summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_stp.c2
-rw-r--r--net/bridge/br_stp_if.c3
-rw-r--r--net/ipv4/inetpeer.c81
-rw-r--r--net/ipv4/route.c12
-rw-r--r--net/ipv4/syncookies.c30
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv6/mcast.c1
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c23
-rw-r--r--net/openvswitch/actions.c44
-rw-r--r--net/openvswitch/datapath.c3
-rw-r--r--net/sched/sch_sfq.c6
12 files changed, 160 insertions, 57 deletions
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 6751ed4e0c0..8c836d96ba7 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -31,7 +31,7 @@ static const char *const br_port_state_names[] = {
void br_log_state(const struct net_bridge_port *p)
{
- br_info(p->br, "port %u(%s) entering %s state\n",
+ br_info(p->br, "port %u(%s) entered %s state\n",
(unsigned) p->port_no, p->dev->name,
br_port_state_names[p->state]);
}
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 19308e305d8..f494496373d 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -98,14 +98,13 @@ void br_stp_disable_port(struct net_bridge_port *p)
struct net_bridge *br = p->br;
int wasroot;
- br_log_state(p);
-
wasroot = br_is_root_bridge(br);
br_become_designated_port(p);
p->state = BR_STATE_DISABLED;
p->topology_change_ack = 0;
p->config_pending = 0;
+ br_log_state(p);
br_ifinfo_notify(RTM_NEWLINK, p);
del_timer(&p->message_age_timer);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index bf4a9c4808e..d4d61b694fa 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -17,6 +17,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/net.h>
+#include <linux/workqueue.h>
#include <net/ip.h>
#include <net/inetpeer.h>
#include <net/secure_seq.h>
@@ -66,6 +67,11 @@
static struct kmem_cache *peer_cachep __read_mostly;
+static LIST_HEAD(gc_list);
+static const int gc_delay = 60 * HZ;
+static struct delayed_work gc_work;
+static DEFINE_SPINLOCK(gc_lock);
+
#define node_height(x) x->avl_height
#define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
@@ -102,6 +108,50 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
+static void inetpeer_gc_worker(struct work_struct *work)
+{
+ struct inet_peer *p, *n;
+ LIST_HEAD(list);
+
+ spin_lock_bh(&gc_lock);
+ list_replace_init(&gc_list, &list);
+ spin_unlock_bh(&gc_lock);
+
+ if (list_empty(&list))
+ return;
+
+ list_for_each_entry_safe(p, n, &list, gc_list) {
+
+ if(need_resched())
+ cond_resched();
+
+ if (p->avl_left != peer_avl_empty) {
+ list_add_tail(&p->avl_left->gc_list, &list);
+ p->avl_left = peer_avl_empty;
+ }
+
+ if (p->avl_right != peer_avl_empty) {
+ list_add_tail(&p->avl_right->gc_list, &list);
+ p->avl_right = peer_avl_empty;
+ }
+
+ n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
+
+ if (!atomic_read(&p->refcnt)) {
+ list_del(&p->gc_list);
+ kmem_cache_free(peer_cachep, p);
+ }
+ }
+
+ if (list_empty(&list))
+ return;
+
+ spin_lock_bh(&gc_lock);
+ list_splice(&list, &gc_list);
+ spin_unlock_bh(&gc_lock);
+
+ schedule_delayed_work(&gc_work, gc_delay);
+}
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
@@ -126,6 +176,7 @@ void __init inet_initpeers(void)
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
NULL);
+ INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker);
}
static int addr_compare(const struct inetpeer_addr *a,
@@ -447,9 +498,8 @@ relookup:
p->rate_last = 0;
p->pmtu_expires = 0;
p->pmtu_orig = 0;
- p->redirect_genid = 0;
memset(&p->redirect_learned, 0, sizeof(p->redirect_learned));
-
+ INIT_LIST_HEAD(&p->gc_list);
/* Link the node. */
link_to_pool(p, base);
@@ -509,3 +559,30 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
return rc;
}
EXPORT_SYMBOL(inet_peer_xrlim_allow);
+
+void inetpeer_invalidate_tree(int family)
+{
+ struct inet_peer *old, *new, *prev;
+ struct inet_peer_base *base = family_to_base(family);
+
+ write_seqlock_bh(&base->lock);
+
+ old = base->root;
+ if (old == peer_avl_empty_rcu)
+ goto out;
+
+ new = peer_avl_empty_rcu;
+
+ prev = cmpxchg(&base->root, old, new);
+ if (prev == old) {
+ base->total = 0;
+ spin_lock(&gc_lock);
+ list_add_tail(&prev->gc_list, &gc_list);
+ spin_unlock(&gc_lock);
+ schedule_delayed_work(&gc_work, gc_delay);
+ }
+
+out:
+ write_sequnlock_bh(&base->lock);
+}
+EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index bcacf54e541..01977479617 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -132,7 +132,6 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
-static int redirect_genid;
static struct delayed_work expires_work;
static unsigned long expires_ljiffies;
@@ -937,7 +936,7 @@ static void rt_cache_invalidate(struct net *net)
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
- redirect_genid++;
+ inetpeer_invalidate_tree(AF_INET);
}
/*
@@ -1485,10 +1484,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
peer = rt->peer;
