aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c177
1 files changed, 100 insertions, 77 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff6f91cdb6c4..cd1fa9f70f1a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -84,6 +84,7 @@
#include <linux/jhash.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/route.h>
@@ -112,14 +113,13 @@
#define DEFAULT_MIN_PMTU (512 + 20 + 20)
#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ)
-
+#define DEFAULT_MIN_ADVMSS 256
static int ip_rt_max_size;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
-static int ip_rt_min_advmss __read_mostly = 256;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
@@ -458,7 +458,7 @@ static u32 *ip_tstamps __read_mostly;
* if one generator is seldom used. This makes hard for an attacker
* to infer how many packets were sent between two points in time.
*/
-u32 ip_idents_reserve(u32 hash, int segs)
+static u32 ip_idents_reserve(u32 hash, int segs)
{
u32 bucket, old, now = (u32)jiffies;
atomic_t *p_id;
@@ -479,7 +479,6 @@ u32 ip_idents_reserve(u32 hash, int segs)
*/
return atomic_add_return(segs + delta, p_id) - segs;
}
-EXPORT_SYMBOL(ip_idents_reserve);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
{
@@ -499,24 +498,34 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
}
EXPORT_SYMBOL(__ip_select_ident);
+static void ip_rt_fix_tos(struct flowi4 *fl4)
+{
+ __u8 tos = RT_FL_TOS(fl4);
+
+ fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+ if (tos & RTO_ONLINK)
+ fl4->flowi4_scope = RT_SCOPE_LINK;
+}
+
static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
- const struct sock *sk,
- const struct iphdr *iph,
- int oif, u8 tos,
- u8 prot, u32 mark, int flow_flags)
+ const struct sock *sk, const struct iphdr *iph,
+ int oif, __u8 tos, u8 prot, u32 mark,
+ int flow_flags)
{
+ __u8 scope = RT_SCOPE_UNIVERSE;
+
if (sk) {
const struct inet_sock *inet = inet_sk(sk);
oif = sk->sk_bound_dev_if;
mark = sk->sk_mark;
- tos = RT_CONN_FLAGS(sk);
+ tos = ip_sock_rt_tos(sk);
+ scope = ip_sock_rt_scope(sk);
prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
}
- flowi4_init_output(fl4, oif, mark, tos,
- RT_SCOPE_UNIVERSE, prot,
- flow_flags,
- iph->daddr, iph->saddr, 0, 0,
+
+ flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope,
+ prot, flow_flags, iph->daddr, iph->saddr, 0, 0,
sock_net_uid(net, sk));
}
@@ -526,9 +535,9 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
const struct net *net = dev_net(skb->dev);
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
- u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
u32 mark = skb->mark;
+ __u8 tos = iph->tos;
__build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
}
@@ -544,7 +553,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+ ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
+ ip_sock_rt_scope(sk),
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
@@ -817,9 +827,9 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct net *net = dev_net(skb->dev);
int oif = skb->dev->ifindex;
- u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
u32 mark = skb->mark;
+ __u8 tos = iph->tos;
rt = (struct rtable *) dst;
@@ -936,6 +946,7 @@ static int ip_error(struct sk_buff *skb)
struct inet_peer *peer;
unsigned long now;
struct net *net;
+ SKB_DR(reason);
bool send;
int code;
@@ -955,10 +966,12 @@ static int ip_error(struct sk_buff *skb)
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
case EHOSTUNREACH:
+ SKB_DR_SET(reason, IP_INADDRERRORS);
__IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS);
break;
case ENETUNREACH:
+ SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
}
@@ -974,6 +987,7 @@ static int ip_error(struct sk_buff *skb)
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
+ SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
@@ -1000,7 +1014,7 @@ static int ip_error(struct sk_buff *skb)
if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
-out: kfree_skb(skb);
+out: kfree_skb_reason(skb, reason);
return 0;
}
@@ -1064,8 +1078,8 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
struct rtable *rt;
u32 mark = IP4_REPLY_MARK(net, skb->mark);
- __build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, mark, 0);
+ __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark,
+ 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
@@ -1153,8 +1167,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, 0, 0);
+ __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
@@ -1298,9 +1311,10 @@ static void set_class_tag(struct rtable *rt, u32 tag)
static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
+ struct net *net = dev_net(dst->dev);
unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
- ip_rt_min_advmss);
+ net->ipv4.ip_rt_min_advmss);
return min(advmss, IPV4_MAX_PMTU - header_size);
}
@@ -1384,7 +1398,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
struct fib_info *fi = res->fi;
