summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/bpf_tcp_ca.c2
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/fib_rules.c5
-rw-r--r--net/ipv4/fib_semantics.c53
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/nexthop.c35
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_cubic.c5
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c11
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/udp.c21
15 files changed, 122 insertions, 44 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0189e3cd4a7d..5f70ffdae1b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -154,7 +154,7 @@ void inet_sock_destruct(struct sock *sk)
kfree(rcu_dereference_protected(inet->inet_opt, 1));
dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
- dst_release(sk->sk_rx_dst);
+ dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1));
sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);
@@ -1994,6 +1994,10 @@ static int __init inet_init(void)
ip_init();
+ /* Initialise per-cpu ipv4 mibs */
+ if (init_ipv4_mibs())
+ panic("%s: Cannot init ipv4 mibs\n", __func__);
+
/* Setup TCP slab cache for open requests. */
tcp_init();
@@ -2024,12 +2028,6 @@ static int __init inet_init(void)
if (init_inet_pernet_ops())
pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
- /*
- * Initialise per-cpu ipv4 mibs
- */
-
- if (init_ipv4_mibs())
- pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
ipv4_proc_init();
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 2cf02b4d77fb..4bb9401b0a3f 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -205,6 +205,8 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
offsetof(struct tcp_congestion_ops, release))
return &bpf_sk_getsockopt_proto;
return NULL;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ec73a0d52d3e..323e622ff9b7 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2591,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
free:
kfree(t);
out:
- return -ENOBUFS;
+ return -ENOMEM;
}
static void __devinet_sysctl_unregister(struct net *net,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 9fe13e4f5d08..4d61ddd8a0ec 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1582,7 +1582,7 @@ static int __net_init fib_net_init(struct net *net)
int error;
#ifdef CONFIG_IP_ROUTE_CLASSID
- net->ipv4.fib_num_tclassid_users = 0;
+ atomic_set(&net->ipv4.fib_num_tclassid_users, 0);
#endif
error = ip_fib_net_init(net);
if (error < 0)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index ce54a30c2ef1..d279cb8ac158 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -141,6 +141,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule,
}
INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule,
+ int flags,
struct fib_lookup_arg *arg)
{
struct fib_result *result = (struct fib_result *) arg->result;
@@ -263,7 +264,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
if (tb[FRA_FLOW]) {
rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
if (rule4->tclassid)
- net->ipv4.fib_num_tclassid_users++;
+ atomic_inc(&net->ipv4.fib_num_tclassid_users);
}
#endif
@@ -295,7 +296,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
#ifdef CONFIG_IP_ROUTE_CLASSID
if (((struct fib4_rule *)rule)->tclassid)
- net->ipv4.fib_num_tclassid_users--;
+ atomic_dec(&net->ipv4.fib_num_tclassid_users);
#endif
net->ipv4.fib_has_custom_rules = true;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3364cb9c67e0..92c29ab3d042 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -220,7 +220,7 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
if (fib_nh->nh_tclassid)
- net->ipv4.fib_num_tclassid_users--;
+ atomic_dec(&net->ipv4.fib_num_tclassid_users);
#endif
fib_nh_common_release(&fib_nh->nh_common);
}
@@ -632,7 +632,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
if (nh->nh_tclassid)
- net->ipv4.fib_num_tclassid_users++;
+ atomic_inc(&net->ipv4.fib_num_tclassid_users);
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->fib_nh_weight = nh_weight;
@@ -662,6 +662,19 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
return nhs;
}
+static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla,
+ struct netlink_ext_ack *extack)
+{
+ if (nla_len(nla) < sizeof(*gw)) {
+ NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY");
+ return -EINVAL;
+ }
+
+ *gw = nla_get_in_addr(nla);
+
+ return 0;
+}
+
/* only called when fib_nh is integrated into fib_info */
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
int remaining, struct fib_config *cfg,
@@ -704,7 +717,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
return -EINVAL;
