diff options
Diffstat (limited to 'net')
84 files changed, 639 insertions, 1050 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 2fb2d88..61fc573 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -210,6 +210,7 @@ out_vid_del: static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; + struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; @@ -260,11 +261,12 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) new_dev->mtu = real_dev->mtu; new_dev->priv_flags |= (real_dev->priv_flags & IFF_UNICAST_FLT); - vlan_dev_priv(new_dev)->vlan_proto = htons(ETH_P_8021Q); - vlan_dev_priv(new_dev)->vlan_id = vlan_id; - vlan_dev_priv(new_dev)->real_dev = real_dev; - vlan_dev_priv(new_dev)->dent = NULL; - vlan_dev_priv(new_dev)->flags = VLAN_FLAG_REORDER_HDR; + vlan = vlan_dev_priv(new_dev); + vlan->vlan_proto = htons(ETH_P_8021Q); + vlan->vlan_id = vlan_id; + vlan->real_dev = real_dev; + vlan->dent = NULL; + vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev); @@ -459,6 +461,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1cd3d2a..9ab8a7e 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -107,10 +107,10 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, u16 vlan_tci = 0; int rc; - if (!(vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR)) { + if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) { vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN); - vlan_tci = vlan_dev_priv(dev)->vlan_id; + vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb); vhdr->h_vlan_TCI = htons(vlan_tci); @@ -133,7 +133,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, saddr = dev->dev_addr; /* Now make the underlying real hard header */ - dev = vlan_dev_priv(dev)->real_dev; + dev = vlan->real_dev; rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen); if (rc > 0) rc += vhdrlen; diff --git a/net/9p/client.c b/net/9p/client.c index 8b93cae..ba93bda 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -658,17 +658,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) /* * if we haven't received a response for oldreq, - * remove it from the list, and notify the transport - * layer that the reply will never arrive. + * remove it from the list */ - spin_lock(&c->lock); if (oldreq->status == REQ_STATUS_FLSH) { + spin_lock(&c->lock); list_del(&oldreq->req_list); spin_unlock(&c->lock); - if (c->trans_mod->cancelled) - c->trans_mod->cancelled(c, req); - } else { - spin_unlock(&c->lock); } p9_free_req(c, req); diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 928f2bb..8f68df5 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -588,17 +588,6 @@ static int rdma_cancel(struct p9_client *client, struct p9_req_t *req) return 1; } -/* A request has been fully flushed without a reply. - * That means we have posted one buffer in excess. - */ -static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req) -{ - struct p9_trans_rdma *rdma = client->trans; - - atomic_inc(&rdma->excess_rc); - return 0; -} - /** * trans_create_rdma - Transport method for creating atransport instance * @client: client instance diff --git a/net/Kconfig b/net/Kconfig index 2b40660..ee02136 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -281,7 +281,7 @@ menu "Network testing" config NET_PKTGEN tristate "Packet Generator (USE WITH CAUTION)" - depends on PROC_FS + depends on INET && PROC_FS ---help--- This module will inject preconfigured packets, at a configurable rate, out of a given interface. It is used for network interface diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 69363bd..0feaaa0 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -245,22 +245,22 @@ fail: int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { struct netpoll *np; - int err = 0; + int err; + + if (!p->br->dev->npinfo) + return 0; np = kzalloc(sizeof(*p->np), gfp); - err = -ENOMEM; if (!np) - goto out; + return -ENOMEM; err = __netpoll_setup(np, p->dev, gfp); if (err) { kfree(np); - goto out; + return err; } p->np = np; - -out: return err; } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 5623be6..aa6c9a8 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -363,7 +363,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err2; - if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) + err = br_netpoll_enable(p, GFP_KERNEL); + if (err) goto err3; err = netdev_master_upper_dev_link(dev, br->dev); diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 3a3f371..2998dd1 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -102,6 +102,11 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, br->dev); + break; } /* Events that may cause spanning tree to refresh */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2f7da41..1514c9f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -334,11 +334,6 @@ extern void br_dev_delete(struct net_device *dev, struct list_head *list); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); #ifdef CONFIG_NET_POLL_CONTROLLER -static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) -{ - return br->dev->npinfo; -} - static inline void br_netpoll_send_skb(const struct net_bridge_port *p, struct sk_buff *skb) { @@ -351,11 +346,6 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp); extern void br_netpoll_disable(struct net_bridge_port *p); #else -static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) -{ - return NULL; -} - static inline void br_netpoll_send_skb(const struct net_bridge_port *p, struct sk_buff *skb) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index eb0a46a..3be308e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -409,7 +409,7 @@ static void ceph_sock_write_space(struct sock *sk) * and net/core/stream.c:sk_stream_write_space(). */ if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { dout("%s %p queueing write work\n", __func__, con); clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); queue_con(con); diff --git a/net/core/dev.c b/net/core/dev.c index 26755dd..58eb802 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -174,7 +174,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id; static DEFINE_HASHTABLE(napi_hash, 8); -seqcount_t devnet_rename_seq; +static seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { @@ -4989,6 +4989,24 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier) EXPORT_SYMBOL(dev_change_carrier); /** + * dev_get_phys_port_id - Get device physical port ID + * @dev: device + * @ppid: port ID + * + * Get device physical port ID + */ +int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_id(dev, ppid); +} +EXPORT_SYMBOL(dev_get_phys_port_id); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 2173544..2e65413 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -33,6 +33,9 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->flags = flags; r->fr_net = hold_net(ops->fro_net); + r->suppress_prefixlen = -1; + r->suppress_ifgroup = -1; + /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); @@ -226,6 +229,9 @@ jumped: else err = ops->action(rule, fl, flags, arg); + if (!err && ops->suppress && ops->suppress(rule, arg)) + continue; + if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(atomic_inc_not_zero(&rule->refcnt))) { @@ -337,6 +343,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); + if (tb[FRA_SUPPRESS_PREFIXLEN]) + rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + else + rule->suppress_prefixlen = -1; + + if (tb[FRA_SUPPRESS_IFGROUP]) + rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + else + rule->suppress_ifgroup = -1; if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); @@ -523,6 +538,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4); /* FRA_FWMASK */ @@ -548,6 +565,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->table = rule->table; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; + if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) + goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; @@ -580,6 +599,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target))) goto nla_put_failure; + + if (rule->suppress_ifgroup != -1) { + if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) + goto nla_put_failure; + } + if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 00ee068..ade9ff1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -139,7 +139,11 @@ ipv6: break; } case IPPROTO_IPIP: - goto again; + proto = htons(ETH_P_IP); + goto ip; + case IPPROTO_IPV6: + proto = htons(ETH_P_IPV6); + goto ipv6; default: break; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9232c68..60533db 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1441,16 +1441,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 981fed3..8826b0d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -334,6 +334,27 @@ static ssize_t store_group(struct device *dev, struct device_attribute *attr, return netdev_store(dev, attr, buf, len, change_group); } +static ssize_t show_phys_port_id(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + struct netdev_phys_port_id ppid; + + ret = dev_get_phys_port_id(netdev, &ppid); + if (!ret) + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + } + rtnl_unlock(); + + return ret; +} + static struct device_attribute net_class_attributes[] = { __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), @@ -355,6 +376,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len), __ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group), + __ATTR(phys_port_id, S_IRUGO, show_phys_port_id, NULL), {} }; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 9640972..261357a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -160,6 +160,8 @@ #include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> #ifdef CONFIG_XFRM #include <net/xfrm.h> @@ -198,6 +200,7 @@ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ #define F_NODE (1<<15) /* Node memory alloc*/ +#define F_UDPCSUM (1<<16) /* Include UDP checksum */ /* Thread control flag bits */ #define T_STOP (1<<0) /* Stop run */ @@ -631,6 +634,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_UDPDST_RND) seq_printf(seq, "UDPDST_RND "); + if (pkt_dev->flags & F_UDPCSUM) + seq_printf(seq, "UDPCSUM "); + if (pkt_dev->flags & F_MPLS_RND) seq_printf(seq, "MPLS_RND "); @@ -1228,6 +1234,12 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!NODE_ALLOC") == 0) pkt_dev->flags &= ~F_NODE; + else if (strcmp(f, "UDPCSUM") == 0) + pkt_dev->flags |= F_UDPCSUM; + + else if (strcmp(f, "!UDPCSUM") == 0) + pkt_dev->flags &= ~F_UDPCSUM; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", @@ -2733,7 +2745,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + udph->check = 0; iph->ihl = 5; iph->version = 4; @@ -2747,11 +2759,28 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); - iph->check = 0; - iph->check = ip_fast_csum((void *)iph, iph->ihl); + ip_send_check(iph); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; + + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum = 0; + udp4_hwcsum(skb, udph->source, udph->dest); + } else { + __wsum csum = udp_csum(skb); + + /* add protocol-dependent pseudo-header */ + udph->check = csum_tcpudp_magic(udph->source, udph->dest, + datalen + 8, IPPROTO_UDP, csum); + + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + } + pktgen_finalize_skb(pkt_dev, skb, datalen); #ifdef CONFIG_XFRM @@ -2768,7 +2797,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; - int datalen; + int datalen, udplen; struct ipv6hdr *iph; __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; @@ -2844,10 +2873,11 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, net_info_ratelimited("increased datalen to %d\n", datalen); } + udplen = datalen + sizeof(struct udphdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(udplen); + udph->check = 0; *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ @@ -2858,7 +2888,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->hop_limit = 32; - iph->payload_len = htons(sizeof(struct udphdr) + datalen); + iph->payload_len = htons(udplen); iph->nexthdr = IPPROTO_UDP; iph->daddr = pkt_dev->cur_in6_daddr; @@ -2868,6 +2898,23 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V6_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); + } else { + __wsum csum = udp_csum(skb); + + /* add protocol-dependent pseudo-header */ + udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); + + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + } + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3de7408..0b2972c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -767,7 +767,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ - + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ + + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -846,6 +847,24 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + struct netdev_phys_port_id ppid; + + err = dev_get_phys_port_id(dev, &ppid); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) @@ -913,6 +932,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } + if (rtnl_phys_port_id_fill(skb, dev)) + goto nla_put_failure; + attr = nla_reserve(skb, IFLA_STATS, sizeof(struct rtnl_link_stats)); if (attr == NULL) @@ -1113,6 +1135,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROMISCUITY] = { .type = NLA_U32 }, [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, + [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN }, }; EXPORT_SYMBOL(ifla_policy); diff --git a/net/core/sock.c b/net/core/sock.c index 2c097c5..83667de 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -93,6 +93,7 @@ #include <linux/capability.h> #include <linux/errno.h> +#include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> @@ -1575,6 +1576,25 @@ void sock_wfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_wfree); +void skb_orphan_partial(struct sk_buff *skb) +{ + /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, + * so we do not completely orphan skb, but transfert all + * accounted bytes but one, to avoid unexpected reorders. + */ + if (skb->destructor == sock_wfree +#ifdef CONFIG_INET + || skb->destructor == tcp_wfree +#endif + ) { + atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); + skb->truesize = 1; + } else { + skb_orphan(skb); + } +} +EXPORT_SYMBOL(skb_orphan_partial); + /* * Read buffer destructor automatically called from kfree_skb. */ @@ -2425,6 +2445,52 @@ void sock_enable_timestamp(struct sock *sk, int flag) } } +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type) +{ + struct sock_exterr_skb *serr; + struct sk_buff *skb, *skb2; + int copied, err; + + err = -EAGAIN; + skb = skb_dequeue(&sk->sk_error_queue); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + serr = SKB_EXT_ERR(skb); + put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + + msg->msg_flags |= MSG_ERRQUEUE; + err = copied; + + /* Reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else + spin_unlock_bh(&sk->sk_error_queue.lock); + +out_free_skb: + kfree_skb(skb); +out: + return err; +} +EXPORT_SYMBOL(sock_recv_errqueue); + /* * Get a socket option on an socket. * diff --git a/net/core/stream.c b/net/core/stream.c index f5df85d..512f0a2 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -30,7 +30,7 @@ void sk_stream_write_space(struct sock *sk) struct socket *sock = sk->sk_socket; struct socket_wq *wq; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { + if (sk_stream_is_writeable(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6c7c78b8..ba64750 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -336,7 +336,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -347,7 +347,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 34ca6d5..43923dc 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1126,10 +1126,7 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len) if (len < (int) sizeof(ifr)) break; memset(&ifr, 0, sizeof(struct ifreq)); - if (ifa->ifa_label) - strcpy(ifr.ifr_name, ifa->ifa_label); - else - strcpy(ifr.ifr_name, dev->name); + strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 26aa65d..523be38 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -101,6 +101,30 @@ errout: return err; } +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; + + /* do not accept result if the route does + * not meet the required prefix length + */ + if (result->prefixlen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + if (!(arg->flags & FIB_LOOKUP_NOREF)) + fib_info_put(result->fi); + return true; +} static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { @@ -267,6 +291,7 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, + .suppress = fib4_rule_suppress, .match = fib4_rule_match, .configure = fib4_rule_configure, .delete = fib4_rule_delete, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cd71190..ef76186 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -88,6 +88,7 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -315,6 +316,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) if (size < 256) return NULL; } + skb->priority = TC_PRIO_CONTROL; igmp_skb_size(skb) = size; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, @@ -670,6 +672,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ip_rt_put(rt); return -1; } + skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); @@ -1323,16 +1326,17 @@ out: EXPORT_SYMBOL(ip_mc_inc_group); /* - * Resend IGMP JOIN report; used for bonding. - * Called with rcu_read_lock() + * Resend IGMP JOIN report; used by netdev notifier. */ -void ip_mc_rejoin_groups(struct in_device *in_dev) +static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; - for_each_pmc_rcu(in_dev, im) { + ASSERT_RTNL(); + + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; @@ -1349,7 +1353,6 @@ void ip_mc_rejoin_groups(struct in_device *in_dev) } #endif } -EXPORT_SYMBOL(ip_mc_rejoin_groups); /* * A socket has left a multicast group on device dev @@ -2735,8 +2738,42 @@ static struct pernet_operations igmp_net_ops = { .exit = igmp_net_exit, }; +static int igmp_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct in_device *in_dev; + + switch (event) { + case NETDEV_RESEND_IGMP: + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) + ip_mc_rejoin_groups(in_dev); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block igmp_notifier = { + .notifier_call = igmp_netdev_event, +}; + int __init igmp_mc_proc_init(void) { - return register_pernet_subsys(&igmp_net_ops); + int err; + + err = register_pernet_subsys(&igmp_net_ops); + if (err) + return err; + err = register_netdevice_notifier(&igmp_notifier); + if (err) + goto reg_notif_fail; + return 0; + +reg_notif_fail: + unregister_pernet_subsys(&igmp_net_ops); + return err; } #endif diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 17cc0ff..79b263d 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -44,176 +44,10 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> -#define HASH_SIZE 16 -#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1)) - static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; -struct vti_net { - struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_wc[1]; - struct ip_tunnel __rcu **tunnels[4]; - - struct net_device *fb_tunnel_dev; -}; - -static int vti_fb_tunnel_init(struct net_device *dev); static int vti_tunnel_init(struct net_device *dev); -static void vti_tunnel_setup(struct net_device *dev); -static void vti_dev_free(struct net_device *dev); -static int vti_tunnel_bind_dev(struct net_device *dev); - -#define VTI_XMIT(stats1, stats2) do { \ - int err; \ - int pkt_len = skb->len; \ - err = dst_output(skb); \ - if (net_xmit_eval(err) == 0) { \ - u64_stats_update_begin(&(stats1)->syncp); \ - (stats1)->tx_bytes += pkt_len; \ - (stats1)->tx_packets++; \ - u64_stats_update_end(&(stats1)->syncp); \ - } else { \ - (stats2)->tx_errors++; \ - (stats2)->tx_aborted_errors++; \ - } \ -} while (0) - - -static struct ip_tunnel *vti_tunnel_lookup(struct net *net, - __be32 remote, __be32 local) -{ - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); - struct ip_tunnel *t; - struct vti_net *ipn = net_generic(net, vti_net_id); - - for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) - if (local == t->parms.iph.saddr && - remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) - return t; - for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) - if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) - return t; - - for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) - if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) - return t; - - for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0]) - if (t && (t->dev->flags&IFF_UP)) - return t; - return NULL; -} - -static struct ip_tunnel __rcu **__vti_bucket(struct vti_net *ipn, - struct ip_tunnel_parm *parms) -{ - __be32 remote = parms->iph.daddr; - __be32 local = parms->iph.saddr; - unsigned h = 0; - int prio = 0; - - if (remote) { - prio |= 2; - h ^= HASH(remote); - } - if (local) { - prio |= 1; - h ^= HASH(local); - } - return &ipn->tunnels[prio][h]; -} - -static inline struct ip_tunnel __rcu **vti_bucket(struct vti_net *ipn, - struct ip_tunnel *t) -{ - return __vti_bucket(ipn, &t->parms); -} - -static void vti_tunnel_unlink(struct vti_net *ipn, struct ip_tunnel *t) -{ - struct ip_tunnel __rcu **tp; - struct ip_tunnel *iter; - - for (tp = vti_bucket(ipn, t); - (iter = rtnl_dereference(*tp)) != NULL; - tp = &iter->next) { - if (t == iter) { - rcu_assign_pointer(*tp, t->next); - break; - } - } -} - -static void vti_tunnel_link(struct vti_net *ipn, struct ip_tunnel *t) -{ - struct ip_tunnel __rcu **tp = vti_bucket(ipn, t); - - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); -} - -static struct ip_tunnel *vti_tunnel_locate(struct net *net, - struct ip_tunnel_parm *parms, - int create) -{ - __be32 remote = parms->iph.daddr; - __be32 local = parms->iph.saddr; - struct ip_tunnel *t, *nt; - struct ip_tunnel __rcu **tp; - struct net_device *dev; - char name[IFNAMSIZ]; - struct vti_net *ipn = net_generic(net, vti_net_id); - - for (tp = __vti_bucket(ipn, parms); - (t = rtnl_dereference(*tp)) != NULL; - tp = &t->next) { - if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) - return t; - } - if (!create) - return NULL; - - if (parms->name[0]) - strlcpy(name, parms->name, IFNAMSIZ); - else - strcpy(name, "vti%d"); - - dev = alloc_netdev(sizeof(*t), name, vti_tunnel_setup); - if (dev == NULL) - return NULL; - - dev_net_set(dev, net); - - nt = netdev_priv(dev); - nt->parms = *parms; - dev->rtnl_link_ops = &vti_link_ops; - - vti_tunnel_bind_dev(dev); - - if (register_netdevice(dev) < 0) - goto failed_free; - - dev_hold(dev); - vti_tunnel_link(ipn, nt); - return nt; - -failed_free: - free_netdev(dev); - return NULL; -} - -static void vti_tunnel_uninit(struct net_device *dev) -{ - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - - vti_tunnel_unlink(ipn, netdev_priv(dev)); - dev_put(dev); -} static int vti_err(struct sk_buff *skb, u32 info) { @@ -222,6 +56,8 @@ static int vti_err(struct sk_buff *skb, u32 info) * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. */ + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -252,7 +88,8 @@ static int vti_err(struct sk_buff *skb, u32 info) err = -ENOENT; - t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); + t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); if (t == NULL) goto out; @@ -281,8 +118,11 @@ static int vti_rcv(struct sk_buff *skb) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); - tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); if (tunnel != NULL) { struct pcpu_tstats *tstats; @@ -311,7 +151,6 @@ static int vti_rcv(struct sk_buff *skb) static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; u8 tos; struct rtable *rt; /* Route to the other host */ @@ -319,6 +158,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct iphdr *old_iph = ip_hdr(skb); __be32 dst = tiph->daddr; struct flowi4 fl4; + int err; if (skb->protocol != htons(ETH_P_IP)) goto tx_error; @@ -367,8 +207,10 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); skb->dev = skb_dst(skb)->dev; - tstats = this_cpu_ptr(dev->tstats); - VTI_XMIT(tstats, &dev->stats); + err = dst_output(skb); + if (net_xmit_eval(err) == 0) + err = skb->len; + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; tx_error_icmp: @@ -379,198 +221,57 @@ tx_error: return NETDEV_TX_OK; } -static int vti_tunnel_bind_dev(struct net_device *dev) -{ - struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; - struct iphdr *iph; - - tunnel = netdev_priv(dev); - iph = &tunnel->parms.iph; - - if (iph->daddr) { - struct rtable *rt; - struct flowi4 fl4; - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), - RT_TOS(iph->tos), RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - iph->daddr, iph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (!IS_ERR(rt)) { - tdev = rt->dst.dev; - ip_rt_put(rt); - } - dev->flags |= IFF_POINTOPOINT; - } - - if (!tdev && tunnel->parms.link) - tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link); - - if (tdev) { - dev->hard_header_len = tdev->hard_header_len + - sizeof(struct iphdr); - dev->mtu = tdev->mtu; - } - dev->iflink = tunnel->parms.link; - return dev->mtu; -} - static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip_tunnel_parm p; - struct ip_tunnel *t; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - - switch (cmd) { - case SIOCGETTUNNEL: - t = NULL; - if (dev == ipn->fb_tunnel_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, - sizeof(p))) { - err = -EFAULT; - break; - } - t = vti_tunnel_locate(net, &p, 0); - } - if (t == NULL) - t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof(p)); - p.i_flags |= GRE_KEY | VTI_ISVTI; - p.o_flags |= GRE_KEY; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; - break; - - case SIOCADDTUNNEL: - case SIOCCHGTUNNEL: - err = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - goto done; - err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) - goto done; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + return -EFAULT; - err = -EINVAL; + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || p.iph.ihl != 5) - goto done; - - t = vti_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); - - if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { - if (t->dev != dev) { - err = -EEXIST; - break; - } - } else { - if (((dev->flags&IFF_POINTOPOINT) && - !p.iph.daddr) || - (!(dev->flags&IFF_POINTOPOINT) && - p.iph.daddr)) { - err = -EINVAL; - break; - } - t = netdev_priv(dev); - vti_tunnel_unlink(ipn, t); - synchronize_net(); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - t->parms.iph.protocol = IPPROTO_IPIP; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - vti_tunnel_link(ipn, t); - netdev_state_change(dev); - } - } - - if (t) { - err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - if (t->parms.link != p.link) { - t->parms.link = p.link; - vti_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } - p.i_flags |= GRE_KEY | VTI_ISVTI; - p.o_flags |= GRE_KEY; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, - sizeof(p))) - err = -EFAULT; - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); - break; + return -EINVAL; + } - case SIOCDELTUNNEL: - err = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - goto done; - - if (dev == ipn->fb_tunnel_dev) { - err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, - sizeof(p))) - goto done; - err = -ENOENT; - - t = vti_tunnel_locate(net, &p, 0); - if (t == NULL) - goto done; - err = -EPERM; - if (t->dev == ipn->fb_tunnel_dev) - goto done; - dev = t->dev; - } - unregister_netdevice(dev); - err = 0; - break; + err = ip_tunnel_ioctl(dev, &p, cmd); + if (err) + return err; - default: - err = -EINVAL; + if (cmd != SIOCDELTUNNEL) { + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; } -done: - return err; -} - -static int vti_tunnel_change_mtu(struct net_device *dev, int new_mtu) -{ - if (new_mtu < 68 || new_mtu > 0xFFF8) - return -EINVAL; - dev->mtu = new_mtu; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + return -EFAULT; return 0; } static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, - .ndo_uninit = vti_tunnel_uninit, + .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, .ndo_do_ioctl = vti_tunnel_ioctl, - .ndo_change_mtu = vti_tunnel_change_mtu, + .