summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_semantics.c5
-rw-r--r--net/ipv4/inet_diag.c3
-rw-r--r--net/ipv4/inet_fragment.c3
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_gre.c5
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c13
-rw-r--r--net/ipv4/ip_tunnel.c13
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c7
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c35
-rw-r--r--net/ipv4/netfilter/ipt_ECN.c12
-rw-r--r--net/ipv4/netfilter/ipt_REJECT.c4
-rw-r--r--net/ipv4/netfilter/ipt_rpfilter.c6
-rw-r--r--net/ipv4/netfilter/nf_flow_table_ipv4.c3
-rw-r--r--net/ipv4/route.c67
-rw-r--r--net/ipv4/tcp.c1
-rw-r--r--net/ipv4/tcp_illinois.c2
-rw-r--r--net/ipv4/tcp_input.c24
-rw-r--r--net/ipv4/tcp_output.c34
-rw-r--r--net/ipv4/tcp_timer.c1
-rw-r--r--net/ipv4/udp.c5
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c3
-rw-r--r--net/ipv4/xfrm4_output.c3
-rw-r--r--net/ipv4/xfrm4_policy.c5
25 files changed, 166 insertions, 96 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c586597da20d..7d36a950d961 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -646,6 +646,11 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
fi->fib_nh, cfg, extack))
return 1;
}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ if (cfg->fc_flow &&
+ cfg->fc_flow != fi->fib_nh->nh_tclassid)
+ return 1;
+#endif
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
(!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
return 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index a383f299ce24..4e5bc4b2f14e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex);
static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
{
if (!inet_diag_table[proto])
- request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, AF_INET, proto);
+ sock_load_diag_module(AF_INET, proto);
mutex_lock(&inet_diag_table_mutex);
if (!inet_diag_table[proto])
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 26a3d0315728..e8ec28999f5c 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -119,6 +119,9 @@ out:
static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
{
+ if (!hlist_unhashed(&q->list_evictor))
+ return false;
+
return q->net->low_thresh == 0 ||
frag_mem_limit(q->net) >= q->net->low_thresh;
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 2dd21c3281a1..b54b948b0596 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
if (skb->ignore_df)
return false;
- if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
return true;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 45d97e9b2759..0901de42ed85 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev)
t_hlen = tunnel->hlen + sizeof(struct iphdr);
- dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
- dev->mtu = ETH_DATA_LEN - t_hlen - 4;
-
dev->features |= GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
@@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev)
erspan_hdr_len(tunnel->erspan_ver);
t_hlen = tunnel->hlen + sizeof(struct iphdr);
- dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4;
- dev->mtu = ETH_DATA_LEN - t_hlen - 4;
dev->features |= GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e8e675be60ec..66340ab750e6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
/* common case: seglen is <= mtu
*/
- if (skb_gso_validate_mtu(skb, mtu))
+ if (skb_gso_validate_network_len(skb, mtu))
return ip_finish_output2(net, sk, skb);
/* Slowpath - GSO segment length exceeds the egress MTU.
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 008be04ac1cc..74c962b9b09c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
return -EINVAL;
- ipc->oif = src_info->ipi6_ifindex;
+ if (src_info->ipi6_ifindex)
+ ipc->oif = src_info->ipi6_ifindex;
ipc->addr = src_info->ipi6_addr.s6_addr32[3];
continue;
}
@@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
return -EINVAL;
info = (struct in_pktinfo *)CMSG_DATA(cmsg);
- ipc->oif = info->ipi_ifindex;
+ if (info->ipi_ifindex)
+ ipc->oif = info->ipi_ifindex;
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
@@ -1567,10 +1569,7 @@ int ip_getsockopt(struct sock *sk, int level,
if (get_user(len, optlen))
return -EFAULT;
- lock_sock(sk);
- err = nf_getsockopt(sk, PF_INET, optname, optval,
- &len);
- release_sock(sk);
+ err = nf_getsockopt(sk, PF_INET, optname, optval, &len);
if (err >= 0)
err = put_user(len, optlen);
return err;
@@ -1602,9 +1601,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
if (get_user(len, optlen))
return -EFAULT;
- lock_sock(sk);
err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
- release_sock(sk);
if (err >= 0)
err = put_user(len, optlen);
