summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig22
-rw-r--r--net/ipv4/af_inet.c49
-rw-r--r--net/ipv4/devinet.c4
-rw-r--r--net/ipv4/fib_rules.c22
-rw-r--r--net/ipv4/icmp.c5
-rw-r--r--net/ipv4/igmp.c4
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_output.c4
-rw-r--r--net/ipv4/ip_sockglue.c20
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipmr.c912
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c4
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c29
-rw-r--r--net/ipv4/tcp.c19
-rw-r--r--net/ipv4/tcp_input.c7
-rw-r--r--net/ipv4/tcp_ipv4.c37
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_output.c14
-rw-r--r--net/ipv4/tcp_timer.c8
-rw-r--r--net/ipv4/udp.c31
-rw-r--r--net/ipv4/xfrm4_policy.c22
23 files changed, 815 insertions, 408 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 0c94a1ac294..8e3a1fd938a 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -250,6 +250,20 @@ config IP_MROUTE
<file:Documentation/networking/multicast.txt>. If you haven't heard
about it, you don't need it.
+config IP_MROUTE_MULTIPLE_TABLES
+ bool "IP: multicast policy routing"
+ depends on IP_MROUTE && IP_ADVANCED_ROUTER
+ select FIB_RULES
+ help
+ Normally, a multicast router runs a userspace daemon and decides
+ what to do with a multicast packet based on the source and
+ destination addresses. If you say Y here, the multicast router
+ will also be able to take interfaces and packet marks into
+ account and run multiple instances of userspace daemons
+ simultaneously, each one handling a single table.
+
+ If unsure, say N.
+
config IP_PIMSM_V1
bool "IP: PIM-SM version 1 support"
depends on IP_MROUTE
@@ -587,9 +601,15 @@ choice
config DEFAULT_HTCP
bool "Htcp" if TCP_CONG_HTCP=y
+ config DEFAULT_HYBLA
+ bool "Hybla" if TCP_CONG_HYBLA=y
+
config DEFAULT_VEGAS
bool "Vegas" if TCP_CONG_VEGAS=y
+ config DEFAULT_VENO
+ bool "Veno" if TCP_CONG_VENO=y
+
config DEFAULT_WESTWOOD
bool "Westwood" if TCP_CONG_WESTWOOD=y
@@ -610,8 +630,10 @@ config DEFAULT_TCP_CONG
default "bic" if DEFAULT_BIC
default "cubic" if DEFAULT_CUBIC
default "htcp" if DEFAULT_HTCP
+ default "hybla" if DEFAULT_HYBLA
default "vegas" if DEFAULT_VEGAS
default "westwood" if DEFAULT_WESTWOOD
+ default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
default "cubic"
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f7135742238..c6c43bcd1c6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -154,7 +154,7 @@ void inet_sock_destruct(struct sock *sk)
WARN_ON(sk->sk_forward_alloc);
kfree(inet->opt);
- dst_release(sk->sk_dst_cache);
+ dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);
@@ -419,6 +419,8 @@ int inet_release(struct socket *sock)
if (sk) {
long timeout;
+ sock_rps_reset_flow(sk);
+
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
@@ -546,7 +548,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -559,9 +561,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeo;
}
@@ -720,6 +722,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
{
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
return -EAGAIN;
@@ -728,12 +732,13 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(inet_sendmsg);
-
static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags)
{
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
return -EAGAIN;
@@ -743,6 +748,22 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
return sock_no_sendpage(sock, page, offset, size, flags);
}
+int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+ size_t size, int flags)
+{
+ struct sock *sk = sock->sk;
+ int addr_len = 0;
+ int err;
+
+ sock_rps_record_flow(sk);
+
+ err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, &addr_len);
+ if (err >= 0)
+ msg->msg_namelen = addr_len;
+ return err;
+}
+EXPORT_SYMBOL(inet_recvmsg);
int inet_shutdown(struct socket *sock, int how)
{
@@ -872,7 +893,7 @@ const struct proto_ops inet_stream_ops = {
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = tcp_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = tcp_sendpage,
.splice_read = tcp_splice_read,
@@ -899,7 +920,7 @@ const struct proto_ops inet_dgram_ops = {
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
@@ -929,7 +950,7 @@ static const struct proto_ops inet_sockraw_ops = {
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
@@ -1302,8 +1323,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto out_unlock;
- id = ntohl(*(u32 *)&iph->id);
- flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ id = ntohl(*(__be32 *)&iph->id);
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
@@ -1316,8 +1337,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if ((iph->protocol ^ iph2->protocol) |
(iph->tos ^ iph2->tos) |
- (iph->saddr ^ iph2->saddr) |
- (iph->daddr ^ iph2->daddr)) {
+ ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+ ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
@@ -1407,10 +1428,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field);
int snmp_mib_init(void __percpu *ptr[2], size_t mibsize)
{
BUG_ON(ptr == NULL);
- ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+ ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long));
if (!ptr[0])
goto err0;
- ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+ ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long));
if (!ptr[1])
goto err1;
return 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 90e3d6379a4..382bc768ed5 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1096,10 +1096,10 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
case NETDEV_DOWN:
ip_mc_down(in_dev);
break;
- case NETDEV_BONDING_OLDTYPE:
+ case NETDEV_PRE_TYPE_CHANGE:
ip_mc_unmap(in_dev);
break;
- case NETDEV_BONDING_NEWTYPE:
+ case NETDEV_POST_TYPE_CHANGE:
ip_mc_remap(in_dev);
break;
case NETDEV_CHANGEMTU:
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index ca2d07b1c70..76daeb5ff56 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -213,7 +213,6 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
{
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
- frh->family = AF_INET;
frh->dst_len = rule4->dst_len;
frh->src_len = rule4->src_len;
frh->tos = rule4->tos;
@@ -234,23 +233,6 @@ nla_put_failure:
return -ENOBUFS;
}
-static u32 fib4_rule_default_pref(struct fib_rules_ops *ops)
-{
- struct list_head *pos;
- struct fib_rule *rule;
-
- if (!list_empty(&ops->rules_list)) {
- pos = ops->rules_list.next;
- if (pos->next != &ops->rules_list) {
- rule = list_entry(pos->next, struct fib_rule, list);
- if (rule->pref)
- return rule->pref - 1;
- }
- }
-
- return 0;
-}
-
static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
{
return nla_total_size(4) /* dst */
@@ -263,7 +245,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
rt_cache_flush(ops->fro_net, -1);
}
-static struct fib_rules_ops fib4_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
.family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
@@ -272,7 +254,7 @@ static struct fib_rules_ops fib4_rules_ops_template = {
.configure = fib4_rule_configure,
.compare = fib4_rule_compare,
.fill = fib4_rule_fill,
- .default_pref = fib4_rule_default_pref,
+ .default_pref = fib_default_rule_pref,
.nlmsg_payload = fib4_rule_nlmsg_payload,
.flush_cache = fib4_rule_flush_cache,
.nlgroup = RTNLGRP_IPV4_RULE,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ac4dec13273..f3d339f728b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -331,9 +331,10 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
if (ip_append_data(sk, icmp_glue_bits, icmp_param,
icmp_param->data_len+icmp_param->head_len,
icmp_param->head_len,
- ipc, rt, MSG_DONTWAIT) < 0)
+ ipc, rt, MSG_DONTWAIT) < 0) {
+ ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_OUTERRORS);
ip_flush_pending_frames(sk);
- else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
+ } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
struct icmphdr *icmph = icmp_hdr(skb);
__wsum csum = 0;
struct sk_buff *skb1;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 15d3eeda92f..5fff865a4fa 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -998,7 +998,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr)
--ANK
*/
if (arp_mc_map(addr, buf, dev, 0) == 0)
- dev_mc_add(dev, buf, dev->addr_len, 0);
+ dev_mc_add(dev, buf);
}
/*
@@ -1011,7 +1011,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr)
struct net_device *dev = in_dev->dev;
if (arp_mc_map(addr, buf, dev, 0) == 0)
- dev_mc_delete(dev, buf, dev->addr_len, 0);
+ dev_mc_del(dev, buf);
}
#ifdef CONFIG_IP_MULTICAST
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8da6429269d..e0a3e3537b1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -234,7 +234,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
* having to remove and re-insert us on the wait queue.
*/
for (;;) {
- prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
if (reqsk_queue_empty(&icsk->icsk_accept_queue))
@@ -253,7 +253,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
if (!timeo)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d1bcc9f21d4..f0392191740 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -311,7 +311,7 @@ int ip_output(struct sk_buff *skb)
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
-int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
+int ip_queue_xmit(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
@@ -370,7 +370,7 @@ packet_routed:
skb_reset_network_header(skb);
iph = ip_hdr(skb);
*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
- if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok)
+ if (ip_dont_fragment(sk, &rt->u.dst) && !skb->local_df)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 1e64dabbd23..ce231780a2b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -287,12 +287,8 @@ int ip_ra_control(struct sock *sk, unsigned char on,
void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload)
{
- struct inet_sock *inet = inet_sk(sk);
struct sock_exterr_skb *serr;
- if (!inet->recverr)
- return;
-
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb)
return;
@@ -958,6 +954,22 @@ e_inval:
return -EINVAL;
}
+/**
+ * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * @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.