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, }; -static void vti_dev_free(struct net_device *dev) +static void vti_tunnel_setup(struct net_device *dev) { - free_percpu(dev->tstats); - free_netdev(dev); + dev->netdev_ops = &vti_netdev_ops; + ip_tunnel_setup(dev, vti_net_id); } -static void vti_tunnel_setup(struct net_device *dev) +static int vti_tunnel_init(struct net_device *dev) { - dev->netdev_ops = &vti_netdev_ops; - dev->destructor = vti_dev_free; + struct ip_tunnel *tunnel = netdev_priv(dev); + struct iphdr *iph = &tunnel->parms.iph; + + memcpy(dev->dev_addr, &iph->saddr, 4); + memcpy(dev->broadcast, &iph->daddr, 4); dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -581,38 +282,18 @@ static void vti_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; -} -static int vti_tunnel_init(struct net_device *dev) -{ - struct ip_tunnel *tunnel = netdev_priv(dev); - - tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); - - dev->tstats = alloc_percpu(struct pcpu_tstats); - if (!dev->tstats) - return -ENOMEM; - - return 0; + return ip_tunnel_init(dev); } -static int __net_init vti_fb_tunnel_init(struct net_device *dev) +static void __net_init vti_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id); iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; - - dev_hold(dev); - rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); - return 0; } static struct xfrm_tunnel vti_handler __read_mostly = { @@ -621,76 +302,30 @@ static struct xfrm_tunnel vti_handler __read_mostly = { .priority = 1, }; -static void vti_destroy_tunnels(struct vti_net *ipn, struct list_head *head) -{ - int prio; - - for (prio = 1; prio < 4; prio++) { - int h; - for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - - t = rtnl_dereference(ipn->tunnels[prio][h]); - while (t != NULL) { - unregister_netdevice_queue(t->dev, head); - t = rtnl_dereference(t->next); - } - } - } -} - static int __net_init vti_init_net(struct net *net) { int err; - struct vti_net *ipn = net_generic(net, vti_net_id); - - ipn->tunnels[0] = ipn->tunnels_wc; - ipn->tunnels[1] = ipn->tunnels_l; - ipn->tunnels[2] = ipn->tunnels_r; - ipn->tunnels[3] = ipn->tunnels_r_l; - - ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), - "ip_vti0", - vti_tunnel_setup); - if (!ipn->fb_tunnel_dev) { - err = -ENOMEM; - goto err_alloc_dev; - } - dev_net_set(ipn->fb_tunnel_dev, net); - - err = vti_fb_tunnel_init(ipn->fb_tunnel_dev); - if (err) - goto err_reg_dev; - ipn->fb_tunnel_dev->rtnl_link_ops = &vti_link_ops; + struct ip_tunnel_net *itn; - err = register_netdev(ipn->fb_tunnel_dev); + err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0"); if (err) - goto err_reg_dev; + return err; + itn = net_generic(net, vti_net_id); + vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; - -err_reg_dev: - vti_dev_free(ipn->fb_tunnel_dev); -err_alloc_dev: - /* nothing */ - return err; } static void __net_exit vti_exit_net(struct net *net) { - struct vti_net *ipn = net_generic(net, vti_net_id); - LIST_HEAD(list); - - rtnl_lock(); - vti_destroy_tunnels(ipn, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + ip_tunnel_delete_net(itn); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, .exit = vti_exit_net, .id = &vti_net_id, - .size = sizeof(struct vti_net), + .size = sizeof(struct ip_tunnel_net), }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -728,78 +363,19 @@ static void vti_netlink_parms(struct nlattr *data[], static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip_tunnel *nt; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - int mtu; - int err; - - nt = netdev_priv(dev); - vti_netlink_parms(data, &nt->parms); - - if (vti_tunnel_locate(net, &nt->parms, 0)) - return -EEXIST; + struct ip_tunnel_parm parms; - mtu = vti_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) - dev->mtu = mtu; - - err = register_netdevice(dev); - if (err) - goto out; - - dev_hold(dev); - vti_tunnel_link(ipn, nt); - -out: - return err; + vti_netlink_parms(data, &parms); + return ip_tunnel_newlink(dev, tb, &parms); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip_tunnel *t, *nt; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); struct ip_tunnel_parm p; - int mtu; - - if (dev == ipn->fb_tunnel_dev) - return -EINVAL; - nt = netdev_priv(dev); vti_netlink_parms(data, &p); - - t = vti_tunnel_locate(net, &p, 0); - - if (t) { - if (t->dev != dev) - return -EEXIST; - } else { - t = nt; - - vti_tunnel_unlink(ipn, t); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - } - vti_tunnel_link(ipn, t); - netdev_state_change(dev); - } - - if (t->parms.link != p.link) { - t->parms.link = p.link; - mtu = vti_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) - dev->mtu = mtu; - netdev_state_change(dev); - } - - return 0; + return ip_tunnel_changelink(dev, tb, &p); } static size_t vti_get_size(const struct net_device *dev) @@ -865,7 +441,7 @@ static int __init vti_init(void) err = xfrm4_mode_tunnel_input_register(&vti_handler); if (err < 0) { unregister_pernet_device(&vti_net_ops); - pr_info(KERN_INFO "vti init: can't register tunnel\n"); + pr_info("vti init: can't register tunnel\n"); } err = rtnl_link_register(&vti_link_ops); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 132a096..bacc0bc 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -127,9 +127,9 @@ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); -static int ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local); +static void ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local); static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, @@ -1795,9 +1795,9 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ -static int ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local) +static void ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local) { int psend = -1; int vif, ct; @@ -1903,14 +1903,13 @@ last_forward: ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { ipmr_queue_xmit(net, mrt, skb, cache, psend); - return 0; + return; } } dont_forward: if (!local) kfree_skb(skb); - return 0; } static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a9a54a2..e805481 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -435,12 +435,12 @@ static inline int ip_rt_proc_init(void) static inline bool rt_is_expired(const struct rtable *rth) { - return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); + return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { - rt_genid_bump(net); + rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -1458,7 +1458,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->dst.output = ip_rt_bug; - rth->rt_genid = rt_genid(dev_net(dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; rth->rt_is_input= 1; @@ -1589,7 +1589,7 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); rth->rt_flags = flags; rth->rt_type = res->type; rth->rt_is_input = 1; @@ -1760,7 +1760,7 @@ local_input: rth->dst.tclassid = itag; #endif - rth->rt_genid = rt_genid(net); + rth->rt_genid = rt_genid_ipv4(net); rth->rt_flags = flags|RTCF_LOCAL; rth->rt_type = res.type; rth->rt_is_input = 1; @@ -1945,7 +1945,7 @@ add: rth->dst.output = ip_output; - rth->rt_genid = rt_genid(dev_net(dev_out)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; rth->rt_is_input = 0; @@ -2227,7 +2227,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; - rt->rt_genid = rt_genid(net); + rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; @@ -2665,7 +2665,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->rt_genid, 0); + atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 610e324..8ed7c32 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -559,6 +559,13 @@ static struct ctl_table ipv4_table[] = { .extra1 = &one, }, { + .procname = "tcp_notsent_lowat", + .data = &sysctl_tcp_notsent_lowat, + .maxlen = sizeof(sysctl_tcp_notsent_lowat), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5423223..ab64eea 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -410,10 +410,6 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - /* Presumed zeroed, in order of appearance: - * cookie_in_always, cookie_out_never, - * s_data_constant, s_data_in, s_data_out - */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -499,7 +495,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -510,7 +506,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } } else @@ -2631,6 +2627,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else tp->tsoffset = val - tcp_time_stamp; break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: err = -ENOPROTOOPT; break; @@ -2847,6 +2847,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_TIMESTAMP: val = tcp_time_stamp + tp->tsoffset; break; + case TCP_NOTSENT_LOWAT: + val = tp->notsent_lowat; + break; default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 28af45a..b61274b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1048,6 +1048,7 @@ struct tcp_sacktag_state { int reord; int fack_count; int flag; + s32 rtt; /* RTT measured by SACKing never-retransmitted data */ }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1108,7 +1109,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - bool dup_sack, int pcount) + int dup_sack, int pcount, u32 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1148,6 +1149,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; + /* Pick the earliest sequence sacked for RTT */ + if (state->rtt < 0) + state->rtt = tcp_time_stamp - xmit_time; } if (sacked & TCPCB_LOST) { @@ -1205,7 +1209,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, * tcp_highest_sack_seq() when skb is highest_sack. */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, - start_seq, end_seq, dup_sack, pcount); + start_seq, end_seq, dup_sack, pcount, + TCP_SKB_CB(skb)->when); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1479,7 +1484,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, dup_sack, - tcp_skb_pcount(skb)); + tcp_skb_pcount(skb), + TCP_SKB_CB(skb)->when); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1536,7 +1542,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una) + u32 prior_snd_una, s32 *sack_rtt) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1554,6 +1560,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; + state.rtt = -1; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1737,6 +1744,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif + *sack_rtt = state.rtt; return state.flag; } @@ -2792,65 +2800,51 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, tcp_xmit_retransmit_queue(sk); } -void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) +static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, + s32 seq_rtt, s32 sack_rtt) { - tcp_rtt_estimator(sk, seq_rtt); - tcp_set_rto(sk); - inet_csk(sk)->icsk_backoff = 0; -} -EXPORT_SYMBOL(tcp_valid_rtt_meas); + const struct tcp_sock *tp = tcp_sk(sk); + + /* Prefer RTT measured from ACK's timing to TS-ECR. This is because + * broken middle-boxes or peers may corrupt TS-ECR fields. But + * Karn's algorithm forbids taking RTT if some retransmitted data + * is acked (RFC6298). + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + seq_rtt = -1; + + if (seq_rtt < 0) + seq_rtt = sack_rtt; -/* Read