summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c1
-rw-r--r--net/ipv4/inet_diag.c18
-rw-r--r--net/ipv4/ip_gre.c21
-rw-r--r--net/ipv4/ip_sockglue.c37
-rw-r--r--net/ipv4/ipip.c3
-rw-r--r--net/ipv4/netfilter/Kconfig9
-rw-r--r--net/ipv4/netfilter/Makefile1
-rw-r--r--net/ipv4/netfilter/ipt_LOG.c516
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c60
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c8
-rw-r--r--net/ipv4/netfilter/nf_nat_h323.c14
-rw-r--r--net/ipv4/netfilter/nf_nat_sip.c7
-rw-r--r--net/ipv4/ping.c3
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/raw.c3
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/tcp_ipv4.c298
-rw-r--r--net/ipv4/tcp_minisocks.c12
-rw-r--r--net/ipv4/tcp_output.c4
-rw-r--r--net/ipv4/udp.c7
20 files changed, 325 insertions, 705 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f7b5670744f0..e588a34e85c2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -381,6 +381,7 @@ lookup_protocol:
inet->mc_all = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
+ inet->rcv_tos = 0;
sk_refcnt_debug_inc(sk);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index fcf281819cd4..8d25a1c557eb 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -960,9 +960,12 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
return -EINVAL;
}
-
- return netlink_dump_start(sock_diag_nlsk, skb, nlh,
- inet_diag_dump_compat, NULL, 0);
+ {
+ struct netlink_dump_control c = {
+ .dump = inet_diag_dump_compat,
+ };
+ return netlink_dump_start(sock_diag_nlsk, skb, nlh, &c);
+ }
}
return inet_diag_get_exact_compat(skb, nlh);
@@ -985,9 +988,12 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
return -EINVAL;
}
-
- return netlink_dump_start(sock_diag_nlsk, skb, h,
- inet_diag_dump, NULL, 0);
+ {
+ struct netlink_dump_control c = {
+ .dump = inet_diag_dump,
+ };
+ return netlink_dump_start(sock_diag_nlsk, skb, h, &c);
+ }
}
return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h));
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38673d2860e2..6ef66af12291 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -730,15 +730,16 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
- if ((dst = rt->rt_gateway) == 0)
- goto tx_error_icmp;
+ dst = rt->rt_gateway;
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb));
const struct in6_addr *addr6;
+ struct neighbour *neigh;
+ bool do_tx_error_icmp;
int addr_type;
+ neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
@@ -751,9 +752,14 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
+ do_tx_error_icmp = true;
+ else {
+ do_tx_error_icmp = false;
+ dst = addr6->s6_addr32[3];
+ }
+ neigh_release(neigh);
+ if (do_tx_error_icmp)
goto tx_error_icmp;
-
- dst = addr6->s6_addr32[3];
}
#endif
else
@@ -914,9 +920,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
__IPTUNNEL_XMIT(tstats, &dev->stats);
return NETDEV_TX_OK;
+#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
-
+#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
@@ -1529,7 +1536,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla
return -EEXIST;
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
- random_ether_addr(dev->dev_addr);
+ eth_hw_addr_random(dev);
mtu = ipgre_tunnel_bind_dev(dev);
if (!tb[IFLA_MTU])
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8aa87c19fa00..ca50d9f9f8c1 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -469,6 +469,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
(1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
(1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) |
(1<<IP_MINTTL) | (1<<IP_NODEFRAG))) ||
+ optname == IP_UNICAST_IF ||
optname == IP_MULTICAST_TTL ||
optname == IP_MULTICAST_ALL ||
optname == IP_MULTICAST_LOOP ||
@@ -628,6 +629,35 @@ static int do_ip_setsockopt(struct sock *sk, int level,
goto e_inval;
inet->mc_loop = !!val;
break;
+ case IP_UNICAST_IF:
+ {
+ struct net_device *dev = NULL;
+ int ifindex;
+
+ if (optlen != sizeof(int))
+ goto e_inval;
+
+ ifindex = (__force int)ntohl((__force __be32)val);
+ if (ifindex == 0) {
+ inet->uc_index = 0;
+ err = 0;
+ break;
+ }
+
+ dev = dev_get_by_index(sock_net(sk), ifindex);
+ err = -EADDRNOTAVAIL;
+ if (!dev)
+ break;
+ dev_put(dev);
+
+ err = -EINVAL;
+ if (sk->sk_bound_dev_if)
+ break;
+
+ inet->uc_index = ifindex;
+ err = 0;
+ break;
+ }
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
@@ -1178,6 +1208,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_MULTICAST_LOOP:
val = inet->mc_loop;
break;
+ case IP_UNICAST_IF:
+ val = (__force int)htonl((__u32) inet->uc_index);
+ break;
case IP_MULTICAST_IF:
{
struct in_addr addr;
@@ -1256,6 +1289,10 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
int hlim = inet->mc_ttl;
put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
}
+ if (inet->cmsg_flags & IP_CMSG_TOS) {
+ int tos = inet->rcv_tos;
+ put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
+ }
len -= msg.msg_controllen;
return put_user(len, optlen);
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 22a199315309..f84ebff5cdb0 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -454,8 +454,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
dev->stats.tx_fifo_errors++;
goto tx_error;
}
- if ((dst = rt->rt_gateway) == 0)
- goto tx_error_icmp;
+ dst = rt->rt_gateway;
}
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 74dfc9e5211f..fcc543cd987a 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -123,15 +123,6 @@ config IP_NF_TARGET_REJECT
To compile it as a module, choose M here. If unsure, say N.
