diff options
Diffstat (limited to 'net')
76 files changed, 634 insertions, 365 deletions
diff --git a/net/Kconfig b/net/Kconfig index 0715db64a5c3..d334678c0bd8 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -224,7 +224,7 @@ source "net/hsr/Kconfig" config RPS boolean - depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS + depends on SMP && SYSFS default y config RFS_ACCEL @@ -235,7 +235,7 @@ config RFS_ACCEL config XPS boolean - depends on SMP && USE_GENERIC_SMP_HELPERS + depends on SMP default y config NETPRIO_CGROUP diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 229d820bdf0b..045d56eaeca2 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -426,6 +426,16 @@ netdev_features_t br_features_recompute(struct net_bridge *br, int br_handle_frame_finish(struct sk_buff *skb); rx_handler_result_t br_handle_frame(struct sk_buff **pskb); +static inline bool br_rx_handler_check_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler) == br_handle_frame; +} + +static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) +{ + return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; +} + /* br_ioctl.c */ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 8660ea3be705..bdb459d21ad8 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; - p = br_port_get_rcu(dev); + p = br_port_get_check_rcu(dev); if (!p) goto err; diff --git a/net/compat.c b/net/compat.c index 618c6a8a911b..dd32e34c1e2c 100644 --- a/net/compat.c +++ b/net/compat.c @@ -72,7 +72,7 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); diff --git a/net/core/dev.c b/net/core/dev.c index ba3b7ea5ebb3..4fc17221545d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4500,7 +4500,7 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, { struct netdev_adjacent *upper; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 95897183226e..e70301eb7a4a 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = { .hdrsize = 0, .name = "NET_DM", .version = 2, - .maxattr = NET_DM_CMD_MAX, }; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ca15f32821fb..36b1443f9ae4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1161,6 +1161,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->parms->reachable_time : 0))); neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 261357a66300..a797fff7f222 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2527,6 +2527,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2548,6 +2550,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2718fed53d8c..06e72d3cdf60 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3584,6 +3584,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; + skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; secpath_reset(skb); diff --git a/net/core/sock.c b/net/core/sock.c index ab20ed9b0f31..5393b4b719d7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -882,7 +882,7 @@ set_rcvbuf: case SO_PEEK_OFF: if (sock->ops->set_peek_off) - sock->ops->set_peek_off(sk, val); + ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4ac71ff7c2e4..2b90a786e475 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -851,7 +851,6 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 4c6bdf97a657..595ddf0459db 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -152,17 +152,6 @@ static const struct file_operations dccpprobe_fops = { .llseek = noop_llseek, }; -static __init int setup_jprobe(void) -{ - int ret = register_jprobe(&dccp_send_probe); - - if (ret) { - request_module("dccp"); - ret = register_jprobe(&dccp_send_probe); - } - return ret; -} - static __init int dccpprobe_init(void) { int ret = -ENOMEM; @@ -174,7 +163,13 @@ static __init int dccpprobe_init(void) if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops)) goto err0; - ret = setup_jprobe(); + ret = register_jprobe(&dccp_send_probe); + if (ret) { + ret = request_module("dccp"); + if (!ret) + ret = register_jprobe(&dccp_send_probe); + } + if (ret) goto err1; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 003f5bb3acd2..4bdab1521878 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -288,7 +288,8 @@ void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr, static bool seq_nr_after(u16 a, u16 b) { /* Remove inconsistency where - * seq_nr_after(a, b) == seq_nr_before(a, b) */ + * seq_nr_after(a, b) == seq_nr_before(a, b) + */ if ((int) b - a == 32768) return false; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 5325af85eea6..01a5261ac7a5 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -23,6 +23,8 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_SLAVE1] = { .type = NLA_U32 }, [IFLA_HSR_SLAVE2] = { .type = NLA_U32 }, [IFLA_HSR_MULTICAST_SPEC] = { .type = NLA_U8 }, + [IFLA_HSR_SUPERVISION_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, }; @@ -59,6 +61,31 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return hsr_dev_finalize(dev, link, multicast_spec); } +static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct hsr_priv *hsr_priv; + + hsr_priv = netdev_priv(dev); + + if (hsr_priv->slave[0]) + if (nla_put_u32(skb, IFLA_HSR_SLAVE1, hsr_priv->slave[0]->ifindex)) + goto nla_put_failure; + + if (hsr_priv->slave[1]) + if (nla_put_u32(skb, IFLA_HSR_SLAVE2, hsr_priv->slave[1]->ifindex)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, + hsr_priv->sup_multicast_addr) || + nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr_priv->sequence_nr)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static struct rtnl_link_ops hsr_link_ops __read_mostly = { .kind = "hsr", .maxtype = IFLA_HSR_MAX, @@ -66,6 +93,7 @@ static struct rtnl_link_ops hsr_link_ops __read_mostly = { .priv_size = sizeof(struct hsr_priv), .setup = hsr_dev_setup, .newlink = hsr_newlink, + .fill_info = hsr_fill_info, }; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 523be38e37de..f2e15738534d 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -104,7 +104,10 @@ errout: static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; - struct net_device *dev = result->fi->fib_dev; + struct net_device *dev = NULL; + + if (result->fi) + dev = result->fi->fib_dev; /* do not accept result if the route does * not meet the required prefix length diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 56a964a553d2..a0f52dac8940 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = inet->inet_dport; + + 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] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; @@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_family = tw->tw_family; r->idiag_retrans = 0; + r->id.idiag_if = tw->tw_bound_dev_if; sock_diag_save_cookie(tw, r->id.idiag_cookie); + r->id.idiag_sport = tw->tw_sport; r->id.idiag_dport = tw->tw_dport; + + 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] = tw->tw_rcv_saddr; r->id.idiag_dst[0] = tw->tw_daddr; + r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = jiffies_to_msecs(tmo); @@ -726,8 +737,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = ireq->ir_rmt_port; + + 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] = ireq->ir_loc_addr; r->id.idiag_dst[0] = ireq->ir_rmt_addr; + r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d7aea4c5b940..e560ef34cf4b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -217,6 +217,7 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) iph->saddr, iph->daddr, tpi->key); if (tunnel) { + skb_pop_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error); return PACKET_RCVD; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3f858266fa7e..ddf32a6bc415 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -386,7 +386,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf /* * Handle MSG_ERRQUEUE */ -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; @@ -423,6 +423,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index f13bd91d9a56..a313c3fbeb46 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -423,6 +423,7 @@ static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par) static struct xt_target synproxy_tg4_reg __read_mostly = { .name = "SYNPROXY", .family = NFPROTO_IPV4, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), .target = synproxy_tg4, .targetsize = sizeof(struct xt_synproxy_info), .checkentry = synproxy_tg4_check, diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index fff5ba1a33b7..4a5e94ac314a 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -72,7 +72,7 @@ static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_reject *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type)) + if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) goto nla_put_failure; switch (priv->type) { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 876c6ca2d8f9..242e7f4ed6f4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -772,7 +772,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -841,10 +841,11 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_ERRQUEUE) { if (family == AF_INET) { - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { - return pingv6_ops.ipv6_recv_error(sk, msg, len); + return pingv6_ops.ipv6_recv_error(sk, msg, len, + addr_len); #endif } } diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index ce848461acbb..46d6a1c923a8 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -31,10 +31,6 @@ const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; -/* - * Add a protocol handler to the hash tables - */ - int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { if (!prot->netns_ok) { @@ -55,10 +51,6 @@ int inet_add_offload(const struct net_offload *prot, unsigned char protocol) } EXPORT_SYMBOL(inet_add_offload); -/* - * Remove a protocol from the hash tables. - */ - int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) { int ret; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5cb8ddb505ee..23c3e5b5bb53 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -697,7 +697,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto out; if (flags & MSG_ERRQUEUE) { - err = ip_recv_error(sk, msg, len); + err = ip_recv_error(sk, msg, len, addr_len); goto out; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3dc0c6cf02a8..c4638e6f0238 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1425,7 +1425,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) do { if (dma_async_is_tx_complete(tp->ucopy.dma_chan, last_issued, &done, - &used) == DMA_SUCCESS) { + &used) == DMA_COMPLETE) { /* Safe to free early-copied skbs now */ __skb_queue_purge(&sk->sk_async_wait_queue); break; @@ -1433,7 +1433,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) struct sk_buff *skb; while ((skb = skb_peek(&sk->sk_async_wait_queue)) && (dma_async_is_complete(skb->dma_cookie, done, - used) == DMA_SUCCESS)) { + used) == DMA_COMPLETE)) { __skb_dequeue(&sk->sk_async_wait_queue); kfree_skb(skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 59a6f8b90cd9..067213924751 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 03e9154f7e68..f7e522c558ba 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -6,13 +6,6 @@ #include <linux/memcontrol.h> #include <linux/module.h> -static void memcg_tcp_enter_memory_pressure(struct sock *sk) -{ - if (sk->sk_cgrp->memory_pressure) - sk->sk_cgrp->memory_pressure = 1; -} -EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); - int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { /* @@ -60,7 +53,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) { struct cg_proto *cg_proto; - u64 old_lim; int i; int ret; @@ -71,7 +63,6 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) if (val > RES_COUNTER_MAX) val = RES_COUNTER_MAX; - old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT); ret = res_counter_set_limit(&cg_proto->memory_allocated, val); if (ret) return ret; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index a2b68a108eae..05606353c7e7 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -274,33 +274,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff * { const struct iphdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + 0); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), IPPROTO_TCP, 0); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5944d7d668dd..f140048334ce 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -560,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { - struct sock *sk; const struct iphdr *iph = ip_hdr(skb); - if (unlikely(sk = skb_steal_sock(skb))) - return sk; - else - return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - udptable); + return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + udptable); } struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, @@ -999,7 +995,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -1098,6 +1094,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; @@ -1236,7 +1235,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, bool slow; if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -1600,12 +1599,16 @@ static void flush_stack(struct sock **stack, unsigned int count, kfree_skb(skb1); } -static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +/* For TCP sockets, sk_rx_dst is protected by socket lock + * For UDP, we use xchg() to guard against concurrent changes. + */ +static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { - struct dst_entry *dst = skb_dst(skb); + struct dst_entry *old; dst_hold(dst); - sk->sk_rx_dst = dst; + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); } /* @@ -1736,15 +1739,16 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - if (skb->sk) { + sk = skb_steal_sock(skb); + if (sk) { + struct dst_entry *dst = skb_dst(skb); int ret; - sk = skb->sk; - if (unlikely(sk->sk_rx_dst == NULL)) - udp_sk_rx_dst_set(sk, skb); + if (unlikely(sk->sk_rx_dst != dst)) + udp_sk_rx_dst_set(sk, dst); ret = udp_queue_rcv_skb(sk, skb); - + sock_put(sk); /* a return value > 0 means to resubmit the input, but * it wants the return to be -protocol, or 0 */ @@ -1910,17 +1914,20 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, void udp_v4_early_demux(struct sk_buff *skb) { - const struct iphdr *iph = ip_hdr(skb); - const struct udphdr *uh = udp_hdr(skb); + struct net *net = dev_net(skb->dev); + const struct iphdr *iph; + const struct udphdr *uh; struct sock *sk; struct dst_entry *dst; - struct net *net = dev_net(skb->dev); int dif = skb->dev->ifindex; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return; + iph = ip_hdr(skb); + uh = udp_hdr(skb); + if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 12c97d8aa6bb..d5fa5b8c443e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2613,7 +2613,7 @@ static void init_loopback(struct net_device *dev) if (sp_ifa->rt) continue; - sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0); + sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, false); /* Failure cases are ignored */ if (!IS_ERR(sp_rt)) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index a454b0ff57c7..93b1aa34c432 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -73,7 +73,6 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - usin->sin6_addr = flowlabel->dst; } } @@ -318,7 +317,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,6 +368,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -377,6 +377,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; + sin->sin6_port = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -423,7 +424,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +459,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index e27591635f92..3fd0a578329e 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -122,7 +122,11 @@ out: static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) { struct rt6_info *rt = (struct rt6_info *) arg->result; - struct net_device *dev = rt->rt6i_idev->dev; + struct net_device *dev = NULL; + + if (rt->rt6i_idev) + dev = rt->rt6i_idev->dev; + /* do not accept result if the route does * not meet the required prefix length */ diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 59df872e2f4d..e6f931997996 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -116,8 +116,8 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -1193,11 +1193,35 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { - if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { - ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen); + unsigned int maxnonfragsize, headersize; + + headersize = sizeof(struct ipv6hdr) + + (opt ? opt->tot_len : 0) + + (dst_allfrag(&rt->dst) ? + sizeof(struct frag_hdr) : 0) + + rt->rt6i_nfheader_len; + + maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ? + mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + + /* dontfrag active */ + if ((cork->length + length > mtu - headersize) && dontfrag && + (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu - headersize + + sizeof(struct ipv6hdr)); + goto emsgsize; + } + + if (cork->length + length > maxnonfragsize - headersize) { +emsgsize: + ipv6_local_error(sk, EMSGSIZE, fl6, + mtu - headersize + + sizeof(struct ipv6hdr)); return -EMSGSIZE; } } @@ -1222,12 +1246,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || - sk->sk_protocol == IPPROTO_RAW)) { - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - skb = skb_peek_tail(&sk->sk_write_queue); cork->length += length; if (((length > mtu) || diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3512177deb4d..300865171394 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1277,6 +1277,9 @@ skip_linkparms: ri->prefix_len == 0) continue; #endif + if (ri->prefix_len == 0 && + !in6_dev->cnf.accept_ra_defrtr) + continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) continue; rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3, diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index f78f41aca8e9..a0d17270117c 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -446,6 +446,7 @@ static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par) static struct xt_target synproxy_tg6_reg __read_mostly = { .name = "SYNPROXY", .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), .target = synproxy_tg6, .targetsize = sizeof(struct xt_synproxy_info), .checkentry = synproxy_tg6_check, diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 8815e31a87fe..a83243c3d656 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -57,7 +57,8 @@ static struct inet_protosw pingv6_protosw = { /* Compatibility glue so we can support IPv6 when it's compiled as a module */ -static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { return -EAFNOSUPPORT; } diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 22d1bd4670da..e048cf1bb6a2 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -36,10 +36,6 @@ int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol } EXPORT_SYMBOL(inet6_add_protocol); -/* - * Remove a protocol from the hash tables. - */ - int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) { int ret; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e24ff1df0401..b6bb87e55805 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -466,10 +466,10 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -792,7 +792,6 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - daddr = &flowlabel->dst; } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7faa9d5e1503..4b4944c3e4c4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -84,6 +84,8 @@ static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -234,9 +236,6 @@ static const struct rt6_info ip6_null_entry_template = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES -static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); - static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -1565,21 +1564,24 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } } - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; + rt->dst.output = dst_discard; + rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.error = -EACCES; + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: - rt->dst.error = -EAGAIN; - break; default: - rt->dst.error = -ENETUNREACH; + rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN + : -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; break; } goto install_route; @@ -1903,9 +1905,7 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, else rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; - if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == - (RTF_DEFAULT | RTF_ADDRCONF)) - rt6_set_from(rt, ort); + rt6_set_from(rt, ort); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -2144,8 +2144,6 @@ static int ip6_pkt_discard_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); @@ -2157,8 +2155,6 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } -#endif - /* * Allocate a dst for local (unicast / anycast) address. */ @@ -2168,12 +2164,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - - if (!rt) { - net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, + DST_NOCOUNT, NULL); + if (!rt) return ERR_PTR(-ENOMEM); - } in6_dev_hold(idev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1b4a4a953675..a710fdec42d3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -478,14 +478,44 @@ static void ipip6_tunnel_uninit(struct net_device *dev) dev_put(dev); } +/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH + * if sufficient data bytes are available + */ +static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct rt6_info *rt; + struct sk_buff *skb2; + + if (!pskb_may_pull(skb, iph->ihl * 4 + sizeof(struct ipv6hdr) + 8)) + return 1; + + skb2 = skb_clone(skb, GFP_ATOMIC); + + if (!skb2) + return 1; + + skb_dst_drop(skb2); + skb_pull(skb2, iph->ihl * 4); + skb_reset_network_header(skb2); + + rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); + + if (rt && rt->dst.dev) + skb2->dev = rt->dst.dev; + + icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); + + if (rt) + ip6_rt_put(rt); + + kfree_skb(skb2); + + return 0; +} static int ipip6_err(struct sk_buff *skb, u32 info) { - -/* All the routers (except for Linux) return only - 8 bytes of packet payload. It