diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 11 | ||||
-rw-r--r-- | net/ipv4/ah4.c | 8 | ||||
-rw-r--r-- | net/ipv4/arp.c | 8 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 16 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 17 | ||||
-rw-r--r-- | net/ipv4/inet_diag.c | 31 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_options.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 35 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 15 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/Kconfig | 1 | ||||
-rw-r--r-- | net/ipv4/ping.c | 2 | ||||
-rw-r--r-- | net/ipv4/proc.c | 9 | ||||
-rw-r--r-- | net/ipv4/raw.c | 10 | ||||
-rw-r--r-- | net/ipv4/route.c | 143 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 44 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 6 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/udp.c | 6 |
23 files changed, 214 insertions, 166 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1b5096a..15dc4c4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1250,7 +1250,8 @@ out: return err; } -static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features) +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; @@ -1572,9 +1573,9 @@ static __net_init int ipv4_mib_init_net(struct net *net) sizeof(struct icmp_mib), __alignof__(struct icmp_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics, - sizeof(struct icmpmsg_mib), - __alignof__(struct icmpmsg_mib)) < 0) + net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), + GFP_KERNEL); + if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); @@ -1598,7 +1599,7 @@ err_tcp_mib: static __net_exit void ipv4_mib_exit_net(struct net *net) { - snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics); + kfree(net->mib.icmpmsg_statistics); snmp_mib_free((void __percpu **)net->mib.icmp_statistics); snmp_mib_free((void __percpu **)net->mib.udplite_statistics); snmp_mib_free((void __percpu **)net->mib.udp_statistics); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c1f4154..36d1440 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); skb_set_transport_header(skb, -ihl); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 96a164a..5c29ac5 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -177,7 +177,7 @@ struct neigh_table arp_tbl = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -592,16 +592,18 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* * Allocate a buffer */ - skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (skb == NULL) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472ef..313ad93 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -304,9 +304,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; while (1) { - skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), + skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; @@ -327,7 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); pip = ip_hdr(skb); @@ -647,6 +649,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; + int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); @@ -661,7 +664,9 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (IS_ERR(rt)) return -1; - skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (skb == NULL) { ip_rt_put(rt); return -1; @@ -669,7 +674,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, skb_dst_set(skb, &rt->dst); - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); @@ -1716,7 +1721,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c14d88a..a598768 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -588,10 +588,19 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); -struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, - const gfp_t priority) +/** + * inet_csk_clone_lock - clone an inet socket, and lock its clone + * @sk: the socket to clone + * @req: request_sock + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *inet_csk_clone_lock(const struct sock *sk, + const struct request_sock *req, + const gfp_t priority) { - struct sock *newsk = sk_clone(sk, priority); + struct sock *newsk = sk_clone_lock(sk, priority); if (newsk != NULL) { struct inet_connection_sock *newicsk = inet_csk(newsk); @@ -615,7 +624,7 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, } return newsk; } -EXPORT_SYMBOL_GPL(inet_csk_clone); +EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f5e2bda..0a46c54 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -125,16 +122,20 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &np->rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &np->daddr); - if (ext & (1 << (INET_DIAG_TOS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass); + *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = np->daddr; + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); } #endif @@ -224,10 +225,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &tw6->tw_v6_rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &tw6->tw_v6_daddr); + *(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail; @@ -603,10 +602,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_inode = 0; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &inet6_rsk(req)->loc_addr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &inet6_rsk(req)->rmt_addr); + *(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr; + *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - b; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c..29a07b6 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d55110e..2b32296 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -171,7 +171,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipgre_get_stats(struct net_device *dev) { @@ -835,6 +835,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec93335..1e60f76 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 09ff51b..80d5fa4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -55,20 +55,13 @@ /* * SOL_IP control messages. */ +#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { - struct in_pktinfo info; - struct rtable *rt = skb_rtable(skb); + struct in_pktinfo info = *PKTINFO_SKB_CB(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; - if (rt) { - info.ipi_ifindex = rt->rt_iif; - info.ipi_spec_dst.s_addr = rt->rt_spec_dst; - } else { - info.ipi_ifindex = 0; - info.ipi_spec_dst.s_addr = 0; - } put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } @@ -992,20 +985,28 @@ e_inval: } /** - * ip_queue_rcv_skb - Queue an skb into sock receive queue + * ipv4_pktinfo_prepare - transfert some info from rtable to skb * @sk: socket * @skb: buffer * - * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option - * is not set, we drop skb dst entry now, while dst cache line is hot. + * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst + * in skb->cb[] before dst drop. + * This way, receiver doesnt make cache line misses to read rtable. */ -int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(struct sk_buff *skb) { - if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO)) - skb_dst_drop(skb); - return sock_queue_rcv_skb(sk, skb); + struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + const struct rtable *rt = skb_rtable(skb); + + if (rt) { + pktinfo->ipi_ifindex = rt->rt_iif; + pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst; + } else { + pktinfo->ipi_ifindex = 0; + pktinfo->ipi_spec_dst.s_addr = 0; + } + skb_dst_drop(skb); } -EXPORT_SYMBOL(ip_queue_rcv_skb); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc..915eb52 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -763,13 +763,15 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d struct sk_buff *skb; struct bootp_pkt *b; struct iphdr *h; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* Allocate packet */ - skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15, + skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15, GFP_KERNEL); if (!skb) return; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt)); memset(b, 0, sizeof(struct bootp_pkt)); @@ -822,8 +824,13 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d skb->dev = dev; skb->protocol = htons(ETH_P_IP); if (dev_hard_header(skb, dev, ntohs(skb->protocol), - dev->broadcast, dev->dev_addr, skb->len) < 0 || - dev_queue_xmit(skb) < 0) + dev->broadcast, dev->dev_addr, skb->len) < 0) { + kfree_skb(skb); + printk("E"); + return; + } + + if (dev_queue_xmit(skb) < 0) printk("E"); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 065effd..9490690 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -148,7 +148,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipip_get_stats(struct net_device *dev) { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a..f19f218 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a06f73f..43d4c3b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -339,7 +339,6 @@ void ping_err(struct sk_buff *skb, u32 info) sk = ping_v4_lookup(net, iph->daddr, iph->saddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk == NULL) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); pr_debug("no socket, dropping\n"); return; /* No socket for error */ } @@ -679,7 +678,6 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { - ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS); kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); return -1; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 466ea8b..961eed4 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -288,7 +288,7 @@ static void icmpmsg_put(struct seq_file *seq) count = 0; for (i = 0; i < ICMPMSG_MIB_MAX; i++) { - val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i); + val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]); if (val) { type[count] = i; vals[count++] = val; @@ -307,6 +307,7 @@ static void icmp_put(struct seq_file *seq) { int i; struct net *net = seq->private; + atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs; seq_puts(seq, "\nIcmp: InMsgs InErrors"); for (i=0; icmpmibmap[i].name != NULL; i++) @@ -319,15 +320,13 @@ static void icmp_put(struct seq_file *seq) snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index)); + atomic_long_read(ptr + icmpmibmap[i].index)); seq_printf(seq, " %lu %lu", snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index | 0x100)); + atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); } /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 007e2eb..3ccda5a 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) { /* Charge it to the socket. */ - if (ip_queue_rcv_skb(sk, skb) < 0) { + ipv4_pktinfo_prepare(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -327,6 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, unsigned int iphlen; int err; struct rtable *rt = *rtp; + int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -336,12 +338,14 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, if (flags&MSG_PROBE) goto out; + hlen = LL_RESERVED_SPACE(rt->dst.dev); + tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, + length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 155138d..fb47c8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -138,7 +138,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +193,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -1304,16 +1304,42 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } +static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; + + dst_confirm(&rt->dst); + + rt->rt_gateway = peer->redirect_learned.a4; + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); + rt->rt_gateway = orig_gw; + return -EAGAIN; + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); + } + return 0; +} + /* called in rcu_read_lock() section */ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1336,33 +1362,42 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; for (s = 0; s < 2; s++) { for (i = 0; i < 2; i++) { - fl4.flowi4_oif = ikeys[i]; - fl4.saddr = skeys[s]; - rt = __ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - continue; - - if (rt->dst.error || rt->dst.dev != dev || - rt->rt_gateway != old_gw) { - ip_rt_put(rt); - continue; - } + unsigned int hash; + struct rtable __rcu **rthp; + struct rtable *rt; + + hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); + + rthp = &rt_hash_table[hash].chain; + + while ((rt = rcu_dereference(*rthp)) != NULL) { + rthp = &rt->dst.rt_next; + + if (rt->rt_key_dst != daddr || + rt->rt_key_src != skeys[s] || + rt->rt_oif != ikeys[i] || + rt_is_input_route(rt) || + rt_is_expired(rt) || + !net_eq(dev_net(rt->dst.dev), net) || + rt->dst.error || + rt->dst.dev != dev || + rt->rt_gateway != old_gw) + continue; - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; - if (peer) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); + peer = rt->peer; + if (peer) { + if (peer->redirect_learned.a4 != new_gw) { + peer->redirect_learned.a4 = new_gw; + atomic_inc(&__rt_peer_genid); + } + check_peer_redir(&rt->dst, peer); + } } - - ip_rt_put(rt); - return; } } return; @@ -1649,33 +1684,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) -{ - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); - - rt->rt_gateway = peer->redirect_learned.a4; - - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - return 0; -} static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { @@ -1806,12 +1814,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -2747,9 +2760,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2767,7 +2782,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, @@ -2845,7 +2860,7 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires = 0; + unsigned long expires = 0; const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; @@ -2902,8 +2917,12 @@ static int rt_fill_info(struct net *net, tsage = get_seconds() - peer->tcp_ts_stamp; } expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) - expires -= jiffies; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; + } } if (rt_is_input_route(rt)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 34f5db1..50c3596 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2653,7 +2653,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features) +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 52b5c2d..78dd38c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2858,7 +2858,7 @@ static void tcp_try_keep_open(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); int state = TCP_CA_Open; - if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker) + if (tcp_left_out(tp) || tcp_any_retrans_done(sk)) state = TCP_CA_Disorder; if (inet_csk(sk)->icsk_ca_state != state) { @@ -2881,7 +2881,8 @@ static void tcp_try_to_open(struct sock *sk, int flag) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); - tcp_moderate_cwnd(tp); + if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) + tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); } @@ -3009,11 +3010,11 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int newly_acked_sacked, int flag) + int newly_acked_sacked, bool is_dupack, + int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); int fast_rexmit = 0, mib_idx; @@ -3066,17 +3067,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } break; - case TCP_CA_Disorder: - tcp_try_undo_dsack(sk); - if (!tp->undo_marker || - /* For SACK case do not Open to allow to undo - * catching for all duplicate ACKs. */ - tcp_is_reno(tp) || tp->snd_una != tp->high_seq) { - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Open); - } - break; - case TCP_CA_Recovery: if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); @@ -3117,7 +3107,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } - if (icsk->icsk_ca_state == TCP_CA_Disorder) + if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk)) { @@ -3681,10 +3671,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; + bool is_dupack = false; u32 prior_in_flight; u32 prior_fackets; int prior_packets; int prior_sacked = tp->sacked_out; + int pkts_acked = 0; int newly_acked_sacked = 0; int frto_cwnd = 0; @@ -3757,6 +3749,7 @@ 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. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + pkts_acked = prior_packets - tp->packets_out; newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out); @@ -3771,8 +3764,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); - tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - newly_acked_sacked, flag); + is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3784,6 +3778,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + /* If data was DSACKed, see if we can undo a cwnd reduction. */ + if (flag & FLAG_DSACKING_ACK) + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3797,10 +3795,14 @@ invalid_ack: return -1; old_ack: + /* If data was SACKed, tag it and see if we should send more data. + * If data was DSACKed, see if we can undo a cwnd reduction. + */ if (TCP_SKB_CB(skb)->sacked) { - tcp_sacktag_write_queue(sk, skb, prior_snd_una); - if (icsk->icsk_ca_state == TCP_CA_Open) - tcp_try_keep_open(sk); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + newly_acked_sacked = tp->sacked_out - prior_sacked; + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a744315..a9db4b1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1510,6 +1510,7 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + tcp_clear_xmit_timers(newsk); bh_unlock_sock(newsk); sock_put(newsk); goto exit; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 66363b6..945efff 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -343,8 +343,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); - ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw6->tw_v6_daddr = np->daddr; + tw6->tw_v6_rcv_saddr = np->rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_ipv6only = np->ipv6only; } @@ -425,7 +425,7 @@ static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, */ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) { - struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC); + struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); if (newsk != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 980b98f..63170e29 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1382,7 +1382,7 @@ static inline int tcp_minshall_check(const struct tcp_sock *tp) /* Return 0, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) - * 3. Or TCP_NODELAY was set. + * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966d..b867ea2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1357,7 +1357,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (inet_sk(sk)->inet_daddr) sock_rps_save_rxhash(sk, skb); - rc = ip_queue_rcv_skb(sk, skb); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1473,6 +1473,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = 0; + ipv4_pktinfo_prepare(skb); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) rc = __udp_queue_rcv_skb(sk, skb); @@ -2246,7 +2247,8 @@ int udp4_ufo_send_check(struct sk_buff *skb) return 0; } -struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features) +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; |