-config IP_NF_TARGET_LOG
- tristate "LOG target support"
- default m if NETFILTER_ADVANCED=n
- help
- This option adds a `LOG' target, which allows you to create rules in
- any iptables table which records the packet header to the syslog.
-
- To compile it as a module, choose M here. If unsure, say N.
-
config IP_NF_TARGET_ULOG
tristate "ULOG target support"
default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 213a462b739b..240b68469a7a 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -54,7 +54,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o
-obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o
obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o
obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o
diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
deleted file mode 100644
index d76d6c9ed946..000000000000
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ /dev/null
@@ -1,516 +0,0 @@
-/*
- * This is a module which is used for logging packets.
- */
-
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/ip.h>
-#include <net/icmp.h>
-#include <net/udp.h>
-#include <net/tcp.h>
-#include <net/route.h>
-
-#include <linux/netfilter.h>
-#include <linux/netfilter/x_tables.h>
-#include <linux/netfilter_ipv4/ipt_LOG.h>
-#include <net/netfilter/nf_log.h>
-#include <net/netfilter/xt_log.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
-MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog");
-
-/* One level of recursion won't kill us */
-static void dump_packet(struct sbuff *m,
- const struct nf_loginfo *info,
- const struct sk_buff *skb,
- unsigned int iphoff)
-{
- struct iphdr _iph;
- const struct iphdr *ih;
- unsigned int logflags;
-
- if (info->type == NF_LOG_TYPE_LOG)
- logflags = info->u.log.logflags;
- else
- logflags = NF_LOG_MASK;
-
- ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph);
- if (ih == NULL) {
- sb_add(m, "TRUNCATED");
- return;
- }
-
- /* Important fields:
- * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */
- /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */
- sb_add(m, "SRC=%pI4 DST=%pI4 ",
- &ih->saddr, &ih->daddr);
-
- /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */
- sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ",
- ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK,
- ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id));
-
- /* Max length: 6 "CE DF MF " */
- if (ntohs(ih->frag_off) & IP_CE)
- sb_add(m, "CE ");
- if (ntohs(ih->frag_off) & IP_DF)
- sb_add(m, "DF ");
- if (ntohs(ih->frag_off) & IP_MF)
- sb_add(m, "MF ");
-
- /* Max length: 11 "FRAG:65535 " */
- if (ntohs(ih->frag_off) & IP_OFFSET)
- sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET);
-
- if ((logflags & IPT_LOG_IPOPT) &&
- ih->ihl * 4 > sizeof(struct iphdr)) {
- const unsigned char *op;
- unsigned char _opt[4 * 15 - sizeof(struct iphdr)];
- unsigned int i, optsize;
-
- optsize = ih->ihl * 4 - sizeof(struct iphdr);
- op = skb_header_pointer(skb, iphoff+sizeof(_iph),
- optsize, _opt);
- if (op == NULL) {
- sb_add(m, "TRUNCATED");
- return;
- }
-
- /* Max length: 127 "OPT (" 15*4*2chars ") " */
- sb_add(m, "OPT (");
- for (i = 0; i < optsize; i++)
- sb_add(m, "%02X", op[i]);
- sb_add(m, ") ");
- }
-
- switch (ih->protocol) {
- case IPPROTO_TCP: {
- struct tcphdr _tcph;
- const struct tcphdr *th;
-
- /* Max length: 10 "PROTO=TCP " */
- sb_add(m, "PROTO=TCP ");
-
- if (ntohs(ih->frag_off) & IP_OFFSET)
- break;
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- th = skb_header_pointer(skb, iphoff + ih->ihl * 4,
- sizeof(_tcph), &_tcph);
- if (th == NULL) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- /* Max length: 20 "SPT=65535 DPT=65535 " */
- sb_add(m, "SPT=%u DPT=%u ",
- ntohs(th->source), ntohs(th->dest));
- /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */
- if (logflags & IPT_LOG_TCPSEQ)
- sb_add(m, "SEQ=%u ACK=%u ",
- ntohl(th->seq), ntohl(th->ack_seq));
- /* Max length: 13 "WINDOW=65535 " */
- sb_add(m, "WINDOW=%u ", ntohs(th->window));
- /* Max length: 9 "RES=0x3F " */
- sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22));
- /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */
- if (th->cwr)
- sb_add(m, "CWR ");
- if (th->ece)
- sb_add(m, "ECE ");
- if (th->urg)
- sb_add(m, "URG ");
- if (th->ack)
- sb_add(m, "ACK ");
- if (th->psh)
- sb_add(m, "PSH ");
- if (th->rst)
- sb_add(m, "RST ");
- if (th->syn)
- sb_add(m, "SYN ");
- if (th->fin)
- sb_add(m, "FIN ");
- /* Max length: 11 "URGP=65535 " */
- sb_add(m, "URGP=%u ", ntohs(th->urg_ptr));
-
- if ((logflags & IPT_LOG_TCPOPT) &&
- th->doff * 4 > sizeof(struct tcphdr)) {
- unsigned char _opt[4 * 15 - sizeof(struct tcphdr)];
- const unsigned char *op;
- unsigned int i, optsize;
-
- optsize = th->doff * 4 - sizeof(struct tcphdr);
- op = skb_header_pointer(skb,
- iphoff+ih->ihl*4+sizeof(_tcph),
- optsize, _opt);
- if (op == NULL) {
- sb_add(m, "TRUNCATED");
- return;
- }