means, that precise relaying of - ICMP in the real Internet is absolutely infeasible. - */ const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -500,7 +530,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: @@ -545,6 +574,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info) goto out; err = 0; + if (!ipip6_err_gen_icmpv6_unreach(skb)) + goto out; + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; @@ -892,7 +924,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (tunnel->parms.iph.daddr && skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; @@ -919,7 +951,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; - dev_kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) @@ -945,7 +977,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, tx_error_icmp: dst_link_failure(skb); tx_error: - dev_kfree_skb(skb); + kfree_skb(skb); out: dev->stats.tx_errors++; return NETDEV_TX_OK; @@ -985,7 +1017,7 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, tx_err: dev->stats.tx_errors++; - dev_kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0740f93a114a..f67033b4bb66 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -156,7 +156,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index c1097c798900..6d18157dc32c 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -37,34 +37,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, { const struct ipv6hdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + wsum); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 81eb8cf8389b..089c741a3992 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -393,10 +393,10 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, bool slow; if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -1140,7 +1140,6 @@ do_udp_sendmsg: flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - daddr = &flowlabel->dst; } } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index cfd65304be60..bb6e206ea70b 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -528,7 +528,6 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - daddr = &flowlabel->dst; } } @@ -665,7 +664,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, *addr_len = sizeof(*lsa); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 2bc2dec20b00..6226803fc490 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -59,7 +59,7 @@ hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1, u32 *multi) { return ip1->ipcmp == ip2->ipcmp && - ip2->ccmp == ip2->ccmp; + ip1->ccmp == ip2->ccmp; } static inline int diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dcddc49c0e08..f93b7d06f4be 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1717,6 +1717,19 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule) return -ENOENT; } +static int nf_table_delrule_by_chain(struct nft_ctx *ctx) +{ + struct nft_rule *rule; + int err; + + list_for_each_entry(rule, &ctx->chain->rules, list) { + err = nf_tables_delrule_one(ctx, rule); + if (err < 0) + return err; + } + return 0; +} + static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -1725,8 +1738,8 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, const struct nft_af_info *afi; struct net *net = sock_net(skb->sk); const struct nft_table *table; - struct nft_chain *chain; - struct nft_rule *rule, *tmp; + struct nft_chain *chain = NULL; + struct nft_rule *rule; int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; @@ -1738,22 +1751,29 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(table)) return PTR_ERR(table); - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); - if (IS_ERR(chain)) - return PTR_ERR(chain); + if (nla[NFTA_RULE_CHAIN]) { + chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]); + if (IS_ERR(chain)) + return PTR_ERR(chain); + } nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla); - if (nla[NFTA_RULE_HANDLE]) { - rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); - if (IS_ERR(rule)) - return PTR_ERR(rule); + if (chain) { + if (nla[NFTA_RULE_HANDLE]) { + rule = nf_tables_rule_lookup(chain, + nla[NFTA_RULE_HANDLE]); + if (IS_ERR(rule)) + return PTR_ERR(rule); - err = nf_tables_delrule_one(&ctx, rule); - } else { - /* Remove all rules in this chain */ - list_for_each_entry_safe(rule, tmp, &chain->rules, list) { err = nf_tables_delrule_one(&ctx, rule); + } else { + err = nf_table_delrule_by_chain(&ctx); + } + } else { + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + err = nf_table_delrule_by_chain(&ctx); if (err < 0) break; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9ff035c71403..a3910fc2122b 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -325,21 +325,24 @@ static void htable_gc(unsigned long htlong) add_timer(&ht->timer); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) +static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(hinfo->net); struct proc_dir_entry *parent; - del_timer_sync(&hinfo->timer); - if (hinfo->family == NFPROTO_IPV4) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; - if(parent != NULL) + if (parent != NULL) remove_proc_entry(hinfo->name, parent); +} +static void htable_destroy(struct xt_hashlimit_htable *hinfo) +{ + del_timer_sync(&hinfo->timer); + htable_remove_proc_entry(hinfo); htable_selective_cleanup(hinfo, select_all); kfree(hinfo->name); vfree(hinfo); @@ -883,21 +886,15 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { struct xt_hashlimit_htable *hinfo; - struct proc_dir_entry *pde; struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); - /* recent_net_exit() is called before recent_mt_destroy(). Make sure - * that the parent xt_recent proc entry is is empty before trying to - * remove it. + /* hashlimit_net_exit() is called before hashlimit_mt_destroy(). + * Make sure that the parent ipt_hashlimit and ip6t_hashlimit proc + * entries is empty before trying to remove it. */ mutex_lock(&hashlimit_mutex); - pde = hashlimit_net->ipt_hashlimit; - if (pde == NULL) - pde = hashlimit_net->ip6t_hashlimit; - hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) - remove_proc_entry(hinfo->name, pde); - + htable_remove_proc_entry(hinfo); hashlimit_net->ipt_hashlimit = NULL; hashlimit_net->ip6t_hashlimit = NULL; mutex_unlock(&hashlimit_mutex); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 4518a57aa5fe..713671ae45af 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -74,9 +74,12 @@ static struct list_head family_ht[GENL_FAM_TAB_SIZE]; * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. + * Bit 18 is marked as already used since the PMCRAID driver + * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | - BIT(GENL_ID_VFS_DQUOT); + BIT(GENL_ID_VFS_DQUOT) | + BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; @@ -139,6 +142,7 @@ static u16 genl_generate_id(void) for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) { if (id_gen_idx != GENL_ID_VFS_DQUOT && + id_gen_idx != GENL_ID_PMCRAID && !genl_family_find_byid(id_gen_idx)) return id_gen_idx; if (++id_gen_idx > GENL_MAX_ID) @@ -214,7 +218,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) { int first_id; int n_groups = family->n_mcgrps; - int err, i; + int err = 0, i; bool groups_allocated = false; if (!n_groups) @@ -236,9 +240,12 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) } else if (strcmp(family->name, "NET_DM") == 0) { first_id = 1; BUG_ON(n_groups != 1); - } else