}
if (nla) {
- fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+ ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla,
+ extack);
+ if (ret)
+ goto errout;
+
if (fib_cfg.fc_gw4)
fib_cfg.fc_gw_family = AF_INET;
} else if (nlav) {
@@ -714,10 +731,18 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
}
nla = nla_find(attrs, attrlen, RTA_FLOW);
- if (nla)
+ if (nla) {
+ if (nla_len(nla) < sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+ return -EINVAL;
+ }
fib_cfg.fc_flow = nla_get_u32(nla);
+ }
fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+ /* RTA_ENCAP_TYPE length checked in
+ * lwtunnel_valid_encap_type_attr
+ */
nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
if (nla)
fib_cfg.fc_encap_type = nla_get_u16(nla);
@@ -902,6 +927,7 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
+ int err;
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
nlav = nla_find(attrs, attrlen, RTA_VIA);
@@ -912,12 +938,17 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
}
if (nla) {
+ __be32 gw;
+
+ err = fib_gw_from_attr(&gw, nla, extack);
+ if (err)
+ return err;
+
if (nh->fib_nh_gw_family != AF_INET ||
- nla_get_in_addr(nla) != nh->fib_nh_gw4)
+ gw != nh->fib_nh_gw4)
return 1;
} else if (nlav) {
struct fib_config cfg2;
- int err;
err = fib_gw_from_via(&cfg2, nlav, extack);
if (err)
@@ -940,8 +971,14 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
- if (nla && nla_get_u32(nla) != nh->nh_tclassid)
- return 1;
+ if (nla) {
+ if (nla_len(nla) < sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+ return -EINVAL;
+ }
+ if (nla_get_u32(nla) != nh->nh_tclassid)
+ return 1;
+ }
#endif
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f7fea3a7c5e6..62a67fdc344c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -721,7 +721,7 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req,
sk_node_init(&nreq_sk->sk_node);
nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
#endif
nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index c8fa6e7f7d12..581b5b2d72a5 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -261,6 +261,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
+ r->idiag_expires = 0;
if (inet_diag_msg_attrs_fill(sk, skb, r, ext,
sk_user_ns(NETLINK_CB(cb->skb).sk),
@@ -314,9 +315,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
- } else {
- r->idiag_timer = 0;
- r->idiag_expires = 0;
}
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 9e8100728d46..5dbd4b5505eb 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
/* if any FIB entries reference this nexthop, any dst entries
* need to be regenerated
*/
-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh,
+ struct nexthop *replaced_nh)
{
struct fib6_info *f6i;
+ struct nh_group *nhg;
+ int i;
if (!list_empty(&nh->fi_list))
rt_cache_flush(net);
list_for_each_entry(f6i, &nh->f6i_list, nh_list)
ipv6_stub->fib6_update_sernum(net, f6i);
+
+ /* if an IPv6 group was replaced, we have to release all old
+ * dsts to make sure all refcounts are released
+ */
+ if (!replaced_nh->is_group)
+ return;
+
+ /* new dsts must use only the new nexthop group */
+ synchronize_net();
+
+ nhg = rtnl_dereference(replaced_nh->nh_grp);
+ for (i = 0; i < nhg->num_nh; i++) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+ struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info);
+
+ if (nhi->family == AF_INET6)
+ ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh);
+ }
}
static int replace_nexthop_grp(struct net *net, struct nexthop *old,
@@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
err = replace_nexthop_single(net, old, new, extack);
if (!err) {
- nh_rt_cache_flush(net, old);
+ nh_rt_cache_flush(net, old, new);
__remove_nexthop(net, new, NULL);
nexthop_put(new);
@@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh,
/* sets nh_dev if successful */
err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
extack);
- if (err)
+ if (err) {
+ /* IPv6 is not enabled, don't call fib6_nh_release */
+ if (err == -EAFNOSUPPORT)
+ goto out;
ipv6_stub->fib6_nh_release(fib6_nh);
- else
+ } else {
nh->nh_flags = fib6_nh->fib_nh_flags;
-
+ }
+out:
return err;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b7796b4cf0a0..2bb28bfd83bf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1758,6 +1758,9 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
{
skb_frag_t *frag;
+ if (unlikely(offset_skb >= skb->len))
+ return NULL;
+
offset_skb -= skb_headlen(skb);
if ((int)offset_skb < 0 || skb_has_frag_list(skb))
return NULL;