-
- /* Max length: 127 "OPT (" 15*4*2chars ") " */
- sb_add(m, "OPT (");
- for (i = 0; i < optsize; i++)
- sb_add(m, "%02X", op[i]);
- sb_add(m, ") ");
- }
- break;
- }
- case IPPROTO_UDP:
- case IPPROTO_UDPLITE: {
- struct udphdr _udph;
- const struct udphdr *uh;
-
- if (ih->protocol == IPPROTO_UDP)
- /* Max length: 10 "PROTO=UDP " */
- sb_add(m, "PROTO=UDP " );
- else /* Max length: 14 "PROTO=UDPLITE " */
- sb_add(m, "PROTO=UDPLITE ");
-
- if (ntohs(ih->frag_off) & IP_OFFSET)
- break;
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- uh = skb_header_pointer(skb, iphoff+ih->ihl*4,
- sizeof(_udph), &_udph);
- if (uh == NULL) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- /* Max length: 20 "SPT=65535 DPT=65535 " */
- sb_add(m, "SPT=%u DPT=%u LEN=%u ",
- ntohs(uh->source), ntohs(uh->dest),
- ntohs(uh->len));
- break;
- }
- case IPPROTO_ICMP: {
- struct icmphdr _icmph;
- const struct icmphdr *ich;
- static const size_t required_len[NR_ICMP_TYPES+1]
- = { [ICMP_ECHOREPLY] = 4,
- [ICMP_DEST_UNREACH]
- = 8 + sizeof(struct iphdr),
- [ICMP_SOURCE_QUENCH]
- = 8 + sizeof(struct iphdr),
- [ICMP_REDIRECT]
- = 8 + sizeof(struct iphdr),
- [ICMP_ECHO] = 4,
- [ICMP_TIME_EXCEEDED]
- = 8 + sizeof(struct iphdr),
- [ICMP_PARAMETERPROB]
- = 8 + sizeof(struct iphdr),
- [ICMP_TIMESTAMP] = 20,
- [ICMP_TIMESTAMPREPLY] = 20,
- [ICMP_ADDRESS] = 12,
- [ICMP_ADDRESSREPLY] = 12 };
-
- /* Max length: 11 "PROTO=ICMP " */
- sb_add(m, "PROTO=ICMP ");
-
- if (ntohs(ih->frag_off) & IP_OFFSET)
- break;
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- ich = skb_header_pointer(skb, iphoff + ih->ihl * 4,
- sizeof(_icmph), &_icmph);
- if (ich == NULL) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- /* Max length: 18 "TYPE=255 CODE=255 " */
- sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code);
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- if (ich->type <= NR_ICMP_TYPES &&
- required_len[ich->type] &&
- skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- switch (ich->type) {
- case ICMP_ECHOREPLY:
- case ICMP_ECHO:
- /* Max length: 19 "ID=65535 SEQ=65535 " */
- sb_add(m, "ID=%u SEQ=%u ",
- ntohs(ich->un.echo.id),
- ntohs(ich->un.echo.sequence));
- break;
-
- case ICMP_PARAMETERPROB:
- /* Max length: 14 "PARAMETER=255 " */
- sb_add(m, "PARAMETER=%u ",
- ntohl(ich->un.gateway) >> 24);
- break;
- case ICMP_REDIRECT:
- /* Max length: 24 "GATEWAY=255.255.255.255 " */
- sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway);
- /* Fall through */
- case ICMP_DEST_UNREACH:
- case ICMP_SOURCE_QUENCH:
- case ICMP_TIME_EXCEEDED:
- /* Max length: 3+maxlen */
- if (!iphoff) { /* Only recurse once. */
- sb_add(m, "[");
- dump_packet(m, info, skb,
- iphoff + ih->ihl*4+sizeof(_icmph));
- sb_add(m, "] ");
- }
-
- /* Max length: 10 "MTU=65535 " */
- if (ich->type == ICMP_DEST_UNREACH &&
- ich->code == ICMP_FRAG_NEEDED)
- sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu));
- }
- break;
- }
- /* Max Length */
- case IPPROTO_AH: {
- struct ip_auth_hdr _ahdr;
- const struct ip_auth_hdr *ah;
-
- if (ntohs(ih->frag_off) & IP_OFFSET)
- break;
-
- /* Max length: 9 "PROTO=AH " */
- sb_add(m, "PROTO=AH ");
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- ah = skb_header_pointer(skb, iphoff+ih->ihl*4,
- sizeof(_ahdr), &_ahdr);
- if (ah == NULL) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- /* Length: 15 "SPI=0xF1234567 " */
- sb_add(m, "SPI=0x%x ", ntohl(ah->spi));
- break;
- }
- case IPPROTO_ESP: {
- struct ip_esp_hdr _esph;
- const struct ip_esp_hdr *eh;
-
- /* Max length: 10 "PROTO=ESP " */
- sb_add(m, "PROTO=ESP ");
-
- if (ntohs(ih->frag_off) & IP_OFFSET)
- break;
-
- /* Max length: 25 "INCOMPLETE [65535 bytes] " */
- eh = skb_header_pointer(skb, iphoff+ih->ihl*4,
- sizeof(_esph), &_esph);
- if (eh == NULL) {
- sb_add(m, "INCOMPLETE [%u bytes] ",
- skb->len - iphoff - ih->ihl*4);
- break;
- }
-
- /* Length: 15 "SPI=0xF1234567 " */
- sb_add(m, "SPI=0x%x ", ntohl(eh->spi));
- break;
- }
- /* Max length: 10 "PROTO 255 " */
- default:
- sb_add(m, "PROTO=%u ", ih->protocol);
- }
-
- /* Max length: 15 "UID=4294967295 " */
- if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) {
- read_lock_bh(&skb->sk->sk_callback_lock);
- if (skb->sk->sk_socket && skb->sk->sk_socket->file)
- sb_add(m, "UID=%u GID=%u ",
- skb->sk->sk_socket->file->f_cred->fsuid,
- skb->sk->sk_socket->file->f_cred->fsgid);
- read_unlock_bh(&skb->sk->sk_callback_lock);
- }
-
- /* Max length: 16 "MARK=0xFFFFFFFF " */
- if (!iphoff && skb->mark)
- sb_add(m, "MARK=0x%x ", skb->mark);
-
- /* Proto Max log string length */
- /* IP: 40+46+6+11+127 = 230 */
- /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */
- /* UDP: 10+max(25,20) = 35 */
- /* UDPLITE: 14+max(25,20) = 39 */
- /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */
- /* ESP: 10+max(25)+15 = 50 */
- /* AH: 9+max(25)+15 = 49 */
- /* unknown: 10 */
-
- /* (ICMP allows recursion one level deep) */