+ */
+int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
+ skb_dst_drop(skb);
+ return sock_queue_rcv_skb(sk, 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 067ce9e043d..b9d84e800cf 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -976,7 +976,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str
/* Is it a reply for the device we are configuring? */
if (b->xid != ic_dev_xid) {
if (net_ratelimit())
- printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet \n");
+ printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet\n");
goto drop_unlock;
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d4f6d1340a..eddfd12f55b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -63,11 +63,40 @@
#include <net/ipip.h>
#include <net/checksum.h>
#include <net/netlink.h>
+#include <net/fib_rules.h>
#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
#define CONFIG_IP_PIMSM 1
#endif
+struct mr_table {
+ struct list_head list;
+#ifdef CONFIG_NET_NS
+ struct net *net;
+#endif
+ u32 id;
+ struct sock *mroute_sk;
+ struct timer_list ipmr_expire_timer;
+ struct list_head mfc_unres_queue;
+ struct list_head mfc_cache_array[MFC_LINES];
+ struct vif_device vif_table[MAXVIFS];
+ int maxvif;
+ atomic_t cache_resolve_queue_len;
+ int mroute_do_assert;
+ int mroute_do_pim;
+#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
+ int mroute_reg_vif_num;
+#endif
+};
+
+struct ipmr_rule {
+ struct fib_rule common;
+};
+
+struct ipmr_result {
+ struct mr_table *mrt;
+};
+
/* Big lock, protecting vif table, mrt cache and mroute socket state.
Note that the changes are semaphored via rtnl_lock.
*/
@@ -78,9 +107,7 @@ static DEFINE_RWLOCK(mrt_lock);
* Multicast router control variables
*/
-#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
-
-static struct mfc_cache *mfc_unres_queue; /* Queue of unresolved entries */
+#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -95,12 +122,215 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
static struct kmem_cache *mrt_cachep __read_mostly;
-static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local);
-static int ipmr_cache_report(struct net *net,
+static struct mr_table *ipmr_new_table(struct net *net, u32 id);
+static int ip_mr_forward(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, struct mfc_cache *cache,
+ int local);
+static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm);
+static void ipmr_expire_process(unsigned long arg);
+
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+#define ipmr_for_each_table(mrt, net) \
+ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+ struct mr_table *mrt;
+
+ ipmr_for_each_table(mrt, net) {
+ if (mrt->id == id)
+ return mrt;
+ }
+ return NULL;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+ struct mr_table **mrt)
+{
+ struct ipmr_result res;
+ struct fib_lookup_arg arg = { .result = &res, };
+ int err;
+
+ err = fib_rules_lookup(net->ipv4.mr_rules_ops, flp, 0, &arg);
+ if (err < 0)
+ return err;
+ *mrt = res.mrt;
+ return 0;
+}
+
+static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
+{
+ struct ipmr_result *res = arg->result;
+ struct mr_table *mrt;
+
+ switch (rule->action) {
+ case FR_ACT_TO_TBL:
+ break;
+ case FR_ACT_UNREACHABLE:
+ return -ENETUNREACH;
+ case FR_ACT_PROHIBIT:
+ return -EACCES;
+ case FR_ACT_BLACKHOLE:
+ default:
+ return -EINVAL;
+ }
+
+ mrt = ipmr_get_table(rule->fr_net, rule->table);
+ if (mrt == NULL)
+ return -EAGAIN;
+ res->mrt = mrt;
+ return 0;
+}
+
+static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+{
+ return 1;
+}
-static struct timer_list ipmr_expire_timer;
+static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = {
+ FRA_GENERIC_POLICY,
+};
+
+static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+ struct fib_rule_hdr *frh, struct nlattr **tb)
+{
+ return 0;
+}
+
+static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+ struct nlattr **tb)
+{
+ return 1;
+}
+
+static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+ struct fib_rule_hdr *frh)
+{
+ frh->dst_len = 0;
+ frh->src_len = 0;
+ frh->tos = 0;
+ return 0;
+}
+
+static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+ .family = RTNL_FAMILY_IPMR,
+ .rule_size = sizeof(struct ipmr_rule),
+ .addr_size = sizeof(u32),
+ .action = ipmr_rule_action,
+ .match = ipmr_rule_match,
+ .configure = ipmr_rule_configure,
+ .compare = ipmr_rule_compare,
+ .default_pref = fib_default_rule_pref,
+ .fill = ipmr_rule_fill,
+ .nlgroup = RTNLGRP_IPV4_RULE,
+ .policy = ipmr_rule_policy,
+ .owner = THIS_MODULE,
+};
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+ struct fib_rules_ops *ops;
+ struct mr_table *mrt;
+ int err;
+
+ ops = fib_rules_register(&ipmr_rules_ops_template, net);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+
+ INIT_LIST_HEAD(&net->ipv4.mr_tables);
+
+ mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+ if (mrt == NULL) {
+ err = -ENOMEM;
+ goto err1;
+ }
+
+ err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0);
+ if (err < 0)
+ goto err2;
+
+ net->ipv4.mr_rules_ops = ops;
+ return 0;
+
+err2:
+ kfree(mrt);
+err1:
+ fib_rules_unregister(ops);
+ return err;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+ struct mr_table *mrt, *next;
+
+ list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list)
+ kfree(mrt);
+ fib_rules_unregister(net->ipv4.mr_rules_ops);
+}
+#else
+#define ipmr_for_each_table(mrt, net) \
+ for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+ return net->ipv4.mrt;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+ struct mr_table **mrt)
+{
+ *mrt = net->ipv4.mrt;
+ return 0;
+}
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+ net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+ return net->ipv4.mrt ? 0 : -ENOMEM;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+ kfree(net->ipv4.mrt);
+}
+#endif
+
+static struct mr_table *ipmr_new_table(struct net *net, u32 id)
+{
+ struct mr_table *mrt;
+ unsigned int i;
+
+ mrt = ipmr_get_table(net, id);
+ if (mrt != NULL)
+ return mrt;
+
+ mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+ if (mrt == NULL)
+ return NULL;
+ write_pnet(&mrt->net, net);
+ mrt->id = id;
+
+ /* Forwarding cache */
+ for (i = 0; i < MFC_LINES; i++)
+ INIT_LIST_HEAD(&mrt->mfc_cache_array[i]);
+
+ INIT_LIST_HEAD(&mrt->mfc_unres_queue);
+
+ setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
+ (unsigned long)mrt);
+
+#ifdef CONFIG_IP_PIMSM
+ mrt->mroute_reg_vif_num = -1;
+#endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+ list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables);
+#endif
+ return mrt;
+}
/* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
@@ -201,12 +431,22 @@ failure:
static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct net *net = dev_net(dev);
+ struct mr_table *mrt;
+ struct flowi fl = {
+ .oif = dev->ifindex,
+ .iif = skb->skb_iif,
+ .mark = skb->mark,
+ };
+ int err;
+
+ err = ipmr_fib_lookup(net, &fl, &mrt);
+ if (err < 0)
+ return err;
read_lock(&mrt_lock);
dev->stats.tx_bytes += skb->len;
dev->stats.tx_packets++;
- ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num,
- IGMPMSG_WHOLEPKT);
+ ipmr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, IGMPMSG_WHOLEPKT);
read_unlock(&mrt_lock);
kfree_skb(skb);
return NETDEV_TX_OK;
@@ -226,12 +466,18 @@ static void reg_vif_setup(struct net_device *dev)
dev->features |= NETIF_F_NETNS_LOCAL;
}
-static struct net_device *ipmr_reg_vif(struct net *net)
+static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
{
struct net_device *dev;
struct in_device *in_dev;
+ char name[IFNAMSIZ];
- dev = alloc_netdev(0, "pimreg", reg_vif_setup);
+ if (mrt->id == RT_TABLE_DEFAULT)
+ sprintf(name, "pimreg");
+ else
+ sprintf(name, "pimreg%u", mrt->id);
+
+ dev = alloc_netdev(0, name, reg_vif_setup);
if (dev == NULL)
return NULL;
@@ -276,17 +522,17 @@ failure:
* @notify: Set to 1, if the caller is a notifier_call
*/
-static int vif_delete(struct net *net, int vifi, int notify,
+static int vif_delete(struct mr_table *mrt, int vifi, int notify,
struct list_head *head)
{
struct vif_device *v;
struct net_device *dev;
struct in_device *in_dev;
- if (vifi < 0 || vifi >= net->ipv4.maxvif)
+ if (vifi < 0 || vifi >= mrt->maxvif)
return -EADDRNOTAVAIL;
- v = &net->ipv4.vif_table[vifi];
+ v = &mrt->vif_table[vifi];
write_lock_bh(&mrt_lock);
dev = v->dev;
@@ -298,17 +544,17 @@ static int vif_delete(struct net *net, int vifi, int notify,
}
#ifdef CONFIG_IP_PIMSM
- if (vifi == net->ipv4.mroute_reg_vif_num)
- net->ipv4.mroute_reg_vif_num = -1;
+ if (vifi == mrt->mroute_reg_vif_num)
+ mrt->mroute_reg_vif_num = -1;
#endif
- if (vifi+1 == net->ipv4.maxvif) {
+ if (vifi+1 == mrt->maxvif) {
int tmp;
for (tmp=vifi-1; tmp>=0; tmp--) {
- if (VIF_EXISTS(net, tmp))
+ if (VIF_EXISTS(mrt, tmp))
break;
}
- net->ipv4.maxvif = tmp+1;
+ mrt->maxvif = tmp+1;
}
write_unlock_bh(&mrt_lock);
@@ -329,7 +575,6 @@ static int vif_delete(struct net *net, int vifi, int notify,
static inline void ipmr_cache_free(struct mfc_cache *c)
{
- release_net(mfc_net(c));
kmem_cache_free(mrt_cachep, c);
}
@@ -337,13 +582,13 @@ static inline void ipmr_cache_free(struct mfc_cache *c)
and reporting error to netlink readers.