draft-ietf-tcplw-high-performance before mucking - * with this code. (Supersedes RFC1323) - */ -static void tcp_ack_saw_tstamp(struct sock *sk, int flag) -{ /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment * acknowledges some new data, i.e., only if it advances the * left edge of the send window. - * * See draft-ietf-tcplw-high-performance-00, section 3.3. - * 1998/04/10 Andrey V. Savochkin <saw@msu.ru> - * - * Changed: reset backoff as soon as we see the first valid sample. - * If we do not, we get strongly overestimated rto. With timestamps - * samples are accepted even from very old segments: f.e., when rtt=1 - * increases to 8, we retransmit 5 times and after 8 seconds delayed - * answer arrives rto becomes 120 seconds! If at least one of segments - * in window is lost... Voila. --ANK (010210) */ - struct tcp_sock *tp = tcp_sk(sk); - - tcp_valid_rtt_meas(sk, tcp_time_stamp - tp->rx_opt.rcv_tsecr); -} + if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) + seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; -static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag) -{ - /* We don't have a timestamp. Can only use - * packets that are not retransmitted to determine - * rtt estimates. Also, we must not reset the - * backoff for rto until we get a non-retransmitted - * packet. This allows us to deal with a situation - * where the network delay has increased suddenly. - * I.e. Karn's algorithm. (SIGCOMM '87, p5.) - */ + if (seq_rtt < 0) + return false; - if (flag & FLAG_RETRANS_DATA_ACKED) - return; + tcp_rtt_estimator(sk, seq_rtt); + tcp_set_rto(sk); - tcp_valid_rtt_meas(sk, seq_rtt); + /* RFC6298: only reset backoff on valid RTT measurement. */ + inet_csk(sk)->icsk_backoff = 0; + return true; } -static inline void tcp_ack_update_rtt(struct sock *sk, const int flag, - const s32 seq_rtt) +/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ +static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { - const struct tcp_sock *tp = tcp_sk(sk); - /* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */ - if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) - tcp_ack_saw_tstamp(sk, flag); - else if (seq_rtt >= 0) - tcp_ack_no_tstamp(sk, seq_rtt, flag); + struct tcp_sock *tp = tcp_sk(sk); + s32 seq_rtt = -1; + + if (tp->lsndtime && !tp->total_retrans) + seq_rtt = tcp_time_stamp - tp->lsndtime; + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) @@ -2939,7 +2933,7 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una) + u32 prior_snd_una, s32 sack_rtt) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2978,8 +2972,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; - ca_seq_rtt = -1; - seq_rtt = -1; } else { ca_seq_rtt = now - scb->when; last_ackt = skb->tstamp; @@ -3031,6 +3023,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; + if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) || + (flag & FLAG_ACKED)) + tcp_rearm_rto(sk); + if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; @@ -3040,9 +3036,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tcp_mtup_probe_success(sk); } - tcp_ack_update_rtt(sk, flag, seq_rtt); - tcp_rearm_rto(sk); - if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); } else { @@ -3274,6 +3267,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ + s32 sack_rtt = -1; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3330,7 +3324,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_ack_update_window(sk, skb, ack, ack_seq); if (TCP_SKB_CB(skb)->sacked) - flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, + &sack_rtt); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3349,7 +3344,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); acked -= tp->packets_out; if (tcp_ack_is_dubious(sk, flag)) { @@ -3402,7 +3397,8 @@ old_ack: * If data was DSACKed, see if we can undo a cwnd reduction. */ if (TCP_SKB_CB(skb)->sacked) { - flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, + &sack_rtt); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -5624,9 +5620,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * so release it. */ if (req) { - tcp_synack_rtt_meas(sk, req); tp->total_retrans = req->num_retrans; - reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for correct metrics. */ @@ -5651,6 +5645,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); + tcp_synack_rtt_meas(sk, req); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b299da5f..280efe5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -890,7 +890,7 @@ bool tcp_syn_flood_action(struct sock *sk, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned) { + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { lopt->synflood_warned = 1; pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); @@ -1462,7 +1462,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * limitations, they conserve resources and peer is * evidently real one. */ - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, "TCP"); if (!want_cookie) goto drop; @@ -1671,8 +1672,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -2802,6 +2801,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ab1c086..58a3e69 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -411,6 +411,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_enable_early_retrans(newtp); newtp->tlp_high_seq = 0; + newtp->lsndtime = treq->snt_synack; + newtp->total_retrans = req->num_retrans; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -666,12 +668,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; - /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */ - if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) - tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; - else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */ - tcp_rsk(req)->snt_synack = 0; - /* For Fast Open no more processing is needed (sk is the * child socket). */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 92fde8d..884efff 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX; +EXPORT_SYMBOL(sysctl_tcp_notsent_lowat); + static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 766e6ba..9e88af0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -704,7 +704,7 @@ EXPORT_SYMBOL(udp_flush_pending_frames); * @src: source IP address * @dst: destination IP address */ -static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) +void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); struct sk_buff *frags = skb_shinfo(skb)->frag_list; @@ -740,6 +740,7 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) uh->check = CSUM_MANGLED_0; } } +EXPORT_SYMBOL_GPL(udp4_hwcsum); static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index da4241c..7fd8572 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4654,6 +4654,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) break; } atomic_inc(&net->ipv6.dev_addr_genid); + rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a5ac969..0d1a9b1 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -766,6 +766,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); if (err) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2e1a432..a6c58ce 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -55,26 +55,33 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, struct fib6_table *table; struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; + int err = 0; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; rt = net->ipv6.ip6_null_entry; goto discard_pkt; default: case FR_ACT_BLACKHOLE: + err = -EINVAL; rt = net->ipv6.ip6_blk_hole_entry; goto discard_pkt; case FR_ACT_PROHIBIT: + err = -EACCES; rt = net->ipv6.ip6_prohibit_entry; goto discard_pkt; } table = fib6_get_table(net, rule->table); - if (table) - rt = lookup(net, table, flp6, flags); + if (!table) { + err = -EAGAIN; + goto out; + } + rt = lookup(net, table, flp6, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -101,6 +108,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, } again: ip6_rt_put(rt); + err = -EAGAIN; rt = NULL; goto out; @@ -108,9 +116,31 @@ discard_pkt: dst_hold(&rt->dst); out: arg->result = rt; - return rt == NULL ? -EAGAIN : 0; + return err; } +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; + /* do not accept result if the route does + * not meet the required prefix length + */ + if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + ip6_rt_put(rt); + return true; +} static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { @@ -244,6 +274,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, .match = fib6_rule_match, + .