u32 mtu = 0;
- if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+ if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) ||
fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
mtu = fi->fib_mtu;
@@ -1485,6 +1499,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
struct uncached_list {
spinlock_t lock;
struct list_head head;
+ struct list_head quarantine;
};
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
@@ -1506,7 +1521,7 @@ void rt_del_uncached_list(struct rtable *rt)
struct uncached_list *ul = rt->rt_uncached_list;
spin_lock_bh(&ul->lock);
- list_del(&rt->rt_uncached);
+ list_del_init(&rt->rt_uncached);
spin_unlock_bh(&ul->lock);
}
}
@@ -1521,20 +1536,23 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
void rt_flush_dev(struct net_device *dev)
{
- struct rtable *rt;
+ struct rtable *rt, *safe;
int cpu;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
+ if (list_empty(&ul->head))
+ continue;
+
spin_lock_bh(&ul->lock);
- list_for_each_entry(rt, &ul->head, rt_uncached) {
+ list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) {
if (rt->dst.dev != dev)
continue;
rt->dst.dev = blackhole_netdev;
- dev_replace_track(dev, blackhole_netdev,
- &rt->dst.dev_tracker,
- GFP_ATOMIC);
+ netdev_ref_replace(dev, blackhole_netdev,
+ &rt->dst.dev_tracker, GFP_ATOMIC);
+ list_move(&rt->rt_uncached, &ul->quarantine);
}
spin_unlock_bh(&ul->lock);
}
@@ -1608,12 +1626,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
struct rtable *rt_dst_alloc(struct net_device *dev,
unsigned int flags, u16 type,
- bool nopolicy, bool noxfrm)
+ bool noxfrm)
{
struct rtable *rt;
rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
- (nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
if (rt) {
@@ -1718,8 +1735,11 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (our)
flags |= RTCF_LOCAL;
+ if (IN_DEV_ORCONF(in_dev, NOPOLICY))
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
- IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+ false);
if (!rth)
return -ENOBUFS;
@@ -1735,6 +1755,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
+ skb_dst_drop(skb);
skb_dst_set(skb, &rth->dst);
return 0;
}
@@ -1822,6 +1843,9 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
+ if (IN_DEV_ORCONF(in_dev, NOPOLICY))
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
fnhe = find_exception(nhc, daddr);
if (do_cache) {
if (fnhe)
@@ -1835,7 +1859,6 @@ static int __mkroute_input(struct sk_buff *skb,
}
rth = rt_dst_alloc(out_dev->dev, 0, res->type,
- IN_DEV_ORCONF(in_dev, NOPOLICY),
IN_DEV_ORCONF(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
@@ -1901,7 +1924,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net,
const struct sk_buff *skb,
bool *p_has_inner)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -1930,7 +1953,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net,
const struct sk_buff *skb,
bool has_inner)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
/* We assume the packet carries an encapsulation, but if none was
@@ -1990,7 +2013,7 @@ static u32 fib_multipath_custom_hash_skb(const struct net *net,
static u32 fib_multipath_custom_hash_fl4(const struct net *net,
const struct flowi4 *fl4)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -2020,7 +2043,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
struct flow_keys hash_keys;
u32 mhash = 0;
- switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+ switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) {
case 0:
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -2258,6 +2281,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
/*
* Now we are ready to route packet.
*/
+ fl4.flowi4_l3mdev = 0;
fl4.flowi4_oif = 0;
fl4.flowi4_iif = dev->ifindex;
fl4.flowi4_mark = skb->mark;
@@ -2327,6 +2351,9 @@ brd_input:
RT_CACHE_STAT_INC(in_brd);
local_input:
+ if (IN_DEV_ORCONF(in_dev, NOPOLICY))
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
do_cache &= res->fi && !itag;
if (do_cache) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
@@ -2340,8 +2367,7 @@ local_input:
}
rth = rt_dst_alloc(ip_rt_get_dev(net, res),
- flags | RTCF_LOCAL, res->type,
- IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+ flags | RTCF_LOCAL, res->type, false);
if (!rth)
goto e_nobufs;
@@ -2406,24 +2432,9 @@ martian_source:
goto out;
}
-int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev)
-{
- struct fib_result res;
- int err;
-
- tos &= IPTOS_RT_MASK;
- rcu_read_lock();
- err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
- rcu_read_unlock();
-
- return err;
-}
-EXPORT_SYMBOL(ip_route_input_noref);
-
/* called with rcu_read_lock held */
-int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev, struct fib_result *res)
+static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev, struct fib_result *res)
{
/* Multicast recognition logic is moved from route cache to here.