*/
-static void ipmr_destroy_unres(struct mfc_cache *c)
+static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
{
+ struct net *net = read_pnet(&mrt->net);
struct sk_buff *skb;
struct nlmsgerr *e;
- struct net *net = mfc_net(c);
- atomic_dec(&net->ipv4.cache_resolve_queue_len);
+ atomic_dec(&mrt->cache_resolve_queue_len);
while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) {
if (ip_hdr(skb)->version == 0) {
@@ -364,42 +609,40 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
}
-/* Single timer process for all the unresolved queue. */
+/* Timer process for the unresolved queue. */
-static void ipmr_expire_process(unsigned long dummy)
+static void ipmr_expire_process(unsigned long arg)
{
+ struct mr_table *mrt = (struct mr_table *)arg;
unsigned long now;
unsigned long expires;
- struct mfc_cache *c, **cp;
+ struct mfc_cache *c, *next;
if (!spin_trylock(&mfc_unres_lock)) {
- mod_timer(&ipmr_expire_timer, jiffies+HZ/10);
+ mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10);
return;
}
- if (mfc_unres_queue == NULL)
+ if (list_empty(&mrt->mfc_unres_queue))
goto out;
now = jiffies;
expires = 10*HZ;
- cp = &mfc_unres_queue;
- while ((c=*cp) != NULL) {
+ list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
if (time_after(c->mfc_un.unres.expires, now)) {
unsigned long interval = c->mfc_un.unres.expires - now;
if (interval < expires)
expires = interval;
- cp = &c->next;
continue;
}
- *cp = c->next;
-
- ipmr_destroy_unres(c);
+ list_del(&c->list);
+ ipmr_destroy_unres(mrt, c);
}
- if (mfc_unres_queue != NULL)
- mod_timer(&ipmr_expire_timer, jiffies + expires);
+ if (!list_empty(&mrt->mfc_unres_queue))
+ mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
out:
spin_unlock(&mfc_unres_lock);
@@ -407,17 +650,17 @@ out:
/* Fill oifs list. It is called under write locked mrt_lock. */
-static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
+static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache,
+ unsigned char *ttls)
{
int vifi;
- struct net *net = mfc_net(cache);
cache->mfc_un.res.minvif = MAXVIFS;
cache->mfc_un.res.maxvif = 0;
memset(cache->mfc_un.res.ttls, 255, MAXVIFS);
- for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) {
- if (VIF_EXISTS(net, vifi) &&
+ for (vifi = 0; vifi < mrt->maxvif; vifi++) {
+ if (VIF_EXISTS(mrt, vifi) &&
ttls[vifi] && ttls[vifi] < 255) {
cache->mfc_un.res.ttls[vifi] = ttls[vifi];
if (cache->mfc_un.res.minvif > vifi)
@@ -428,16 +671,17 @@ static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
}
}
-static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
+static int vif_add(struct net *net, struct mr_table *mrt,
+ struct vifctl *vifc, int mrtsock)
{
int vifi = vifc->vifc_vifi;
- struct vif_device *v = &net->ipv4.vif_table[vifi];
+ struct vif_device *v = &mrt->vif_table[vifi];
struct net_device *dev;
struct in_device *in_dev;
int err;
/* Is vif busy ? */
- if (VIF_EXISTS(net, vifi))
+ if (VIF_EXISTS(mrt, vifi))
return -EADDRINUSE;
switch (vifc->vifc_flags) {
@@ -447,9 +691,9 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
* Special Purpose VIF in PIM
* All the packets will be sent to the daemon
*/
- if (net->ipv4.mroute_reg_vif_num >= 0)
+ if (mrt->mroute_reg_vif_num >= 0)
return -EADDRINUSE;
- dev = ipmr_reg_vif(net);
+ dev = ipmr_reg_vif(net, mrt);
if (!dev)
return -ENOBUFS;
err = dev_set_allmulti(dev, 1);
@@ -525,49 +769,47 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
v->dev = dev;
#ifdef CONFIG_IP_PIMSM
if (v->flags&VIFF_REGISTER)
- net->ipv4.mroute_reg_vif_num = vifi;
+ mrt->mroute_reg_vif_num = vifi;
#endif
- if (vifi+1 > net->ipv4.maxvif)
- net->ipv4.maxvif = vifi+1;
+ if (vifi+1 > mrt->maxvif)
+ mrt->maxvif = vifi+1;
write_unlock_bh(&mrt_lock);
return 0;
}
-static struct mfc_cache *ipmr_cache_find(struct net *net,
+static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt,
__be32 origin,
__be32 mcastgrp)
{
int line = MFC_HASH(mcastgrp, origin);
struct mfc_cache *c;
- for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) {
- if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp)
- break;
+ list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
+ if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp)
+ return c;
}
- return c;
+ return NULL;
}
/*
* Allocate a multicast cache entry
*/
-static struct mfc_cache *ipmr_cache_alloc(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc(void)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (c == NULL)
return NULL;
c->mfc_un.res.minvif = MAXVIFS;
- mfc_net_set(c, net);
return c;
}
-static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc_unres(void)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (c == NULL)
return NULL;
skb_queue_head_init(&c->mfc_un.unres.unresolved);
c->mfc_un.unres.expires = jiffies + 10*HZ;
- mfc_net_set(c, net);
return c;
}
@@ -575,7 +817,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
* A cache entry has gone into a resolved state from queued
*/
-static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
+static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
+ struct mfc_cache *uc, struct mfc_cache *c)
{
struct sk_buff *skb;
struct nlmsgerr *e;
@@ -588,7 +831,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
- if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
nlh->nlmsg_len = (skb_tail_pointer(skb) -
(u8 *)nlh);
} else {
@@ -600,9 +843,9 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
memset(&e->msg, 0, sizeof(e->msg));
}
- rtnl_unicast(skb, mfc_net(c), NETLINK_CB(skb).pid);
+ rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
} else
- ip_mr_forward(skb, c, 0);
+ ip_mr_forward(net, mrt, skb, c, 0);
}
}
@@ -613,7 +856,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
* Called under mrt_lock.
*/
-static int ipmr_cache_report(struct net *net,
+static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert)
{
struct sk_buff *skb;
@@ -646,7 +889,7 @@ static int ipmr_cache_report(struct net *net,
memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
msg->im_msgtype = IGMPMSG_WHOLEPKT;
msg->im_mbz = 0;
- msg->im_vif = net->ipv4.mroute_reg_vif_num;
+ msg->im_vif = mrt->mroute_reg_vif_num;
ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
sizeof(struct iphdr));
@@ -678,7 +921,7 @@ static int ipmr_cache_report(struct net *net,
skb->transport_header = skb->network_header;
}
- if (net->ipv4.mroute_sk == NULL) {
+ if (mrt->mroute_sk == NULL) {
kfree_skb(skb);
return -EINVAL;
}
@@ -686,7 +929,7 @@ static int ipmr_cache_report(struct net *net,
/*
* Deliver to mrouted
*/
- ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb);
+ ret = sock_queue_rcv_skb(mrt->mroute_sk, skb);
if (ret < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n");
@@ -701,27 +944,29 @@ static int ipmr_cache_report(struct net *net,
*/
static int
-ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
+ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
{
+ bool found = false;
int err;
struct mfc_cache *c;
const struct iphdr *iph = ip_hdr(skb);
spin_lock_bh(&mfc_unres_lock);
- for (c=mfc_unres_queue; c; c=c->next) {
- if (net_eq(mfc_net(c), net) &&
- c->mfc_mcastgrp == iph->daddr &&
- c->mfc_origin == iph->saddr)
+ list_for_each_entry(c, &mrt->mfc_unres_queue, list) {
+ if (c->mfc_mcastgrp == iph->daddr &&
+ c->mfc_origin == iph->saddr) {
+ found = true;
break;
+ }
}
- if (c == NULL) {
+ if (!found) {
/*
* Create a new entry if allowable
*/
- if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 ||
- (c = ipmr_cache_alloc_unres(net)) == NULL) {
+ if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 ||
+ (c = ipmr_cache_alloc_unres()) == NULL) {
spin_unlock_bh(&mfc_unres_lock);
kfree_skb(skb);
@@ -738,7 +983,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
/*
* Reflect first query at mrouted.