if (peer) {
- if (peer->redirect_learned.a4 != new_gw ||
- peer->redirect_genid != redirect_genid) {
+ if (peer->redirect_learned.a4 != new_gw) {
peer->redirect_learned.a4 = new_gw;
- peer->redirect_genid = redirect_genid;
atomic_inc(&__rt_peer_genid);
}
check_peer_redir(&rt->dst, peer);
@@ -1793,8 +1790,6 @@ static void ipv4_validate_peer(struct rtable *rt)
if (peer) {
check_peer_pmtu(&rt->dst, peer);
- if (peer->redirect_genid != redirect_genid)
- peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway)
check_peer_redir(&rt->dst, peer);
@@ -1958,8 +1953,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
dst_init_metrics(&rt->dst, peer->metrics, false);
check_peer_pmtu(&rt->dst, peer);
- if (peer->redirect_genid != redirect_genid)
- peer->redirect_learned.a4 = 0;
+
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway) {
rt->rt_gateway = peer->redirect_learned.a4;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 51fdbb49043..eab2a7fb15d 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -278,6 +278,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct rtable *rt;
__u8 rcv_wscale;
bool ecn_ok = false;
+ struct flowi4 fl4;
if (!sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
@@ -346,20 +347,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- {
- struct flowi4 fl4;
-
- flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
- RT_SCOPE_UNIVERSE, IPPROTO_TCP,
- inet_sk_flowi_flags(sk),
- (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
- ireq->loc_addr, th->source, th->dest);
- security_req_classify_flow(req, flowi4_to_flowi(&fl4));
- rt = ip_route_output_key(sock_net(sk), &fl4);
- if (IS_ERR(rt)) {
- reqsk_free(req);
- goto out;
- }
+ flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
+ RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+ inet_sk_flowi_flags(sk),
+ (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
+ ireq->loc_addr, th->source, th->dest);
+ security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+ rt = ip_route_output_key(sock_net(sk), &fl4);
+ if (IS_ERR(rt)) {
+ reqsk_free(req);
+ goto out;
}
/* Try to redo what tcp_v4_send_synack did. */
@@ -373,5 +370,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
ireq->rcv_wscale = rcv_wscale;
ret = get_cookie_sock(sk, skb, req, &rt->dst);
+ /* ip_queue_xmit() depends on our flow being setup
+ * Normal sockets get it right from inet_csk_route_child_sock()
+ */
+ if (ret)
+ inet_sk(ret)->cork.fl.u.ip4 = fl4;
out: return ret;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 94d683a61cb..fd54c5f8a25 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1466,9 +1466,13 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
newinet->inet_id = newtp->write_seq ^ jiffies;
- if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
- goto put_and_exit;
-
+ if (!dst) {
+ dst = inet_csk_route_child_sock(sk, newsk, req);
+ if (!dst)
+ goto put_and_exit;
+ } else {
+ /* syncookie case : see end of cookie_v4_check() */
+ }
sk_setup_caps(newsk, dst);
tcp_mtup_init(newsk);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b853f06cc14..16c33e30812 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -257,7 +257,6 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
if (rt) {
dev = rt->dst.dev;
- dev_hold(dev);
dst_release(&rt->dst);
}
} else
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8c2e3ab58f2..22b766407de 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1077,7 +1077,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct net *net = dev_net(dev);
if (unlikely(!idev))
- return NULL;
+ return ERR_PTR(-ENODEV);
rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
if (unlikely(!rt)) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 10687692831..b49da6c925b 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -943,20 +943,21 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
}
}
- if (nf_conntrack_event_report(IPCT_DESTROY, ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh)) < 0) {
+ if (del_timer(&ct->timeout)) {
+ if (nf_conntrack_event_report(IPCT_DESTROY, ct,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh)) < 0) {
+ nf_ct_delete_from_lists(ct);
+ /* we failed to report the event, try later */
+ nf_ct_insert_dying_list(ct);
+ nf_ct_put(ct);
+ return 0;
+ }
+ /* death_by_timeout would report the event again */
+ set_bit(IPS_DYING_BIT, &ct->status);
nf_ct_delete_from_lists(ct);
- /* we failed to report the event, try later */
- nf_ct_insert_dying_list(ct);
nf_ct_put(ct);
- return 0;
}
-
- /* death_by_timeout would report the event again */
- set_bit(IPS_DYING_BIT, &ct->status);
-
- nf_ct_kill(ct);
nf_ct_put(ct);
return 0;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2725d1bdf29..48badffaafc 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2011 Nicira Networks.