return err;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d786a8441bce..6d21068f9b55 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
}
- if (tunnel->fwmark) {
- init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
- tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
- tunnel->fwmark);
- }
- else {
- init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
- tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
- skb->mark);
- }
+ init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
+ tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+ tunnel->fwmark);
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
goto tx_error;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 4ffe302f9b82..e3e420f3ba7b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -252,6 +252,10 @@ unsigned int arpt_do_table(struct sk_buff *skb,
}
if (table_base + v
!= arpt_next_entry(e)) {
+ if (unlikely(stackidx >= private->stacksize)) {
+ verdict = NF_DROP;
+ break;
+ }
jumpstack[stackidx++] = e;
}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 9a71f3149507..e38395a8dcf2 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -330,8 +330,13 @@ ipt_do_table(struct sk_buff *skb,
continue;
}
if (table_base + v != ipt_next_entry(e) &&
- !(e->ip.flags & IPT_F_GOTO))
+ !(e->ip.flags & IPT_F_GOTO)) {
+ if (unlikely(stackidx >= private->stacksize)) {
+ verdict = NF_DROP;
+ break;
+ }
jumpstack[stackidx++] = e;
+ }
e = get_entry(table_base, v);
continue;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 3a84a60f6b39..8a8ae61cea71 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -107,12 +107,6 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
local_bh_disable();
if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
- list_del_rcu(&c->list);
- spin_unlock(&cn->lock);
- local_bh_enable();
-
- unregister_netdevice_notifier(&c->notifier);
-
/* In case anyone still accesses the file, the open/close
* functions are also incrementing the refcount on their own,
* so it's safe to remove the entry even if it's in use. */
@@ -120,6 +114,12 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
if (cn->procdir)
proc_remove(c->pde);
#endif
+ list_del_rcu(&c->list);
+ spin_unlock(&cn->lock);
+ local_bh_enable();
+
+ unregister_netdevice_notifier(&c->notifier);
+
return;
}
local_bh_enable();
@@ -154,8 +154,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
#endif
if (unlikely(!refcount_inc_not_zero(&c->refcount)))
c = NULL;
- else if (entry)
- refcount_inc(&c->entries);
+ else if (entry) {
+ if (unlikely(!refcount_inc_not_zero(&c->entries))) {
+ clusterip_config_put(c);
+ c = NULL;
+ }
+ }
}
rcu_read_unlock_bh();
@@ -228,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
c->hash_mode = i->hash_mode;
c->hash_initval = i->hash_initval;
refcount_set(&c->refcount, 1);
- refcount_set(&c->entries, 1);
spin_lock_bh(&cn->lock);
if (__clusterip_config_find(net, ip)) {
@@ -259,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
c->notifier.notifier_call = clusterip_netdev_event;
err = register_netdevice_notifier(&c->notifier);
- if (!err)
+ if (!err) {
+ refcount_set(&c->entries, 1);
return c;
+ }
#ifdef CONFIG_PROC_FS
proc_remove(c->pde);
@@ -269,7 +274,7 @@ err:
spin_lock_bh(&cn->lock);
list_del_rcu(&c->list);
spin_unlock_bh(&cn->lock);
- kfree(c);
+ clusterip_config_put(c);
return ERR_PTR(err);
}
@@ -492,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
return PTR_ERR(config);
}
}
- cipinfo->config = config;
ret = nf_ct_netns_get(par->net, par->family);
- if (ret < 0)
+ if (ret < 0) {
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
+ clusterip_config_entry_put(par->net, config);
+ clusterip_config_put(config);
+ return ret;
+ }
if (!par->net->xt.clusterip_deprecated_warning) {
pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, "
@@ -505,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
par->net->xt.clusterip_deprecated_warning = true;
}
+ cipinfo->config = config;
return ret;
}
diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c
index 270765236f5e..aaaf9a81fbc9 100644
--- a/net/ipv4/netfilter/ipt_ECN.c
+++ b/net/ipv4/netfilter/ipt_ECN.c
@@ -98,17 +98,15 @@ static int ecn_tg_check(const struct xt_tgchk_param *par)
const struct ipt_ECN_info *einfo = par->targinfo;
const struct ipt_entry *e = par->entryinfo;
- if (einfo->operation & IPT_ECN_OP_MASK) {
- pr_info("unsupported ECN operation %x\n", einfo->operation);
+ if (einfo->operation & IPT_ECN_OP_MASK)
return -EINVAL;
- }
- if (einfo->ip_ect & ~IPT_ECN_IP_MASK) {
- pr_info("new ECT codepoint %x out of mask\n", einfo->ip_ect);
+
+ if (einfo->ip_ect & ~IPT_ECN_IP_MASK)