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, .compare = fib6_rule_compare, .fill = fib6_rule_fill, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bff3d82..ed828d6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -425,8 +425,8 @@ out: * node. */ -static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, - int addrlen, int plen, +static struct fib6_node *fib6_add_1(struct fib6_node *root, + struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required) { @@ -543,7 +543,7 @@ insert_above: but if it is >= plen, the value is ignored in any case. */ - bit = __ipv6_addr_diff(addr, &key->addr, addrlen); + bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] @@ -822,9 +822,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), - allow_create, replace_required); + fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + offsetof(struct rt6_info, rt6i_dst), allow_create, + replace_required); if (IS_ERR(fn)) { err = PTR_ERR(fn); @@ -863,7 +863,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); @@ -882,7 +882,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) fn->subtree = sfn; } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 03986d3..a60a84e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -110,8 +110,8 @@ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr6_table *mrt); -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache); +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, @@ -2074,8 +2074,8 @@ static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) return ct; } -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache) +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; @@ -2156,12 +2156,11 @@ forward: last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); - return 0; + return; } dont_forward: kfree_skb(skb); - return 0; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 99cd65c..db25b8e 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -44,6 +44,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/netfilter.h> @@ -1376,6 +1377,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) if (!skb) return NULL; + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { @@ -1769,7 +1771,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) rcu_read_unlock(); return; } - + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c45f7a5..c1e5334 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -63,6 +63,8 @@ #include <linux/seq_file.h> #include <linux/export.h> +#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ + static struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; @@ -108,11 +110,14 @@ found: */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *_hdr; + struct icmp6hdr _hdr; const struct icmp6hdr *hdr; + /* We require only the four bytes of the ICMPv6 header, not any + * additional bytes of message body in "struct icmp6hdr". + */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_hdr), &_hdr); + ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b70f8979..e22c4db 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -283,9 +283,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid(net); + rt->rt6i_genid = rt_genid_ipv6(net); INIT_LIST_HEAD(&rt->rt6i_siblings); - rt->rt6i_nsiblings = 0; } return rt; } @@ -1062,7 +1061,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6e1649d..38c196c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -963,7 +963,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); if (!want_cookie) goto drop; @@ -1237,8 +1238,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; @@ -1926,6 +1925,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, diff --git a/net/irda/irttp.c b/net/irda/irttp.c index ae43c62..85372cf 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -75,7 +75,7 @@ static pi_minor_info_t pi_minor_call_table[] = { { NULL, 0 }, /* 0x00 */ { irttp_param_max_sdu_size, PV_INTEGER | PV_BIG_ENDIAN } /* 0x01 */ }; -static pi_major_info_t pi_major_call_table[] = {{ pi_minor_call_table, 2 }}; +static pi_major_info_t pi_major_call_table[] = { { pi_minor_call_table, 2 } }; static pi_param_info_t param_info = { pi_major_call_table, 1, 0x0f, 4 }; /************************ GLOBAL PROCEDURES ************************/ @@ -205,7 +205,7 @@ static void irttp_todo_expired(unsigned long data) */ static void irttp_flush_queues(struct tsap_cb *self) { - struct sk_buff* skb; + struct sk_buff *skb; IRDA_DEBUG(4, "%s()\n", __func__); @@ -400,7 +400,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify) /* The IrLMP spec (IrLMP 1.1 p10) says that we have the right to * use only 0x01-0x6F. Of course, we can use LSAP_ANY as well. * JeanII */ - if((stsap_sel != LSAP_ANY) && + if ((stsap_sel != LSAP_ANY) && ((stsap_sel < 0x01) || (stsap_sel >= 0x70))) { IRDA_DEBUG(0, "%s(), invalid tsap!\n", __func__); return NULL; @@ -427,7 +427,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify) ttp_notify.data_indication = irttp_data_indication; ttp_notify.udata_indication = irttp_udata_indication; ttp_notify.flow_indication = irttp_flow_indication; - if(notify->status_indication != NULL) + if (notify->status_indication != NULL) ttp_notify.status_indication = irttp_status_indication; ttp_notify.instance = self; strncpy(ttp_notify.name, notify->name, NOTIFY_MAX_NAME); @@ -639,8 +639,7 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb) */ if ((self->tx_max_sdu_size != 0) && (self->tx_max_sdu_size != TTP_SAR_UNBOUND) && - (skb->len > self->tx_max_sdu_size)) - { + (skb->len > self->tx_max_sdu_size)) { IRDA_ERROR("%s: SAR enabled, but data is larger than TxMaxSduSize!\n", __func__); ret = -EMSGSIZE; @@ -733,8 +732,7 @@ static void irttp_run_tx_queue(struct tsap_cb *self) * poll us through irttp_flow_indication() - Jean II */ while ((self->send_credit > 0) && (!irlmp_lap_tx_queue_full(self->lsap)) && - (skb = skb_dequeue(&self->tx_queue))) - { + (skb = skb_dequeue(&self->tx_queue))) { /* * Since we can transmit and receive frames concurrently, * the code below is a critical region and we must assure that @@ -798,8 +796,7 @@ static void irttp_run_tx_queue(struct tsap_cb *self) * where we can spend a bit of time doing stuff. - Jean II */ if ((self->tx_sdu_busy) && (skb_queue_len(&self->tx_queue) < TTP_TX_LOW_THRESHOLD) && - (!self->close_pend)) - { + (!self->close_pend)) { if (self->notify.flow_indication) self->notify.flow_indication(self->notify.instance, self, FLOW_START); @@ -892,7 +889,7 @@ static int irttp_udata_indication(void *instance, void *sap, /* Just pass data to layer above */ if (self->notify.udata_indication) { err = self->notify.udata_indication(self->notify.instance, - self,skb); + self, skb); /* Same comment as in irttp_do_data_indication() */ if (!err) return 0; @@ -1057,7 +1054,7 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow) * to do that. Jean II */ /* If we need to send disconnect. try to do it now */ - if(self->disconnect_pend) + if (self->disconnect_pend) irttp_start_todo_timer(self, 0); } @@ -1116,7 +1113,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -EBADR;); if (self->connected) { - if(userdata) + if (userdata) dev_kfree_skb(userdata); return -EISCONN; } @@ -1137,7 +1134,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, * headers */ IRDA_ASSERT(skb_headroom(userdata) >= TTP_MAX_HEADER, - { dev_kfree_skb(userdata); return -1; } ); + { dev_kfree_skb(userdata); return -1; }); } /* Initialize connection parameters */ @@ -1157,7 +1154,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, * Give away max 127 credits for now */ if (n > 127) { - self->avail_credit=n-127; + self->avail_credit = n - 127; n = 127; } @@ -1166,10 +1163,10 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, /* SAR enabled? */ if (max_sdu_size > 0) { IRDA_ASSERT(skb_headroom(tx_skb) >= (TTP_MAX_HEADER + TTP_SAR_HEADER), - { dev_kfree_skb(tx_skb); return -1; } ); + { dev_kfree_skb(tx_skb); return -1; }); /* Insert SAR parameters */ - frame = skb_push(tx_skb, TTP_HEADER+TTP_SAR_HEADER); + frame = skb_push(tx_skb, TTP_HEADER + TTP_SAR_HEADER); frame[0] = TTP_PARAMETERS | n; frame[1] = 0x04; /* Length */ @@ -1386,7 +1383,7 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size, * headers */ IRDA_ASSERT(skb_headroom(userdata) >= TTP_MAX_HEADER, - { dev_kfree_skb(userdata); return -1; } ); + { dev_kfree_skb(userdata); return -1; }); } self->avail_credit = 0; @@ -1409,10 +1406,10 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size, /* SAR enabled? */ if (max_sdu_size > 0) { IRDA_ASSERT(skb_headroom(tx_skb) >= (TTP_MAX_HEADER + TTP_SAR_HEADER), - { dev_kfree_skb(tx_skb); return -1; } ); + { dev_kfree_skb(tx_skb); return -1; }); /* Insert TTP header with SAR parameters */ - frame = skb_push(tx_skb, TTP_HEADER+TTP_SAR_HEADER); + frame = skb_push(tx_skb, TTP_HEADER + TTP_SAR_HEADER); frame[0] = TTP_PARAMETERS | n; frame[1] = 0x04; /* Length */ @@ -1522,7 +1519,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata, * function may be called from various context, like user, timer * for following a disconnect_indication() (i.e. net_bh). * Jean II */ - if(test_and_set_bit(0, &self->disconnect_pend)) { + if (test_and_set_bit(0, &self->disconnect_pend)) { IRDA_DEBUG(0, "%s(), disconnect already pending\n", __func__); if (userdata) @@ -1627,7 +1624,7 @@ static void irttp_disconnect_indication(void *instance, void *sap, * Jean II */ /* No need to notify the client if has already tried to disconnect */ - if(self->notify.disconnect_indication) + if (self->notify.disconnect_indication) self->notify.disconnect_indication(self->notify.instance, self, reason, skb); else @@ -1738,8 +1735,7 @@ static void irttp_run_rx_queue(struct tsap_cb *self) * This is the last fragment, so time to reassemble! */ if ((self->rx_sdu_size <= self->rx_max_sdu_size) || - (self->rx_max_sdu_size == TTP_SAR_UNBOUND)) - { + (self->rx_max_sdu_size == TTP_SAR_UNBOUND)) { /* * A little optimizing. Only queue the fragment if * there are other fragments. Since if this is the @@ -1860,7 +1856,7 @@ static int irttp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "dtsap_sel: %02x\n", self->dtsap_sel); seq_printf(seq, " connected: %s, ", - self->connected? "TRUE":"FALSE"); + self->connected ? "TRUE" : "FALSE"); seq_printf(seq, "avail credit: %d, ", self->avail_credit); seq_printf(seq, "remote credit: %d, ", @@ -1876,9 +1872,9 @@ static int irttp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "rx_queue len: %u\n", skb_queue_len(&self->rx_queue)); seq_printf(seq, " tx_sdu_busy: %s, ", - self->tx_sdu_busy? "TRUE":"FALSE"); + self->tx_sdu_busy ? "TRUE" : "FALSE"); seq_printf(seq, "rx_sdu_busy: %s\n", - self->rx_sdu_busy? "TRUE":"FALSE"); + self->rx_sdu_busy ? "TRUE" : "FALSE"); seq_printf(seq, " max_seg_size: %u, ", self->max_seg_size); seq_printf(seq, "tx_max_sdu_size: %u, ", diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3c0da87..23e596e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -66,15 +66,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, unsigned int sctphoff) { - __u32 crc32; - struct sk_buff *iter; - - crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, - skb_headlen(iter), crc32); - sctph->checksum = sctp_end_cksum(crc32); - + sctph->checksum = sctp_compute_cksum(skb, sctphoff); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -151,10 +143,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int sctphoff; struct sctphdr *sh, _sctph; - struct sk_buff *iter; - __le32 cmp; - __le32 val; - __u32 tmp; + __le32 cmp, val; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) @@ -168,13 +157,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 0; cmp = sh->checksum; - - tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb)); - skb_walk_frags(skb, iter) - tmp = sctp_update_cksum((__u8 *) iter->data, - skb_headlen(iter), tmp); - - val = sctp_end_cksum(tmp); + val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 396e55d..754536f 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -34,9 +34,7 @@ sctp_manip_pkt(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { - struct sk_buff *frag; sctp_sctphdr_t *hdr; - __u32 crc32; if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) return false; @@ -51,11 +49,7 @@ sctp_manip_pkt(struct sk_buff *skb, hdr->dest = tuple->dst.u.sctp.port; } - crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); - skb_walk_frags(skb, frag) - crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), - crc32); - hdr->checksum = sctp_end_cksum(crc32); + hdr->checksum = sctp_compute_cksum(skb, hdroff); return true; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0c61b59..6273772 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -294,14 +294,14 @@ static void **alloc_pg_vec(struct netlink_sock *nlk, { unsigned int block_nr = req->nm_block_nr; unsigned int i; - void **pg_vec, *ptr; + void **pg_vec; pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL); if (pg_vec == NULL) return NULL; for (i = 0; i < block_nr; i++) { - pg_vec[i] = ptr = alloc_one_pg_vec_page(order); + pg_vec[i] = alloc_one_pg_vec_page(order); if (pg_vec[i] == NULL) goto err1; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4b66c75..0c0f6c9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,6 +88,7 @@ #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> +#include <linux/if_arp.h> #ifdef CONFIG_INET #include <net/inet_common.h> @@ -1923,7 +1924,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, __be16 proto, unsigned char *addr, int hlen) { union tpacket_uhdr ph; - int to_write, offset, len, tp_len, nr_frags, len_max; + int to_write, offset, len, tp_len, nr_frags, len_max, max_frame_len; struct socket *sock = po->sk.sk_socket; struct page *page; void *data; @@ -1946,10 +1947,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, tp_len = ph.h1->tp_len; break; } - if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); - return -EMSGSIZE; - } skb_reserve(skb, hlen); skb_reset_network_header(skb); @@ -2005,10 +2002,25 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, if (unlikely(err)) return err; + if (dev->type == ARPHRD_ETHER) + skb->protocol = eth_type_trans(skb, dev); + data += dev->hard_header_len; to_write -= dev->hard_header_len; } + max_frame_len = dev->mtu + dev->hard_header_len; + if (skb->protocol == htons(ETH_P_8021Q)) + max_frame_len += VLAN_HLEN; + + if (size_max > max_frame_len) + size_max = max_frame_len; + + if (unlikely(tp_len > size_max)) { + pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + return -EMSGSIZE; + } + offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); @@ -2047,7 +2059,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct net_device *dev; __be16 proto; bool need_rls_dev = false; - int err, reserve = 0; + int err; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; int tp_len, size_max; @@ -2080,8 +2092,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(dev == NULL)) goto out; - reserve = dev->hard_header_len; - err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; @@ -2089,9 +2099,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); - if (size_max > dev->mtu + reserve) - size_max = dev->mtu + reserve; - do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); @@ -2324,22 +2331,20 @@ static int packet_snd(struct socket *sock, sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + if (dev->type == ARPHRD_ETHER) { + skb->protocol = eth_type_trans(skb, dev); + if (skb->protocol == htons(ETH_P_8021Q)) + reserve += VLAN_HLEN; + } else { + skb->protocol = proto; + skb->dev = dev; + } + if (!gso_type && (len > dev->mtu + reserve + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_free; - } + err = -EMSGSIZE; + goto out_free; } - skb->protocol = proto; - skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -2638,51 +2643,6 @@ out: return err; } -static int packet_recv_error(struct sock *sk, struct msghdr *msg, int len) -{ - struct sock_exterr_skb *serr; - struct sk_buff *skb, *skb2; - int copied, err; - - err = -EAGAIN; - skb = skb_dequeue(&sk->sk_error_queue); - if (skb == NULL) - goto out; - - copied = skb->len; - if (copied > len) { - msg->msg_flags |= MSG_TRUNC; - copied = len; - } - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (err) - goto out_free_skb; - - sock_recv_timestamp(msg, sk, skb); - - serr = SKB_EXT_ERR(skb); - put_cmsg(msg, SOL_PACKET, PACKET_TX_TIMESTAMP, - sizeof(serr->ee), &serr->ee); - - msg->msg_flags |= MSG_ERRQUEUE; - err = copied; - - /* Reset and regenerate socket error */ - spin_lock_bh(&sk->sk_error_queue.lock); - sk->sk_err = 0; - if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { - sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_bh(&sk->sk_error_queue.lock); - sk->sk_error_report(sk); - } else - spin_unlock_bh(&sk->sk_error_queue.lock); - -out_free_skb: - kfree_skb(skb); -out: - return err; -} - /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. @@ -2708,7 +2668,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, #endif if (flags & MSG_ERRQUEUE) { - err = packet_recv_error(sk, msg, len); + err = sock_recv_errqueue(sk, msg, len, + SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 82f6016..a6d788d 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,12 +412,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) - * Ideally, this orphaning should be done after the rate limiting - * module, because this breaks TCP Small Queue, and other mechanisms - * based on socket sk_wmem_alloc. */ if (q->latency || q->jitter) - skb_orphan(skb); + skb_orphan_partial(skb); /* * If we need to duplicate packet, then re-insert at top of the diff --git a/net/sctp/associola.c b/net/sctp/associola.c index bce5b79..e425ba0 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/auth.c b/net/sctp/auth.c index ba1dfc3..3aab967 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -22,7 +22,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 64977ea..f34ce8b 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 5780565..b50b90c 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -24,7 +24,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/command.c b/net/sctp/command.c index c004401..f4bebda 100644 --- a/net/sctp/command.c +++ b/net/sctp/command.c @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/debug.c b/net/sctp/debug.c index f499878..44aa4e7 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 9e3d257..825b754 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/input.c b/net/sctp/input.c index 3fa4d85..fa91aff 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -87,15 +87,7 @@ static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb) { struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; - struct sk_buff *list; - __le32 val; - __u32 tmp = sctp_start_cksum((__u8 *)sh, skb_headlen(skb)); - - skb_walk_frags(skb, list) - tmp = sctp_update_cksum((__u8 *)list->data, skb_headlen(list), - tmp); - - val = sctp_end_cksum(tmp); + __le32 val = sctp_compute_cksum(skb, 0); if (val != cmp) { /* CRC failure, dump it. */ diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index cb25f04..e70f60a 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -30,7 +30,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 09ffcc9..5a9402e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -351,7 +351,7 @@ out: rt = (struct rt6_info *)dst; t->dst = dst; - + t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; pr_debug("rt6_dst:%pI6 rt6_src:%pI6\n", &rt->rt6i_dst.addr, &fl6->saddr); } else { diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c index fe012c4..aec346c 100644 --- a/net/sctp/objcnt.c +++ b/net/sctp/objcnt.c @@ -26,7 +26,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/output.c b/net/sctp/output.c index a46d1eb..5a55c55d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -26,7 +26,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index ef9e2bb..5131323 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c index 794bb14..31fa437 100644 --- a/net/sctp/primitive.c +++ b/net/sctp/primitive.