*/
- err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE);
+ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE);
if (err < 0) {
/* If the report failed throw the cache entry
out - Brad Parker
@@ -750,11 +995,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
return err;
}
- atomic_inc(&net->ipv4.cache_resolve_queue_len);
- c->next = mfc_unres_queue;
- mfc_unres_queue = c;
+ atomic_inc(&mrt->cache_resolve_queue_len);
+ list_add(&c->list, &mrt->mfc_unres_queue);
- mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
+ mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
}
/*
@@ -776,19 +1020,18 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
* MFC cache manipulation by user space mroute daemon
*/
-static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
+static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
{
int line;
- struct mfc_cache *c, **cp;
+ struct mfc_cache *c, *next;
line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
- for (cp = &net->ipv4.mfc_cache_array[line];
- (c = *cp) != NULL; cp = &c->next) {
+ list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
write_lock_bh(&mrt_lock);
- *cp = c->next;
+ list_del(&c->list);
write_unlock_bh(&mrt_lock);
ipmr_cache_free(c);
@@ -798,27 +1041,30 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
return -ENOENT;
}
-static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
+static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
+ struct mfcctl *mfc, int mrtsock)
{
+ bool found = false;
int line;
- struct mfc_cache *uc, *c, **cp;
+ struct mfc_cache *uc, *c;
if (mfc->mfcc_parent >= MAXVIFS)
return -ENFILE;
line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
- for (cp = &net->ipv4.mfc_cache_array[line];
- (c = *cp) != NULL; cp = &c->next) {
+ list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
- c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr)
+ c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
+ found = true;
break;
+ }
}
- if (c != NULL) {
+ if (found) {
write_lock_bh(&mrt_lock);
c->mfc_parent = mfc->mfcc_parent;
- ipmr_update_thresholds(c, mfc->mfcc_ttls);
+ ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
@@ -828,43 +1074,42 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
return -EINVAL;
- c = ipmr_cache_alloc(net);
+ c = ipmr_cache_alloc();
if (c == NULL)
return -ENOMEM;
c->mfc_origin = mfc->mfcc_origin.s_addr;
c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr;
c->mfc_parent = mfc->mfcc_parent;
- ipmr_update_thresholds(c, mfc->mfcc_ttls);
+ ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_lock_bh(&mrt_lock);
- c->next = net->ipv4.mfc_cache_array[line];
- net->ipv4.mfc_cache_array[line] = c;
+ list_add(&c->list, &mrt->mfc_cache_array[line]);
write_unlock_bh(&mrt_lock);
/*
* Check to see if we resolved a queued list. If so we
* need to send on the frames and tidy up.
*/
+ found = false;
spin_lock_bh(&mfc_unres_lock);
- for (cp = &mfc_unres_queue; (uc=*cp) != NULL;
- cp = &uc->next) {
- if (net_eq(mfc_net(uc), net) &&
- uc->mfc_origin == c->mfc_origin &&
+ list_for_each_entry(uc, &mrt->mfc_unres_queue, list) {
+ if (uc->mfc_origin == c->mfc_origin &&
uc->mfc_mcastgrp == c->mfc_mcastgrp) {
- *cp = uc->next;
- atomic_dec(&net->ipv4.cache_resolve_queue_len);
+ list_del(&uc->list);
+ atomic_dec(&mrt->cache_resolve_queue_len);
+ found = true;
break;
}
}
- if (mfc_unres_queue == NULL)
- del_timer(&ipmr_expire_timer);
+ if (list_empty(&mrt->mfc_unres_queue))
+ del_timer(&mrt->ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
- if (uc) {
- ipmr_cache_resolve(uc, c);
+ if (found) {
+ ipmr_cache_resolve(net, mrt, uc, c);
ipmr_cache_free(uc);
}
return 0;
@@ -874,53 +1119,41 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct net *net)
+static void mroute_clean_tables(struct mr_table *mrt)
{
int i;
LIST_HEAD(list);
+ struct mfc_cache *c, *next;
/*
* Shut down all active vif entries
*/
- for (i = 0; i < net->ipv4.maxvif; i++) {
- if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC))
- vif_delete(net, i, 0, &list);
+ for (i = 0; i < mrt->maxvif; i++) {
+ if (!(mrt->vif_table[i].flags&VIFF_STATIC))
+ vif_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
/*
* Wipe the cache
*/
- for (i=0; i<MFC_LINES; i++) {
- struct mfc_cache *c, **cp;
-
- cp = &net->ipv4.mfc_cache_array[i];
- while ((c = *cp) != NULL) {
- if (c->mfc_flags&MFC_STATIC) {
- cp = &c->next;
+ for (i = 0; i < MFC_LINES; i++) {
+ list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
+ if (c->mfc_flags&MFC_STATIC)
continue;
- }
write_lock_bh(&mrt_lock);
- *cp = c->next;
+ list_del(&c->list);
write_unlock_bh(&mrt_lock);
ipmr_cache_free(c);
}
}
- if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) {
- struct mfc_cache *c, **cp;
-
+ if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
spin_lock_bh(&mfc_unres_lock);
- cp = &mfc_unres_queue;
- while ((c = *cp) != NULL) {
- if (!net_eq(mfc_net(c), net)) {
- cp = &c->next;
- continue;
- }
- *cp = c->next;
-
- ipmr_destroy_unres(c);
+ list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
+ list_del(&c->list);
+ ipmr_destroy_unres(mrt, c);
}
spin_unlock_bh(&mfc_unres_lock);
}
@@ -929,16 +1162,19 @@ static void mroute_clean_tables(struct net *net)
static void mrtsock_destruct(struct sock *sk)
{
struct net *net = sock_net(sk);
+ struct mr_table *mrt;
rtnl_lock();
- if (sk == net->ipv4.mroute_sk) {
- IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+ ipmr_for_each_table(mrt, net) {
+ if (sk == mrt->mroute_sk) {
+ IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
- write_lock_bh(&mrt_lock);
- net->ipv4.mroute_sk = NULL;
- write_unlock_bh(&mrt_lock);
+ write_lock_bh(&mrt_lock);
+ mrt->mroute_sk = NULL;
+ write_unlock_bh(&mrt_lock);
- mroute_clean_tables(net);
+ mroute_clean_tables(mrt);
+ }
}
rtnl_unlock();
}
@@ -956,9 +1192,14 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
struct vifctl vif;
struct mfcctl mfc;
struct net *net = sock_net(sk);
+ struct mr_table *mrt;
+
+ mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return -ENOENT;
if (optname != MRT_INIT) {
- if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN))
+ if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN))
return -EACCES;
}
@@ -971,7 +1212,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
return -ENOPROTOOPT;
rtnl_lock();
- if (net->ipv4.mroute_sk) {
+ if (mrt->mroute_sk) {
rtnl_unlock();
return -EADDRINUSE;
}
@@ -979,7 +1220,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
ret = ip_ra_control(sk, 1, mrtsock_destruct);
if (ret == 0) {
write_lock_bh(&mrt_lock);
- net->ipv4.mroute_sk = sk;
+ mrt->mroute_sk = sk;
write_unlock_bh(&mrt_lock);
IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
@@ -987,7 +1228,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
rtnl_unlock();
return ret;
case MRT_DONE:
- if (sk != net->ipv4.mroute_sk)
+ if (sk != mrt->mroute_sk)
return -EACCES;
return ip_ra_control(sk, 0, NULL);
case MRT_ADD_VIF:
@@ -1000,9 +1241,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
return -ENFILE;
rtnl_lock();
if (optname == MRT_ADD_VIF) {
- ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk);
+ ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk);
} else {
- ret = vif_delete(net, vif.vifc_vifi, 0, NULL);
+ ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL);
}
rtnl_unlock();
return ret;
@@ -1019,9 +1260,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
return -EFAULT;
rtnl_lock();
if (optname == MRT_DEL_MFC)
- ret = ipmr_mfc_delete(net, &mfc);
+ ret = ipmr_mfc_delete(mrt, &mfc);
else
- ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk);
+ ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk);
rtnl_unlock();
return ret;
/*
@@ -1032,7 +1273,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
int v;
if (get_user(v,(int __user *)optval))
return -EFAULT;
- net->ipv4.mroute_do_assert = (v) ? 1 : 0;
+ mrt->mroute_do_assert = (v) ? 1 : 0;
return 0;
}
#ifdef CONFIG_IP_PIMSM
@@ -1046,14 +1287,35 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
rtnl_lock();
ret = 0;
- if (v != net->ipv4.mroute_do_pim) {
- net->ipv4.mroute_do_pim = v;
- net->ipv4.mroute_do_assert = v;
+ if (v != mrt->mroute_do_pim) {
+ mrt->mroute_do_pim = v;
+ mrt->mroute_do_assert = v;
}
rtnl_unlock();
return ret;
}
#endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+ case MRT_TABLE:
+ {
+ u32 v;
+
+ if (optlen != sizeof(u32))
+ return -EINVAL;
+ if (get_user(v, (u32 __user *)optval))
+ return -EFAULT;
+ if (sk == mrt->mroute_sk)
+ return -EBUSY;
+
+ rtnl_lock();
+ ret = 0;
+ if (!ipmr_new_table(net, v))
+ ret = -ENOMEM;
+ raw_sk(sk)->ipmr_table = v;
+ rtnl_unlock();
+ return ret;
+ }
+#endif
/*
* Spurious command, or MRT_VERSION which you cannot
* set.
