summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c1
-rw-r--r--net/ipv4/fib_frontend.c12
-rw-r--r--net/ipv4/fib_semantics.c50
-rw-r--r--net/ipv4/inet_connection_sock.c5
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/ip_tunnel.c9
-rw-r--r--net/ipv4/ipmr_base.c2
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/sysctl_net_ipv4.c6
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/udp.c51
-rw-r--r--net/ipv4/xfrm4_input.c1
-rw-r--r--net/ipv4/xfrm4_mode_transport.c4
14 files changed, 116 insertions, 43 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 20fda8fb8ffd..1fbe2f815474 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
if (encap)
skb_reset_inner_headers(skb);
skb->network_header = (u8 *)iph - skb->head;
+ skb_reset_mac_len(skb);
} while ((skb = skb->next));
out:
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2998b0e47d4b..0113993e9b2c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1243,7 +1243,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct netdev_notifier_changeupper_info *info;
+ struct netdev_notifier_changeupper_info *upper_info = ptr;
+ struct netdev_notifier_info_ext *info_ext = ptr;
struct in_device *in_dev;
struct net *net = dev_net(dev);
unsigned int flags;
@@ -1278,16 +1279,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
fib_sync_up(dev, RTNH_F_LINKDOWN);
else
fib_sync_down_dev(dev, event, false);
- /* fall through */
+ rt_cache_flush(net);
+ break;
case NETDEV_CHANGEMTU:
+ fib_sync_mtu(dev, info_ext->ext.mtu);
rt_cache_flush(net);
break;
case NETDEV_CHANGEUPPER:
- info = ptr;
+ upper_info = ptr;
/* flush all routes if dev is linked to or unlinked from
* an L3 master device (e.g., VRF)
*/
- if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+ if (upper_info->upper_dev &&
+ netif_is_l3_master(upper_info->upper_dev))
fib_disable_ip(dev, NETDEV_DOWN, true);
break;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f3c89ccf14c5..446204ca7406 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1470,6 +1470,56 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
return NOTIFY_DONE;
}
+/* Update the PMTU of exceptions when:
+ * - the new MTU of the first hop becomes smaller than the PMTU
+ * - the old MTU was the same as the PMTU, and it limited discovery of
+ * larger MTUs on the path. With that limit raised, we can now
+ * discover larger MTUs
+ * A special case is locked exceptions, for which the PMTU is smaller
+ * than the minimal accepted PMTU:
+ * - if the new MTU is greater than the PMTU, don't make any change
+ * - otherwise, unlock and set PMTU
+ */
+static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+{
+ struct fnhe_hash_bucket *bucket;
+ int i;
+
+ bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+ if (!bucket)
+ return;
+
+ for (i = 0; i < FNHE_HASH_SIZE; i++) {
+ struct fib_nh_exception *fnhe;
+
+ for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
+ fnhe;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
+ if (fnhe->fnhe_mtu_locked) {
+ if (new <= fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ fnhe->fnhe_mtu_locked = false;
+ }
+ } else if (new < fnhe->fnhe_pmtu ||
+ orig == fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ }
+ }
+ }
+}
+
+void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
+{
+ unsigned int hash = fib_devindex_hashfn(dev->ifindex);
+ struct hlist_head *head = &fib_info_devhash[hash];
+ struct fib_nh *nh;
+
+ hlist_for_each_entry(nh, head, nh_hash) {
+ if (nh->nh_dev == dev)
+ nh_update_mtu(nh, dev->mtu, orig_mtu);
+ }
+}
+
/* Event force Flags Description
* NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host
* NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dfd5009f96ef..15e7f7915a21 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -544,7 +544,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
struct ip_options_rcu *opt;
struct rtable *rt;
- opt = ireq_opt_deref(ireq);
+ rcu_read_lock();
+ opt = rcu_dereference(ireq->ireq_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
@@ -558,11 +559,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
+ rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
+ rcu_read_unlock();
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c0fe5ad996f2..26c36cccabdc 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -149,7 +149,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
- const struct iphdr *iph = ip_hdr(skb);
__be16 *ports;
int end;
@@ -164,7 +163,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
ports = (__be16 *)skb_transport_header(skb);
sin.sin_family = AF_INET;
- sin.sin_addr.s_addr = iph->daddr;
+ sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
sin.sin_port = ports[1];
memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c4f5602308ed..284a22154b4e 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -627,6 +627,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
+ unsigned int inner_nhdr_len = 0;
const struct iphdr *inner_iph;
struct flowi4 fl4;
u8 tos, ttl;
@@ -636,6 +637,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
__be32 dst;
bool connected;
+ /* ensure we can access the inner net header, for several users below */
+ if (skb->protocol == htons(ETH_P_IP))
+ inner_nhdr_len = sizeof(struct iphdr);