return -EINVAL;
- }
+
if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) &&
(e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) {
- pr_info("cannot use TCP operations on a non-tcp rule\n");
+ pr_info_ratelimited("cannot use operation on non-tcp rule\n");
return -EINVAL;
}
return 0;
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 8bd0d7b26632..e8bed3390e58 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -74,13 +74,13 @@ static int reject_tg_check(const struct xt_tgchk_param *par)
const struct ipt_entry *e = par->entryinfo;
if (rejinfo->with == IPT_ICMP_ECHOREPLY) {
- pr_info("ECHOREPLY no longer supported.\n");
+ pr_info_ratelimited("ECHOREPLY no longer supported.\n");
return -EINVAL;
} else if (rejinfo->with == IPT_TCP_RESET) {
/* Must specify that it's a TCP packet */
if (e->ip.proto != IPPROTO_TCP ||
(e->ip.invflags & XT_INV_PROTO)) {
- pr_info("TCP_RESET invalid for non-tcp\n");
+ pr_info_ratelimited("TCP_RESET invalid for non-tcp\n");
return -EINVAL;
}
}
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 37fb9552e858..fd01f13c896a 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -105,14 +105,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par)
const struct xt_rpfilter_info *info = par->matchinfo;
unsigned int options = ~XT_RPFILTER_OPTION_MASK;
if (info->flags & options) {
- pr_info("unknown options encountered");
+ pr_info_ratelimited("unknown options\n");
return -EINVAL;
}
if (strcmp(par->table, "mangle") != 0 &&
strcmp(par->table, "raw") != 0) {
- pr_info("match only valid in the \'raw\' "
- "or \'mangle\' tables, not \'%s\'.\n", par->table);
+ pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n",
+ par->table);
return -EINVAL;
}
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 25d2975da156..0cd46bffa469 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
default:
return -1;
}
+ csum_replace4(&iph->check, addr, new_addr);
return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
}
@@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
return false;
- if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
return true;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 49cc1c1df1ba..299e247b2032 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -128,10 +128,11 @@ 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_mtu_expires __read_mostly = 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
+static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+
/*
* Interface to generic destination cache.
*/
@@ -633,6 +634,7 @@ static inline u32 fnhe_hashfun(__be32 daddr)
static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
{
rt->rt_pmtu = fnhe->fnhe_pmtu;
+ rt->rt_mtu_locked = fnhe->fnhe_mtu_locked;
rt->dst.expires = fnhe->fnhe_expires;
if (fnhe->fnhe_gw) {
@@ -643,7 +645,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
}
static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
- u32 pmtu, unsigned long expires)
+ u32 pmtu, bool lock, unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
@@ -680,8 +682,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_genid = genid;
if (gw)
fnhe->fnhe_gw = gw;
- if (pmtu)
+ if (pmtu) {
fnhe->fnhe_pmtu = pmtu;
+ fnhe->fnhe_mtu_locked = lock;
+ }
fnhe->fnhe_expires = max(1UL, expires);
/* Update all cached dsts too */
rt = rcu_dereference(fnhe->fnhe_rth_input);
@@ -705,6 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
+ fnhe->fnhe_mtu_locked = lock;
fnhe->fnhe_expires = expires;
/* Exception created; mark the cached routes for the nexthop
@@ -786,7 +791,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, new_gw,
- 0, jiffies + ip_rt_gc_timeout);
+ 0, false,
+ jiffies + ip_rt_gc_timeout);
}
if (kill_route)
rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -930,14 +936,23 @@ out_put_peer:
static int ip_error(struct sk_buff *skb)
{
- struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
struct rtable *rt = skb_rtable(skb);
+ struct net_device *dev = skb->dev;
+ struct in_device *in_dev;
struct inet_peer *peer;
unsigned long now;
struct net *net;
bool send;
int code;
+ if (netif_is_l3_master(skb->dev)) {
+ dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+ if (!dev)
+ goto out;
+ }
+
+ in_dev = __in_dev_get_rcu(dev);
+
/* IP on this device is disabled. */
if (!in_dev)
goto out;
@@ -999,15 +1014,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
struct fib_result res;
+ bool lock = false;
- if (dst_metric_locked(dst, RTAX_MTU))
+ if (ip_mtu_locked(dst))
return;
if (ipv4_mtu(dst) < mtu)
return;
- if (mtu < ip_rt_min_pmtu)
+ if (mtu < ip_rt_min_pmtu) {
+ lock = true;
mtu = ip_rt_min_pmtu;