- /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */
- /* maxlen = 230+ 91 + 230 + 252 = 803 */
-}
-
-static void dump_mac_header(struct sbuff *m,
- const struct nf_loginfo *info,
- const struct sk_buff *skb)
-{
- struct net_device *dev = skb->dev;
- unsigned int logflags = 0;
-
- if (info->type == NF_LOG_TYPE_LOG)
- logflags = info->u.log.logflags;
-
- if (!(logflags & IPT_LOG_MACDECODE))
- goto fallback;
-
- switch (dev->type) {
- case ARPHRD_ETHER:
- sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
- eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
- ntohs(eth_hdr(skb)->h_proto));
- return;
- default:
- break;
- }
-
-fallback:
- sb_add(m, "MAC=");
- if (dev->hard_header_len &&
- skb->mac_header != skb->network_header) {
- const unsigned char *p = skb_mac_header(skb);
- unsigned int i;
-
- sb_add(m, "%02x", *p++);
- for (i = 1; i < dev->hard_header_len; i++, p++)
- sb_add(m, ":%02x", *p);
- }
- sb_add(m, " ");
-}
-
-static struct nf_loginfo default_loginfo = {
- .type = NF_LOG_TYPE_LOG,
- .u = {
- .log = {
- .level = 5,
- .logflags = NF_LOG_MASK,
- },
- },
-};
-
-static void
-ipt_log_packet(u_int8_t pf,
- unsigned int hooknum,
- const struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- const struct nf_loginfo *loginfo,
- const char *prefix)
-{
- struct sbuff *m = sb_open();
-
- if (!loginfo)
- loginfo = &default_loginfo;
-
- sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level,
- prefix,
- in ? in->name : "",
- out ? out->name : "");
-#ifdef CONFIG_BRIDGE_NETFILTER
- if (skb->nf_bridge) {
- const struct net_device *physindev;
- const struct net_device *physoutdev;
-
- physindev = skb->nf_bridge->physindev;
- if (physindev && in != physindev)
- sb_add(m, "PHYSIN=%s ", physindev->name);
- physoutdev = skb->nf_bridge->physoutdev;
- if (physoutdev && out != physoutdev)
- sb_add(m, "PHYSOUT=%s ", physoutdev->name);
- }
-#endif
-
- if (in != NULL)
- dump_mac_header(m, loginfo, skb);
-
- dump_packet(m, loginfo, skb, 0);
-
- sb_close(m);
-}
-
-static unsigned int
-log_tg(struct sk_buff *skb, const struct xt_action_param *par)
-{
- const struct ipt_log_info *loginfo = par->targinfo;
- struct nf_loginfo li;
-
- li.type = NF_LOG_TYPE_LOG;
- li.u.log.level = loginfo->level;
- li.u.log.logflags = loginfo->logflags;
-
- ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, par->out, &li,
- loginfo->prefix);
- return XT_CONTINUE;
-}
-
-static int log_tg_check(const struct xt_tgchk_param *par)
-{
- const struct ipt_log_info *loginfo = par->targinfo;
-
- if (loginfo->level >= 8) {
- pr_debug("level %u >= 8\n", loginfo->level);
- return -EINVAL;
- }
- if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') {
- pr_debug("prefix is not null-terminated\n");
- return -EINVAL;
- }
- return 0;
-}
-
-static struct xt_target log_tg_reg __read_mostly = {
- .name = "LOG",
- .family = NFPROTO_IPV4,
- .target = log_tg,
- .targetsize = sizeof(struct ipt_log_info),
- .checkentry = log_tg_check,
- .me = THIS_MODULE,
-};
-
-static struct nf_logger ipt_log_logger __read_mostly = {
- .name = "ipt_LOG",
- .logfn = &ipt_log_packet,
- .me = THIS_MODULE,
-};
-
-static int __init log_tg_init(void)
-{
- int ret;
-
- ret = xt_register_target(&log_tg_reg);
- if (ret < 0)
- return ret;
- nf_log_register(NFPROTO_IPV4, &ipt_log_logger);
- return 0;
-}
-
-static void __exit log_tg_exit(void)
-{
- nf_log_unregister(&ipt_log_logger);
- xt_unregister_target(&log_tg_reg);
-}
-
-module_init(log_tg_init);
-module_exit(log_tg_exit);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index ab5b27a2916f..7cbe9cb261c2 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -75,25 +75,31 @@ static int icmp_print_tuple(struct seq_file *s,
ntohs(tuple->src.u.icmp.id));
}
+static unsigned int *icmp_get_timeouts(struct net *net)
+{
+ return &nf_ct_icmp_timeout;
+}
+
/* Returns verdict for packet, or -1 for invalid. */
static int icmp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
u_int8_t pf,
- unsigned int hooknum)
+ unsigned int hooknum,
+ unsigned int *timeout)
{
/* Do not immediately delete the connection after the first
successful reply to avoid excessive conntrackd traffic
and also to handle correctly ICMP echo reply duplicates. */
- nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
+ nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
return NF_ACCEPT;
}
/* Called when a new connection for this protocol found. */
static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
- unsigned int dataoff)
+ unsigned int dataoff, unsigned int *timeouts)
{
static const u_int8_t valid_new[] = {
[ICMP_ECHO] = 1,
@@ -263,6 +269,44 @@ static int icmp_nlattr_tuple_size(void)
}
#endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_cttimeout.h>
+
+static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data)
+{
+ unsigned int *timeout = data;
+
+ if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
+ *timeout =
+ ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
+ } else {
+ /* Set default ICMP timeout. */
+ *timeout = nf_ct_icmp_timeout;
+ }
+ return 0;
+}
+
+static int
+icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
+{
+ const unsigned int *timeout = data;
+
+ NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ));
+
+ return 0;
+
+nla_put_failure:
+ return -ENOSPC;
+}
+
+static const struct nla_policy
+icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = {
+ [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 },
+};
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *icmp_sysctl_header;
static struct ctl_table icmp_sysctl_table[] = {
@@ -298,6 +342,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly =
.invert_tuple = icmp_invert_tuple,
.print_tuple = icmp_print_tuple,
.packet = icmp_packet,
+ .get_timeouts = icmp_get_timeouts,
.new = icmp_new,
.error = icmp_error,
.destroy = NULL,
@@ -308,6 +353,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly =
.nlattr_to_tuple = icmp_nlattr_to_tuple,
.nla_policy = icmp_nla_policy,
#endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+ .ctnl_timeout = {
+ .nlattr_to_obj = icmp_timeout_nlattr_to_obj,
+ .obj_to_nlattr = icmp_timeout_obj_to_nlattr,
+ .nlattr_max = CTA_TIMEOUT_ICMP_MAX,
+ .obj_size = sizeof(unsigned int),
+ .nla_policy = icmp_timeout_nla_policy,
+ },
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
#ifdef CONFIG_SYSCTL
.ctl_table_header = &icmp_sysctl_header,
.ctl_table = icmp_sysctl_table,
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index a708933dc230..abb52adf5acd 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -686,6 +686,11 @@ static struct pernet_operations nf_nat_net_ops = {
.exit = nf_nat_net_exit,
};
+static struct nf_ct_helper_expectfn follow_master_nat = {
+ .name = "nat-follow-master",
+ .expectfn = nf_nat_follow_master,
+};
+
static int __init nf_nat_init(void)
{
size_t i;
@@ -717,6 +722,8 @@ static int __init nf_nat_init(void)
l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);
+ nf_ct_helper_expectfn_register(&follow_master_nat);
+
BUG_ON(nf_nat_seq_adjust_hook != NULL);
RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust);
BUG_ON(nfnetlink_parse_nat_setup_hook != NULL);
@@ -736,6 +743,7 @@ static void __exit nf_nat_cleanup(void)
unregister_pernet_subsys(&nf_nat_net_ops);
nf_ct_l3proto_put(l3proto);
nf_ct_extend_unregister(&nat_extend);
+ nf_ct_helper_expectfn_unregister(&follow_master_nat);
RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL);
RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL);
RCU_INIT_POINTER(nf_ct_nat_offset, NULL);
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index dc1dd912baf4..82536701e3a3 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -568,6 +568,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
+static struct nf_ct_helper_expectfn q931_nat = {
+ .name = "Q.931",
+ .expectfn = ip_nat_q931_expect,
+};
+
+static struct nf_ct_helper_expectfn callforwarding_nat = {
+ .name = "callforwarding",
+ .expectfn = ip_nat_callforwarding_expect,
+};
+
/****************************************************************************/
static int __init init(void)
{
@@ -590,6 +600,8 @@ static int __init init(void)
RCU_INIT_POINTER(nat_h245_hook, nat_h245);
RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding);
RCU_INIT_POINTER(nat_q931_hook, nat_q931);
+ nf_ct_helper_expectfn_register(&q931_nat);
+ nf_ct_helper_expectfn_register(&callforwarding_nat);
return 0;
}
@@ -605,6 +617,8 @@ static void __exit fini(void)
RCU_INIT_POINTER(nat_h245_hook, NULL);
RCU_INIT_POINTER(nat_callforwarding_hook, NULL);
RCU_INIT_POINTER(nat_q931_hook, NULL);
+ nf_ct_helper_expectfn_unregister(&q931_nat);
+ nf_ct_helper_expectfn_unregister(&callforwarding_nat);
synchronize_rcu();
}
diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c
index d0319f96269f..57932c43960e 100644
--- a/net/ipv4/netfilter/nf_nat_sip.c
+++ b/net/ipv4/netfilter/nf_nat_sip.c
@@ -526,6 +526,11 @@ err1:
return NF_DROP;
}
+static struct nf_ct_helper_expectfn sip_nat = {
+ .name = "sip",
+ .expectfn = ip_nat_sip_expected,
+};
+
static void __exit nf_nat_sip_fini(void)
{
RCU_INIT_POINTER(nf_nat_sip_hook, NULL);
@@ -535,6 +540,7 @@ static void __exit nf_nat_sip_fini(void)
RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL);
RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL);
RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL);
+ nf_ct_helper_expectfn_unregister(&sip_nat);
synchronize_rcu();
}
@@ -554,6 +560,7 @@ static int __init nf_nat_sip_init(void)
RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port);
RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session);
RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media);
+ nf_ct_helper_expectfn_register(&sip_nat);
return 0;
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b072386cee21..4398a45a9600 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -556,7 +556,8 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