+ * Copyright (c) 2007-2012 Nicira Networks.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -145,9 +145,16 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
*addr, new_addr, 1);
} else if (nh->protocol == IPPROTO_UDP) {
- if (likely(transport_len >= sizeof(struct udphdr)))
- inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
- *addr, new_addr, 1);
+ if (likely(transport_len >= sizeof(struct udphdr))) {
+ struct udphdr *uh = udp_hdr(skb);
+
+ if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace4(&uh->check, skb,
+ *addr, new_addr, 1);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+ }
}
csum_replace4(&nh->check, *addr, new_addr);
@@ -197,8 +204,22 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port,
skb->rxhash = 0;
}
-static int set_udp_port(struct sk_buff *skb,
- const struct ovs_key_udp *udp_port_key)
+static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
+{
+ struct udphdr *uh = udp_hdr(skb);
+
+ if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+ set_tp_port(skb, port, new_port, &uh->check);
+
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ *port = new_port;
+ skb->rxhash = 0;
+ }
+}
+
+static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
{
struct udphdr *uh;
int err;
@@ -210,16 +231,15 @@ static int set_udp_port(struct sk_buff *skb,
uh = udp_hdr(skb);
if (udp_port_key->udp_src != uh->source)
- set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+ set_udp_port(skb, &uh->source, udp_port_key->udp_src);
if (udp_port_key->udp_dst != uh->dest)
- set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+ set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
return 0;
}
-static int set_tcp_port(struct sk_buff *skb,
- const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
{
struct tcphdr *th;
int err;
@@ -328,11 +348,11 @@ static int execute_set_action(struct sk_buff *skb,
break;
case OVS_KEY_ATTR_TCP:
- err = set_tcp_port(skb, nla_data(nested_attr));
+ err = set_tcp(skb, nla_data(nested_attr));
break;
case OVS_KEY_ATTR_UDP:
- err = set_udp_port(skb, nla_data(nested_attr));
+ err = set_udp(skb, nla_data(nested_attr));
break;
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ce64c18b8c7..2c030505b33 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1521,6 +1521,9 @@ static struct vport *lookup_vport(struct ovs_header *ovs_header,
vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME]));
if (!vport)
return ERR_PTR(-ENODEV);
+ if (ovs_header->dp_ifindex &&
+ ovs_header->dp_ifindex != get_dpifindex(vport->dp))
+ return ERR_PTR(-ENODEV);
return vport;
} else if (a[OVS_VPORT_ATTR_PORT_NO]) {
u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 60d47180f04..02a21abea65 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -469,11 +469,15 @@ enqueue:
if (slot->qlen == 1) { /* The flow is new */
if (q->tail == NULL) { /* It is the first flow */
slot->next = x;
- q->tail = slot;
} else {
slot->next = q->tail->next;
q->tail->next = x;
}
+ /* We put this flow at the end of our flow list.
+ * This might sound unfair for a new flow to wait after old ones,
+ * but we could endup servicing new flows only, and freeze old ones.
+ */
+ q->tail = slot;
/* We could use a bigger initial quantum for new flows */
slot->allot = q->scaled_quantum;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-10 01:32:39 +0000