+ }
if (rt->rt_pmtu == mtu &&
time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
@@ -1017,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
struct fib_nh *nh = &FIB_RES_NH(res);
- update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
+ update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
jiffies + ip_rt_mtu_expires);
}
rcu_read_unlock();
@@ -1270,7 +1288,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = READ_ONCE(dst->dev->mtu);
- if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
+ if (unlikely(ip_mtu_locked(dst))) {
if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
@@ -1383,7 +1401,7 @@ struct uncached_list {
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
-static void rt_add_uncached_list(struct rtable *rt)
+void rt_add_uncached_list(struct rtable *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
@@ -1394,14 +1412,8 @@ static void rt_add_uncached_list(struct rtable *rt)
spin_unlock_bh(&ul->lock);
}
-static void ipv4_dst_destroy(struct dst_entry *dst)
+void rt_del_uncached_list(struct rtable *rt)
{
- struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
- struct rtable *rt = (struct rtable *) dst;
-
- if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
- kfree(p);
-
if (!list_empty(&rt->rt_uncached)) {
struct uncached_list *ul = rt->rt_uncached_list;
@@ -1411,6 +1423,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
}
}
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+ struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
+ struct rtable *rt = (struct rtable *)dst;
+
+ if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
+ kfree(p);
+
+ rt_del_uncached_list(rt);
+}
+
void rt_flush_dev(struct net_device *dev)
{
struct net *net = dev_net(dev);
@@ -1506,6 +1529,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
rt->rt_is_input = 0;
rt->rt_iif = 0;
rt->rt_pmtu = 0;
+ rt->rt_mtu_locked = 0;
rt->rt_gateway = 0;
rt->rt_uses_gateway = 0;
rt->rt_table_id = 0;
@@ -1826,6 +1850,8 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
return skb_get_hash_raw(skb) >> 1;
memset(&hash_keys, 0, sizeof(hash_keys));
skb_flow_dissect_flow_keys(skb, &keys, flag);
+
+ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
hash_keys.ports.src = keys.ports.src;
@@ -2529,6 +2555,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_is_input = ort->rt_is_input;
rt->rt_iif = ort->rt_iif;
rt->rt_pmtu = ort->rt_pmtu;
+ rt->rt_mtu_locked = ort->rt_mtu_locked;
rt->rt_genid = rt_genid_ipv4(net);
rt->rt_flags = ort->rt_flags;
@@ -2631,6 +2658,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
if (rt->rt_pmtu && expires)
metrics[RTAX_MTU - 1] = rt->rt_pmtu;
+ if (rt->rt_mtu_locked && expires)
+ metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU);
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
@@ -2816,6 +2845,7 @@ void ip_rt_multicast_event(struct in_device *in_dev)
static int ip_rt_gc_interval __read_mostly = 60 * HZ;
static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_gc_elasticity __read_mostly = 8;
+static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU;
static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write,
void __user *buffer,
@@ -2931,7 +2961,8 @@ static struct ctl_table ipv4_route_table[] = {
.data = &ip_rt_min_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &ip_min_valid_pmtu,
},
{
.procname = "min_adv_mss",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 48636aee23c3..8b8059b7af4d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3566,6 +3566,7 @@ int tcp_abort(struct sock *sk, int err)
bh_unlock_sock(sk);
local_bh_enable();
+ tcp_write_queue_purge(sk);
release_sock(sk);
return 0;
}
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 7c843578f233..faddf4f9a707 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -6,7 +6,7 @@
* The algorithm is described in:
* "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm
* for High-Speed Networks"
- * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf
+ * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf
*
* Implemented from description in paper and ns-2 simulation.
* Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org>
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 575d3c1fb6e8..9a1b3c1c1c14 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk)
/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
- *
- * In theory F-RTO can be used repeatedly during loss recovery.
- * In practice this interacts badly with broken middle-boxes that
- * falsely raise the receive window, which results in repeated
- * timeouts and stop-and-go behavior.