@@ -1072,6 +1334,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
int olr;
int val;
struct net *net = sock_net(sk);
+ struct mr_table *mrt;
+
+ mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return -ENOENT;
if (optname != MRT_VERSION &&
#ifdef CONFIG_IP_PIMSM
@@ -1093,10 +1360,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
val = 0x0305;
#ifdef CONFIG_IP_PIMSM
else if (optname == MRT_PIM)
- val = net->ipv4.mroute_do_pim;
+ val = mrt->mroute_do_pim;
#endif
else
- val = net->ipv4.mroute_do_assert;
+ val = mrt->mroute_do_assert;
if (copy_to_user(optval, &val, olr))
return -EFAULT;
return 0;
@@ -1113,16 +1380,21 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
struct vif_device *vif;
struct mfc_cache *c;
struct net *net = sock_net(sk);
+ struct mr_table *mrt;
+
+ mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return -ENOENT;
switch (cmd) {
case SIOCGETVIFCNT:
if (copy_from_user(&vr, arg, sizeof(vr)))
return -EFAULT;
- if (vr.vifi >= net->ipv4.maxvif)
+ if (vr.vifi >= mrt->maxvif)
return -EINVAL;
read_lock(&mrt_lock);
- vif = &net->ipv4.vif_table[vr.vifi];
- if (VIF_EXISTS(net, vr.vifi)) {
+ vif = &mrt->vif_table[vr.vifi];
+ if (VIF_EXISTS(mrt, vr.vifi)) {
vr.icount = vif->pkt_in;
vr.ocount = vif->pkt_out;
vr.ibytes = vif->bytes_in;
@@ -1140,7 +1412,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
return -EFAULT;
read_lock(&mrt_lock);
- c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr);
+ c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
@@ -1163,16 +1435,20 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
{
struct net_device *dev = ptr;
struct net *net = dev_net(dev);
+ struct mr_table *mrt;
struct vif_device *v;
int ct;
LIST_HEAD(list);
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
- v = &net->ipv4.vif_table[0];
- for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) {
- if (v->dev == dev)
- vif_delete(net, ct, 1, &list);
+
+ ipmr_for_each_table(mrt, net) {
+ v = &mrt->vif_table[0];
+ for (ct = 0; ct < mrt->maxvif; ct++, v++) {
+ if (v->dev == dev)
+ vif_delete(mrt, ct, 1, &list);
+ }
}
unregister_netdevice_many(&list);
return NOTIFY_DONE;
@@ -1231,11 +1507,11 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
* Processing handlers for ipmr_forward
*/
-static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
+static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, struct mfc_cache *c, int vifi)
{
- struct net *net = mfc_net(c);
const struct iphdr *iph = ip_hdr(skb);
- struct vif_device *vif = &net->ipv4.vif_table[vifi];
+ struct vif_device *vif = &mrt->vif_table[vifi];
struct net_device *dev;
struct rtable *rt;
int encap = 0;
@@ -1249,7 +1525,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
vif->bytes_out += skb->len;
vif->dev->stats.tx_bytes += skb->len;
vif->dev->stats.tx_packets++;
- ipmr_cache_report(net, skb, vifi, IGMPMSG_WHOLEPKT);
+ ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT);
goto out_free;
}
#endif
@@ -1332,12 +1608,12 @@ out_free:
return;
}
-static int ipmr_find_vif(struct net_device *dev)
+static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev)
{
- struct net *net = dev_net(dev);
int ct;
- for (ct = net->ipv4.maxvif-1; ct >= 0; ct--) {
- if (net->ipv4.vif_table[ct].dev == dev)
+
+ for (ct = mrt->maxvif-1; ct >= 0; ct--) {
+ if (mrt->vif_table[ct].dev == dev)
break;
}
return ct;
@@ -1345,11 +1621,12 @@ static int ipmr_find_vif(struct net_device *dev)
/* "local" means that we should preserve one skb (for local delivery) */
-static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local)
+static int ip_mr_forward(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, struct mfc_cache *cache,
+ int local)
{
int psend = -1;
int vif, ct;
- struct net *net = mfc_net(cache);
vif = cache->mfc_parent;
cache->mfc_un.res.pkt++;
@@ -1358,7 +1635,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
- if (net->ipv4.vif_table[vif].dev != skb->dev) {
+ if (mrt->vif_table[vif].dev != skb->dev) {
int true_vifi;
if (skb_rtable(skb)->fl.iif == 0) {
@@ -1377,26 +1654,26 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
}
cache->mfc_un.res.wrong_if++;
- true_vifi = ipmr_find_vif(skb->dev);
+ true_vifi = ipmr_find_vif(mrt, skb->dev);
- if (true_vifi >= 0 && net->ipv4.mroute_do_assert &&
+ if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
so that we cannot check that packet arrived on an oif.
It is bad, but otherwise we would need to move pretty
large chunk of pimd to kernel. Ough... --ANK
*/
- (net->ipv4.mroute_do_pim ||
+ (mrt->mroute_do_pim ||
cache->mfc_un.res.ttls[true_vifi] < 255) &&
time_after(jiffies,
cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
cache->mfc_un.res.last_assert = jiffies;
- ipmr_cache_report(net, skb, true_vifi, IGMPMSG_WRONGVIF);
+ ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
}
goto dont_forward;
}
- net->ipv4.vif_table[vif].pkt_in++;
- net->ipv4.vif_table[vif].bytes_in += skb->len;
+ mrt->vif_table[vif].pkt_in++;
+ mrt->vif_table[vif].bytes_in += skb->len;
/*
* Forward the frame
@@ -1406,7 +1683,8 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(skb2, cache, psend);
+ ipmr_queue_xmit(net, mrt, skb2, cache,
+ psend);
}
psend = ct;
}
@@ -1415,9 +1693,9 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local
if (local) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(skb2, cache, psend);
+ ipmr_queue_xmit(net, mrt, skb2, cache, psend);
} else {
- ipmr_queue_xmit(skb, cache, psend);
+ ipmr_queue_xmit(net, mrt, skb, cache, psend);
return 0;
}
}
@@ -1438,6 +1716,8 @@ int ip_mr_input(struct sk_buff *skb)
struct mfc_cache *cache;
struct net *net = dev_net(skb->dev);
int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
+ struct mr_table *mrt;
+ int err;
/* Packet is looped back after forward, it should not be
forwarded second time, but still can be delivered locally.
@@ -1445,6 +1725,10 @@ int ip_mr_input(struct sk_buff *skb)
if (IPCB(skb)->flags&IPSKB_FORWARDED)
goto dont_forward;
+ err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt);
+ if (err < 0)
+ return err;
+
if (!local) {
if (IPCB(skb)->opt.router_alert) {
if (ip_call_ra_chain(skb))
@@ -1457,9 +1741,9 @@ int ip_mr_input(struct sk_buff *skb)
that we can forward NO IGMP messages.
