diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Kconfig | 2 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
-rw-r--r-- | net/ipv4/esp4.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 7 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 6 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 2 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 13 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_recent.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_bic.c | 5 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 14 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 14 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_beet.c | 11 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_tunnel.c | 2 | ||||
-rw-r--r-- | net/ipv4/xfrm4_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/xfrm4_state.c | 2 |
17 files changed, 56 insertions, 36 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 19880b086e7..9c7e5ffb223 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -343,7 +343,7 @@ config INET_ESP tristate "IP: ESP transformation" select XFRM select CRYPTO - select CRYPTO_AEAD + select CRYPTO_AUTHENC select CRYPTO_HMAC select CRYPTO_MD5 select CRYPTO_CBC diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 09ca5293d08..0d109504ed8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -458,7 +458,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EADDRNOTAVAIL; if (!sysctl_ip_nonlocal_bind && !inet->freebind && - addr->sin_addr.s_addr != INADDR_ANY && + addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 091e6709f83..f3ceca31aa4 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -168,7 +168,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_encap_tmpl *encap = x->encap; struct udphdr *uh; __be32 *udpdata32; - unsigned int sport, dport; + __be16 sport, dport; int encap_type; spin_lock_bh(&x->lock); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1ff446d0fa8..f6cdc012eec 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -177,10 +177,13 @@ static inline struct tnode *node_parent_rcu(struct node *node) return rcu_dereference(ret); } +/* Same as rcu_assign_pointer + * but that macro() assumes that value is a pointer. + */ static inline void node_set_parent(struct node *node, struct tnode *ptr) { - rcu_assign_pointer(node->parent, - (unsigned long)ptr | NODE_TYPE(node)); + smp_wmb(); + node->parent = (unsigned long)ptr | NODE_TYPE(node); } static inline struct node *tnode_get_child(struct tnode *tn, unsigned int i) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a13c074dac0..a944e8053e2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -591,7 +591,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } if (xfrm_decode_session_reverse(skb_in, &fl, AF_INET)) - goto out_unlock; + goto ende; if (inet_addr_type(net, fl.fl4_src) == RTN_LOCAL) err = __ip_route_output_key(net, &rt2, &fl); @@ -601,7 +601,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) fl2.fl4_dst = fl.fl4_src; if (ip_route_output_key(net, &rt2, &fl2)) - goto out_unlock; + goto ende; /* Ugh! */ odst = skb_in->dst; @@ -614,7 +614,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } if (err) - goto out_unlock; + goto ende; err = xfrm_lookup((struct dst_entry **)&rt2, &fl, NULL, XFRM_LOOKUP_ICMP); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a2e92f9709d..3b2e5adca83 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -568,7 +568,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(IPSTATS_MIB_REASMREQDS); - net = skb->dev->nd_net; + net = skb->dev ? skb->dev->nd_net : skb->dst->dev->nd_net; /* Start by cleaning up the memory. */ if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh) ip_evictor(net); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index de0572c8885..f72457b4b0a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -583,7 +583,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } if (!mreq.imr_ifindex) { - if (mreq.imr_address.s_addr == INADDR_ANY) { + if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { inet->mc_index = 0; inet->mc_addr = 0; err = 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 10013ccee8d..7c992fbbc2c 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -103,6 +103,7 @@ - '3' from resolv.h */ #define NONE __constant_htonl(INADDR_NONE) +#define ANY __constant_htonl(INADDR_ANY) /* * Public IP configuration @@ -753,9 +754,9 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d printk("Unknown ARP type 0x%04x for device %s\n", dev->type, dev->name); b->htype = dev->type; /* can cause undefined behavior */ } + + /* server_ip and your_ip address are both already zero per RFC2131 */ b->hlen = dev->addr_len; - b->your_ip = NONE; - b->server_ip = NONE; memcpy(b->hw_addr, dev->dev_addr, dev->addr_len); b->secs = htons(jiffies_diff / HZ); b->xid = d->xid; @@ -1479,19 +1480,19 @@ static int __init ip_auto_config_setup(char *addrs) DBG(("IP-Config: Parameter #%d: `%s'\n", num, ip)); switch (num) { case 0: - if ((ic_myaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_myaddr = in_aton(ip)) == ANY) ic_myaddr = NONE; break; case 1: - if ((ic_servaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_servaddr = in_aton(ip)) == ANY) ic_servaddr = NONE; break; case 2: - if ((ic_gateway = in_aton(ip)) == INADDR_ANY) + if ((ic_gateway = in_aton(ip)) == ANY) ic_gateway = NONE; break; case 3: - if ((ic_netmask = in_aton(ip)) == INADDR_ANY) + if ((ic_netmask = in_aton(ip)) == ANY) ic_netmask = NONE; break; case 4: diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 68cbe3ca01c..8e8f0425a8e 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -252,6 +252,8 @@ recent_mt_check(const char *tablename, const void *ip, if ((info->check_set & (IPT_RECENT_SET | IPT_RECENT_REMOVE)) && (info->seconds || info->hit_count)) return false; + if (info->hit_count > ip_pkt_list_tot) + return false; if (info->name[0] == '\0' || strnlen(info->name, IPT_RECENT_NAME_LEN) == IPT_RECENT_NAME_LEN) return false; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 071e83a894a..39b629ac240 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -735,7 +735,7 @@ new_segment: if (!