ icsk->icsk_backoff++; - icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); + icsk->icsk_rto = min(icsk->icsk_rto << 1, tcp_rto_max(sk)); } - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + tcp_clamp_rto_to_user_timeout(sk), false); if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); @@ -684,7 +686,8 @@ out:; } /* Called with bottom-half processing disabled. - Called by tcp_write_timer() */ + * Called by tcp_write_timer() and tcp_release_cb(). + */ void tcp_write_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -694,11 +697,11 @@ void tcp_write_timer_handler(struct sock *sk) !icsk->icsk_pending) return; - if (time_after(icsk->icsk_timeout, jiffies)) { - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); + if (time_after(tcp_timeout_expires(sk), jiffies)) { + sk_reset_timer(sk, &sk->tcp_retransmit_timer, + tcp_timeout_expires(sk)); return; } - tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; @@ -722,12 +725,10 @@ void tcp_write_timer_handler(struct sock *sk) static void tcp_write_timer(struct timer_list *t) { - struct inet_connection_sock *icsk = - from_timer(icsk, t, icsk_retransmit_timer); - struct sock *sk = &icsk->icsk_inet.sk; + struct sock *sk = timer_container_of(sk, t, tcp_retransmit_timer); /* Avoid locking the socket when there is no pending event. */ - if (!smp_load_acquire(&icsk->icsk_pending)) + if (!smp_load_acquire(&inet_csk(sk)->icsk_pending)) goto out; bh_lock_sock(sk); @@ -749,7 +750,16 @@ void tcp_syn_ack_timeout(const struct request_sock *req) __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); } -EXPORT_SYMBOL(tcp_syn_ack_timeout); + +void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) +{ + sk_reset_timer(sk, &inet_csk(sk)->icsk_keepalive_timer, jiffies + len); +} + +static void tcp_delete_keepalive_timer(struct sock *sk) +{ + sk_stop_timer(sk, &inet_csk(sk)->icsk_keepalive_timer); +} void tcp_set_keepalive(struct sock *sk, int val) { @@ -757,17 +767,17 @@ void tcp_set_keepalive(struct sock *sk, int val) return; if (val && !sock_flag(sk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); + tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); else if (!val) - inet_csk_delete_keepalive_timer(sk); + tcp_delete_keepalive_timer(sk); } -EXPORT_SYMBOL_GPL(tcp_set_keepalive); - +EXPORT_IPV6_MOD_GPL(tcp_set_keepalive); -static void tcp_keepalive_timer (struct timer_list *t) +static void tcp_keepalive_timer(struct timer_list *t) { - struct sock *sk = from_timer(sk, t, sk_timer); - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + timer_container_of(icsk, t, icsk_keepalive_timer); + struct sock *sk = &icsk->icsk_inet.sk; struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; @@ -775,7 +785,7 @@ static void tcp_keepalive_timer (struct timer_list *t) bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ - inet_csk_reset_keepalive_timer (sk, HZ/20); + tcp_reset_keepalive_timer(sk, HZ/20); goto out; } @@ -827,7 +837,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) { - icsk->icsk_probes_out++; + WRITE_ONCE(icsk->icsk_probes_out, icsk->icsk_probes_out + 1); elapsed = keepalive_intvl_when(tp); } else { /* If keepalive was lost due to local congestion, @@ -841,7 +851,7 @@ static void tcp_keepalive_timer (struct timer_list *t) } resched: - inet_csk_reset_keepalive_timer (sk, elapsed); + tcp_reset_keepalive_timer(sk, elapsed); goto out; death: @@ -884,11 +894,9 @@ void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); - hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED_SOFT); - tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; + hrtimer_setup(&tcp_sk(sk)->pacing_timer, tcp_pace_kick, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); - hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED_SOFT); - tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick; + hrtimer_setup(&tcp_sk(sk)->compressed_ack_timer, tcp_compressed_ack_kick, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED_SOFT); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6a01905d379f..ffe074cb5865 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -68,7 +68,7 @@ * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind * a single port at the same time. - * Derek Atkins <derek@ihtfp.com>: Add Encapulation Support + * Derek Atkins <derek@ihtfp.com>: Add Encapsulation Support * James Chapman : Add L2TP encapsulation type. */ @@ -93,6 +93,7 @@ #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/slab.h> +#include <linux/sock_diag.h> #include <net/tcp_states.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> @@ -119,15 +120,13 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif +#include <net/rps.h> struct udp_table udp_table __read_mostly; -EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_udp_mem); +EXPORT_IPV6_MOD(sysctl_udp_mem); -atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; -EXPORT_SYMBOL(udp_memory_allocated); DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); @@ -144,8 +143,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, unsigned long *bitmap, struct sock *sk, unsigned int log) { + kuid_t uid = sk_uid(sk); struct sock *sk2; - kuid_t uid = sock_i_uid(sk); sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && @@ -157,7 +156,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && - uid_eq(uid, sock_i_uid(sk2))) { + uid_eq(uid, sk_uid(sk2))) { if (!bitmap) return 0; } else { @@ -179,8 +178,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, struct udp_hslot *hslot2, struct sock *sk) { + kuid_t uid = sk_uid(sk); struct sock *sk2; - kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); @@ -194,7 +193,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && - uid_eq(uid, sock_i_uid(sk2))) { + uid_eq(uid, sk_uid(sk2))) { res = 0; } else { res = 1; @@ -209,7 +208,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) { struct net *net = sock_net(sk); - kuid_t uid = sock_i_uid(sk); + kuid_t uid = sk_uid(sk); struct sock *sk2; sk_for_each(sk2, &hslot->head) { @@ -219,7 +218,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) ipv6_only_sock(sk2) == ipv6_only_sock(sk) && (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && + sk2->sk_reuseport && uid_eq(uid, sk_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) { return reuseport_add_sock(sk, sk2, inet_rcv_saddr_any(sk)); @@ -352,7 +351,7 @@ fail_unlock: fail: return error; } -EXPORT_SYMBOL(udp_lib_get_port); +EXPORT_IPV6_MOD(udp_lib_get_port); int udp_v4_get_port(struct sock *sk, unsigned short snum) { @@ -418,7 +417,50 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, return __inet_ehashfn(laddr, lport, faddr, fport, udp_ehash_secret + net_hash_mix(net)); } -EXPORT_SYMBOL(udp_ehashfn); +EXPORT_IPV6_MOD(udp_ehashfn); + +/** + * udp4_lib_lookup1() - Simplified lookup using primary hash (destination port) + * @net: Network namespace + * @saddr: Source address, network order + * @sport: Source port, network order + * @daddr: Destination address, network order + * @hnum: Destination port, host order + * @dif: Destination interface index + * @sdif: Destination bridge port index, if relevant + * @udptable: Set of UDP hash tables + * + * Simplified