*/
read_lock(&mrt_lock);
- if (net->ipv4.mroute_sk) {
+ if (mrt->mroute_sk) {
nf_reset(skb);
- raw_rcv(net->ipv4.mroute_sk, skb);
+ raw_rcv(mrt->mroute_sk, skb);
read_unlock(&mrt_lock);
return 0;
}
@@ -1468,7 +1752,7 @@ int ip_mr_input(struct sk_buff *skb)
}
read_lock(&mrt_lock);
- cache = ipmr_cache_find(net, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
+ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
/*
* No usable cache entry
@@ -1486,19 +1770,19 @@ int ip_mr_input(struct sk_buff *skb)
skb = skb2;
}
- vif = ipmr_find_vif(skb->dev);
+ vif = ipmr_find_vif(mrt, skb->dev);
if (vif >= 0) {
- int err = ipmr_cache_unresolved(net, vif, skb);
+ int err2 = ipmr_cache_unresolved(mrt, vif, skb);
read_unlock(&mrt_lock);
- return err;
+ return err2;
}
read_unlock(&mrt_lock);
kfree_skb(skb);
return -ENODEV;
}
- ip_mr_forward(skb, cache, local);
+ ip_mr_forward(net, mrt, skb, cache, local);
read_unlock(&mrt_lock);
@@ -1515,11 +1799,11 @@ dont_forward:
}
#ifdef CONFIG_IP_PIMSM
-static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
+static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb,
+ unsigned int pimlen)
{
struct net_device *reg_dev = NULL;
struct iphdr *encap;
- struct net *net = dev_net(skb->dev);
encap = (struct iphdr *)(skb_transport_header(skb) + pimlen);
/*
@@ -1534,8 +1818,8 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
return 1;
read_lock(&mrt_lock);
- if (net->ipv4.mroute_reg_vif_num >= 0)
- reg_dev = net->ipv4.vif_table[net->ipv4.mroute_reg_vif_num].dev;
+ if (mrt->mroute_reg_vif_num >= 0)
+ reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev;
if (reg_dev)
dev_hold(reg_dev);
read_unlock(&mrt_lock);
@@ -1570,17 +1854,21 @@ int pim_rcv_v1(struct sk_buff * skb)
{
struct igmphdr *pim;
struct net *net = dev_net(skb->dev);
+ struct mr_table *mrt;
if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
goto drop;
pim = igmp_hdr(skb);
- if (!net->ipv4.mroute_do_pim ||
+ if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
+ goto drop;
+
+ if (!mrt->mroute_do_pim ||
pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
goto drop;
- if (__pim_rcv(skb, sizeof(*pim))) {
+ if (__pim_rcv(mrt, skb, sizeof(*pim))) {
drop:
kfree_skb(skb);
}
@@ -1592,6 +1880,8 @@ drop:
static int pim_rcv(struct sk_buff * skb)
{
struct pimreghdr *pim;
+ struct net *net = dev_net(skb->dev);
+ struct mr_table *mrt;
if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
goto drop;
@@ -1603,7 +1893,10 @@ static int pim_rcv(struct sk_buff * skb)
csum_fold(skb_checksum(skb, 0, skb->len, 0))))
goto drop;
- if (__pim_rcv(skb, sizeof(*pim))) {
+ if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
+ goto drop;
+
+ if (__pim_rcv(mrt, skb, sizeof(*pim))) {
drop:
kfree_skb(skb);
}
@@ -1611,12 +1904,11 @@ drop:
}
#endif
-static int
-ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm)
{
int ct;
struct rtnexthop *nhp;
- struct net *net = mfc_net(c);
u8 *b = skb_tail_pointer(skb);
struct rtattr *mp_head;
@@ -1624,19 +1916,19 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
if (c->mfc_parent > MAXVIFS)
return -ENOENT;
- if (VIF_EXISTS(net, c->mfc_parent))
- RTA_PUT(skb, RTA_IIF, 4, &net->ipv4.vif_table[c->mfc_parent].dev->ifindex);
+ if (VIF_EXISTS(mrt, c->mfc_parent))
+ RTA_PUT(skb, RTA_IIF, 4, &mrt->vif_table[c->mfc_parent].dev->ifindex);
mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
- if (VIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) {
+ if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
goto rtattr_failure;
nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
- nhp->rtnh_ifindex = net->ipv4.vif_table[ct].dev->ifindex;
+ nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
@@ -1654,11 +1946,16 @@ int ipmr_get_route(struct net *net,
struct sk_buff *skb, struct rtmsg *rtm, int nowait)
{
int err;
+ struct mr_table *mrt;
struct mfc_cache *cache;
struct rtable *rt = skb_rtable(skb);
+ mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return -ENOENT;
+
read_lock(&mrt_lock);
- cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst);
+ cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst);
if (cache == NULL) {
struct sk_buff *skb2;
@@ -1672,7 +1969,7 @@ int ipmr_get_route(struct net *net,
}
dev = skb->dev;
- if (dev == NULL || (vif = ipmr_find_vif(dev)) < 0) {
+ if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) {
read_unlock(&mrt_lock);
return -ENODEV;
}
@@ -1689,24 +1986,107 @@ int ipmr_get_route(struct net *net,
iph->saddr = rt->rt_src;
iph->daddr = rt->rt_dst;
iph->version = 0;
- err = ipmr_cache_unresolved(net, vif, skb2);
+ err = ipmr_cache_unresolved(mrt, vif, skb2);
read_unlock(&mrt_lock);
return err;
}
if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
cache->mfc_flags |= MFC_NOTIFY;
- err = ipmr_fill_mroute(skb, cache, rtm);
+ err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
read_unlock(&mrt_lock);
return err;
}
+static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ u32 pid, u32 seq, struct mfc_cache *c)
+{
+ struct nlmsghdr *nlh;
+ struct rtmsg *rtm;
+
+ nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ rtm = nlmsg_data(nlh);
+ rtm->rtm_family = RTNL_FAMILY_IPMR;
+ rtm->rtm_dst_len = 32;
+ rtm->rtm_src_len = 32;
+ rtm->rtm_tos = 0;
+ rtm->rtm_table = mrt->id;
+ NLA_PUT_U32(skb, RTA_TABLE, mrt->id);
+ rtm->rtm_type = RTN_MULTICAST;
+ rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+ rtm->rtm_protocol = RTPROT_UNSPEC;
+ rtm->rtm_flags = 0;
+
+ NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin);
+ NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp);
+
+ if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct mr_table *mrt;
+ struct mfc_cache *mfc;
+ unsigned int t = 0, s_t;
+ unsigned int h = 0, s_h;
+ unsigned int e = 0, s_e;
+
+ s_t = cb->args[0];
+ s_h = cb->args[1];
+ s_e = cb->args[2];
+
+ read_lock(&mrt_lock);
+ ipmr_for_each_table(mrt, net) {
+ if (t < s_t)
+ goto next_table;
+ if (t > s_t)
+ s_h = 0;
+ for (h = s_h; h < MFC_LINES; h++) {
+ list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) {
+ if (e < s_e)
+ goto next_entry;
+ if (ipmr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0)
+ goto done;
+next_entry:
+ e++;
+ }
+ e = s_e = 0;
+ }
+ s_h = 0;
+next_table:
+ t++;
+ }
+done:
+ read_unlock(&mrt_lock);
+
+ cb->args[2] = e;
+ cb->args[1] = h;
+ cb->args[0] = t;
+
+ return skb->len;
+}
+
#ifdef CONFIG_PROC_FS
/*
* The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
*/
struct ipmr_vif_iter {
struct seq_net_private p;
+ struct mr_table *mrt;
int ct;
};
@@ -1714,11 +2094,13 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net,
struct ipmr_vif_iter *iter,
loff_t pos)
{
- for (iter->ct = 0; iter->ct < net->ipv4.maxvif; ++iter->ct) {
- if (!VIF_EXISTS(net, iter->ct))
+ struct mr_table *mrt = iter->mrt;
+
+ for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
+ if (!VIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
- return &net->ipv4.vif_table[iter->ct];
+ return &mrt->vif_table[iter->ct];
}
return NULL;
}
@@ -1726,7 +2108,15 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net,
static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(mrt_lock)
{
+ struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr_table *mrt;
+
+ mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return ERR_PTR(-ENOENT);
+
+ iter->mrt = mrt;
read_lock(&mrt_lock);
return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1)
@@ -1737,15 +2127,16 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_vif_seq_idx(net, iter, 0);
- while (++iter->ct < net->ipv4.maxvif) {
- if (!VIF_EXISTS(net, iter->ct))
+ while (++iter->ct < mrt->maxvif) {
+ if (!VIF_EXISTS(mrt, iter->ct))
continue;
- return &net->ipv4.vif_table[iter->ct];
+ return &mrt->vif_table[iter->ct];
}
return NULL;
}
@@ -1758,7 +2149,8 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
{
- struct net *net = seq_file_net(seq);
+ struct ipmr_vif_iter *iter = seq->private;
+ struct mr_table *mrt = iter->mrt;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -1769,7 +2161,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
seq_printf(seq,
"%2Zd %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n",
- vif - net->ipv4.vif_table,
+ vif - mrt->vif_table,
name, vif->bytes_in, vif->pkt_in,
vif->bytes_out, vif->pkt_out,
vif->flags, vif->local, vif->remote);
@@ -1800,7 +2192,8 @@ static const struct file_operations ipmr_vif_fops = {
struct ipmr_mfc_iter {
struct seq_net_private p;
- struct mfc_cache **cache;
+ struct mr_table *mrt;
+ struct list_head *cache;
int ct;
};
@@ -1808,22 +2201,22 @@ struct ipmr_mfc_iter {
static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
struct ipmr_mfc_iter *it, loff_t pos)
{
+ struct mr_table *mrt = it->mrt;
struct mfc_cache *mfc;
- it->cache = net->ipv4.mfc_cache_array;
read_lock(&mrt_lock);
- for (it->ct = 0; it->ct < MFC_LINES; it->ct++)
- for (mfc = net->ipv4.mfc_cache_array[it->ct];
- mfc; mfc = mfc->next)
+ for (it->ct = 0; it->ct < MFC_LINES; it->ct++) {
+ it->cache = &mrt->mfc_cache_array[it->ct];
+ list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
+ }
read_unlock(&mrt_lock);
- it->cache = &mfc_unres_queue;
spin_lock_bh(&mfc_unres_lock);
- for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
- if (net_eq(mfc_net(mfc), net) &&
- pos-- == 0)
+ it->cache = &mrt->mfc_unres_queue;
+ list_for_each_entry(mfc, it->cache, list)
+ if (pos-- == 0)
return mfc;
spin_unlock_bh(&mfc_unres_lock);