- }
+ } else if (!ipc.oif)
+ ipc.oif = inet->uc_index;
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 6afc807ee2ad..02d61079f08b 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -256,6 +256,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW),
SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES),
SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
+ SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 3ccda5ae8a27..ab466305b629 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
- }
+ } else if (!ipc.oif)
+ ipc.oif = inet->uc_index;
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 019774796174..815989b90dea 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1116,12 +1116,17 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo
static const __be32 inaddr_any = 0;
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
+ const struct rtable *rt;
struct neighbour *n;
+ rt = (const struct rtable *) dst;
+
if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
pkey = &inaddr_any;
+ else if (rt->rt_gateway)
+ pkey = (const __be32 *) &rt->rt_gateway;
- n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey);
+ n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey);
if (n)
return n;
return neigh_create(&arp_tbl, pkey, dev);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 94d683a61cba..507924b640ef 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -90,16 +90,8 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency);
#ifdef CONFIG_TCP_MD5SIG
-static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
- __be32 addr);
-static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, const struct tcphdr *th);
-#else
-static inline
-struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
-{
- return NULL;
-}
#endif
struct inet_hashinfo tcp_hashinfo;
@@ -601,6 +593,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
+ const __u8 *hash_location = NULL;
+ unsigned char newhash[16];
+ int genhash;
+ struct sock *sk1 = NULL;
#endif
struct net *net;
@@ -631,7 +627,36 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
arg.iov[0].iov_len = sizeof(rep.th);
#ifdef CONFIG_TCP_MD5SIG
- key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL;
+ hash_location = tcp_parse_md5sig_option(th);
+ if (!sk && hash_location) {
+ /*
+ * active side is lost. Try to find listening socket through
+ * source port, and then find md5 key through listening socket.
+ * we are not loose security here:
+ * Incoming packet is checked with md5 hash with finding key,
+ * no RST generated if md5 hash doesn't match.
+ */
+ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
+ &tcp_hashinfo, ip_hdr(skb)->daddr,
+ ntohs(th->source), inet_iif(skb));
+ /* don't send rst if it can't find key */
+ if (!sk1)
+ return;
+ rcu_read_lock();
+ key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
+ &ip_hdr(skb)->saddr, AF_INET);
+ if (!key)
+ goto release_sk1;
+
+ genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb);
+ if (genhash || memcmp(hash_location, newhash, 16) != 0)
+ goto release_sk1;
+ } else {
+ key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
+ &ip_hdr(skb)->saddr,
+ AF_INET) : NULL;
+ }
+
if (key) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -664,6 +689,14 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
+
+#ifdef CONFIG_TCP_MD5SIG
+release_sk1:
+ if (sk1) {
+ rcu_read_unlock();
+ sock_put(sk1);
+ }
+#endif
}
/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
@@ -764,7 +797,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
req->ts_recent,
0,
- tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
}
@@ -881,153 +915,138 @@ static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk,
*/
/* Find the Key structure for an address. */
-static struct tcp_md5sig_key *
- tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
+struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+ const union tcp_md5_addr *addr,
+ int family)
{
struct tcp_sock *tp = tcp_sk(sk);
- int i;
-
- if (!tp->md5sig_info || !tp->md5sig_info->entries4)
+ struct tcp_md5sig_key *key;
+ struct hlist_node *pos;
+ unsigned int size = sizeof(struct in_addr);
+ struct tcp_md5sig_info *md5sig;
+
+ /* caller either holds rcu_read_lock() or socket lock */
+ md5sig = rcu_dereference_check(tp->md5sig_info,
+ sock_owned_by_user(sk) ||
+ lockdep_is_held(&sk->sk_lock.slock));
+ if (!md5sig)
return NULL;
- for (i = 0; i < tp->md5sig_info->entries4; i++) {
- if (tp->md5sig_info->keys4[i].addr == addr)
- return &tp->md5sig_info->keys4[i].base;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (family == AF_INET6)
+ size = sizeof(struct in6_addr);
+#endif
+ hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) {
+ if (key->family != family)
+ continue;
+ if (!memcmp(&key->addr, addr, size))
+ return key;
}
return NULL;
}
+EXPORT_SYMBOL(tcp_md5_do_lookup);
struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
struct sock *addr_sk)
{
- return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
+ union tcp_md5_addr *addr;
+
+ addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr;
+ return tcp_md5_do_lookup(sk, addr, AF_INET);
}
EXPORT_SYMBOL(tcp_v4_md5_lookup);
static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
struct request_sock *req)
{
- return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
+ union tcp_md5_addr *addr;
+
+ addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr;
+ return tcp_md5_do_lookup(sk, addr, AF_INET);
}
/* This can be called on a newly created socket, from other files */
-int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
- u8 *newkey, u8 newkeylen)
+int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
+ int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
{
/* Add Key to the list */
struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp4_md5sig_key *keys;
+ struct tcp_md5sig_info *md5sig;
- key = tcp_v4_md5_do_lookup(sk, addr);
+ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
if (key) {
/* Pre-existing entry - just update that one. */
- kfree(key->key);
- key->key = newkey;
+ memcpy(key->key, newkey, newkeylen);
key->keylen = newkeylen;
- } else {
- struct tcp_md5sig_info *md5sig;
-
- if (!tp->md5sig_info) {
- tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
- GFP_ATOMIC);
- if (!tp->md5sig_info) {
- kfree(newkey);
- return -ENOMEM;
- }
- sk_nocaps_add(sk, NETIF_F_GSO_MASK);
- }
+ return 0;
+ }
- md5sig = tp->md5sig_info;
- if (md5sig->entries4 == 0 &&
- tcp_alloc_md5sig_pool(sk) == NULL) {
- kfree(newkey);
+ md5sig = rcu_dereference_protected(tp->md5sig_info,
+ sock_owned_by_user(sk));
+ if (!md5sig) {
+ md5sig = kmalloc(sizeof(*md5sig), gfp);
+ if (!md5sig)
return -ENOMEM;
- }
-
- if (md5sig->alloced4 == md5sig->entries4) {
- keys = kmalloc((sizeof(*keys) *
- (md5sig->entries4 + 1)), GFP_ATOMIC);
- if (!keys) {
- kfree(newkey);
- if (md5sig->entries4 == 0)
- tcp_free_md5sig_pool();
- return -ENOMEM;
- }
- if (md5sig->entries4)
- memcpy(keys, md5sig->keys4,
- sizeof(*keys) * md5sig->entries4);
+ sk_nocaps_add(sk, NETIF_F_GSO_MASK);
+ INIT_HLIST_HEAD(&md5sig->head);
+ rcu_assign_pointer(tp->md5sig_info, md5sig);
+ }
- /* Free old key list, and reference new one */
- kfree(md5sig->keys4);
- md5sig->keys4 = keys;
- md5sig->alloced4++;
- }
- md5sig->entries4++;
- md5sig->keys4[md5sig->entries4 - 1].addr = addr;
- md5sig->keys4[md5sig->entries4 - 1].base.key = newkey;
- md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen;
+ key = sock_kmalloc(sk, sizeof(*key), gfp);
+ if (!key)
+ return -ENOMEM;
+ if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) {
+ sock_kfree_s(sk, key, sizeof(*key));
+ return -ENOMEM;
}
- return 0;
-}
-EXPORT_SYMBOL(tcp_v4_md5_do_add);
-static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
- u8 *newkey, u8 newkeylen)
-{
- return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr,
- newkey, newkeylen);
+ memcpy(key->key, newkey, newkeylen);
+ key->keylen = newkeylen;
+ key->family = family;
+ memcpy(&key->addr, addr,
+ (family == AF_INET6) ? sizeof(struct in6_addr) :
+ sizeof(struct in_addr));
+ hlist_add_head_rcu(&key->node, &md5sig->head);
+ return 0;
}
+EXPORT_SYMBOL(tcp_md5_do_add);
-int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
+int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
struct tcp_sock *tp = tcp_sk(sk);
- int i;
-
- for (i = 0; i < tp->md5sig_info->entries4; i++) {
- if (tp->md5sig_info->keys4[i].addr == addr) {
- /* Free the key */
- kfree(tp->md5sig_info->keys4[i].base.key);
- tp->md5sig_info->entries4--;
-
- if (tp->md5sig_info->entries4 == 0) {
- kfree(tp->md5sig_info->keys4);
- tp->md5sig_info->keys4 = NULL;
- tp->md5sig_info->alloced4 = 0;
- tcp_free_md5sig_pool();
- } else if (tp->md5sig_info->entries4 != i) {
- /* Need to do some manipulation */
- memmove(&tp->md5sig_info->keys4[i],
- &tp->md5sig_info->keys4[i+1],
- (tp->md5sig_info->entries4 - i) *
- sizeof(struct tcp4_md5sig_key));
- }
- return 0;
- }
- }
- return -ENOENT;
+ struct tcp_md5sig_key *key;
+ struct tcp_md5sig_info *md5sig;
+
+ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
+ if (!key)
+ return -ENOENT;
+ hlist_del_rcu(&key->node);
+ atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
+ kfree_rcu(key, rcu);
+ md5sig = rcu_dereference_protected(tp->md5sig_info,
+ sock_owned_by_user(sk));
+ if (hlist_empty(&md5sig->head))
+ tcp_free_md5sig_pool();
+ return 0;
}
-EXPORT_SYMBOL(tcp_v4_md5_do_del);
+EXPORT_SYMBOL(tcp_md5_do_del);
-static void tcp_v4_clear_md5_list(struct sock *sk)
+void tcp_clear_md5_list(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_md5sig_key *key;
+ struct hlist_node *pos, *n;
+ struct tcp_md5sig_info *md5sig;
- /* Free each key, then the set of key keys,
- * the crypto element, and then decrement our
- * hold on the last resort crypto.
