summaryrefslogtreecommitdiff
path: root/net/ipv6/udp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/udp.c')
-rw-r--r--net/ipv6/udp.c102
1 files changed, 74 insertions, 28 deletions
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d766fd798ecf..794c13674e8a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
+#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
@@ -66,10 +67,11 @@ static void udpv6_destruct_sock(struct sock *sk)
int udpv6_init_sock(struct sock *sk)
{
- udp_lib_init_sock(sk);
+ int res = udp_lib_init_sock(sk);
+
sk->sk_destruct = udpv6_destruct_sock;
set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
- return 0;
+ return res;
}
INDIRECT_CALLABLE_SCOPE
@@ -170,6 +172,49 @@ static int compute_score(struct sock *sk, const struct net *net,
return score;
}
+/**
+ * udp6_lib_lookup1() - Simplified lookup using primary hash (destination port)
+ * @net: Network namespace
+ * @saddr: Source address, network order
+ * @sport: Source port, network order
+ * @daddr: Destination address, network order
+ * @hnum: Destination port, host order
+ * @dif: Destination interface index
+ * @sdif: Destination bridge port index, if relevant
+ * @udptable: Set of UDP hash tables
+ *
+ * Simplified lookup to be used as fallback if no sockets are found due to a
+ * potential race between (receive) address change, and lookup happening before
+ * the rehash operation. This function ignores SO_REUSEPORT groups while scoring
+ * result sockets, because if we have one, we don't need the fallback at all.
+ *
+ * Called under rcu_read_lock().
+ *
+ * Return: socket with highest matching score if any, NULL if none
+ */
+static struct sock *udp6_lib_lookup1(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned int hnum, int dif, int sdif,
+ const struct udp_table *udptable)
+{
+ unsigned int slot = udp_hashfn(net, hnum, udptable->mask);
+ struct udp_hslot *hslot = &udptable->hash[slot];
+ struct sock *sk, *result = NULL;
+ int score, badness = 0;
+
+ sk_for_each_rcu(sk, &hslot->head) {
+ score = compute_score(sk, net,
+ saddr, sport, daddr, hnum, dif, sdif);
+ if (score > badness) {
+ result = sk;
+ badness = score;
+ }
+ }
+
+ return result;
+}
+
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -216,7 +261,7 @@ rescore:
/* compute_score is too long of a function to be
* inlined, and calling it again here yields
- * measureable overhead for some
+ * measurable overhead for some
* workloads. Work around it by jumping
* backwards to rescore 'result'.
*/
@@ -347,6 +392,13 @@ struct sock *__udp6_lib_lookup(const struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
hslot2, skb);
+ if (!IS_ERR_OR_NULL(result))
+ goto done;
+
+ /* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */
+ result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif,
+ udptable);
+
done:
if (IS_ERR(result))
return NULL;
@@ -398,7 +450,7 @@ struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr
EXPORT_SYMBOL_GPL(udp6_lib_lookup);
#endif
-/* do not use the scratch area len for jumbogram: their length execeeds the
+/* do not use the scratch area len for jumbogram: their length exceeds the
* scratch area space; note that the IP6CB flags is still in the first
* cacheline, so checking for jumbograms is cheap
*/
@@ -428,7 +480,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len, addr_len);
- if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu))
return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
@@ -473,7 +525,7 @@ try_again:
}
if (unlikely(err)) {
if (!peeking) {
- atomic_inc(&sk->sk_drops);
+ udp_drops_inc(sk);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
@@ -536,7 +588,7 @@ csum_copy_err:
SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
@@ -699,7 +751,8 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT) {
if (tunnel) {
ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
- READ_ONCE(sk->sk_mark), sk->sk_uid);
+ READ_ONCE(sk->sk_mark),
+ sk_uid(sk));
} else {
ip6_sk_redirect(skb, sk);
}
@@ -842,10 +895,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
udp_lib_checksum_complete(skb))
goto csum_error;
- if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
- drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+ if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason))
goto drop;
- }
udp_csum_pull_header(skb);
@@ -858,7 +909,7 @@ csum_error:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
drop:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- atomic_inc(&sk->sk_drops);
+ udp_drops_inc(sk);
sk_skb_reason_drop(sk, skb, drop_reason);
return -1;
}
@@ -963,7 +1014,7 @@ start_lookup:
}
nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb)) {
- atomic_inc(&sk->sk_drops);
+ udp_drops_inc(sk);
__UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
IS_UDPLITE(sk));
__UDP6_INC_STATS(net, UDP_MIB_INERRORS,
@@ -998,7 +1049,7 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst));
}
-/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+/* wrapper for udp_queue_rcv_skb taking care of csum conversion and
* return code conversion for ip layer consumption
*/
static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
@@ -1231,7 +1282,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
}
}
-static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+static int udpv6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
int addr_len)
{
if (addr_len < offsetofend(struct sockaddr, sa_family))
@@ -1252,7 +1303,8 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
-static int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int udpv6_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
+ int addr_len)
{
int res;
@@ -1339,9 +1391,9 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
- if (hlen + cork->gso_size > cork->fragsize) {
+ if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
kfree_skb(skb);
- return -EINVAL;
+ return -EMSGSIZE;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
@@ -1444,10 +1496,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
- ipcm6_init(&ipc6);
+ ipcm6_init_sk(&ipc6, sk);
ipc6.gso_size = READ_ONCE(up->gso_size);
- ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
- ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
/* destination address check */
if (sin6) {
@@ -1571,7 +1621,7 @@ do_udp_sendmsg:
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
- fl6->flowi6_uid = sk->sk_uid;
+ fl6->flowi6_uid = sk_uid(sk);
if (msg->msg_controllen) {
opt = &opt_space;
@@ -1653,9 +1703,6 @@ do_udp_sendmsg:
security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
@@ -1701,8 +1748,6 @@ back_from_confirm:
WRITE_ONCE(up->pending, AF_INET6);
do_append_data:
- if (ipc6.dontfrag < 0)
- ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
&ipc6, fl6, dst_rt6_info(dst),
@@ -1782,6 +1827,7 @@ void udpv6_destroy_sock(struct sock *sk)
if (udp_test_bit(ENCAP_ENABLED, sk)) {
static_branch_dec(&udpv6_encap_needed_key);
udp_encap_disable();
+ udp_tunnel_cleanup_gro(sk);
}
}
}
@@ -1879,7 +1925,7 @@ struct proto udpv6_prot = {
.psock_update_sk_prot = udp_bpf_update_proto,
#endif
- .memory_allocated = &udp_memory_allocated,
+ .memory_allocated = &net_aligned_data.udp_memory_allocated,
.per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc,
.sysctl_mem = sysctl_udp_mem,
generated by cgit (git 2.34.1) at 2025-12-24 18:25:42 +0000