@@ -3009,8 +3012,7 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
- dst_release(sk->sk_rx_dst);
- sk->sk_rx_dst = NULL;
+ dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
tcp_saved_syn_free(tp);
tp->compressed_ack = 0;
tp->segs_in = 0;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 5e9d9c51164c..e07837e23b3f 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
return;
if (tcp_in_slow_start(tp)) {
- if (hystart && after(ack, ca->end_seq))
- bictcp_hystart_reset(sk);
acked = tcp_slow_start(tp, acked);
if (!acked)
return;
@@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay)
struct bictcp *ca = inet_csk_ca(sk);
u32 threshold;
+ if (after(tp->snd_una, ca->end_seq))
+ bictcp_hystart_reset(sk);
+
if (hystart_detect & HYSTART_ACK_TRAIN) {
u32 now = bictcp_clock_us(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 246ab7b5e857..0ce46849ec3d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5787,7 +5787,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
trace_tcp_probe(sk, skb);
tcp_mstamp_refresh(tp);
- if (unlikely(!sk->sk_rx_dst))
+ if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 13d868c43284..084df223b5df 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1701,7 +1701,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
struct sock *rsk;
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst;
+
+ dst = rcu_dereference_protected(sk->sk_rx_dst,
+ lockdep_sock_is_held(sk));
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
@@ -1709,8 +1712,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
if (sk->sk_rx_dst_ifindex != skb->skb_iif ||
!INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check,
dst, 0)) {
+ RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
dst_release(dst);
- sk->sk_rx_dst = NULL;
}
}
tcp_rcv_established(sk, skb);
@@ -1786,7 +1789,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk_fullsock(sk)) {
- struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+ struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
@@ -2201,7 +2204,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
if (dst && dst_hold_safe(dst)) {
- sk->sk_rx_dst = dst;
+ rcu_assign_pointer(sk->sk_rx_dst, dst);
sk->sk_rx_dst_ifindex = skb->skb_iif;
}
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index cf913a66df17..7c2d3ac2363a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -829,8 +829,8 @@ int tcp_child_process(struct sock *parent, struct sock *child,
int ret = 0;
int state = child->sk_state;
- /* record NAPI ID of child */
- sk_mark_napi_id(child, skb);
+ /* record sk_napi_id and sk_rx_queue_mapping of child. */
+ sk_mark_napi_id_set(child, skb);
tcp_segs_in(tcp_sk(child), skb);
if (!sock_owned_by_user(child)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 319dd7bbfe33..0cd6b857e7ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -916,7 +916,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
kfree_skb(skb);
return -EINVAL;
}
- if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+ if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
@@ -1807,6 +1807,17 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
skb = skb_recv_udp(sk, 0, 1, &err);
if (!skb)
return err;
+
+ if (udp_lib_checksum_complete(skb)) {
+ __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
+ IS_UDPLITE(sk));
+ __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
+ IS_UDPLITE(sk));
+ atomic_inc(&sk->sk_drops);
+ kfree_skb(skb);
+ continue;
+ }
+
used = recv_actor(desc, skb, 0, skb->len);
if (used <= 0) {
if (!copied)
@@ -2239,7 +2250,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
struct dst_entry *old;
if (dst_hold_safe(dst)) {
- old = xchg(&sk->sk_rx_dst, dst);
+ old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst);
dst_release(old);
return old != dst;
}
@@ -2429,7 +2440,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
struct dst_entry *dst = skb_dst(skb);
int ret;
- if (unlikely(sk->sk_rx_dst != dst))
+ if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp_sk_rx_dst_set(sk, dst);
ret = udp_unicast_rcv_skb(sk, skb, uh);
@@ -2588,7 +2599,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_efree;
- dst = READ_ONCE(sk->sk_rx_dst);
+ dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
@@ -3064,7 +3075,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
{
seq_setwidth(seq, 127);
if (v == SEQ_START_TOKEN)
- seq_puts(seq, " sl local_address rem_address st tx_queue "
+ seq_puts(seq, " sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
"inode ref pointer drops");
else {
generated by cgit (git 2.34.1) at 2024-04-19 05:30:39 +0000