- */
- if (tp->md5sig_info->entries4) {
- int i;
- for (i = 0; i < tp->md5sig_info->entries4; i++)
- kfree(tp->md5sig_info->keys4[i].base.key);
- tp->md5sig_info->entries4 = 0;
+ md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
+
+ if (!hlist_empty(&md5sig->head))
tcp_free_md5sig_pool();
- }
- if (tp->md5sig_info->keys4) {
- kfree(tp->md5sig_info->keys4);
- tp->md5sig_info->keys4 = NULL;
- tp->md5sig_info->alloced4 = 0;
+ hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) {
+ hlist_del_rcu(&key->node);
+ atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
+ kfree_rcu(key, rcu);
}
}
@@ -1036,7 +1055,6 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
{
struct tcp_md5sig cmd;
struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
- u8 *newkey;
if (optlen < sizeof(cmd))
return -EINVAL;
@@ -1047,32 +1065,16 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
if (sin->sin_family != AF_INET)
return -EINVAL;
- if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
- if (!tcp_sk(sk)->md5sig_info)
- return -ENOENT;
- return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
- }
+ if (!cmd.tcpm_key || !cmd.tcpm_keylen)
+ return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
+ AF_INET);
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
- if (!tcp_sk(sk)->md5sig_info) {
- struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_md5sig_info *p;
-
- p = kzalloc(sizeof(*p), sk->sk_allocation);
- if (!p)
- return -EINVAL;
-
- tp->md5sig_info = p;
- sk_nocaps_add(sk, NETIF_F_GSO_MASK);
- }
-
- newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation);
- if (!newkey)
- return -ENOMEM;
- return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr,
- newkey, cmd.tcpm_keylen);
+ return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
+ AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
+ GFP_KERNEL);
}
static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
@@ -1098,7 +1100,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
}
-static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, const struct tcphdr *th)
{
struct tcp_md5sig_pool *hp;
@@ -1198,7 +1200,8 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
int genhash;
unsigned char newhash[16];
- hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
+ hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
+ AF_INET);
hash_location = tcp_parse_md5sig_option(th);
/* We've parsed the options - do we have a hash? */
@@ -1461,6 +1464,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
+ newinet->rcv_tos = ip_hdr(skb)->tos;
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
@@ -1486,7 +1490,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
- key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
+ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
+ AF_INET);
if (key != NULL) {
/*
* We're using one, so create a matching key
@@ -1494,10 +1499,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
* memory, then we end up not copying the key
* across. Shucks.
*/
- char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
- if (newkey != NULL)
- tcp_v4_md5_do_add(newsk, newinet->inet_daddr,
- newkey, key->keylen);
+ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
+ AF_INET, key->key, key->keylen, GFP_ATOMIC);
sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
}
#endif
@@ -1858,7 +1861,6 @@ EXPORT_SYMBOL(ipv4_specific);
static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
.md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
- .md5_add = tcp_v4_md5_add_func,
.md5_parse = tcp_v4_parse_md5_keys,
};
#endif
@@ -1947,8 +1949,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
#ifdef CONFIG_TCP_MD5SIG
/* Clean up the MD5 key list, if any */
if (tp->md5sig_info) {
- tcp_v4_clear_md5_list(sk);
- kfree(tp->md5sig_info);
+ tcp_clear_md5_list(sk);
+ kfree_rcu(tp->md5sig_info, rcu);
tp->md5sig_info = NULL;
}
#endif
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 550e755747e0..3cabafb5cdd1 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -359,13 +359,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
*/
do {
struct tcp_md5sig_key *key;
- memset(tcptw->tw_md5_key, 0, sizeof(tcptw->tw_md5_key));
- tcptw->tw_md5_keylen = 0;
+ tcptw->tw_md5_key = NULL;
key = tp->af_specific->md5_lookup(sk, sk);
if (key != NULL) {
- memcpy(&tcptw->tw_md5_key, key->key, key->keylen);
- tcptw->tw_md5_keylen = key->keylen;
- if (tcp_alloc_md5sig_pool(sk) == NULL)
+ tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
+ if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL)
BUG();
}
} while (0);
@@ -405,8 +403,10 @@ void tcp_twsk_destructor(struct sock *sk)
{
#ifdef CONFIG_TCP_MD5SIG
struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_keylen)
+ if (twsk->tw_md5_key) {
tcp_free_md5sig_pool();
+ kfree_rcu(twsk->tw_md5_key, rcu);
+ }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4ff3b6dc74fc..364784a91939 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2306,8 +2306,10 @@ begin_fwd:
if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
continue;
- if (tcp_retransmit_skb(sk, skb))
+ if (tcp_retransmit_skb(sk, skb)) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
return;
+ }
NET_INC_STATS_BH(sock_net(sk), mib_idx);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5d075b5f70fc..7c41ab84e72e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -917,7 +917,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (!saddr)
saddr = inet->mc_addr;
connected = 0;
- }
+ } else if (!ipc.oif)
+ ipc.oif = inet->uc_index;
if (connected)
rt = (struct rtable *)sk_dst_check(sk, 0);
@@ -1166,7 +1167,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
struct sk_buff *skb;
unsigned int ulen, copied;
- int peeked;
+ int peeked, off = 0;
int err;
int is_udplite = IS_UDPLITE(sk);
bool slow;
@@ -1182,7 +1183,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &err);
+ &peeked, &off, &err);
if (!skb)
goto out;
generated by cgit v1.2.3 (git 2.39.0) at 2024-08-21 10:03:01 +0300