lookup to be used as fallback if no sockets are found due to a + * potential race between (receive) address change, and lookup happening before + * the rehash operation. This function ignores SO_REUSEPORT groups while scoring + * result sockets, because if we have one, we don't need the fallback at all. + * + * Called under rcu_read_lock(). + * + * Return: socket with highest matching score if any, NULL if none + */ +static struct sock *udp4_lib_lookup1(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + const struct udp_table *udptable) +{ + unsigned int slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot = &udptable->hash[slot]; + struct sock *sk, *result = NULL; + int score, badness = 0; + + sk_for_each_rcu(sk, &hslot->head) { + score = compute_score(sk, net, + saddr, sport, daddr, hnum, dif, sdif); + if (score > badness) { + result = sk; + badness = score; + } + } + + return result; +} /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(const struct net *net, @@ -467,7 +509,7 @@ rescore: /* compute_score is too long of a function to be * inlined, and calling it again here yields - * measureable overhead for some + * measurable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ @@ -533,7 +575,7 @@ begin: return NULL; } -/* In hash4, rehash can happen in connect(), where hash4_cnt keeps unchanged. */ +/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */ static void udp_rehash4(struct udp_table *udptable, struct sock *sk, u16 newhash4) { @@ -582,15 +624,13 @@ void udp_lib_hash4(struct sock *sk, u16 hash) struct net *net = sock_net(sk); struct udp_table *udptable; - /* Connected udp socket can re-connect to another remote address, - * so rehash4 is needed. + /* Connected udp socket can re-connect to another remote address, which + * will be handled by rehash. Thus no need to redo hash4 here. */ - udptable = net->ipv4.udp_table; - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, hash); + if (udp_hashed4(sk)) return; - } + udptable = net->ipv4.udp_table; hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); hslot4 = udp_hashslot4(udptable, hash); @@ -612,7 +652,7 @@ void udp_lib_hash4(struct sock *sk, u16 hash) spin_unlock_bh(&hslot->lock); } -EXPORT_SYMBOL(udp_lib_hash4); +EXPORT_IPV6_MOD(udp_lib_hash4); /* call with sock lock */ void udp4_hash4(struct sock *sk) @@ -628,7 +668,7 @@ void udp4_hash4(struct sock *sk) udp_lib_hash4(sk, hash); } -EXPORT_SYMBOL(udp4_hash4); +EXPORT_IPV6_MOD(udp4_hash4); #endif /* CONFIG_BASE_SMALL */ /* UDP is nearly always wildcards out the wazoo, it makes no sense to try @@ -683,6 +723,19 @@ struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif, hslot2, skb); + if (!IS_ERR_OR_NULL(result)) + goto done; + + /* Primary hash (destination port) lookup as fallback for this race: + * 1. __ip4_datagram_connect() sets sk_rcv_saddr + * 2. lookup (this function): new sk_rcv_saddr, hashes not updated yet + * 3. rehash operation updating _secondary and four-tuple_ hashes + * The primary hash doesn't need an update after 1., so, thanks to this + * further step, 1. and 3. don't need to be atomic against the lookup. + */ + result = udp4_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif, + udptable); + done: if (IS_ERR(result)) return NULL; @@ -755,11 +808,11 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); -EXPORT_SYMBOL(udp_encap_needed_key); +EXPORT_IPV6_MOD(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); -EXPORT_SYMBOL(udpv6_encap_needed_key); +EXPORT_IPV6_MOD(udpv6_encap_needed_key); #endif void udp_encap_enable(void) @@ -987,7 +1040,7 @@ void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } -EXPORT_SYMBOL(udp_flush_pending_frames); +EXPORT_IPV6_MOD(udp_flush_pending_frames); /** * udp4_hwcsum - handle outgoing HW checksumming @@ -1087,9 +1140,9 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) { + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { kfree_skb(skb); - return -EINVAL; + return -EMSGSIZE; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); @@ -1175,7 +1228,7 @@ out: WRITE_ONCE(up->pending, 0); return err; } -EXPORT_SYMBOL(udp_push_pending_frames); +EXPORT_IPV6_MOD(udp_push_pending_frames); static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) { @@ -1212,7 +1265,7 @@ int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) return need_ip; } -EXPORT_SYMBOL_GPL(udp_cmsg_send); +EXPORT_IPV6_MOD_GPL(udp_cmsg_send); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { @@ -1227,7 +1280,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int free = 0; int connected = 0; __be32 daddr, faddr, saddr; - u8 tos, scope; + u8 scope; __be16 dport; int err, is_udplite = IS_UDPLITE(sk); int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; @@ -1351,7 +1404,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) faddr = ipc.opt->opt.faddr; connected = 0; } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); if (scope == RT_SCOPE_LINK) connected = 0; @@ -1388,9 +1440,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, sk->sk_protocol, flow_flags, faddr, saddr, - dport, inet->inet_sport, sk->sk_uid); + dport, inet->inet_sport, + sk_uid(sk)); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); @@ -1507,7 +1561,7 @@ void udp_splice_eof(struct socket *sock) udp_push_pending_frames(sk); release_sock(sk); } -EXPORT_SYMBOL_GPL(udp_splice_eof); +EXPORT_IPV6_MOD_GPL(udp_splice_eof); #define UDP_SKB_IS_STATELESS 0x80000000 @@ -1572,12 +1626,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb) } /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial, - bool rx_queue_lock_held) +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; - int amt; + unsigned int amt; if (likely(partial)) { up->forward_deficit += size; @@ -1597,10 +1651,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); - - sk_forward_alloc_add(sk, size); - amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk_forward_alloc_add(sk, -amt); + amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); + sk_forward_alloc_add(sk, size - amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1624,7 +1676,7 @@ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } -EXPORT_SYMBOL(udp_skb_destructor); +EXPORT_IPV6_MOD(udp_skb_destructor); /* as above, but the caller held the rx queue lock, too */ static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) @@ -1633,31 +1685,6 @@ static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); } -/* Idea of busylocks is to let producers grab an extra spinlock - * to relieve pressure on the receive_queue spinlock shared by consumer. - * Under flood, this means that only one producer can be in line - * trying to acquire the receive_queue spinlock. - * These busylock can be allocated on a per cpu manner, instead of a - * per socket one (that would consume a cache line per socket) - */ -static int udp_busylocks_log __read_mostly; -static spinlock_t *udp_busylocks __read_mostly; - -static spinlock_t *busylock_acquire(void *ptr) -{ - spinlock_t *busy; - - busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log); - spin_lock(busy); - return busy; -} - -static void busylock_release(spinlock_t *busy) -{ - if (busy) - spin_unlock(busy); -} - static int udp_rmem_schedule(struct sock *sk, int size) { int delta; @@ -1672,18 +1699,35 @@ static int udp_rmem_schedule(struct sock *sk, int size) int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; - int rmem, err = -ENOMEM; - spinlock_t *busy = NULL; - bool becomes_readable; - int size, rcvbuf; + struct udp_prod_queue *udp_prod_queue; + struct sk_buff *next, *to_drop = NULL; + struct llist_node *ll_list; + unsigned int rmem, rcvbuf; + int size, err = -ENOMEM; + int total_size = 0; + int q_size = 0; + int dropcount; + int nb = 0; - /* Immediately drop when the receive queue is full. - * Always allow at least one packet. - */ rmem = atomic_read(&sk->sk_rmem_alloc); rcvbuf = READ_ONCE(sk->sk_rcvbuf); - if (rmem > rcvbuf) - goto drop; + size = skb->truesize; + + udp_prod_queue = &udp_sk(sk)->udp_prod_queue[numa_node_id()]; + + rmem += atomic_read(&udp_prod_queue->rmem_alloc); + + /* Immediately drop when the receive queue is full. + * Cast to unsigned int performs the boundary check for INT_MAX. + */ + if (rmem + size > rcvbuf) { + if (rcvbuf > INT_MAX >> 1) + goto drop; + + /* Accept the packet if queue is empty. */ + if (rmem) + goto drop; + } /* Under mem pressure, it might be helpful to help udp_recvmsg() * having linear skbs : @@ -1693,53 +1737,81 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ if (rmem > (rcvbuf >> 1)) { skb_condense(skb); - - busy = busylock_acquire(sk); + size = skb->truesize; } - size = skb->truesize; + udp_set_dev_scratch(skb); - atomic_add(size, &sk->sk_rmem_alloc); + atomic_add(size, &udp_prod_queue->rmem_alloc); + + if (!llist_add(&skb->ll_node, &udp_prod_queue->ll_root)) + return 0; + + dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? sk_drops_read(sk) : 0; spin_lock(&list->lock); - err = udp_rmem_schedule(sk, size); - if (err) { - spin_unlock(&list->lock); - goto uncharge_drop; - } - sk_forward_alloc_add(sk, -size); + ll_list = llist_del_all(&udp_prod_queue->ll_root); - /* no need to setup a destructor, we will explicitly release the - * forward allocated memory on dequeue - */ - sock_skb_set_dropcount(sk, skb); + ll_list = llist_reverse_order(ll_list); + + llist_for_each_entry_safe(skb, next, ll_list, ll_node) { + size = udp_skb_truesize(skb); + total_size += size; + err = udp_rmem_schedule(sk, size); + if (unlikely(err)) { + /* Free the skbs outside of locked section. */ + skb->next = to_drop; + to_drop = skb; + continue; + } + + q_size += size; + sk_forward_alloc_add(sk, -size); + + /* no need to setup a destructor, we will explicitly release the + * forward allocated memory on dequeue + */ + SOCK_SKB_CB(skb)->dropcount = dropcount; + nb++; + __skb_queue_tail(list, skb); + } + + atomic_add(q_size, &sk->sk_rmem_alloc); - becomes_readable = skb_queue_empty(list); - __skb_queue_tail(list, skb); spin_unlock(&list->lock); if (!sock_flag(sk, SOCK_DEAD)) { - if (becomes_readable || - sk->sk_data_ready != sock_def_readable || - READ_ONCE(sk->sk_peek_off) >= 0) + /* Multiple threads might be blocked in recvmsg(), + * using prepare_to_wait_exclusive(). + */ + while (nb) { INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk); - else - sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); + nb--; + } } - busylock_release(busy); - return 0; -uncharge_drop: - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + if (unlikely(to_drop)) { + for (nb = 0; to_drop != NULL; nb++) { + skb = to_drop; + to_drop = skb->next; + skb_mark_not_on_list(skb); + /* TODO: update SNMP values. */ + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_PROTO_MEM); + } + numa_drop_add(&udp_sk(sk)->drop_counters, nb); + } + + atomic_sub(total_size, &udp_prod_queue->rmem_alloc); + + return 0; drop: - atomic_inc(&sk->sk_drops); - busylock_release(busy); + udp_drops_inc(sk); return err; } -EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); +EXPORT_IPV6_MOD_GPL(__udp_enqueue_schedule_skb); void udp_destruct_common(struct sock *sk) { @@ -1754,8 +1826,9 @@ void udp_destruct_common(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); + kfree(up->udp_prod_queue); } -EXPORT_SYMBOL_GPL(udp_destruct_common); +EXPORT_IPV6_MOD_GPL(udp_destruct_common); static void udp_destruct_sock(struct sock *sk) { @@ -1765,10 +1838,11 @@ static void udp_destruct_sock(struct sock *sk) int udp_init_sock(struct sock *sk) { - udp_lib_init_sock(sk); + int res = udp_lib_init_sock(sk); + sk->sk_destruct = udp_destruct_sock; set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); - return 0; + return res; } void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) @@ -1776,6 +1850,11 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) if (unlikely(READ_ONCE(udp_sk(sk)->peeking_with_offset))) sk_peek_offset_bwd(sk, len); + if (!skb_shared(skb)) { + skb_attempt_defer_free(skb); + return; + } + if (!skb_unref(skb)) return; @@ -1786,11 +1865,11 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) skb_release_head_state(skb); __consume_stateless_skb(skb); } -EXPORT_SYMBOL_GPL(skb_consume_udp); +EXPORT_IPV6_MOD_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, - int *total) + unsigned int *total) { struct sk_buff *skb; @@ -1800,10 +1879,10 @@ static struct sk_buff *__first_packet_length(struct sock *sk, IS_UDPLITE(sk)); __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); - atomic_inc(&sk->sk_drops); + udp_drops_inc(sk); __skb_unlink(skb, rcvq); *total += skb->truesize; - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); } else { udp_skb_csum_unnecessary_set(skb); break; @@ -1823,8 +1902,8 @@ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - int total = 0; int res; spin_lock_bh(&rcvq->lock); @@ -1868,7 +1947,7 @@ int udp_ioctl(struct sock *sk, int cmd, int *karg) return 0; } -EXPORT_SYMBOL(udp_ioctl); +EXPORT_IPV6_MOD(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, int *err) @@ -1891,8 +1970,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, error = -EAGAIN; do { spin_lock_bh(&queue->lock); - skb = __skb_try_recv_from_queue(sk, queue, flags, off, - err, &last); + skb = __skb_try_recv_from_queue(queue, flags, off, err, + &last); if (skb) { if (!(flags & MSG_PEEK)) udp_skb_destructor(sk, skb); @@ -1913,8 +1992,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); - skb = __skb_try_recv_from_queue(sk, queue, flags, off, - err, &last); + skb = __skb_try_recv_from_queue(queue, flags, off, err, + &last); if (skb && !