diff options
Diffstat (limited to 'net/ipv4')
31 files changed, 211 insertions, 146 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bc19bd06dd0..c6b5092f29a 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -258,7 +258,7 @@ static struct in_device *inetdev_init(struct net_device *dev) ip_mc_up(in_dev); /* we can receive as soon as ip_ptr is set -- do this last */ - rcu_assign_pointer(dev->ip_ptr, in_dev); + RCU_INIT_POINTER(dev->ip_ptr, in_dev); out: return in_dev; out_kfree: @@ -291,7 +291,7 @@ static void inetdev_destroy(struct in_device *in_dev) inet_free_ifa(ifa); } - rcu_assign_pointer(dev->ip_ptr, NULL); + RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); @@ -1175,7 +1175,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: printk(KERN_DEBUG "inetdev_event: bug\n"); - rcu_assign_pointer(dev->ip_ptr, NULL); + RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index de9e2978476..89d6f71a6a9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -204,7 +204,7 @@ static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node) return (struct tnode *)(parent & ~NODE_TYPE_MASK); } -/* Same as rcu_assign_pointer +/* Same as RCU_INIT_POINTER * but that macro() assumes that value is a pointer. */ static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) @@ -528,7 +528,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node * if (n) node_set_parent(n, tn); - rcu_assign_pointer(tn->child[i], n); + RCU_INIT_POINTER(tn->child[i], n); } #define MAX_WORK 10 @@ -1014,7 +1014,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) tp = node_parent((struct rt_trie_node *) tn); if (!tp) - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); if (!tp) @@ -1026,7 +1026,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) if (IS_TNODE(tn)) tn = (struct tnode *)resize(t, (struct tnode *)tn); - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); } @@ -1163,7 +1163,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)tn); } else { - rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); + RCU_INIT_POINTER(t->trie, (struct rt_trie_node *)tn); tp = tn; } } @@ -1621,7 +1621,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) put_child(t, (struct tnode *)tp, cindex, NULL); trie_rebalance(t, tp); } else - rcu_assign_pointer(t->trie, NULL); + RCU_INIT_POINTER(t->trie, NULL); free_leaf(l); } diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index dbfc21de347..8cb1ebb7cd7 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -34,7 +34,7 @@ int gre_add_protocol(const struct gre_protocol *proto, u8 version) if (gre_proto[version]) goto err_out_unlock; - rcu_assign_pointer(gre_proto[version], proto); + RCU_INIT_POINTER(gre_proto[version], proto); spin_unlock(&gre_proto_lock); return 0; @@ -54,7 +54,7 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) if (rcu_dereference_protected(gre_proto[version], lockdep_is_held(&gre_proto_lock)) != proto) goto err_out_unlock; - rcu_assign_pointer(gre_proto[version], NULL); + RCU_INIT_POINTER(gre_proto[version], NULL); spin_unlock(&gre_proto_lock); synchronize_rcu(); return 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f1d27f6c935..ce57bdee14c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1009,7 +1009,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST - is changed. This check should be done in dev->set_multicast_list + is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK @@ -1242,7 +1242,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - rcu_assign_pointer(in_dev->mc_list, im); + RCU_INIT_POINTER(in_dev->mc_list, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); @@ -1718,7 +1718,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[sfmode]--; for (j=0; j<i; j++) - (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); + (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; @@ -1813,7 +1813,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; - rcu_assign_pointer(inet->mc_list, iml); + RCU_INIT_POINTER(inet->mc_list, iml); ip_mc_inc_group(in_dev, addr); err = 0; done: @@ -1835,7 +1835,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); - rcu_assign_pointer(iml->sflist, NULL); + RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); @@ -2000,7 +2000,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } - rcu_assign_pointer(pmc->sflist, newpsl); + RCU_INIT_POINTER(pmc->sflist, newpsl); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2103,7 +2103,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); - rcu_assign_pointer(pmc->sflist, newpsl); + RCU_INIT_POINTER(pmc->sflist, newpsl); pmc->sfmode = msf->imsf_fmode; err = 0; done: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3c0369a3a66..984ec656b03 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -21,6 +21,7 @@ #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#include <net/secure_seq.h> #include <net/ip.h> /* diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index ef7ae6049a5..8e6be5aad11 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -433,7 +433,7 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, if (!lro_mgr->get_frag_header || lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, (void *)&tcph, &flags, priv)) { - mac_hdr = page_address(frags->page) + frags->page_offset; + mac_hdr = skb_frag_address(frags); goto out1; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e38213817d0..86f13c67ea8 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -19,6 +19,7 @@ #include <linux/net.h> #include <net/ip.h> #include <net/inetpeer.h> +#include <net/secure_seq.h> /* * Theory of operations. diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ccaaa851ab4..ae3bb147aff 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -122,6 +122,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(newskb)); + skb_dst_force(newskb); netif_rx_ni(newskb); return 0; } @@ -204,9 +205,15 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } + rcu_read_lock(); neigh = dst_get_neighbour(dst); - if (neigh) - return neigh_output(neigh, skb); + if (neigh) { + int res = neigh_output(neigh, skb); + + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); @@ -982,13 +989,13 @@ alloc_new_skb: if (page && (left = PAGE_SIZE - off) > 0) { if (copy >= left) copy = left; - if (page != frag->page) { + if (page != skb_frag_page(frag)) { if (i == MAX_SKB_FRAGS) { err = -EMSGSIZE; goto error; } - get_page(page); skb_fill_page_desc(skb, i, page, off, 0); + skb_frag_ref(skb, i); frag = &skb_shinfo(skb)->frags[i]; } } else if (i < MAX_SKB_FRAGS) { @@ -1008,7 +1015,8 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { + if (getfrag(from, skb_frag_address(frag)+frag->size, + offset, copy, skb->len, skb) < 0) { err = -EFAULT; goto error; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ab0c9efd1ef..8905e92f896 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1067,7 +1067,7 @@ EXPORT_SYMBOL(compat_ip_setsockopt); */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen, unsigned flags) { struct inet_sock *inet = inet_sk(sk); int val; @@ -1240,7 +1240,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; @@ -1294,7 +1294,7 @@ int ip_getsockopt(struct sock *sk, int level, { int err; - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && @@ -1327,7 +1327,8 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, return compat_mc_getsockopt(sk, level, optname, optval, optlen, ip_getsockopt); - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 378b20b7ca6..065effd8349 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -231,7 +231,7 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { - rcu_assign_pointer(*tp, t->next); + RCU_INIT_POINTER(*tp, t->next); break; } } @@ -241,8 +241,8 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t); - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); + RCU_INIT_POINTER(t->next, rtnl_dereference(*tp)); + RCU_INIT_POINTER(*tp, t); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -301,7 +301,7 @@ static void ipip_tunnel_uninit(struct net_device *dev) struct ipip_net *ipn = net_generic(net, ipip_net_id); if (dev == ipn->fb_tunnel_dev) - rcu_assign_pointer(ipn->tunnels_wc[0], NULL); + RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL); else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); @@ -791,7 +791,7 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev) return -ENOMEM; dev_hold(dev); - rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + RCU_INIT_POINTER(ipn->tunnels_wc[0], tunnel); return 0; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 58e87915797..6164e982e0e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1176,7 +1176,7 @@ static void mrtsock_destruct(struct sock *sk) ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - rcu_assign_pointer(mrt->mroute_sk, NULL); + RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } } @@ -1203,7 +1203,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOENT; if (optname != MRT_INIT) { - if (sk != rcu_dereference_raw(mrt->mroute_sk) && + if (sk != rcu_access_pointer(mrt->mroute_sk) && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1224,13 +1224,13 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { - rcu_assign_pointer(mrt->mroute_sk, sk); + RCU_INIT_POINTER(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; } rtnl_unlock(); return ret; case MRT_DONE: - if (sk != rcu_dereference_raw(mrt->mroute_sk)) + if (sk != rcu_access_pointer(mrt->mroute_sk)) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 2e97e3ec1eb..929b27bdeb7 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -18,17 +18,15 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - __u8 flags = 0; + __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; unsigned int hh_len; - if (!skb->sk && addr_type != RTN_LOCAL) { - if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); - if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) - flags |= FLOWI_FLAG_ANYSRC; - else - saddr = 0; - } + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. @@ -38,7 +36,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return -1; diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 703f366fd23..7b22382ff0e 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -70,14 +70,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_amanda_fini(void) { - rcu_assign_pointer(nf_nat_amanda_hook, NULL); + RCU_INIT_POINTER(nf_nat_amanda_hook, NULL); synchronize_rcu(); } static int __init nf_nat_amanda_init(void) { BUG_ON(nf_nat_amanda_hook != NULL); - rcu_assign_pointer(nf_nat_amanda_hook, help); + RCU_INIT_POINTER(nf_nat_amanda_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 3346de5d94d..447bc5cfdc6 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -514,7 +514,7 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) ret = -EBUSY; goto out; } - rcu_assign_pointer(nf_nat_protos[proto->protonum], proto); + RCU_INIT_POINTER(nf_nat_protos[proto->protonum], proto); out: spin_unlock_bh(&nf_nat_lock); return ret; @@ -525,7 +525,7 @@ EXPORT_SYMBOL(nf_nat_protocol_register); void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) { spin_lock_bh(&nf_nat_lock); - rcu_assign_pointer(nf_nat_protos[proto->protonum], + RCU_INIT_POINTER(nf_nat_protos[proto->protonum], &nf_nat_unknown_protocol); spin_unlock_bh(&nf_nat_lock); synchronize_rcu(); @@ -736,10 +736,10 @@ static int __init nf_nat_init(void) /* Sew in builtin protocols. */ spin_lock_bh(&nf_nat_lock); for (i = 0; i < MAX_IP_NAT_PROTO; i++) - rcu_assign_pointer(nf_nat_protos[i], &nf_nat_unknown_protocol); - rcu_assign_pointer(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); - rcu_assign_pointer(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); - rcu_assign_pointer(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); + RCU_INIT_POINTER(nf_nat_protos[i], &nf_nat_unknown_protocol); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); + RCU_INIT_POINTER(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); spin_unlock_bh(&nf_nat_lock); /* Initialize fake conntrack so that NAT will skip it */ @@ -748,12 +748,12 @@ static int __init nf_nat_init(void) l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); BUG_ON(nf_nat_seq_adjust_hook != NULL); - rcu_assign_pointer(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); - rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, nfnetlink_parse_nat_setup); BUG_ON(nf_ct_nat_offset != NULL); - rcu_assign_pointer(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); return 0; cleanup_extend: @@ -766,9 +766,9 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_l3proto_put(l3proto); nf_ct_extend_unregister(&nat_extend); - rcu_assign_pointer(nf_nat_seq_adjust_hook, NULL); - rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, NULL); - rcu_assign_pointer(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); synchronize_net(); } diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index dc73abb3fe2..e462a957d08 