* The problem was that too many Ethernet cards have broken/missing
@@ -2472,6 +2483,21 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
return ip_route_input_slow(skb, daddr, saddr, tos, dev, res);
}
+int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev)
+{
+ struct fib_result res;
+ int err;
+
+ tos &= IPTOS_RT_MASK;
+ rcu_read_lock();
+ err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
+ rcu_read_unlock();
+
+ return err;
+}
+EXPORT_SYMBOL(ip_route_input_noref);
+
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4, int orig_oif,
@@ -2564,7 +2590,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
add:
rth = rt_dst_alloc(dev_out, flags, type,
- IN_DEV_ORCONF(in_dev, NOPOLICY),
IN_DEV_ORCONF(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -2603,7 +2628,6 @@ add:
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
const struct sk_buff *skb)
{
- __u8 tos = RT_FL_TOS(fl4);
struct fib_result res = {
.type = RTN_UNSPEC,
.fi = NULL,
@@ -2613,9 +2637,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
struct rtable *rth;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
- fl4->flowi4_tos = tos & IPTOS_RT_MASK;
- fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+ ip_rt_fix_tos(fl4);
rcu_read_lock();
rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
@@ -2733,8 +2755,7 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
res->fi = NULL;
res->table = NULL;
if (fl4->flowi4_oif &&
- (ipv4_is_multicast(fl4->daddr) ||
- !netif_index_is_l3_master(net, fl4->flowi4_oif))) {
+ (ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) {
/* Apparently, routing tables are wrong. Assume,
* that the destination is on link.
*
@@ -2821,7 +2842,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
new->output = dst_discard_out;
new->dev = net->loopback_dev;
- dev_hold_track(new->dev, &new->dev_tracker, GFP_ATOMIC);
+ netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC);
rt->rt_is_input = ort->rt_is_input;
rt->rt_iif = ort->rt_iif;
@@ -3379,7 +3400,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
fri.tb_id = table_id;
fri.dst = res.prefix;
fri.dst_len = res.prefixlen;
- fri.tos = fl4.flowi4_tos;
+ fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos);
fri.type = rt->rt_type;
fri.offload = 0;
fri.trap = 0;
@@ -3392,11 +3413,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (fa->fa_slen == slen &&
fa->tb_id == fri.tb_id &&
- fa->fa_tos == fri.tos &&
+ fa->fa_dscp == fri.dscp &&
fa->fa_info == res.fi &&
fa->fa_type == fri.type) {
- fri.offload = fa->offload;
- fri.trap = fa->trap;
+ fri.offload = READ_ONCE(fa->offload);
+ fri.trap = READ_ONCE(fa->trap);
break;
}
}
@@ -3535,13 +3556,6 @@ static struct ctl_table ipv4_route_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "min_adv_mss",
- .data = &ip_rt_min_advmss,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
{ }
};
@@ -3569,6 +3583,13 @@ static struct ctl_table ipv4_route_netns_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "min_adv_mss",
+ .data = &init_net.ipv4.ip_rt_min_advmss,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ },
};
@@ -3631,6 +3652,7 @@ static __net_init int netns_ip_rt_init(struct net *net)
/* Set default value for namespaceified sysctls */
net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU;
net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES;
+ net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS;
return 0;
}
@@ -3642,7 +3664,7 @@ static __net_init int rt_genid_init(struct net *net)
{
atomic_set(&net->ipv4.rt_genid, 0);
atomic_set(&net->fnhe_genid, 0);
- atomic_set(&net->ipv4.dev_addr_genid, get_random_int());
+ atomic_set(&net->ipv4.dev_addr_genid, get_random_u32());
return 0;
}
@@ -3697,7 +3719,7 @@ int __init ip_rt_init(void)
ip_idents = idents_hash;
- prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents));
+ get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents));
ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents);
@@ -3705,6 +3727,7 @@ int __init ip_rt_init(void)
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
INIT_LIST_HEAD(&ul->head);
+ INIT_LIST_HEAD(&ul->quarantine);
spin_lock_init(&ul->lock);
}
#ifdef CONFIG_IP_ROUTE_CLASSID