(flags & MSG_PEEK)) udp_skb_dtor_locked(sk, skb); spin_unlock(&sk_queue->lock); @@ -1956,15 +2035,15 @@ try_again: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite); __UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - kfree_skb(skb); + udp_drops_inc(sk); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); goto try_again; } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); return recv_actor(sk, skb); } -EXPORT_SYMBOL(udp_read_skb); +EXPORT_IPV6_MOD(udp_read_skb); /* * This should be easy, if there is something there we @@ -2026,7 +2105,7 @@ try_again: if (unlikely(err)) { if (!peeking) { - atomic_inc(&sk->sk_drops); + udp_drops_inc(sk); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } @@ -2072,7 +2151,7 @@ csum_copy_err: UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); /* starting over for a new packet, but check if we need to yield */ cond_resched(); @@ -2080,7 +2159,8 @@ csum_copy_err: goto try_again; } -int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int udp_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { /* This check is replicated from __ip4_datagram_connect() and * intended to prevent BPF program called below from accessing bytes @@ -2091,9 +2171,10 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } -EXPORT_SYMBOL(udp_pre_connect); +EXPORT_IPV6_MOD(udp_pre_connect); -static int udp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int udp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { int res; @@ -2140,7 +2221,7 @@ int udp_disconnect(struct sock *sk, int flags) release_sock(sk); return 0; } -EXPORT_SYMBOL(udp_disconnect); +EXPORT_IPV6_MOD(udp_disconnect); void udp_lib_unhash(struct sock *sk) { @@ -2148,6 +2229,7 @@ void udp_lib_unhash(struct sock *sk) struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; + sock_rps_delete_flow(sk); hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); @@ -2170,7 +2252,7 @@ void udp_lib_unhash(struct sock *sk) spin_unlock_bh(&hslot->lock); } } -EXPORT_SYMBOL(udp_lib_unhash); +EXPORT_IPV6_MOD(udp_lib_unhash); /* * inet_rcv_saddr was changed, we must rehash secondary hash @@ -2181,14 +2263,14 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { - hslot = udp_hashslot(udptable, sock_net(sk), - udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) @@ -2207,24 +2289,34 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) spin_unlock(&nhslot2->lock); } - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, newhash4); + spin_unlock_bh(&hslot->lock); + } - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); + /* Now process hash4 if necessary: + * (1) update hslot4; + * (2) update hslot2->hash4_cnt. + * Note that hslot2/hslot4 should be checked separately, as + * either of them may change with the other unchanged. + */ + if (udp_hashed4(sk)) { + spin_lock_bh(&hslot->lock); - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); - } + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); } + spin_unlock_bh(&hslot->lock); } } } -EXPORT_SYMBOL(udp_lib_rehash); +EXPORT_IPV6_MOD(udp_lib_rehash); void udp_v4_rehash(struct sock *sk) { @@ -2284,7 +2376,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { - int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; + enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); @@ -2373,10 +2465,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; - } udp_csum_pull_header(skb); @@ -2388,7 +2478,7 @@ csum_error: __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - atomic_inc(&sk->sk_drops); + udp_drops_inc(sk); sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -2429,7 +2519,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } return false; } -EXPORT_SYMBOL(udp_sk_rx_dst_set); +EXPORT_IPV6_MOD(udp_sk_rx_dst_set); /* * Multicasts and broadcasts go to each listener. @@ -2473,7 +2563,7 @@ start_lookup: nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { - atomic_inc(&sk->sk_drops); + udp_drops_inc(sk); __UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(net, UDP_MIB_INERRORS, @@ -2548,7 +2638,7 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, return 0; } -/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and +/* wrapper for udp_queue_rcv_skb taking care of csum conversion and * return code conversion for ip layer consumption */ static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, @@ -2746,7 +2836,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, return NULL; } -int udp_v4_early_demux(struct sk_buff *skb) +enum skb_drop_reason udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct in_device *in_dev = NULL; @@ -2760,7 +2850,7 @@ int udp_v4_early_demux(struct sk_buff *skb) /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) - return 0; + return SKB_NOT_DROPPED_YET; iph = ip_hdr(skb); uh = udp_hdr(skb); @@ -2769,12 +2859,12 @@ int udp_v4_early_demux(struct sk_buff *skb) in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) - return 0; + return SKB_NOT_DROPPED_YET; ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, iph->protocol); if (!ours) - return 0; + return SKB_NOT_DROPPED_YET; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, @@ -2785,7 +2875,7 @@ int udp_v4_early_demux(struct sk_buff *skb) } if (!sk) - return 0; + return SKB_NOT_DROPPED_YET; skb->sk = sk; DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); @@ -2812,7 +2902,7 @@ int udp_v4_early_demux(struct sk_buff *skb) ip4h_dscp(iph), skb->dev, in_dev, &itag); } - return 0; + return SKB_NOT_DROPPED_YET; } int udp_rcv(struct sk_buff *skb) @@ -2836,20 +2926,40 @@ void udp_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (udp_test_bit(ENCAP_ENABLED, sk)) + if (udp_test_bit(ENCAP_ENABLED, sk)) { static_branch_dec(&udp_encap_needed_key); + udp_tunnel_cleanup_gro(sk); + } } } +typedef struct sk_buff *(*udp_gro_receive_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); + static void set_xfrm_gro_udp_encap_rcv(__u16 encap_type, unsigned short family, struct sock *sk) { #ifdef CONFIG_XFRM + udp_gro_receive_t new_gro_receive; + if (udp_test_bit(GRO_ENABLED, sk) && encap_type == UDP_ENCAP_ESPINUDP) { - if (family == AF_INET) - WRITE_ONCE(udp_sk(sk)->gro_receive, xfrm4_gro_udp_encap_rcv); - else if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) - WRITE_ONCE(udp_sk(sk)->gro_receive, ipv6_stub->xfrm6_gro_udp_encap_rcv); + if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) + new_gro_receive = ipv6_stub->xfrm6_gro_udp_encap_rcv; + else + new_gro_receive = xfrm4_gro_udp_encap_rcv; + + if (udp_sk(sk)->gro_receive != new_gro_receive) { + /* + * With IPV6_ADDRFORM the gro callback could change + * after being set, unregister the old one, if valid. + */ + if (udp_sk(sk)->gro_receive) + udp_tunnel_update_gro_rcv(sk, false); + + WRITE_ONCE(udp_sk(sk)->gro_receive, new_gro_receive); + udp_tunnel_update_gro_rcv(sk, true); + } } #endif } @@ -2899,6 +3009,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_ENCAP: + sockopt_lock_sock(sk); switch (val) { case 0: #ifdef CONFIG_XFRM @@ -2922,6 +3033,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, err = -ENOPROTOOPT; break; } + sockopt_release_sock(sk); break; case UDP_NO_CHECK6_TX: @@ -2939,13 +3051,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_GRO: - + sockopt_lock_sock(sk); /* when enabling GRO, accept the related GSO packet type */ if (valbool) udp_tunnel_encap_enable(sk); udp_assign_bit(GRO_ENABLED, sk, valbool); udp_assign_bit(ACCEPT_L4, sk, valbool); set_xfrm_gro_udp_encap_rcv(up->encap_type, sk->sk_family, sk); + sockopt_release_sock(sk); break; /* @@ -2985,7 +3098,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } -EXPORT_SYMBOL(udp_lib_setsockopt); +EXPORT_IPV6_MOD(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) @@ -3056,7 +3169,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } -EXPORT_SYMBOL(udp_lib_getsockopt); +EXPORT_IPV6_MOD(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -3098,7 +3211,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) return mask; } -EXPORT_SYMBOL(udp_poll); +EXPORT_IPV6_MOD(udp_poll); int udp_abort(struct sock *sk, int err) { @@ -3121,7 +3234,7 @@ out: return 0; } -EXPORT_SYMBOL_GPL(udp_abort); +EXPORT_IPV6_MOD_GPL(udp_abort); struct proto udp_prot = { .name = "UDP", @@ -3147,7 +3260,7 @@ struct proto udp_prot = { #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, @@ -3255,7 +3368,7 @@ void *udp_seq_start(struct seq_file *seq, loff_t *pos) return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } -EXPORT_SYMBOL(udp_seq_start); +EXPORT_IPV6_MOD(udp_seq_start); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { @@ -3269,7 +3382,7 @@ void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } -EXPORT_SYMBOL(udp_seq_next); +EXPORT_IPV6_MOD(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { @@ -3281,7 +3394,7 @@ void udp_seq_stop(struct seq_file *seq, void *v) if (state->bucket <= udptable->mask) spin_unlock_bh(&udptable->hash[state->bucket].lock); } -EXPORT_SYMBOL(udp_seq_stop); +EXPORT_IPV6_MOD(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, @@ -3299,10 +3412,10 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, sk_wmem_alloc_get(sp), udp_rqueue_get(sp), 0, 0L, 0, - from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + from_kuid_munged(seq_user_ns(f), sk_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops)); + sk_drops_read(sp)); } int udp4_seq_show(struct seq_file *seq, void *v) @@ -3329,34 +3442,55 @@ struct bpf_iter__udp { int bucket __aligned(8); }; +union bpf_udp_iter_batch_item { + struct sock *sk; + __u64 cookie; +}; + struct bpf_udp_iter_state { struct udp_iter_state state; unsigned int cur_sk; unsigned int end_sk; unsigned int max_sk; - int offset; - struct sock **batch; - bool st_bucket_done; + union bpf_udp_iter_batch_item *batch; }; static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, - unsigned int new_batch_sz); + unsigned int new_batch_sz, gfp_t flags); +static struct sock *bpf_iter_udp_resume(struct sock *first_sk, + union bpf_udp_iter_batch_item *cookies, + int n_cookies) +{ + struct sock *sk = NULL; + int i; + + for (i = 0; i < n_cookies; i++) { + sk = first_sk; + udp_portaddr_for_each_entry_from(sk) + if (cookies[i].cookie == atomic64_read(&sk->sk_cookie)) + goto done; + } +done: + return sk; +} + static struct sock *bpf_iter_udp_batch(struct seq_file *seq) { struct bpf_udp_iter_state *iter = seq->private; struct udp_iter_state *state = &iter->state; + unsigned int find_cookie, end_cookie; struct net *net = seq_file_net(seq); - int resume_bucket, resume_offset; struct udp_table *udptable; unsigned int batch_sks = 0; - bool resized = false; + int resume_bucket; + int resizes = 0; struct sock *sk; + int err = 0; resume_bucket = state->bucket; - resume_offset = iter->offset; /* The current batch is done, so advance the bucket. */ - if (iter->st_bucket_done) + if (iter->cur_sk == iter->end_sk) state->bucket++; udptable = udp_get_table_seq(seq, net); @@ -3369,62 +3503,89 @@ again: * before releasing the bucket lock. This allows BPF programs that are * called in seq_show to acquire the bucket lock if needed. */ + find_cookie = iter->cur_sk; + end_cookie = iter->end_sk; iter->cur_sk = 0; iter->end_sk = 0; - iter->st_bucket_done = false; batch_sks = 0; for (; state->bucket <= udptable->mask; state->bucket++) { struct udp_hslot *hslot2 = &udptable->hash2[state->bucket].hslot; if (hlist_empty(&hslot2->head)) - continue; + goto next_bucket; - iter->offset = 0; spin_lock_bh(&hslot2->lock); - udp_portaddr_for_each_entry(sk, &hslot2->head) { + sk = hlist_entry_safe(hslot2->head.first, struct sock, + __sk_common.skc_portaddr_node); + /* Resume from the first (in iteration order) unseen socket from + * the last batch that still exists in resume_bucket. Most of + * the time this will just be where the last iteration left off + * in resume_bucket unless that socket disappeared between + * reads. + */ + if (state->bucket == resume_bucket) + sk = bpf_iter_udp_resume(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); +fill_batch: + udp_portaddr_for_each_entry_from(sk) { if (seq_sk_match(seq, sk)) { - /* Resume from the last iterated socket at the - * offset in the bucket before iterator was stopped. - */ - if (state->bucket == resume_bucket && - iter->offset < resume_offset) { - ++iter->offset; - continue; - } if (iter->end_sk < iter->max_sk) { sock_hold(sk); - iter->batch[iter->end_sk++] = sk; + iter->batch[iter->end_sk++].sk = sk; } batch_sks++; } } + + /* Allocate a larger batch and try again. */ + if (unlikely(resizes <= 1 && iter->end_sk && + iter->end_sk != batch_sks)) { + resizes++; + + /* First, try with GFP_USER to maximize the chances of + * grabbing more memory. + */ + if (resizes == 1) { + spin_unlock_bh(&hslot2->lock); + err = bpf_iter_udp_realloc_batch(iter, + batch_sks * 3 / 2, + GFP_USER); + if (err) + return ERR_PTR(err); + /* Start over. */ + goto again; + } + + /* Next, hold onto the lock, so the bucket doesn't + * change while we get the rest of the sockets. + */ + err = bpf_iter_udp_realloc_batch(iter, batch_sks, + GFP_NOWAIT); + if (err) { + spin_unlock_bh(&hslot2->lock); + return ERR_PTR(err); + } + + /* Pick up where we left off. */ + sk = iter->batch[iter->end_sk - 1].sk; + sk = hlist_entry_safe(sk->__sk_common.skc_portaddr_node.next, + struct sock, + __sk_common.skc_portaddr_node); + batch_sks = iter->end_sk; + goto fill_batch; + } + spin_unlock_bh(&hslot2->lock); if (iter->end_sk) break; +next_bucket: + resizes = 0; } - /* All done: no batch made. */ - if (!iter->end_sk) - return NULL; - - if (iter->end_sk == batch_sks) { - /* Batching is done for the current bucket; return the first - * socket to be iterated from the batch. - */ - iter->st_bucket_done = true; - goto done; - } - if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) { - resized = true; - /* After allocating a larger batch, retry one more time to grab - * the whole bucket. - */ - goto again; - } -done: - return iter->batch[0]; + WARN_ON_ONCE(iter->end_sk != batch_sks); + return iter->end_sk ? iter->batch[0].sk : NULL; } static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -3435,16 +3596,14 @@ static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* Whenever seq_next() is called, the iter->cur_sk is * done with seq_show(), so unref the iter->cur_sk. */ - if (iter->cur_sk < iter->end_sk) { - sock_put(iter->batch[iter->cur_sk++]); - ++iter->offset; - } + if (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++].sk); /* After updating iter->cur_sk, check if there are more sockets * available in the current bucket batch. */ if (iter->cur_sk < iter->end_sk) - sk = iter->batch[iter->cur_sk]; + sk = iter->batch[iter->cur_sk].sk; else /* Prepare a new batch. */ sk = bpf_iter_udp_batch(seq); @@ -3496,7 +3655,7 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) goto unlock; } - uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket); @@ -3508,8 +3667,19 @@ unlock: static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter) { - while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + union bpf_udp_iter_batch_item *item; + unsigned int cur_sk = iter->cur_sk; + __u64 cookie; + + /* Remember the cookies of the sockets we haven't seen yet, so we can + * pick up where we left off next time around. + */ + while (cur_sk < iter->end_sk) { + item = &iter->batch[cur_sk++]; + cookie = sock_gen_cookie(item->sk); + sock_put(item->sk); + item->cookie = cookie; + } } static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) @@ -3525,10 +3695,8 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) (void)udp_prog_seq_show(prog, &meta, v, 0, 0); } - if (iter->cur_sk < iter->end_sk) { + if (iter->cur_sk < iter->end_sk) bpf_iter_udp_put_batch(iter); - iter->st_bucket_done = false; - } } static const struct seq_operations bpf_iter_udp_seq_ops = { @@ -3560,7 +3728,7 @@ const struct seq_operations udp_seq_ops = { .stop = udp_seq_stop, .show = udp4_seq_show, }; -EXPORT_SYMBOL(udp_seq_ops); +EXPORT_IPV6_MOD(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, @@ -3749,6 +3917,15 @@ fallback: static int __net_init udp_pernet_init(struct net *net) { +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) + int i; + + /* No tunnel is configured */ + for (i = 0; i < ARRAY_SIZE(net->ipv4.udp_tunnel_gro); ++i) { + INIT_HLIST_HEAD(&net->ipv4.udp_tunnel_gro[i].list); + RCU_INIT_POINTER(net->ipv4.udp_tunnel_gro[i].sk, NULL); + } +#endif udp_sysctl_init(net); udp_set_table(net); @@ -3770,16 +3947,19 @@ DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, - unsigned int new_batch_sz) + unsigned int new_batch_sz, gfp_t flags) { - struct sock **new_batch; + union bpf_udp_iter_batch_item *new_batch; new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), - GFP_USER | __GFP_NOWARN); + flags | __GFP_NOWARN); if (!new_batch) return -ENOMEM; - bpf_iter_udp_put_batch(iter); + if (flags != GFP_NOWAIT) + bpf_iter_udp_put_batch(iter); + + memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk); kvfree(iter->batch); iter->batch = new_batch; iter->max_sk = new_batch_sz; @@ -3798,10 +3978,12 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) if (ret) return ret; - ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ); + ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER); if (ret) bpf_iter_fini_seq_net(priv_data); + iter->state.bucket = -1; + return ret; } @@ -3841,7 +4023,6 @@ static void __init bpf_iter_register(void) void __init udp_init(void) { unsigned long limit; - unsigned int i; udp_table_init(&udp_table, "UDP"); limit = nr_free_buffer_pages() / 8; @@ -3850,15 +4031,6 @@ void __init udp_init(void) sysctl_udp_mem[1] = limit; sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; - /* 16 spinlocks per cpu */ - udp_busylocks_log = ilog2(nr_cpu_ids) + 4; - udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log, - GFP_KERNEL); - if (!udp_busylocks) - panic("UDP: failed to alloc udp_busylocks\n"); - for (i = 0; i < (1U << udp_busylocks_log); i++) - spin_lock_init(udp_busylocks + i); - if (register_pernet_subsys(&udp_sysctl_ops)) panic("UDP: failed to init sysctl parameters.\n"); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 38cb3a28e4ed..6e491c720c90 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -16,9 +16,9 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, - struct nlattr *bc, bool net_admin) + bool net_admin) { - if (!inet_diag_bc_sk(bc, sk)) + if (!inet_diag_bc_sk(cb->data, sk)) return 0; return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI, @@ -92,12 +92,8 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); - struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; - struct nlattr *bc; - cb_data = cb->data; - bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; @@ -130,7 +126,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { + if (sk_diag_dump(sk, skb, cb, r, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index e1ff3a375996..c7142213fc21 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _UDP4_IMPL_H #define _UDP4_IMPL_H +#include <net/aligned_data.h> #include <net/udp.h> #include <net/udplite.h> #include <net/protocol.h> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index a5be6e4ed326..19d0b5b09ffa 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -12,6 +12,162 @@ #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> +#include <net/udp_tunnel.h> + +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) + +/* + * Dummy GRO tunnel callback, exists mainly to avoid dangling/NULL + * values for the udp tunnel static call. + */ +static struct sk_buff *dummy_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->flush = 1; + return NULL; +} + +typedef struct sk_buff *(*udp_tunnel_gro_rcv_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); + +struct udp_tunnel_type_entry { + udp_tunnel_gro_rcv_t gro_receive; + refcount_t count; +}; + +#define UDP_MAX_TUNNEL_TYPES (IS_ENABLED(CONFIG_GENEVE) + \ + IS_ENABLED(CONFIG_VXLAN) * 2 + \ + IS_ENABLED(CONFIG_NET_FOU) * 2 + \ + IS_ENABLED(CONFIG_XFRM) * 2) + +DEFINE_STATIC_CALL(udp_tunnel_gro_rcv, dummy_gro_rcv); +static DEFINE_STATIC_KEY_FALSE(udp_tunnel_static_call); +static DEFINE_MUTEX(udp_tunnel_gro_type_lock); +static struct udp_tunnel_type_entry udp_tunnel_gro_types[UDP_MAX_TUNNEL_TYPES]; +static unsigned int udp_tunnel_gro_type_nr; +static DEFINE_SPINLOCK(udp_tunnel_gro_lock); + +void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add) +{ + bool is_ipv6 = sk->sk_family == AF_INET6; + struct udp_sock *tup, *up = udp_sk(sk); + struct udp_tunnel_gro *udp_tunnel_gro; + + spin_lock(&udp_tunnel_gro_lock); + udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6]; + if (add) + hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list); + else if (up->tunnel_list.pprev) + hlist_del_init(&up->tunnel_list); + + if (udp_tunnel_gro->list.first && + !udp_tunnel_gro->list.first->next) { + tup = hlist_entry(udp_tunnel_gro->list.first, struct udp_sock, + tunnel_list); + + rcu_assign_pointer(udp_tunnel_gro->sk, (struct sock *)tup); + } else { + RCU_INIT_POINTER(udp_tunnel_gro->sk, NULL); + } + + spin_unlock(&udp_tunnel_gro_lock); +} +EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup); + +void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) +{ + struct udp_tunnel_type_entry *cur = NULL; + struct udp_sock *up = udp_sk(sk); + int i, old_gro_type_nr; + + if (!UDP_MAX_TUNNEL_TYPES || !up->gro_receive) + return; + + mutex_lock(&udp_tunnel_gro_type_lock); + + /* Check if the static call is permanently disabled. */ + if (udp_tunnel_gro_type_nr > UDP_MAX_TUNNEL_TYPES) + goto out; + + for (i = 0; i < udp_tunnel_gro_type_nr; i++) + if (udp_tunnel_gro_types[i].gro_receive == up->gro_receive) + cur = &udp_tunnel_gro_types[i]; + + old_gro_type_nr = udp_tunnel_gro_type_nr; + if (add) { + /* + * Update the matching entry, if found, or add a new one + * if needed + */ + if (cur) { + refcount_inc(&cur->count); + goto out; + } + + if (unlikely(udp_tunnel_gro_type_nr == UDP_MAX_TUNNEL_TYPES)) { + pr_err_once("Too many UDP tunnel types, please increase UDP_MAX_TUNNEL_TYPES\n"); + /* Ensure static call will never be enabled */ + udp_tunnel_gro_type_nr = UDP_MAX_TUNNEL_TYPES + 1; + } else { + cur = &udp_tunnel_gro_types[udp_tunnel_gro_type_nr++]; + refcount_set(&cur->count, 1); + cur->gro_receive = up->gro_receive; + } + } else { + /* + * The stack cleanups only successfully added tunnel, the + * lookup on removal should never fail. + */ + if (WARN_ON_ONCE(!cur)) + goto out; + + if (!refcount_dec_and_test(&cur->count)) + goto out; + + /* Avoid gaps, so that the enable tunnel has always id 0 */ + *cur = udp_tunnel_gro_types[--udp_tunnel_gro_type_nr]; + } + + if (udp_tunnel_gro_type_nr == 1) { + static_call_update(udp_tunnel_gro_rcv, + udp_tunnel_gro_types[0].gro_receive); + static_branch_enable(&udp_tunnel_static_call); + } else if (old_gro_type_nr == 1) { + static_branch_disable(&udp_tunnel_static_call); + static_call_update(udp_tunnel_gro_rcv, dummy_gro_rcv); + } + +out: + mutex_unlock(&udp_tunnel_gro_type_lock); +} +EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_rcv); + +static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + if (static_branch_likely(&udp_tunnel_static_call)) { + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + return static_call(udp_tunnel_gro_rcv)(sk, head, skb); + } + return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); +} + +#else + +static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); +} + +#endif static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, @@ -61,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && @@ -247,6 +403,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) return segs; } +static void __udpv6_gso_segment_csum(struct sk_buff *seg, + struct in6_addr *oldip, + const struct in6_addr *newip, + __be16 *oldport, __be16 newport) +{ + struct udphdr *uh = udp_hdr(seg); + + if (ipv6_addr_equal(oldip, newip) && *oldport == newport) + return; + + if (uh->check) { + inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32, + newip->s6_addr32, true); + + inet_proto_csum_replace2(&uh->check, seg, *oldport, newport, + false); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + + *oldip = *newip; + *oldport = newport; +} + +static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct ipv6hdr *iph; + const struct udphdr *uh; + struct ipv6hdr *iph2; + struct sk_buff *seg; + struct udphdr *uh2; + + seg = segs; + uh = udp_hdr(seg); + iph = ipv6_hdr(seg); + uh2 = udp_hdr(seg->next); + iph2 = ipv6_hdr(seg->next); + + if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) && + ipv6_addr_equal(&iph->saddr, &iph2->saddr) && + ipv6_addr_equal(&iph->daddr, &iph2->daddr)) + return segs; + + while ((seg = seg->next)) { + uh2 = udp_hdr(seg); + iph2 = ipv6_hdr(seg); + + __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, + &uh2->source, uh->source); + __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, + &uh2->dest, uh->dest); + } + + return segs; +} + static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) @@ -259,7 +471,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); - return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); + if (is_ipv6) + return __udpv6_gso_segment_list_csum(skb); + else + return __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, @@ -273,6 +488,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, bool copy_dtor; __sum16 check; __be16 newlen; + int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) @@ -301,6 +517,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); + ret = __skb_linearize(gso_skb); + if (ret) + return ERR_PTR(ret); + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); @@ -321,13 +541,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; - if (copy_dtor) + if (copy_dtor) { gso_skb->destructor = NULL; + gso_skb->sk = NULL; + } segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { - if (copy_dtor) + if (copy_dtor) { gso_skb->destructor = sock_wfree; + gso_skb->sk = sk; + } return segs; } @@ -536,6 +760,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, NAPI_GRO_CB(skb)->flush = 1; return NULL; } + skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, @@ -618,7 +843,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); - pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); + pp = udp_tunnel_gro_rcv(sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); @@ -630,9 +855,14 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); + struct sock *sk; int iif, sdif; + sk = udp_tunnel_sk(net, false); + if (sk && dport == htons(sk->sk_num)) + return sk; + inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, @@ -661,8 +891,6 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: - NAPI_GRO_CB(skb)->is_ipv6 = 0; - if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); @@ -763,5 +991,6 @@ int __init udpv4_offload_init(void) .gro_complete = udp4_gro_complete, }, }; + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 619a53eb672d..b1f667c52cb2 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -4,6 +4,7 @@ #include <linux/socket.h> #include <linux/kernel.h> #include <net/dst_metadata.h> +#include <net/flow.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/inet_dscp.h> @@ -28,7 +29,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; - err = kernel_bind(sock, (struct sockaddr *)&udp_addr, + err = kernel_bind(sock, (struct sockaddr_unsized *)&udp_addr, sizeof(udp_addr)); if (err < 0) goto error; @@ -37,7 +38,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->peer_ip; udp_addr.sin_port = cfg->peer_udp_port; - err = kernel_connect(sock, (struct sockaddr *)&udp_addr, + err = kernel_connect(sock, (struct sockaddr_unsized *)&udp_addr, sizeof(udp_addr), 0); if (err < 0) goto error; @@ -58,6 +59,15 @@ error: } EXPORT_SYMBOL(udp_sock_create4); +static bool sk_saddr_any(struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + return ipv6_addr_any(&sk->sk_v6_rcv_saddr); +#else + return !sk->sk_rcv_saddr; +#endif +} + void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *cfg) { @@ -80,6 +90,12 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, udp_sk(sk)->gro_complete = cfg->gro_complete; udp_tunnel_encap_enable(sk); + + udp_tunnel_update_gro_rcv(sk, true); + + if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk) && + sk->sk_kern_sock) + udp_tunnel_update_gro_lookup(net, sk, true); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); @@ -119,15 +135,17 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) struct udp_tunnel_info ti; struct net_device *dev; + ASSERT_RTNL(); + ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_add_port(dev, &ti); + udp_tunnel_nic_unlock(dev); } - rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port); @@ -139,22 +157,24 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) struct udp_tunnel_info ti; struct net_device *dev; + ASSERT_RTNL(); + ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_del_port(dev, &ti); + udp_tunnel_nic_unlock(dev); } - rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port); void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck) + bool xnet, bool nocheck, u16 ipcb_flags) { struct udphdr *uh; @@ -170,7 +190,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb udp_set_csum(nocheck, skb, src, dst, skb->len); - iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); + iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet, + ipcb_flags); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); @@ -233,7 +254,7 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, fl4.saddr = key->u.ipv4.src; fl4.fl4_dport = dport; fl4.fl4_sport = sport; - fl4.flowi4_tos = tos & INET_DSCP_MASK; + fl4.flowi4_dscp = inet_dsfield_to_dscp(tos); fl4.flowi4_flags = key->flow_flags; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index b6d2d16189c0..944b3cf25468 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -29,6 +29,7 @@ struct udp_tunnel_nic_table_entry { * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer + * @lock: protects all fields * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled @@ -41,6 +42,8 @@ struct udp_tunnel_nic { struct net_device *dev; + struct mutex lock; + u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; @@ -298,22 +301,11 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { - const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; - bool may_sleep; - if (!utn->need_sync) return; - /* Drivers which sleep in the callback need to update from - * the workqueue, if we come from the tunnel driver's notification. - */ - may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; - if (!may_sleep) - __udp_tunnel_nic_device_sync(dev, utn); - if (may_sleep || utn->need_replay) { - queue_work(udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending = 1; - } + queue_work(udp_tunnel_nic_workqueue, &utn->work); + utn->work_pending = 1; } static bool @@ -554,12 +546,12 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) struct udp_tunnel_nic *utn; unsigned int i, j; - ASSERT_RTNL(); - utn = dev->udp_tunnel_nic; if (!utn) return; + mutex_lock(&utn->lock); + utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { @@ -569,7 +561,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); - /* We don't release rtnl across ops */ + /* We don't release utn lock across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; @@ -579,6 +571,8 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) } __udp_tunnel_nic_device_sync(dev, utn); + + mutex_unlock(&utn->lock); } static size_t @@ -643,6 +637,33 @@ err_cancel: return -EMSGSIZE; } +static void __udp_tunnel_nic_assert_locked(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + lockdep_assert_held(&utn->lock); +} + +static void __udp_tunnel_nic_lock(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + mutex_lock(&utn->lock); +} + +static void __udp_tunnel_nic_unlock(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + mutex_unlock(&utn->lock); +} + static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, @@ -651,6 +672,9 @@ static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, + .assert_locked = __udp_tunnel_nic_assert_locked, + .lock = __udp_tunnel_nic_lock, + .unlock = __udp_tunnel_nic_unlock, }; static void @@ -710,11 +734,15 @@ static void udp_tunnel_nic_device_sync_work(struct work_struct *work) container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); + mutex_lock(&utn->lock); + utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); + + mutex_unlock(&utn->lock); rtnl_unlock(); } @@ -730,6 +758,7 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); + mutex_init(&utn->lock); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, @@ -821,8 +850,11 @@ static int udp_tunnel_nic_register(struct net_device *dev) dev_hold(dev); dev->udp_tunnel_nic = utn; - if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) + if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) { + udp_tunnel_nic_lock(dev); udp_tunnel_get_rx_info(dev); + udp_tunnel_nic_unlock(dev); + } return 0; } @@ -832,6 +864,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + udp_tunnel_nic_lock(dev); + /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ @@ -841,8 +875,10 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; - if (list_entry_is_head(node, &info->shared->devices, list)) + if (list_entry_is_head(node, &info->shared->devices, list)) { + udp_tunnel_nic_unlock(dev); return; + } list_del(&node->list); kfree(node); @@ -852,6 +888,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; + udp_tunnel_nic_unlock(dev); goto release_dev; } @@ -862,6 +899,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); + udp_tunnel_nic_unlock(dev); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. @@ -892,7 +930,7 @@ udp_tunnel_nic_netdevice_event(struct notifier_block *unused, err = udp_tunnel_nic_register(dev); if (err) - netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); + netdev_warn(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ @@ -910,12 +948,16 @@ udp_tunnel_nic_netdevice_event(struct notifier_block *unused, return NOTIFY_DONE; if (event == NETDEV_UP) { + udp_tunnel_nic_lock(dev); WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); + udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_flush(dev, utn); + udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index af37af3ab727..d3e621a11a1a 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -60,7 +60,7 @@ struct proto udplite_prot = { .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, - .memory_allocated = &udp_memory_allocated, + .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index b5b06323cfd9..f28cfd88eaf5 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, int offset = skb_gro_offset(skb); const struct net_offload *ops; struct sk_buff *pp = NULL; - int ret; - - offset = offset - sizeof(struct udphdr); + int len, dlen; + __u8 *udpdata; + __be32 *udpdata32; - if (!pskb_pull(skb, offset)) + len = skb->len - offset; + dlen = offset + min(len, 8); + udpdata = skb_gro_header(skb, dlen, offset); + udpdata32 = (__be32 *)udpdata; + if (unlikely(!udpdata)) return NULL; rcu_read_lock(); @@ -194,11 +198,13 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (!ops || !ops->callbacks.gro_receive) goto out; - ret = __xfrm4_udp_encap_rcv(sk, skb, false); - if (ret) + /* check if it is a keepalive or IKE packet */ + if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; - skb_push(skb, offset); + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); @@ -208,7 +214,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, out: rcu_read_unlock(); - skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 3cff51ba72bb..0ae67d537499 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -31,7 +31,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, skb->dev, skb_dst(skb)->dev, + net, sk, skb, skb->dev, skb_dst_dev(skb), __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 7fb6205619e7..58faf1ddd2b1 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -14,7 +14,7 @@ #include <linux/inetdevice.h> #include <net/dst.h> #include <net/xfrm.h> -#include <net/inet_dscp.h> +#include <net/flow.h> #include <net/ip.h> #include <net/l3mdev.h> @@ -25,7 +25,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = params->daddr->a4; - fl4->flowi4_tos = inet_dscp_to_dsfield(params->dscp); + fl4->flowi4_dscp = params->dscp; fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(params->net, params->oif); fl4->flowi4_mark = params->mark; |