(psize -= copy)) goto out; - if (skb->len < mss_now || (flags & MSG_OOB)) + if (skb->len < size_goal || (flags & MSG_OOB)) continue; if (forced_push(tp)) { @@ -981,7 +981,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < mss_now || (flags & MSG_OOB)) + if (skb->len < size_goal || (flags & MSG_OOB)) continue; if (forced_push(tp)) { diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 5212ed9b0c9..7eb7636db0d 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -1,12 +1,13 @@ /* * Binary Increase Congestion control for TCP - * + * Home page: + * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of BICTCP in * Lison-Xu, Kahaled Harfoush, and Injong Rhee. * "Binary Increase Congestion Control for Fast, Long Distance * Networks" in InfoComm 2004 * Available from: - * http://www.csc.ncsu.edu/faculty/rhee/export/bitcp.pdf + * http://netsrv.csc.ncsu.edu/export/bitcp.pdf * * Unless BIC is enabled and congestion window is large * this behaves the same as the original Reno. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 19c449f6267..7facdb0f696 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1367,7 +1367,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, * a normal way */ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, - u32 skip_to_seq) + u32 skip_to_seq, int *fack_count) { tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) @@ -1375,6 +1375,8 @@ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, if (!before(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) break; + + *fack_count += tcp_skb_pcount(skb); } return skb; } @@ -1390,7 +1392,7 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, return skb; if (before(next_dup->start_seq, skip_to_seq)) { - skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq); + skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); tcp_sacktag_walk(skb, sk, NULL, next_dup->start_seq, next_dup->end_seq, 1, fack_count, reord, flag); @@ -1537,7 +1539,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, /* Head todo? */ if (before(start_seq, cache->start_seq)) { - skb = tcp_sacktag_skip(skb, sk, start_seq); + skb = tcp_sacktag_skip(skb, sk, start_seq, + &fack_count); skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, cache->start_seq, @@ -1565,7 +1568,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, goto walk; } - skb = tcp_sacktag_skip(skb, sk, cache->end_seq); + skb = tcp_sacktag_skip(skb, sk, cache->end_seq, + &fack_count); /* Check overlap against next cached too (past this one already) */ cache++; continue; @@ -1577,7 +1581,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, break; fack_count = tp->fackets_out; } - skb = tcp_sacktag_skip(skb, sk, start_seq); + skb = tcp_sacktag_skip(skb, sk, start_seq, &fack_count); walk: skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ed750f9ceb0..72b9350006f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -255,7 +255,7 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ - new_win = cur_win; + new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; @@ -1035,6 +1035,13 @@ static void tcp_cwnd_validate(struct sock *sk) * introducing MSS oddities to segment boundaries. In rare cases where * mss_now != mss_cache, we will request caller to create a small skb * per input skb which could be mostly avoided here (if desired). + * + * We explicitly want to create a request for splitting write queue tail + * to a small skb for Nagle purposes while avoiding unnecessary modulos, + * thus all the complexity (cwnd_len is always MSS multiple which we + * return whenever allowed by the other factors). Basically we need the + * modulo only when the receiver window alone is the limiting factor or + * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) @@ -1048,10 +1055,11 @@ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) return cwnd_len; - if (skb == tcp_write_queue_tail(sk) && cwnd_len <= skb->len) + needed = min(skb->len, window); + + if (skb == tcp_write_queue_tail(sk) && cwnd_len <= needed) return cwnd_len; - needed = min(skb->len, window); return needed - needed % mss_now; } diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index b47030ba162..9c798abce73 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -39,13 +39,11 @@ static void xfrm4_beet_make_header(struct sk_buff *skb) static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) { struct ip_beet_phdr *ph; - struct iphdr *iph, *top_iph; + struct iphdr *top_iph; int hdrlen, optlen; - iph = ip_hdr(skb); - hdrlen = 0; - optlen = iph->ihl * 4 - sizeof(*iph); + optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); @@ -53,11 +51,12 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) hdrlen); skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); - skb->transport_header = skb->network_header + sizeof(*iph); + skb->transport_header = skb->network_header + sizeof(*top_iph); xfrm4_beet_make_header(skb); - ph = (struct ip_beet_phdr *)__skb_pull(skb, sizeof(*iph) - hdrlen); + ph = (struct ip_beet_phdr *) + __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 8dee617ee90..584e6d74e3a 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -41,7 +41,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; - top_iph->protocol = x->inner_mode->afinfo->proto; + top_iph->protocol = xfrm_af2proto(skb->dst->ops->family); /* DS disclosed */ top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d5a58a81802..8c3180adddb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -56,7 +56,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - err = x->inner_mode->afinfo->extract_output(x, skb); + err = xfrm_inner_extract_output(x, skb); if (err) return err; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index fdeebe68a37..07735ed280d 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -52,10 +52,12 @@ int xfrm4_extract_header(struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); XFRM_MODE_SKB_CB(skb)->id = iph->id; XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off; XFRM_MODE_SKB_CB(skb)->tos = iph->tos; XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl; + XFRM_MODE_SKB_CB(skb)->optlen = iph->ihl * 4 - sizeof(*iph); memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0, sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); |