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -113,14 +113,14 @@ out: static void __exit nf_nat_ftp_fini(void) { - rcu_assign_pointer(nf_nat_ftp_hook, NULL); + RCU_INIT_POINTER(nf_nat_ftp_hook, NULL); synchronize_rcu(); } static int __init nf_nat_ftp_init(void) { BUG_ON(nf_nat_ftp_hook != NULL); - rcu_assign_pointer(nf_nat_ftp_hook, nf_nat_ftp); + RCU_INIT_POINTER(nf_nat_ftp_hook, nf_nat_ftp); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 790f3160e01..b9a1136addb 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -581,30 +581,30 @@ static int __init init(void) BUG_ON(nat_callforwarding_hook != NULL); BUG_ON(nat_q931_hook != NULL); - rcu_assign_pointer(set_h245_addr_hook, set_h245_addr); - rcu_assign_pointer(set_h225_addr_hook, set_h225_addr); - rcu_assign_pointer(set_sig_addr_hook, set_sig_addr); - rcu_assign_pointer(set_ras_addr_hook, set_ras_addr); - rcu_assign_pointer(nat_rtp_rtcp_hook, nat_rtp_rtcp); - rcu_assign_pointer(nat_t120_hook, nat_t120); - rcu_assign_pointer(nat_h245_hook, nat_h245); - rcu_assign_pointer(nat_callforwarding_hook, nat_callforwarding); - rcu_assign_pointer(nat_q931_hook, nat_q931); + RCU_INIT_POINTER(set_h245_addr_hook, set_h245_addr); + RCU_INIT_POINTER(set_h225_addr_hook, set_h225_addr); + RCU_INIT_POINTER(set_sig_addr_hook, set_sig_addr); + RCU_INIT_POINTER(set_ras_addr_hook, set_ras_addr); + RCU_INIT_POINTER(nat_rtp_rtcp_hook, nat_rtp_rtcp); + RCU_INIT_POINTER(nat_t120_hook, nat_t120); + RCU_INIT_POINTER(nat_h245_hook, nat_h245); + RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding); + RCU_INIT_POINTER(nat_q931_hook, nat_q931); return 0; } /****************************************************************************/ static void __exit fini(void) { - rcu_assign_pointer(set_h245_addr_hook, NULL); - rcu_assign_pointer(set_h225_addr_hook, NULL); - rcu_assign_pointer(set_sig_addr_hook, NULL); - rcu_assign_pointer(set_ras_addr_hook, NULL); - rcu_assign_pointer(nat_rtp_rtcp_hook, NULL); - rcu_assign_pointer(nat_t120_hook, NULL); - rcu_assign_pointer(nat_h245_hook, NULL); - rcu_assign_pointer(nat_callforwarding_hook, NULL); - rcu_assign_pointer(nat_q931_hook, NULL); + RCU_INIT_POINTER(set_h245_addr_hook, NULL); + RCU_INIT_POINTER(set_h225_addr_hook, NULL); + RCU_INIT_POINTER(set_sig_addr_hook, NULL); + RCU_INIT_POINTER(set_ras_addr_hook, NULL); + RCU_INIT_POINTER(nat_rtp_rtcp_hook, NULL); + RCU_INIT_POINTER(nat_t120_hook, NULL); + RCU_INIT_POINTER(nat_h245_hook, NULL); + RCU_INIT_POINTER(nat_callforwarding_hook, NULL); + RCU_INIT_POINTER(nat_q931_hook, NULL); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 535e1a80235..979ae165f4e 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -75,14 +75,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_irc_fini(void) { - rcu_assign_pointer(nf_nat_irc_hook, NULL); + RCU_INIT_POINTER(nf_nat_irc_hook, NULL); synchronize_rcu(); } static int __init nf_nat_irc_init(void) { BUG_ON(nf_nat_irc_hook != NULL); - rcu_assign_pointer(nf_nat_irc_hook, help); + RCU_INIT_POINTER(nf_nat_irc_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 4c060038d29..3e8284ba46b 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -282,25 +282,25 @@ static int __init nf_nat_helper_pptp_init(void) nf_nat_need_gre(); BUG_ON(nf_nat_pptp_hook_outbound != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); + RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); BUG_ON(nf_nat_pptp_hook_inbound != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); + RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); BUG_ON(nf_nat_pptp_hook_exp_gre != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); + RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); BUG_ON(nf_nat_pptp_hook_expectfn != NULL); - rcu_assign_pointer(nf_nat_pptp_hook_expectfn, pptp_nat_expected); + RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, pptp_nat_expected); return 0; } static void __exit nf_nat_helper_pptp_fini(void) { - rcu_assign_pointer(nf_nat_pptp_hook_expectfn, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_exp_gre, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_inbound, NULL); - rcu_assign_pointer(nf_nat_pptp_hook_outbound, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, NULL); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 3e61faf23a9..f52d41ea069 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -12,6 +12,7 @@ #include <linux/ip.h> #include <linux/netfilter.h> +#include <net/secure_seq.