@@ -1836,7 +2229,13 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr_table *mrt;
+ mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
+ if (mrt == NULL)
+ return ERR_PTR(-ENOENT);
+
+ it->mrt = mrt;
it->cache = NULL;
it->ct = 0;
return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
@@ -1848,37 +2247,36 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
struct mfc_cache *mfc = v;
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr_table *mrt = it->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_mfc_seq_idx(net, seq->private, 0);
- if (mfc->next)
- return mfc->next;
+ if (mfc->list.next != it->cache)
+ return list_entry(mfc->list.next, struct mfc_cache, list);
- if (it->cache == &mfc_unres_queue)
+ if (it->cache == &mrt->mfc_unres_queue)
goto end_of_list;
- BUG_ON(it->cache != net->ipv4.mfc_cache_array);
+ BUG_ON(it->cache != &mrt->mfc_cache_array[it->ct]);
while (++it->ct < MFC_LINES) {
- mfc = net->ipv4.mfc_cache_array[it->ct];
- if (mfc)
- return mfc;
+ it->cache = &mrt->mfc_cache_array[it->ct];
+ if (list_empty(it->cache))
+ continue;
+ return list_first_entry(it->cache, struct mfc_cache, list);
}
/* exhausted cache_array, show unresolved */
read_unlock(&mrt_lock);
- it->cache = &mfc_unres_queue;
+ it->cache = &mrt->mfc_unres_queue;
it->ct = 0;
spin_lock_bh(&mfc_unres_lock);
- mfc = mfc_unres_queue;
- while (mfc && !net_eq(mfc_net(mfc), net))
- mfc = mfc->next;
- if (mfc)
- return mfc;
+ if (!list_empty(it->cache))
+ return list_first_entry(it->cache, struct mfc_cache, list);
end_of_list:
spin_unlock_bh(&mfc_unres_lock);
@@ -1890,18 +2288,17 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct ipmr_mfc_iter *it = seq->private;
- struct net *net = seq_file_net(seq);
+ struct mr_table *mrt = it->mrt;
- if (it->cache == &mfc_unres_queue)
+ if (it->cache == &mrt->mfc_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
- else if (it->cache == net->ipv4.mfc_cache_array)
+ else if (it->cache == &mrt->mfc_cache_array[it->ct])
read_unlock(&mrt_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
int n;
- struct net *net = seq_file_net(seq);
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -1909,20 +2306,21 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
} else {
const struct mfc_cache *mfc = v;
const struct ipmr_mfc_iter *it = seq->private;
+ const struct mr_table *mrt = it->mrt;
- seq_printf(seq, "%08lX %08lX %-3hd",
- (unsigned long) mfc->mfc_mcastgrp,
- (unsigned long) mfc->mfc_origin,
+ seq_printf(seq, "%08X %08X %-3hd",
+ (__force u32) mfc->mfc_mcastgrp,
+ (__force u32) mfc->mfc_origin,
mfc->mfc_parent);
- if (it->cache != &mfc_unres_queue) {
+ if (it->cache != &mrt->mfc_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
mfc->mfc_un.res.pkt,
mfc->mfc_un.res.bytes,
mfc->mfc_un.res.wrong_if);
for (n = mfc->mfc_un.res.minvif;
n < mfc->mfc_un.res.maxvif; n++ ) {
- if (VIF_EXISTS(net, n) &&
+ if (VIF_EXISTS(mrt, n) &&
mfc->mfc_un.res.ttls[n] < 255)
seq_printf(seq,
" %2d:%-3d",
@@ -1974,27 +2372,11 @@ static const struct net_protocol pim_protocol = {
*/
static int __net_init ipmr_net_init(struct net *net)
{
- int err = 0;
+ int err;
- net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device),
- GFP_KERNEL);
- if (!net->ipv4.vif_table) {
- err = -ENOMEM;
+ err = ipmr_rules_init(net);
+ if (err < 0)
goto fail;
- }
-
- /* Forwarding cache */
- net->ipv4.mfc_cache_array = kcalloc(MFC_LINES,
- sizeof(struct mfc_cache *),
- GFP_KERNEL);
- if (!net->ipv4.mfc_cache_array) {
- err = -ENOMEM;
- goto fail_mfc_cache;
- }
-
-#ifdef CONFIG_IP_PIMSM
- net->ipv4.mroute_reg_vif_num = -1;
-#endif
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
@@ -2009,10 +2391,8 @@ static int __net_init ipmr_net_init(struct net *net)
proc_cache_fail:
proc_net_remove(net, "ip_mr_vif");
proc_vif_fail:
- kfree(net->ipv4.mfc_cache_array);
+ ipmr_rules_exit(net);
#endif
-fail_mfc_cache:
- kfree(net->ipv4.vif_table);
fail:
return err;
}
@@ -2023,8 +2403,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
proc_net_remove(net, "ip_mr_cache");
proc_net_remove(net, "ip_mr_vif");
#endif
- kfree(net->ipv4.mfc_cache_array);
- kfree(net->ipv4.vif_table);
+ ipmr_rules_exit(net);
}
static struct pernet_operations ipmr_net_ops = {
@@ -2047,7 +2426,6 @@ int __init ip_mr_init(void)
if (err)
goto reg_pernet_fail;
- setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
err = register_netdevice_notifier(&ip_mr_notifier);
if (err)
goto reg_notif_fail;
@@ -2058,6 +2436,7 @@ int __init ip_mr_init(void)
goto add_proto_fail;
}
#endif
+ rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute);
return 0;
#ifdef CONFIG_IP_PIMSM_V2
@@ -2065,7 +2444,6 @@ add_proto_fail:
unregister_netdevice_notifier(&ip_mr_notifier);
#endif
reg_notif_fail:
- del_timer(&ipmr_expire_timer);
unregister_pernet_subsys(&ipmr_net_ops);
reg_pernet_fail:
kmem_cache_destroy(mrt_cachep);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index ab828400ed7..a992dc826f1 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -88,7 +88,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
list_del(&c->list);
write_unlock_bh(&clusterip_lock);
- dev_mc_delete(c->dev, c->clustermac, ETH_ALEN, 0);
+ dev_mc_del(c->dev, c->clustermac);
dev_put(c->dev);
/* In case anyone still accesses the file, the open/close
@@ -397,7 +397,7 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par)
dev_put(dev);
return false;
}
- dev_mc_add(config->dev,config->clustermac, ETH_ALEN, 0);
+ dev_mc_add(config->dev, config->clustermac);
}
}
cipinfo->config = config;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4f1f337f433..3dc9914c1dc 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -251,6 +251,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK),
SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP),
SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP),
+ SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index cc6f097fbd5..52ef5af78a4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -290,7 +290,7 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk, skb) < 0) {
+ if (ip_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cb562fdd9b9..a947428ef0a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -258,10 +258,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
(__raw_get_cpu_var(rt_cache_stat).field++)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
+ int genid)
{
- return jhash_3words((__force u32)(__be32)(daddr),
- (__force u32)(__be32)(saddr),
+ return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
@@ -378,12 +377,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
struct rtable *r = v;
int len;
- seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
- "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
+ seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
+ "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
r->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
+ r->u.dst.__use, 0, (__force u32)r->rt_src,
(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
(int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
dst_metric(&r->u.dst, RTAX_WINDOW),
@@ -685,18 +685,17 @@ static inline bool rt_caching(const struct net *net)
static inline bool compare_hash_inputs(const struct flowi *fl1,
const struct flowi *fl2)
{
- return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+ return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->iif ^ fl2->iif)) == 0);
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
+ return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
@@ -2319,8 +2318,8 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->u.dst.rt_next)) {
- if (((rth->fl.fl4_dst ^ daddr) |
- (rth->fl.fl4_src ^ saddr) |
+ if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
+ ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
(rth->fl.iif ^ iif) |
rth->fl.oif |
(rth->fl.fl4_tos ^ tos)) == 0 &&
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0f8caf64caa..8ce29747ad9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -378,7 +378,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sock *sk = sock->sk;
struct tcp_sock *tp = tcp_sk(sk);
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -2298,7 +2298,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (sock_flag(sk, SOCK_KEEPOPEN) &&
!((1 << sk->sk_state) &
(TCPF_CLOSE | TCPF_LISTEN))) {
- __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ u32 elapsed = keepalive_time_elapsed(tp);
if (tp->keepalive_time > elapsed)
elapsed = tp->keepalive_time - elapsed;
else
@@ -2721,7 +2721,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct tcphdr *th2;
unsigned int len;
unsigned int thlen;
- unsigned int flags;
+ __be32 flags;
unsigned int mss = 1;
unsigned int hlen;
unsigned int off;
@@ -2771,10 +2771,10 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
found:
flush = NAPI_GRO_CB(p)->flush;
- flush |= flags & TCP_FLAG_CWR;
- flush |= (flags ^ tcp_flag_word(th2)) &
- ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
- flush |= th->ack_seq ^ th2->ack_seq;
+ flush |= (__force int)(flags & TCP_FLAG_CWR);
+ flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
+ ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
+ flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
for (i = sizeof(*th); i < thlen; i += 4)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
@@ -2795,8 +2795,9 @@ found:
out_check_final:
flush = len < mss;
- flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
- TCP_FLAG_SYN | TCP_FLAG_FIN);
+ flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
+ TCP_FLAG_RST | TCP_FLAG_SYN |
+ TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
pp = head;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f240f57b219..e82162c211b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3710,7 +3710,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
- dst_confirm(sk->sk_dst_cache);
+ dst_confirm(__sk_dst_get(sk));
return 1;
@@ -4319,7 +4319,7 @@ static void tcp_ofo_queue(struct sock *sk)
}
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
- SOCK_DEBUG(sk, "ofo packet was already received \n");
+ SOCK_DEBUG(sk, "ofo packet was already received\n");
__skb_unlink(skb, &tp->out_of_order_queue);
__kfree_skb(skb);
continue;
@@ -4367,6 +4367,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
goto drop;
+ skb_dst_drop(skb);
__skb_pull(skb, th->doff * 4);
TCP_ECN_accept_cwr(tp, skb);
@@ -5833,7 +5834,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
if (tp->snd_una == tp->write_seq) {
tcp_set_state(sk, TCP_FIN_WAIT2);
sk->sk_shutdown |= SEND_SHUTDOWN;
- dst_confirm(sk->sk_dst_cache);
+ dst_confirm(__sk_dst_get(sk));
if (!sock_flag(sk, SOCK_DEAD))
/* Wake up lingering close() */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3c23e70885f..771f8146a2e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -519,26 +519,31 @@ out:
sock_put(sk);
}
-/* This routine computes an IPv4 TCP checksum. */
-void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
+static void __tcp_v4_send_check(struct sk_buff *skb,
+ __be32 saddr, __be32 daddr)
{
- struct inet_sock *inet = inet_sk(sk);
struct tcphdr *th = tcp_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- th->check = ~tcp_v4_check(len, inet->inet_saddr,
- inet->inet_daddr, 0);
+ th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
} else {
- th->check = tcp_v4_check(len, inet->inet_saddr,
- inet->inet_daddr,
+ th->check = tcp_v4_check(skb->len, saddr, daddr,
csum_partial(th,
th->doff << 2,
skb->csum));
}
}
+/* This routine computes an IPv4 TCP checksum. */
+void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
+{
+ struct inet_sock *inet = inet_sk(sk);
+
+ __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
+}
+
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
const struct iphdr *iph;
@@ -551,10 +556,8 @@ int tcp_v4_gso_send_check(struct sk_buff *skb)
th = tcp_hdr(skb);
th->check = 0;
- th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
+ __tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
@@ -763,13 +766,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, rvp);
if (skb) {
- struct tcphdr *th = tcp_hdr(skb);
-
- th->check = tcp_v4_check(skb->len,
- ireq->loc_addr,
- ireq->rmt_addr,
- csum_partial(th, skb->len,
- skb->csum));
+ __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
ireq->rmt_addr,
@@ -1289,8 +1286,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_release;
/* Secret recipe starts with IP addresses */
- *mess++ ^= daddr;
- *mess++ ^= saddr;
+ *mess++ ^= (__force u32)daddr;
+ *mess++ ^= (__force u32)saddr;
/* plus variable length Initiator Cookie */
c = (u8 *)mess;
@@ -1675,6 +1672,8 @@ process:
skb->dev = NULL;
+ sock_rps_save_rxhash(sk, skb->rxhash);
+
bh_lock_sock_nested(sk);
ret = 0;
if (!sock_owned_by_user(sk)) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 5fabff9ac6d..794c2e122a4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -672,6 +672,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
inet_rsk(req)->acked = 1;
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP);
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0dda86e72ad..5db3a2c6cb3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -350,6 +350,7 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
*/
static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
{
+ skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
TCP_SKB_CB(skb)->flags = flags;
@@ -860,7 +861,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
- th->urg_ptr = 0xFFFF;
+ th->urg_ptr = htons(0xFFFF);
th->urg = 1;
}
}
@@ -878,7 +879,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
}
#endif
- icsk->icsk_af_ops->send_check(sk, skb->len, skb);
+ icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->flags & TCPCB_FLAG_ACK))
tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
@@ -887,9 +888,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
+ tcp_skb_pcount(skb));
- err = icsk->icsk_af_ops->queue_xmit(skb, 0);
+ err = icsk->icsk_af_ops->queue_xmit(skb);
if (likely(err <= 0))
return err;
@@ -2484,7 +2486,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
*tail-- ^= TCP_SKB_CB(skb)->seq + 1;
/* recommended */
- *tail-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
sha_transform((__u32 *)&xvp->cookie_bakery[0],
@@ -2502,7 +2504,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
th->window = htons(min(req->rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8a0ab2977f1..440a5c6004f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -172,14 +172,14 @@ static int tcp_write_timeout(struct sock *sk)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
- dst_negative_advice(&sk->sk_dst_cache, sk);
+ dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
- dst_negative_advice(&sk->sk_dst_cache, sk);
+ dst_negative_advice(sk);
}
retry_until = sysctl_tcp_retries2;
@@ -517,7 +517,7 @@ static void tcp_keepalive_timer (unsigned long data)
struct sock *sk = (struct sock *) data;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- __u32 elapsed;
+ u32 elapsed;
/* Only process if socket is not in use. */
bh_lock_sock(sk);
@@ -554,7 +554,7 @@ static void tcp_keepalive_timer (unsigned long data)
if (tp->packets_out || tcp_send_head(sk))
goto resched;
- elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ elapsed = keepalive_time_elapsed(tp);
if (elapsed >= keepalive_time_when(tp)) {
if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8fef859db35..4560b291180 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -307,13 +307,13 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr,
unsigned int port)
{
- return jhash_1word(saddr, net_hash_mix(net)) ^ port;
+ return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
- udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum);
+ udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
@@ -466,14 +466,14 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
daddr, hnum, dif,
hslot2, slot2);
if (!result) {
- hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum);
+ hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp4_lib_lookup2(net, saddr, sport,
- INADDR_ANY, hnum, dif,
+ htonl(INADDR_ANY), hnum, dif,
hslot2, slot2);
}
rcu_read_unlock();
@@ -1062,10 +1062,10 @@ static unsigned int first_packet_length(struct sock *sk)
spin_unlock_bh(&rcvq->lock);
if (!skb_queue_empty(&list_kill)) {
- lock_sock(sk);
+ lock_sock_bh(sk);
__skb_queue_purge(&list_kill);
sk_mem_reclaim_partial(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
return res;
}
@@ -1196,10 +1196,10 @@ out:
return err;
csum_copy_err:
- lock_sock(sk);
+ lock_sock_bh(sk);
if (!skb_kill_datagram(sk, skb, flags))
UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- release_sock(sk);
+ unlock_sock_bh(sk);
if (noblock)
return -EAGAIN;
@@ -1217,6 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags)
sk->sk_state = TCP_CLOSE;
inet->inet_daddr = 0;
inet->inet_dport = 0;
+ sock_rps_save_rxhash(sk, 0);
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
@@ -1258,8 +1259,12 @@ EXPORT_SYMBOL(udp_lib_unhash);
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
- int rc = sock_queue_rcv_skb(sk, skb);
+ int rc;
+
+ if (inet_sk(sk)->inet_daddr)
+ sock_rps_save_rxhash(sk, skb->rxhash);
+ rc = ip_queue_rcv_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -1367,6 +1372,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto drop;
}
+
+ if (sk_rcvqueues_full(sk, skb))
+ goto drop;
+
rc = 0;
bh_lock_sock(sk);
@@ -1615,9 +1624,9 @@ int udp_rcv(struct sk_buff *skb)
void udp_destroy_sock(struct sock *sk)
{
- lock_sock(sk);
+ lock_sock_bh(sk);
udp_flush_pending_frames(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
/*
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index e4a1483fba7..1705476670e 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -59,27 +59,6 @@ static int xfrm4_get_saddr(struct net *net,
return 0;
}
-static struct dst_entry *
-__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
- struct dst_entry *dst;
-
- read_lock_bh(&policy->lock);
- for (dst = policy->bundles; dst; dst = dst->next) {
- struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/
- xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
- xdst->u.rt.fl.fl4_src == fl->fl4_src &&
- xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
- xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
- dst_clone(dst);
- break;
- }
- }
- read_unlock_bh(&policy->lock);
- return dst;
-}
-
static int xfrm4_get_tos(struct flowi *fl)
{
return fl->fl4_tos;
@@ -259,7 +238,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.dst_ops = &xfrm4_dst_ops,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
- .find_bundle = __xfrm4_find_bundle,
.decode_session = _decode_session4,
.get_tos = xfrm4_get_tos,
.init_path = xfrm4_init_path,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-01-16 11:36:17 +0000