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 62526c4..aff0cac 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -22,7 +22,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 4a17494d..b52ec25 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -1547,7 +1547,7 @@ module_exit(sctp_exit); */ MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132"); MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132"); -MODULE_AUTHOR("Linux Kernel SCTP developers <lksctp-developers@lists.sourceforge.net>"); +MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>"); MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)"); module_param_named(no_checksums, sctp_checksum_disable, bool, 0644); MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification"); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 362ae6e..780a2d4 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 9da6885..f1f3aac 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f6b7109..93271f0 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 84d98d8..64ea5fd 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c6670d2..0245712 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -34,7 +34,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index da86035..72b5939 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -24,7 +24,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 9a5c4c9..1906747 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bdbbc3f..9602c52 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -30,7 +30,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index b460195..0eff866 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 44a45db..c07624f 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 04e3d47..2cdb301 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7762b9f..9c9caaa 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -442,7 +442,7 @@ static void svc_tcp_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) + if (sk_stream_is_writeable(sk) && sock) clear_bit(SOCK_NOSPACE, &sock->flags); svc_write_space(sk); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ddf0602..d6656d7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1602,7 +1602,7 @@ static void xs_tcp_write_space(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) xs_write_space(sk); read_unlock_bh(&sk->sk_callback_lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 593071d..57896ee 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -96,8 +96,7 @@ #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> - -#include "af_vsock.h" +#include <net/af_vsock.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); diff --git a/net/vmw_vsock/af_vsock.h b/net/vmw_vsock/af_vsock.h deleted file mode 100644 index 7d64d36..0000000 --- a/net/vmw_vsock/af_vsock.h +++ /dev/null @@ -1,175 +0,0 @@ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation version 2 and no later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#ifndef __AF_VSOCK_H__ -#define __AF_VSOCK_H__ - -#include <linux/kernel.h> -#include <linux/workqueue.h> -#include <linux/vm_sockets.h> - -#include "vsock_addr.h" - -#define LAST_RESERVED_PORT 1023 - -#define vsock_sk(__sk) ((struct vsock_sock *)__sk) -#define sk_vsock(__vsk) (&(__vsk)->sk) - -struct vsock_sock { - /* sk must be the first member. */ - struct sock sk; - struct sockaddr_vm local_addr; - struct sockaddr_vm remote_addr; - /* Links for the global tables of bound and connected sockets. */ - struct list_head bound_table; - struct list_head connected_table; - /* Accessed without the socket lock held. This means it can never be - * modified outsided of socket create or destruct. - */ - bool trusted; - bool cached_peer_allow_dgram; /* Dgram communication allowed to - * cached peer? - */ - u32 cached_peer; /* Context ID of last dgram destination check. */ - const struct cred *owner; - /* Rest are SOCK_STREAM only. */ - long connect_timeout; - /* Listening socket that this came from. */ - struct sock *listener; - /* Used for pending list and accept queue during connection handshake. - * The listening socket is the head for both lists. Sockets created - * for connection requests are placed in the pending list until they - * are connected, at which point they are put in the accept queue list - * so they can be accepted in accept(). If accept() cannot accept the - * connection, it is marked as rejected so the cleanup function knows - * to clean up the socket. - */ - struct list_head pending_links; - struct list_head accept_queue; - bool rejected; - struct delayed_work dwork; - u32 peer_shutdown; - bool sent_request; - bool ignore_connecting_rst; - - /* Private to transport. */ - void *trans; -}; - -s64 vsock_stream_has_data(struct vsock_sock *vsk); -s64 vsock_stream_has_space(struct vsock_sock *vsk); -void vsock_pending_work(struct work_struct *work); -struct sock *__vsock_create(struct net *net, - struct socket *sock, - struct sock *parent, - gfp_t priority, unsigned short type); - -/**** TRANSPORT ****/ - -struct vsock_transport_recv_notify_data { - u64 data1; /* Transport-defined. */ - u64 data2; /* Transport-defined. */ - bool notify_on_block; -}; - -struct vsock_transport_send_notify_data { - u64 data1; /* Transport-defined. */ - u64 data2; /* Transport-defined. */ -}; - -struct vsock_transport { - /* Initialize/tear-down socket. */ - int (*init)(struct vsock_sock *, struct vsock_sock *); - void (*destruct)(struct vsock_sock *); - void (*release)(struct vsock_sock *); - - /* Connections. */ - int (*connect)(struct vsock_sock *); - - /* DGRAM. */ - int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); - int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk, - struct msghdr *msg, size_t len, int flags); - int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, - struct iovec *, size_t len); - bool (*dgram_allow)(u32 cid, u32 port); - - /* STREAM. */ - /* TODO: stream_bind() */ - ssize_t (*stream_dequeue)(struct vsock_sock *, struct iovec *, - size_t len, int flags); - ssize_t (*stream_enqueue)(struct vsock_sock *, struct iovec *, - size_t len); - s64 (*stream_has_data)(struct vsock_sock *); - s64 (*stream_has_space)(struct vsock_sock *); - u64 (*stream_rcvhiwat)(struct vsock_sock *); - bool (*stream_is_active)(struct vsock_sock *); - bool (*stream_allow)(u32 cid, u32 port); - - /* Notification. */ - int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); - int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); - int (*notify_recv_init)(struct vsock_sock *, size_t, - struct vsock_transport_recv_notify_data *); - int (*notify_recv_pre_block)(struct vsock_sock *, size_t, - struct vsock_transport_recv_notify_data *); - int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t, - struct vsock_transport_recv_notify_data *); - int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t, - ssize_t, bool, struct vsock_transport_recv_notify_data *); - int (*notify_send_init)(struct vsock_sock *, - struct vsock_transport_send_notify_data *); - int (*notify_send_pre_block)(struct vsock_sock *, - struct vsock_transport_send_notify_data *); - int (*notify_send_pre_enqueue)(struct vsock_sock *, - struct vsock_transport_send_notify_data *); - int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, - struct vsock_transport_send_notify_data *); - - /* Shutdown. */ - int (*shutdown)(struct vsock_sock *, int); - - /* Buffer sizes. */ - void (*set_buffer_size)(struct vsock_sock *, u64); - void (*set_min_buffer_size)(struct vsock_sock *, u64); - void (*set_max_buffer_size)(struct vsock_sock *, u64); - u64 (*get_buffer_size)(struct vsock_sock *); - u64 (*get_min_buffer_size)(struct vsock_sock *); - u64 (*get_max_buffer_size)(struct vsock_sock *); - - /* Addressing. */ - u32 (*get_local_cid)(void); -}; - -/**** CORE ****/ - -int vsock_core_init(const struct vsock_transport *t); -void vsock_core_exit(void); - -/**** UTILS ****/ - -void vsock_release_pending(struct sock *pending); -void vsock_add_pending(struct sock *listener, struct sock *pending); -void vsock_remove_pending(struct sock *listener, struct sock *pending); -void vsock_enqueue_accept(struct sock *listener, struct sock *connected); -void vsock_insert_connected(struct vsock_sock *vsk); -void vsock_remove_bound(struct vsock_sock *vsk); -void vsock_remove_connected(struct vsock_sock *vsk); -struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); -struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst); -void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); - -#endif /* __AF_VSOCK_H__ */ diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index ffc11df..9d69866 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -34,8 +34,8 @@ #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> +#include <net/af_vsock.h> -#include "af_vsock.h" #include "vmci_transport_notify.h" static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index fd88ea8..ce6c962 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -19,8 +19,8 @@ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> -#include "vsock_addr.h" -#include "af_vsock.h" +#include <net/vsock_addr.h> +#include <net/af_vsock.h> /* If the packet format changes in a release then this should change too. */ #define VMCI_TRANSPORT_PACKET_VERSION 1 diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c index ec2611b..82486ee 100644 --- a/net/vmw_vsock/vsock_addr.c +++ b/net/vmw_vsock/vsock_addr.c @@ -17,8 +17,7 @@ #include <linux/socket.h> #include <linux/stddef.h> #include <net/sock.h> - -#include "vsock_addr.h" +#include <net/vsock_addr.h> void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port) { diff --git a/net/vmw_vsock/vsock_addr.h b/net/vmw_vsock/vsock_addr.h deleted file mode 100644 index 9ccd531..0000000 --- a/net/vmw_vsock/vsock_addr.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation version 2 and no later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#ifndef _VSOCK_ADDR_H_ -#define _VSOCK_ADDR_H_ - -#include <linux/vm_sockets.h> - -void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port); -int vsock_addr_validate(const struct sockaddr_vm *addr); -bool vsock_addr_bound(const struct sockaddr_vm *addr); -void vsock_addr_unbind(struct sockaddr_vm *addr); -bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, - const struct sockaddr_vm *other); -int vsock_addr_cast(const struct sockaddr *addr, size_t len, - struct sockaddr_vm **out_addr); - -#endif diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e52cab3..d8da6b8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -660,7 +660,13 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; atomic_inc(&flow_cache_genid); - rt_genid_bump(net); + + /* After previous checking, family can either be AF_INET or AF_INET6 */ + if (policy->family == AF_INET) + rt_genid_bump_ipv4(net); + else + rt_genid_bump_ipv6(net); + if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); |