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_rule.h> diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index e40cf7816fd..78844d9208f 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -528,13 +528,13 @@ err1: static void __exit nf_nat_sip_fini(void) { - rcu_assign_pointer(nf_nat_sip_hook, NULL); - rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, NULL); - rcu_assign_pointer(nf_nat_sip_expect_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_addr_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_port_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_session_hook, NULL); - rcu_assign_pointer(nf_nat_sdp_media_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); synchronize_rcu(); } @@ -547,13 +547,13 @@ static int __init nf_nat_sip_init(void) BUG_ON(nf_nat_sdp_port_hook != NULL); BUG_ON(nf_nat_sdp_session_hook != NULL); BUG_ON(nf_nat_sdp_media_hook != NULL); - rcu_assign_pointer(nf_nat_sip_hook, ip_nat_sip); - rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); - rcu_assign_pointer(nf_nat_sip_expect_hook, ip_nat_sip_expect); - rcu_assign_pointer(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); - rcu_assign_pointer(nf_nat_sdp_port_hook, ip_nat_sdp_port); - rcu_assign_pointer(nf_nat_sdp_session_hook, ip_nat_sdp_session); - rcu_assign_pointer(nf_nat_sdp_media_hook, ip_nat_sdp_media); + RCU_INIT_POINTER(nf_nat_sip_hook, ip_nat_sip); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, ip_nat_sip_expect); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 076b7c8c4aa..d1cb412c18e 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1310,7 +1310,7 @@ static int __init nf_nat_snmp_basic_init(void) int ret = 0; BUG_ON(nf_nat_snmp_hook != NULL); - rcu_assign_pointer(nf_nat_snmp_hook, help); + RCU_INIT_POINTER(nf_nat_snmp_hook, help); ret = nf_conntrack_helper_register(&snmp_trap_helper); if (ret < 0) { @@ -1322,7 +1322,7 @@ static int __init nf_nat_snmp_basic_init(void) static void __exit nf_nat_snmp_basic_fini(void) { - rcu_assign_pointer(nf_nat_snmp_hook, NULL); + RCU_INIT_POINTER(nf_nat_snmp_hook, NULL); nf_conntrack_helper_unregister(&snmp_trap_helper); } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index a6e606e8482..92900482ede 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -284,7 +284,7 @@ static int __init nf_nat_standalone_init(void) #ifdef CONFIG_XFRM BUG_ON(ip_nat_decode_session != NULL); - rcu_assign_pointer(ip_nat_decode_session, nat_decode_session); + RCU_INIT_POINTER(ip_nat_decode_session, nat_decode_session); #endif ret = nf_nat_rule_init(); if (ret < 0) { @@ -302,7 +302,7 @@ static int __init nf_nat_standalone_init(void) nf_nat_rule_cleanup(); cleanup_decode_session: #ifdef CONFIG_XFRM - rcu_assign_pointer(ip_nat_decode_session, NULL); + RCU_INIT_POINTER(ip_nat_decode_session, NULL); synchronize_net(); #endif return ret; @@ -313,7 +313,7 @@ static void __exit nf_nat_standalone_fini(void) nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); nf_nat_rule_cleanup(); #ifdef CONFIG_XFRM - rcu_assign_pointer(ip_nat_decode_session, NULL); + RCU_INIT_POINTER(ip_nat_decode_session, NULL); synchronize_net(); #endif /* Conntrack caches are unregistered in nf_conntrack_cleanup */ diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index 7274a43c7a1..a2901bf829c 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -36,14 +36,14 @@ static unsigned int help(struct sk_buff *skb, static void __exit nf_nat_tftp_fini(void) { - rcu_assign_pointer(nf_nat_tftp_hook, NULL); + RCU_INIT_POINTER(nf_nat_tftp_hook, NULL); synchronize_rcu(); } static int __init nf_nat_tftp_init(void) { BUG_ON(nf_nat_tftp_hook != NULL); - rcu_assign_pointer(nf_nat_tftp_hook, help); + RCU_INIT_POINTER(nf_nat_tftp_hook, help); return 0; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1457acb39ce..61714bd5292 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, - FLOWI_FLAG_CAN_SLEEP, daddr, saddr, 0, 0); + inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP, + daddr, saddr, 0, 0); if (!inet->hdrincl) { err = raw_probe_proto_opt(&fl4, msg); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1730689f560..2c21d3be891 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -109,6 +109,7 @@ #include <linux/sysctl.h> #endif #include <net/atmclip.h> +#include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) @@ -323,7 +324,7 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) struct rtable *r = NULL; for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) { - if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)) + if (!rcu_access_pointer(rt_hash_table[st->bucket].chain)) continue; rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); @@ -349,7 +350,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, do { if (--st->bucket < 0) return NULL; - } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)); + } while (!rcu_access_pointer(rt_hash_table[st->bucket].chain)); rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); } @@ -721,7 +722,7 @@ static inline bool compare_hash_inputs(const struct rtable *rt1, { return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0); + (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0); } static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) @@ -730,8 +731,8 @@ static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | (rt1->rt_mark ^ rt2->rt_mark) | (rt1->rt_key_tos ^ rt2->rt_key_tos) | - (rt1->rt_oif ^ rt2->rt_oif) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0; + (rt1->rt_route_iif ^ rt2->rt_route_iif) | + (rt1->rt_oif ^ rt2->rt_oif)) == 0; } static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) @@ -760,7 +761,7 @@ static void rt_do_flush(struct net *net, int process_context) if (process_context && need_resched()) cond_resched(); - rth = rcu_dereference_raw(rt_hash_table[i].chain); + rth = rcu_access_pointer(rt_hash_table[i].chain); if (!rth) continue; @@ -1628,16 +1629,18 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; - struct neighbour *n; + struct neighbour *n, *old_n; dst_confirm(&rt->dst); - neigh_release(dst_get_neighbour(&rt->dst)); - dst_set_neighbour(&rt->dst, NULL); - rt->rt_gateway = peer->redirect_learned.a4; - rt_bind_neighbour(rt); - n = dst_get_neighbour(&rt->dst); + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); if (!n || !(n->nud_state & NUD_VALID)) { if (n) neigh_event_send(n, NULL); @@ -2317,8 +2320,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth = rcu_dereference(rth->dst.rt_next)) { if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) | ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | - (rth->rt_iif ^ iif) | - rth->rt_oif | + (rth->rt_route_iif ^ iif) | (rth->rt_key_tos ^ tos)) == 0 && rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 92bb9434b33..3bc5c8f7c71 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -276,7 +276,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - bool ecn_ok; + bool ecn_ok = false; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46febcacb72..5fe632c763f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3035,7 +3035,8 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const struct skb_frag_struct *f = &shi->frags[i]; - sg_set_page(&sg, f->page, f->size, f->page_offset); + struct page *page = skb_frag_page(f); + sg_set_page(&sg, page, f->size, f->page_offset); if (crypto_hash_update(desc, &sg, f->size)) return 1; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ea0d2183df4..385c470195e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2830,9 +2830,13 @@ static int tcp_try_undo_loss(struct sock *sk) static inline void tcp_complete_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - /* Do not moderate cwnd if it's already undone in cwr or recovery */ - if (tp->undo_marker && tp->snd_cwnd > tp->snd_ssthresh) { - tp->snd_cwnd = tp->snd_ssthresh; + + /* Do not moderate cwnd if it's already undone in cwr or recovery. */ + if (tp->undo_marker) { + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); + else /* PRR */ + tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); @@ -2950,6 +2954,38 @@ void tcp_simple_retransmit(struct sock *sk) } EXPORT_SYMBOL(tcp_simple_retransmit); +/* This function implements the PRR algorithm, specifcally the PRR-SSRB + * (proportional rate reduction with slow start reduction bound) as described in + * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. + * It computes the number of packets to send (sndcnt) based on packets newly + * delivered: + * 1) If the packets in