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ inner_nhdr_len = sizeof(struct ipv6hdr);
+ if (unlikely(!pskb_may_pull(skb, inner_nhdr_len)))
+ goto tx_error;
+
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
connected = (tunnel->parms.iph.daddr != 0);
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 1ad9aa62a97b..eab8cd5ec2f5 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -296,8 +296,6 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
next_entry:
e++;
}
- e = 0;
- s_e = 0;
spin_lock_bh(lock);
list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b678466da451..8501554e96a4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1001,21 +1001,22 @@ out: kfree_skb(skb);
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
+ u32 old_mtu = ipv4_mtu(dst);
struct fib_result res;
bool lock = false;
if (ip_mtu_locked(dst))
return;
- if (ipv4_mtu(dst) < mtu)
+ if (old_mtu < mtu)
return;
if (mtu < ip_rt_min_pmtu) {
lock = true;
- mtu = ip_rt_min_pmtu;
+ mtu = min(old_mtu, ip_rt_min_pmtu);
}
- if (rt->rt_pmtu == mtu &&
+ if (rt->rt_pmtu == mtu && !lock &&
time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
return;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b92f422f2fa8..891ed2f91467 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,6 +48,7 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static int comp_sack_nr_max = 255;
+static u32 u32_max_div_HZ = UINT_MAX / HZ;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -745,9 +746,10 @@ static struct ctl_table ipv4_net_table[] = {
{
.procname = "tcp_probe_interval",
.data = &init_net.ipv4.sysctl_tcp_probe_interval,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(u32),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_douintvec_minmax,
+ .extra2 = &u32_max_div_HZ,
},
{
.procname = "igmp_link_local_mcast_reports",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4cf2f7bb2802..47e08c1b5bc3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6009,11 +6009,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
if (th->fin)
goto discard;
/* It is possible that we process SYN packets from backlog,
- * so we need to make sure to disable BH right there.
+ * so we need to make sure to disable BH and RCU right there.
*/
+ rcu_read_lock();
local_bh_disable();
acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
local_bh_enable();
+ rcu_read_unlock();
if (!acceptable)
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 44c09eddbb78..cd426313a298 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -943,9 +943,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
+ rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq_opt_deref(ireq));
+ rcu_dereference(ireq->ireq_opt));
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f4e35b2ff8b8..c32a4c16b7ff 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1627,7 +1627,7 @@ busy_check:
*err = error;
return NULL;
}
-EXPORT_SYMBOL_GPL(__skb_recv_udp);
+EXPORT_SYMBOL(__skb_recv_udp);
/*
* This should be easy, if there is something there we
@@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
inet_compute_pseudo);
}
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+ struct udphdr *uh)
+{
+ int ret;
+
+ if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+ skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ inet_compute_pseudo);
+
+ ret = udp_queue_rcv_skb(sk, skb);
+
+ /* a return value > 0 means to resubmit the input, but
+ * it wants the return to be -protocol, or 0
+ */
+ if (ret > 0)
+ return -ret;
+ return 0;
+}
+
/*
* All we need to do is get the socket, and then do a checksum.
*/
@@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (unlikely(sk->sk_rx_dst != dst))
udp_sk_rx_dst_set(sk, dst);
- ret = udp_queue_rcv_skb(sk, skb);
+ ret = udp_unicast_rcv_skb(sk, skb, uh);
sock_put(sk);
- /* a return value > 0 means to resubmit the input, but
- * it wants the return to be -protocol, or 0
- */
- if (ret > 0)
- return -ret;
- return 0;
+ return ret;
}
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
@@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
saddr, daddr, udptable, proto);
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
- if (sk) {
- int ret;
-
- if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
- skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
- inet_compute_pseudo);
-
- ret = udp_queue_rcv_skb(sk, skb);
-
- /* a return value > 0 means to resubmit the input, but
- * it wants the return to be -protocol, or 0
- */
- if (ret > 0)
- return -ret;
- return 0;
- }
+ if (sk)
+ return udp_unicast_rcv_skb(sk, skb, uh);
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index bcfc00e88756..f8de2482a529 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) {
skb_mac_header_rebuild(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 3d36644890bb..1ad2c2c4e250 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
@@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
skb->network_header = skb->transport_header;
}
ip_hdr(skb)->tot_len = htons(skb->len + ihl);
- if (!xo || !(xo->flags & XFRM_GRO))
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(skb);
return 0;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-11 23:59:04 +0300