*/
tp->frto = net->ipv4.sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
@@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
tcp_try_undo_loss(sk, false))
return;
- /* The ACK (s)acks some never-retransmitted data meaning not all
- * the data packets before the timeout were lost. Therefore we
- * undo the congestion window and state. This is essentially
- * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
- * a retransmitted skb is permantly marked, we can apply such an
- * operation even if F-RTO was not used.
- */
- if ((flag & FLAG_ORIG_SACK_ACKED) &&
- tcp_try_undo_loss(sk, tp->undo_marker))
- return;
-
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
+ return;
+
if (after(tp->snd_nxt, tp->high_seq)) {
if (flag & FLAG_DATA_SACKED || is_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
@@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk)
/* This barrier is coupled with smp_rmb() in tcp_poll() */
smp_wmb();
+ tcp_write_queue_purge(sk);
tcp_done(sk);
if (!sock_flag(sk, SOCK_DEAD))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e9f985e42405..6818042cd8a9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1730,7 +1730,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
*/
segs = max_t(u32, bytes / mss_now, min_tso_segs);
- return min_t(u32, segs, sk->sk_gso_max_segs);
+ return segs;
}
EXPORT_SYMBOL(tcp_tso_autosize);
@@ -1742,9 +1742,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
- return tso_segs ? :
- tcp_tso_autosize(sk, mss_now,
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+ if (!tso_segs)
+ tso_segs = tcp_tso_autosize(sk, mss_now,
+ sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+ return min_t(u32, tso_segs, sk->sk_gso_max_segs);
}
/* Returns the portion of skb which can be sent right away */
@@ -2027,6 +2028,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
}
}
+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
+{
+ struct sk_buff *skb, *next;
+
+ skb = tcp_send_head(sk);
+ tcp_for_write_queue_from_safe(skb, next, sk) {
+ if (len <= skb->len)
+ break;
+
+ if (unlikely(TCP_SKB_CB(skb)->eor))
+ return false;
+
+ len -= skb->len;
+ }
+
+ return true;
+}
+
/* Create a new MTU probe if we are ready.
* MTU probe is regularly attempting to increase the path MTU by
* deliberately sending larger packets. This discovers routing
@@ -2099,6 +2118,9 @@ static int tcp_mtu_probe(struct sock *sk)
return 0;
}
+ if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
+ return -1;
+
/* We're allowed to probe. Build it now. */
nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
@@ -2134,6 +2156,10 @@ static int tcp_mtu_probe(struct sock *sk)
/* We've eaten all the data from this skb.
* Throw it away. */
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ /* If this is the last SKB we copy and eor is set
+ * we need to propagate it to the new skb.
+ */
+ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
} else {
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 71fc60f1b326..f7d944855f8e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk)
sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
sk->sk_error_report(sk);
+ tcp_write_queue_purge(sk);
tcp_done(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bfaefe560b5c..e5ef7c38c934 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2024,6 +2024,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
err = udplite_checksum_init(skb, uh);
if (err)
return err;
+
+ if (UDP_SKB_CB(skb)->partial_cov) {
+ skb->csum = inet_compute_pseudo(skb, proto);
+ return 0;
+ }
}
/* Note, we are only interested in != 0 or == 0, thus the
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 63faeee989a9..2a9764bd1719 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
- eth_hdr(skb)->h_proto = skb->protocol;
+ if (skb->mac_len)
+ eth_hdr(skb)->h_proto = skb->protocol;
err = 0;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 94b8702603bc..be980c195fc5 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
mtu = dst_mtu(skb_dst(skb));
if ((!skb_is_gso(skb) && skb->len > mtu) ||
- (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) {
+ (skb_is_gso(skb) &&
+ !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
skb->protocol = htons(ETH_P_IP);
if (skb->sk)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 05017e2c849c..fbebda67ac1b 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,8 +100,10 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+ xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
xdst->u.rt.rt_table_id = rt->rt_table_id;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
+ rt_add_uncached_list(&xdst->u.rt);
return 0;
}
@@ -241,7 +243,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
dst_destroy_metrics_generic(dst);
-
+ if (xdst->u.rt.rt_uncached_list)
+ rt_del_uncached_list(&xdst->u.rt);
xfrm_dst_destroy(xdst);
}
generated by cgit (git 2.34.1) at 2024-05-25 05:18:10 +0000