if (strcmp(family->name, "VFS_DQUOT") == 0) { + } else if (family->id == GENL_ID_VFS_DQUOT) { first_id = GENL_ID_VFS_DQUOT; BUG_ON(n_groups != 1); + } else if (family->id == GENL_ID_PMCRAID) { + first_id = GENL_ID_PMCRAID; + BUG_ON(n_groups != 1); } else { groups_allocated = true; err = genl_allocate_reserve_groups(n_groups, &first_id); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ac27c86ef6d1..88cfbc189558 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -237,6 +237,30 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +static struct net_device *packet_cached_dev_get(struct packet_sock *po) +{ + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(po->cached_dev); + if (likely(dev)) + dev_hold(dev); + rcu_read_unlock(); + + return dev; +} + +static void packet_cached_dev_assign(struct packet_sock *po, + struct net_device *dev) +{ + rcu_assign_pointer(po->cached_dev, dev); +} + +static void packet_cached_dev_reset(struct packet_sock *po) +{ + RCU_INIT_POINTER(po->cached_dev, NULL); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -246,12 +270,10 @@ static void register_prot_hook(struct sock *sk) struct packet_sock *po = pkt_sk(sk); if (!po->running) { - if (po->fanout) { + if (po->fanout) __fanout_link(sk, po); - } else { + else dev_add_pack(&po->prot_hook); - rcu_assign_pointer(po->cached_dev, po->prot_hook.dev); - } sock_hold(sk); po->running = 1; @@ -270,12 +292,11 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) struct packet_sock *po = pkt_sk(sk); po->running = 0; - if (po->fanout) { + + if (po->fanout) __fanout_unlink(sk, po); - } else { + else __dev_remove_pack(&po->prot_hook); - RCU_INIT_POINTER(po->cached_dev, NULL); - } __sock_put(sk); @@ -439,9 +460,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; - spin_lock(&rb_queue->lock); + spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; - spin_unlock(&rb_queue->lock); + spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } @@ -2059,19 +2080,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, return tp_len; } -static struct net_device *packet_cached_dev_get(struct packet_sock *po) -{ - struct net_device *dev; - - rcu_read_lock(); - dev = rcu_dereference(po->cached_dev); - if (dev) - dev_hold(dev); - rcu_read_unlock(); - - return dev; -} - static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb; @@ -2088,7 +2096,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); - if (saddr == NULL) { + if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; @@ -2242,7 +2250,7 @@ static int packet_snd(struct socket *sock, * Get and verify the address. */ - if (saddr == NULL) { + if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; @@ -2451,6 +2459,8 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + packet_cached_dev_reset(po); + if (po->prot_hook.dev) { dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -2506,14 +2516,17 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc spin_lock(&po->bind_lock); unregister_prot_hook(sk, true); + po->num = protocol; po->prot_hook.type = protocol; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; + po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + if (protocol == 0) goto out_unlock; @@ -2626,7 +2639,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po = pkt_sk(sk); sk->sk_family = PF_PACKET; po->num = proto; - RCU_INIT_POINTER(po->cached_dev, NULL); + + packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); @@ -3337,6 +3351,7 @@ static int packet_notifier(struct notifier_block *this, sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { + packet_cached_dev_reset(po); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index e59094981175..37be6e226d1b 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -552,9 +552,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); scat = &rm->data.op_sg[sg]; - ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; - ret = min_t(int, ret, scat->length - conn->c_xmit_data_off); - return ret; + ret = max_t(int, RDS_CONG_MAP_BYTES, scat->length); + return sizeof(struct rds_header) + ret; } /* FIXME we may overallocate here */ diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fd7072827a40..69cb848e8345 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -270,6 +270,16 @@ int tcf_register_action(struct tc_action_ops *act) { struct tc_action_ops *a, **ap; + /* Must supply act, dump, cleanup and init */ + if (!act->act || !act->dump || !act->cleanup || !act->init) + return -EINVAL; + + /* Supply defaults */ + if (!act->lookup) + act->lookup = tcf_hash_search; + if (!act->walk) + act->walk = tcf_generic_walker; + write_lock(&act_mod_lock); for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { @@ -381,7 +391,7 @@ int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act, } while ((a = act) != NULL) { repeat: - if (a->ops && a->ops->act) { + if (a->ops) { ret = a->ops->act(skb, a, res); if (TC_MUNGED & skb->tc_verd) { /* copied already, allow trampling */ @@ -405,7 +415,7 @@ void tcf_action_destroy(struct tc_action *act, int bind) struct tc_action *a; for (a = act; a; a = act) { - if (a->ops && a->ops->cleanup) { + if (a->ops) { if (a->ops->cleanup(a, bind) == ACT_P_DELETED) module_put(a->ops->owner); act = act->next; @@ -424,7 +434,7 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { int err = -EINVAL; - if (a->ops == NULL || a->ops->dump == NULL) + if (a->ops == NULL) return err; return a->ops->dump(skb, a, bind, ref); } @@ -436,7 +446,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (a->ops == NULL || a->ops->dump == NULL) + if (a->ops == NULL) return err; if (nla_put_string(skb, TCA_KIND, a->ops->kind)) @@ -723,8 +733,6 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (a->ops == NULL) goto err_free; - if (a->ops->lookup == NULL) - goto err_mod; err = -ENOENT; if (a->ops->lookup(a, index) == 0) goto err_mod; @@ -1084,12 +1092,6 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) memset(&a, 0, sizeof(struct tc_action)); a.ops = a_o; - if (a_o->walk == NULL) { - WARN(1, "tc_dump_action: %s !capable of dumping table\n", - a_o->kind); - goto out_module_put; - } - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 3a4c0caa1f7d..5c5edf56adbd 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -585,9 +585,7 @@ static struct tc_action_ops act_csum_ops = { .act = tcf_csum, .dump = tcf_csum_dump, .cleanup = tcf_csum_cleanup, - .lookup = tcf_hash_search, .init = tcf_csum_init, - .walk = tcf_generic_walker }; MODULE_DESCRIPTION("Checksum updating actions"); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index fd2b3cff5fa2..5645a4d32abd 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -206,9 +206,7 @@ static struct tc_action_ops act_gact_ops = { .act = tcf_gact, .dump = tcf_gact_dump, .cleanup = tcf_gact_cleanup, - .lookup = tcf_hash_search, .init = tcf_gact_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 60d88b6b9560..882a89762f77 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -298,9 +298,7 @@ static struct tc_action_ops act_ipt_ops = { .act = tcf_ipt, .dump = tcf_ipt_dump, .cleanup = tcf_ipt_cleanup, - .lookup = tcf_hash_search, .init = tcf_ipt_init, - .walk = tcf_generic_walker }; static struct tc_action_ops act_xt_ops = { @@ -312,9 +310,7 @@ static struct tc_action_ops act_xt_ops = { .act = tcf_ipt, .dump = tcf_ipt_dump, .cleanup = tcf_ipt_cleanup, - .lookup = tcf_hash_search, .init = tcf_ipt_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 977c10e0631b..252378121ce7 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -271,9 +271,7 @@ static struct tc_action_ops act_mirred_ops = { .act = tcf_mirred, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_cleanup, - .lookup = tcf_hash_search, .init = tcf_mirred_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 876f0ef29694..6a15ace00241 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -308,9 +308,7 @@ static struct tc_action_ops act_nat_ops = { .act = tcf_nat, .dump = tcf_nat_dump, .cleanup = tcf_nat_cleanup, - .lookup = tcf_hash_search, .init = tcf_nat_init, - .walk = tcf_generic_walker }; MODULE_DESCRIPTION("Stateless NAT actions"); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 7ed78c9e505c..03b67674169c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -243,9 +243,7 @@ static struct tc_action_ops act_pedit_ops = { .act = tcf_pedit, .dump = tcf_pedit_dump, .cleanup = tcf_pedit_cleanup, - .lookup = tcf_hash_search, .init = tcf_pedit_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 272d8e924cf6..16a62c36928a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -407,7 +407,6 @@ static struct tc_action_ops act_police_ops = { .act = tcf_act_police, .dump = tcf_act_police_dump, .cleanup = tcf_act_police_cleanup, - .lookup = tcf_hash_search, .init = tcf_act_police_locate, .walk = tcf_act_police_walker }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 7725eb4ab756..31157d3e729c 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -201,7 +201,6 @@ static struct tc_action_ops act_simp_ops = { .dump = tcf_simp_dump, .cleanup = tcf_simp_cleanup, .init = tcf_simp_init, - .walk = tcf_generic_walker, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index cb4221171f93..35ea643b4325 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -203,7 +203,6 @@ static struct tc_action_ops act_skbedit_ops = { .dump = tcf_skbedit_dump, .cleanup = tcf_skbedit_cleanup, .init = tcf_skbedit_init, - .walk = tcf_generic_walker, }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 0e1e38b40025..717b2108f852 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1477,11 +1477,22 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, sch_tree_lock(sch); } + rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + + ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + + psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64); + psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); + /* it used to be a nasty bug here, we have to check that node * is really leaf before changing cl->un.leaf ! */ if (!cl->level) { - cl->quantum = hopt->rate.rate / q->rate2quantum; + u64 quantum = cl->rate.rate_bytes_ps; + + do_div(quantum, q->rate2quantum); + cl->quantum = min_t(u64, quantum, INT_MAX); + if (!hopt->quantum && cl->quantum < 1000) { pr_warning( "HTB: quantum of class %X is small. Consider r2q change.\n", @@ -1500,13 +1511,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->prio = TC_HTB_NUMPRIO - 1; } - rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; - - ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; - - psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64); - psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); - cl->buffer = PSCHED_TICKS2NS(hopt->buffer); cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 75c94e59a3bd..bccd52b36e97 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -215,10 +215,10 @@ static bool loss_4state(struct netem_sched_data *q) if (rnd < clg->a4) { clg->state = 4; return true; - } else if (clg->a4 < rnd && rnd < clg->a1) { + } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { clg->state = 3; return true; - } else if (clg->a1 < rnd) + } else if (clg->a1 + clg->a4 < rnd) clg->state = 1; break; @@ -268,10 +268,11 @@ static bool loss_gilb_ell(struct netem_sched_data *q) clg->state = 2; if (net_random() < clg->a4) return true; + break; case 2: if (net_random() < clg->a2) clg->state = 1; - if (clg->a3 > net_random()) + if (net_random() > clg->a3) return true; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 68f98595819c..887e672f9d7d 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -21,6 +21,7 @@ #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> +#include <net/tcp.h> /* Simple Token Bucket Filter. @@ -117,6 +118,48 @@ struct tbf_sched_data { }; +/* Time to Length, convert time in ns to length in bytes + * to determinate how many bytes can be sent in given time. + */ +static u64 psched_ns_t2l(const struct psched_ratecfg *r, + u64 time_in_ns) +{ + /* The formula is : + * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC + */ + u64 len = time_in_ns * r->rate_bytes_ps; + + do_div(len, NSEC_PER_SEC); + + if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) { + do_div(len, 53); + len = len * 48; + } + + if (len > r->overhead) + len -= r->overhead; + else + len = 0; + + return len; +} + +/* + * Return length of individual segments of a gso packet, + * including all headers (MAC, IP, TCP/UDP) + */ +static unsigned int skb_gso_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + return hdr_len + shinfo->gso_size; +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -136,12 +179,8 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) while (segs) { nskb = segs->next; segs->next = NULL; - if (likely(segs->len <= q->max_size)) { - qdisc_skb_cb(segs)->pkt_len = segs->len; - ret = qdisc_enqueue(segs, q->qdisc); - } else { - ret = qdisc_reshape_fail(skb, sch); - } + qdisc_skb_cb(segs)->pkt_len = segs->len; + ret = qdisc_enqueue(segs, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) sch->qstats.drops++; @@ -163,7 +202,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb)) + if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size) return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); } @@ -276,10 +315,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) struct tbf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_TBF_MAX + 1]; struct tc_tbf_qopt *qopt; - struct qdisc_rate_table *rtab = NULL; - struct qdisc_rate_table *ptab = NULL; struct Qdisc *child = NULL; - int max_size, n; + struct psched_ratecfg rate; + struct psched_ratecfg peak; + u64 max_size; + s64 buffer, mtu; u64 rate64 = 0, prate64 = 0; err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy); @@ -291,33 +331,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) goto done; qopt = nla_data(tb[TCA_TBF_PARMS]); - rtab = qdisc_get_rtab(&qopt->rate, tb[TCA_TBF_RTAB]); - if (rtab == NULL) - goto done; + if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE) + qdisc_put_rtab(qdisc_get_rtab(&qopt->rate, + tb[TCA_TBF_RTAB])); - if (qopt->peakrate.rate) { - if (qopt->peakrate.rate > qopt->rate.rate) - ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]); - if (ptab == NULL) - goto done; - } - - for (n = 0; n < 256; n++) - if (rtab->data[n] > qopt->buffer) - break; - max_size = (n << qopt->rate.cell_log) - 1; - if (ptab) { - int size; - - for (n = 0; n < 256; n++) - if (ptab->data[n] > qopt->mtu) - break; - size = (n << qopt->peakrate.cell_log) - 1; - if (size < max_size) - max_size = size; - } - if (max_size < 0) - goto done; + if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE) + qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, + tb[TCA_TBF_PTAB])); if (q->qdisc != &noop_qdisc) { err = fifo_set_limit(q->qdisc, qopt->limit); @@ -331,6 +351,39 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) } } + buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); + mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); + + if (tb[TCA_TBF_RATE64]) + rate64 = nla_get_u64(tb[TCA_TBF_RATE64]); + psched_ratecfg_precompute(&rate, &qopt->rate, rate64); + + max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U); + + if (qopt->peakrate.rate) { + if (tb[TCA_TBF_PRATE64]) + prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]); + psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64); + if (peak.rate_bytes_ps <= rate.rate_bytes_ps) { + pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n", + peak.rate_bytes_ps, rate.rate_bytes_ps); + err = -EINVAL; + goto done; + } + + max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); + } + + if (max_size < psched_mtu(qdisc_dev(sch))) + pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n", + max_size, qdisc_dev(sch)->name, + psched_mtu(qdisc_dev(sch))); + + if (!max_size) { + err = -EINVAL; + goto done; + } + sch_tree_lock(sch); if (child) { qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); @@ -344,13 +397,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->tokens = q->buffer; q->ptokens = q->mtu; - if (tb[TCA_TBF_RATE64]) - rate64 = nla_get_u64(tb[TCA_TBF_RATE64]); - psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64); - if (ptab) { - if (tb[TCA_TBF_PRATE64]) - prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]); - psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64); + memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg)); + if (qopt->peakrate.rate) { + memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); q->peak_present = true; } else { q->peak_present = false; @@ -359,10 +408,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) sch_tree_unlock(sch); err = 0; done: - if (rtab) - qdisc_put_rtab(rtab); - if (ptab) - qdisc_put_rtab(ptab); return err; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 68a27f9796d2..31ed008c8e13 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -154,8 +154,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; - asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - min_t(unsigned long, sp->autoclose, net->sctp.max_autoclose) * HZ; + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) @@ -291,8 +290,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->peer.ipv6_address = 1; INIT_LIST_HEAD(&asoc->asocs); - asoc->autoclose = sp->autoclose; - asoc->default_stream = sp->default_stream; asoc->default_ppid = sp->default_ppid; asoc->default_flags = sp->default_flags; diff --git a/net/sctp/output.c b/net/sctp/output.c index e650978daf27..0fb140f8f088 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -474,10 +474,11 @@ int sctp_packet_transmit(struct sctp_packet *packet) * for a given destination transport address. */ - if (!tp->rto_pending) { + if (!chunk->resent && !tp->rto_pending) { chunk->rtt_in_progress = 1; tp->rto_pending = 1; } + has_data = 1; } @@ -580,7 +581,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) unsigned long timeout; /* Restart the AUTOCLOSE timer when sending data. */ - if (sctp_state(asoc, ESTABLISHED) && asoc->autoclose) { + if (sctp_state(asoc, ESTABLISHED) && + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) { timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]; timeout = asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 94df75877869..f51ba985a36e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -446,6 +446,8 @@ void sctp_retransmit_mark(struct sctp_outq *q, transport->rto_pending = 0; } + chunk->resent = 1; + /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ @@ -1375,6 +1377,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * instance). */ if (!tchunk->tsn_gap_acked && + !tchunk->resent && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; @@ -1391,7 +1394,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, */ if (!tchunk->tsn_gap_acked) { tchunk->tsn_gap_acked = 1; - *highest_new_tsn_in_sack = tsn; + if (TSN_lt(*highest_new_tsn_in_sack, tsn)) + *highest_new_tsn_in_sack = tsn; bytes_acked += sctp_data_size(tchunk); if (!tchunk->transport) migrate_bytes += sctp_data_size(tchunk); diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 53c452efb40b..5e68b94ee640 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -38,6 +38,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +MODULE_SOFTDEP("pre: sctp"); MODULE_AUTHOR("Wei Yongjun <yjwei@cn.fujitsu.com>"); MODULE_DESCRIPTION("SCTP snooper"); MODULE_LICENSE("GPL"); @@ -182,6 +183,20 @@ static struct jprobe sctp_recv_probe = { .entry = jsctp_sf_eat_sack, }; +static __init int sctp_setup_jprobe(void) +{ + int ret = register_jprobe(&sctp_recv_probe); + + if (ret) { + if (request_module("sctp")) + goto out; + ret = register_jprobe(&sctp_recv_probe); + } + +out: + return ret; +} + static __init int sctpprobe_init(void) { int ret = -ENOMEM; @@ -202,7 +217,7 @@ static __init int sctpprobe_init(void) &sctpprobe_fops)) goto free_kfifo; - ret = register_jprobe(&sctp_recv_probe); + ret = sctp_setup_jprobe(); if (ret) goto remove_proc; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dfe3f36ff2aa..a26065be7289 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -820,7 +820,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_PASSIVEESTABS); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); - if (new_asoc->autoclose) + if (new_asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); @@ -908,7 +908,7 @@ sctp_disposition_t sctp_sf_do_5_1E_ca(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); SCTP_INC_STATS(net, SCTP_MIB_ACTIVEESTABS); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); - if (asoc->autoclose) + if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); @@ -2970,7 +2970,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, if (chunk->chunk_hdr->flags & SCTP_DATA_SACK_IMM) force = SCTP_FORCE(); - if (asoc->autoclose) { + if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); } @@ -3878,7 +3878,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, SCTP_CHUNK(chunk)); /* Count this as receiving DATA. */ - if (asoc->autoclose) { + if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); } @@ -5267,7 +5267,7 @@ sctp_disposition_t sctp_sf_do_9_2_start_shutdown( sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); - if (asoc->autoclose) + if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); @@ -5346,7 +5346,7 @@ sctp_disposition_t sctp_sf_do_9_2_shutdown_ack( sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); - if (asoc->autoclose) + if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 72046b9729a8..42b709c95cf3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2196,6 +2196,7 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); + struct net *net = sock_net(sk); /* Applicable to UDP-style socket only */ if (sctp_style(sk, TCP)) @@ -2205,6 +2206,9 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; + if (sp->autoclose > net->sctp.max_autoclose) + sp->autoclose = net->sctp.max_autoclose; + return 0; } @@ -2811,6 +2815,8 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne { struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; + unsigned long rto_min, rto_max; + struct sctp_sock *sp = sctp_sk(sk); if (optlen != sizeof (struct sctp_rtoinfo)) return -EINVAL; @@ -2824,26 +2830,36 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP)) return -EINVAL; + rto_max = rtoinfo.srto_max; + rto_min = rtoinfo.srto_min; + + if (rto_max) + rto_max = asoc ? msecs_to_jiffies(rto_max) : rto_max; + else + rto_max = asoc ? asoc->rto_max : sp->rtoinfo.srto_max; + + if (rto_min) + rto_min = asoc ? msecs_to_jiffies(rto_min) : rto_min; + else + rto_min = asoc ? asoc->rto_min : sp->rtoinfo.srto_min; + + if (rto_min > rto_max) + return -EINVAL; + if (asoc) { if (rtoinfo.srto_initial != 0) asoc->rto_initial = msecs_to_jiffies(rtoinfo.srto_initial); - if (rtoinfo.srto_max != 0) - asoc->rto_max = msecs_to_jiffies(rtoinfo.srto_max); - if (rtoinfo.srto_min != 0) - asoc->rto_min = msecs_to_jiffies(rtoinfo.srto_min); + asoc->rto_max = rto_max; + asoc->rto_min = rto_min; } else { /* If there is no association or the association-id = 0 * set the values to the endpoint. */ - struct sctp_sock *sp = sctp_sk(sk); - if (rtoinfo.srto_initial != 0) sp->rtoinfo.srto_initial = rtoinfo.srto_initial; - if (rtoinfo.srto_max != 0) - sp->rtoinfo.srto_max = rtoinfo.srto_max; - if (rtoinfo.srto_min != 0) - sp->rtoinfo.srto_min = rtoinfo.srto_min; + sp->rtoinfo.srto_max = rto_max; + sp->rtoinfo.srto_min = rto_min; } return 0; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b36561a1b3b..b0565afb61c7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -56,11 +56,16 @@ extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; extern int sysctl_sctp_wmem[3]; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, - int write, +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, - loff_t *ppos); + static struct ctl_table sctp_table[] = { { .procname = "sctp_mem", @@ -102,17 +107,17 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.rto_min, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_sctp_do_rto_min, .extra1 = &one, - .extra2 = &timer_max + .extra2 = &init_net.sctp.rto_max }, { .procname = "rto_max", .data = &init_net.sctp.rto_max, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .proc_handler = proc_sctp_do_rto_max, + .extra1 = &init_net.sctp.rto_min, .extra2 = &timer_max }, { @@ -294,8 +299,7 @@ static struct ctl_table sctp_net_table[] = { { /* sentinel */ } }; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, - int write, +static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -342,6 +346,60 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, return ret; } +static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + int new_value; + struct ctl_table tbl; + unsigned int min = *(unsigned int *) ctl->extra1; + unsigned int max = *(unsigned int *) ctl->extra2; + int ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.rto_min; + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write) { + if (ret || new_value > max || new_value < min) + return -EINVAL; + net->sctp.rto_min = new_value; + } + return ret; +} + +static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + int new_value; + struct ctl_table tbl; + unsigned int min = *(unsigned int *) ctl->extra1; + unsigned int max = *(unsigned int *) ctl->extra2; + int ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.rto_max; + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write) { + if (ret || new_value > max || new_value < min) + return -EINVAL; + net->sctp.rto_max = new_value; + } + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e332efb124cc..efc46ffed1fd 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -573,7 +573,7 @@ void sctp_transport_burst_limited(struct sctp_transport *t) u32 old_cwnd = t->cwnd; u32 max_burst_bytes; - if (t->burst_limited) + if (t->burst_limited || asoc->max_burst == 0) return; max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu); diff --git a/net/socket.c b/net/socket.c index 0b18693f2be6..e83c416708af 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1973,7 +1973,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 97912b40c254..42fdfc634e56 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1517,7 +1517,7 @@ out: static int gss_refresh_null(struct rpc_task *task) { - return -EACCES; + return 0; } static __be32 * diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index d0d14a04dce1..bf04b30a788a 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -471,15 +471,6 @@ struct rpc_filelist { umode_t mode; }; -static int rpc_delete_dentry(const struct dentry *dentry) -{ - return 1; -} - -static const struct dentry_operations rpc_dentry_operations = { - .d_delete = rpc_delete_dentry, -}; - static struct inode * rpc_get_inode(struct super_block *sb, umode_t mode) { @@ -1266,7 +1257,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = RPCAUTH_GSSMAGIC; sb->s_op = &s_ops; - sb->s_d_op = &rpc_dentry_operations; + sb->s_d_op = &simple_dentry_operations; sb->s_time_gran = 1; inode = rpc_get_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO); diff --git a/net/tipc/core.c b/net/tipc/core.c index fd4eeeaa972a..c6d3f75a9e1b 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -113,7 +113,6 @@ err: static void tipc_core_stop(void) { tipc_netlink_stop(); - tipc_handler_stop(); tipc_cfg_stop(); tipc_subscr_stop(); tipc_nametbl_stop(); @@ -146,9 +145,10 @@ static int tipc_core_start(void) res = tipc_subscr_start(); if (!res) res = tipc_cfg_init(); - if (res) + if (res) { + tipc_handler_stop(); tipc_core_stop(); - + } return res; } @@ -178,6 +178,7 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { + tipc_handler_stop(); tipc_core_stop_net(); tipc_core_stop(); pr_info("Deactivated\n"); diff --git a/net/tipc/handler.c b/net/tipc/handler.c index b36f0fcd9bdf..e4bc8a296744 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -56,12 +56,13 @@ unsigned int tipc_k_signal(Handler routine, unsigned long argument) { struct queue_item *item; + spin_lock_bh(&qitem_lock); if (!handler_enabled) { pr_err("Signal request ignored by handler\n"); + spin_unlock_bh(&qitem_lock); return -ENOPROTOOPT; } - spin_lock_bh(&qitem_lock); item = kmem_cache_alloc(tipc_queue_item_cache, GFP_ATOMIC); if (!item) { pr_err("Signal queue out of memory\n"); @@ -112,10 +113,14 @@ void tipc_handler_stop(void) struct list_head *l, *n; struct queue_item *item; - if (!handler_enabled) + spin_lock_bh(&qitem_lock); + if (!handler_enabled) { + spin_unlock_bh(&qitem_lock); return; - + } handler_enabled = 0; + spin_unlock_bh(&qitem_lock); + tasklet_kill(&tipc_tasklet); spin_lock_bh(&qitem_lock); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 01625ccc3ae6..a427623ee574 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -530,13 +530,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); -static void unix_set_peek_off(struct sock *sk, int val) +static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - mutex_lock(&u->readlock); + if (mutex_lock_interruptible(&u->readlock)) + return -EINTR; + sk->sk_peek_off = val; mutex_unlock(&u->readlock); + + return 0; } @@ -714,7 +718,9 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + return err; err = 0; if (u->addr) @@ -873,7 +879,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + goto out; err = -EINVAL; if (u->addr) |