flight is larger than ssthresh, PRR spreads the + * cwnd reductions across a full RTT. + * 2) If packets in flight is lower than ssthresh (such as due to excess + * losses and/or application stalls), do not perform any further cwnd + * reductions, but instead slow start up to ssthresh. + */ +static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, + int fast_rexmit, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + int sndcnt = 0; + int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + + if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + + tp->prior_cwnd - 1; + sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; + } else { + sndcnt = min_t(int, delta, + max_t(int, tp->prr_delivered - tp->prr_out, + newly_acked_sacked) + 1); + } + + sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); + tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2961,7 +2997,8 @@ EXPORT_SYMBOL(tcp_simple_retransmit); * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ -static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) +static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, + int newly_acked_sacked, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3111,13 +3148,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; tcp_set_ca_state(sk, TCP_CA_Recovery); fast_rexmit = 1; } if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk))) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_down(sk, flag); + tp->prr_delivered += newly_acked_sacked; + tcp_update_cwnd_in_recovery(sk, newly_acked_sacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3632,6 +3673,8 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) u32 prior_in_flight; u32 prior_fackets; int prior_packets; + int prior_sacked = tp->sacked_out; + int newly_acked_sacked = 0; int frto_cwnd = 0; /* If the ack is older than previous acks @@ -3703,6 +3746,9 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + newly_acked_sacked = (prior_packets - prior_sacked) - + (tp->packets_out - tp->sacked_out); + if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); /* Guarantee sacktag reordering detection against wrap-arounds */ @@ -3715,7 +3761,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - flag); + newly_acked_sacked, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 955b8e65b69..b3f26114b03 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -72,6 +72,7 @@ #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/netdma.h> +#include <net/secure_seq.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -1577,7 +1578,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1594,7 +1595,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { - sock_rps_save_rxhash(nsk, skb->rxhash); + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; @@ -1602,7 +1603,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } } else - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 882e0b0964d..081dcd6fd0c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1095,7 +1095,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); eat -= skb_shinfo(skb)->frags[i].size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; @@ -1796,11 +1796,13 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); - sent_pkts++; + sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += sent_pkts; if (likely(sent_pkts)) { tcp_cwnd_validate(sk); @@ -2294,6 +2296,9 @@ begin_fwd: return; NET_INC_STATS_BH(sock_net(sk), mib_idx); + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += tcp_skb_pcount(skb); + if (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b5a19340a9..ebaa96bd346 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1267,7 +1267,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; - sock_rps_save_rxhash(sk, 0); + sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1355,7 +1355,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) int rc; if (inet_sk(sk)->inet_daddr) - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); rc = ip_queue_rcv_skb(sk, skb); if (rc < 0) { @@ -1461,10 +1461,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } - if (rcu_dereference_raw(sk->sk_filter)) { - if (udp_lib_checksum_complete(skb)) - goto drop; - } + if (rcu_access_pointer(sk->sk_filter) && + udp_lib_checksum_complete(skb)) + goto drop; if (sk_rcvqueues_full(sk, skb)) |