summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/inet_diag.c3
-rw-r--r--net/ipv4/inet_hashtables.c16
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_ipv4.c7
-rw-r--r--net/ipv4/tcp_output.c13
-rw-r--r--net/ipv6/addrconf.c8
-rw-r--r--net/smc/af_smc.c14
-rw-r--r--net/vmw_vsock/virtio_transport_common.c25
8 files changed, 58 insertions, 34 deletions
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index af154977904c..f11e997e517b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
struct inet_listen_hashbucket *ilb;
+ struct hlist_nulls_node *node;
num = 0;
ilb = &hashinfo->listening_hash[i];
spin_lock(&ilb->lock);
- sk_for_each(sk, &ilb->head) {
+ sk_nulls_for_each(sk, node, &ilb->nulls_head) {
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 83fb00153018..2bbaaf0c7176 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
struct inet_listen_hashbucket *ilb)
{
struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+ const struct hlist_nulls_node *node;
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
- sk_for_each_rcu(sk2, &ilb->head) {
+ sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
if (sk2 != sk &&
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
@@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
}
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
- hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+ __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
else
- hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+ __sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
inet_hash2(hashinfo, sk);
ilb->count++;
sock_set_flag(sk, SOCK_RCU_FREE);
@@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk)
reuseport_detach_sock(sk);
if (ilb) {
inet_unhash2(hashinfo, sk);
- __sk_del_node_init(sk);
- ilb->count--;
- } else {
- __sk_nulls_del_node_init_rcu(sk);
+ ilb->count--;
}
+ __sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
unlock:
spin_unlock_bh(lock);
@@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
for (i = 0; i < INET_LHTABLE_SIZE; i++) {
spin_lock_init(&h->listening_hash[i].lock);
- INIT_HLIST_HEAD(&h->listening_hash[i].head);
+ INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+ i + LISTENING_NULLS_BASE);
h->listening_hash[i].count = 0;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8a39ee794891..716938313a32 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1087,8 +1087,7 @@ do_error:
goto out;
out_err:
/* make sure we wake any epoll edge trigger waiter */
- if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
- err == -EAGAIN)) {
+ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
sk->sk_write_space(sk);
tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
@@ -1419,8 +1418,7 @@ out_err:
sock_zerocopy_put_abort(uarg, true);
err = sk_stream_error(sk, flags, err);
/* make sure we wake any epoll edge trigger waiter */
- if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
- err == -EAGAIN)) {
+ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
sk->sk_write_space(sk);
tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 92282f98dc82..1c7326e04f9b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
struct inet_listen_hashbucket *ilb;
+ struct hlist_nulls_node *node;
struct sock *sk = cur;
if (!sk) {
get_head:
ilb = &tcp_hashinfo.listening_hash[st->bucket];
spin_lock(&ilb->lock);
- sk = sk_head(&ilb->head);
+ sk = sk_nulls_head(&ilb->nulls_head);
st->offset = 0;
goto get_sk;
}
@@ -2161,9 +2162,9 @@ get_head:
++st->num;
++st->offset;
- sk = sk_next(sk);
+ sk = sk_nulls_next(sk);
get_sk:
- sk_for_each_from(sk) {
+ sk_nulls_for_each_from(sk, node) {
if (!net_eq(sock_net(sk), net))
continue;
if (sk->sk_family == afinfo->family)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b184f03d7437..36902d08473e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
if (tcp_small_queue_check(sk, skb, 0))
break;
+ /* Argh, we hit an empty skb(), presumably a thread
+ * is sleeping in sendmsg()/sk_stream_wait_memory().
+ * We do not want to send a pure-ack packet and have
+ * a strange looking rtx queue with empty packet(s).
+ */
+ if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
+ break;
+
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
@@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size)
*/
void tcp_send_fin(struct sock *sk)
{
- struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
+ struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* Optimization, tack on the FIN if we have one skb in write queue and
@@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk)
* Note: in the latter case, FIN packet will be sent after a timeout,
* as TCP stack thinks it has already been transmitted.
*/
+ tskb = tail;
if (!tskb && tcp_under_memory_pressure(sk))
tskb = skb_rb_last(&sk->tcp_rtx_queue);
@@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk)
TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
- if (tcp_write_queue_empty(sk)) {
+ if (!tail) {
/* This means tskb was already sent.
* Pretend we included the FIN on previous transmit.
* We need to set tp->snd_nxt to the value it would have
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 98d82305d6de..39d861d00377 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
return -EINVAL;
}
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_ipv6_policy, extack);
+
ifm = nlmsg_data(nlh);
if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
return -EINVAL;
}
- if (!netlink_strict_get_check(skb))
- return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
- ifa_ipv6_policy, extack);
-
err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
ifa_ipv6_policy, extack);
if (err)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index b997072c72e5..cee5bf4a9bb9 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
goto out;
sock_hold(&smc->sk); /* sock put in passive closing */
+ if (smc->use_fallback)
+ goto out;
if (flags & O_NONBLOCK) {
if (schedule_work(&smc->connect_work))
smc->connect_nonblock = 1;
@@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
sk->sk_err = smc->clcsock->sk->sk_err;
sk->sk_error_report(sk);
}
- if (rc)
- return rc;
if (optlen < sizeof(int))
return -EINVAL;
@@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
lock_sock(sk);
+ if (rc || smc->use_fallback)
+ goto out;
switch (optname) {
case TCP_ULP:
case TCP_FASTOPEN:
@@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
- if (!smc->use_fallback)
- rc = -EINVAL;
+ rc = -EINVAL;
}
break;
case TCP_NODELAY:
if (sk->sk_state != SMC_INIT &&
sk->sk_state != SMC_LISTEN &&
sk->sk_state != SMC_CLOSED) {
- if (val && !smc->use_fallback)
+ if (val)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
}
@@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
if (sk->sk_state != SMC_INIT &&
sk->sk_state != SMC_LISTEN &&
sk->sk_state != SMC_CLOSED) {
- if (!val && !smc->use_fallback)
+ if (!val)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
}
@@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
default:
break;
}
+out:
release_sock(sk);
return rc;
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index e5ea29c6bca7..6abec3fc81d1 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -34,6 +34,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk)
{
const struct vsock_transport *t = vsock_core_get_transport(vsk);
+ if (WARN_ON(!t))
+ return NULL;
+
return container_of(t, struct virtio_transport, transport);
}
@@ -161,15 +164,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
}
EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
+/* This function can only be used on connecting/connected sockets,
+ * since a socket assigned to a transport is required.
+ *
+ * Do not use on listener sockets!
+ */
static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
struct virtio_vsock_pkt_info *info)
{
u32 src_cid, src_port, dst_cid, dst_port;
+ const struct virtio_transport *t_ops;
struct virtio_vsock_sock *vvs;
struct virtio_vsock_pkt *pkt;
u32 pkt_len = info->pkt_len;
- src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid();
+ t_ops = virtio_transport_get_ops(vsk);
+ if (unlikely(!t_ops))
+ return -EFAULT;
+
+ src_cid = t_ops->transport.get_local_cid();
src_port = vsk->local_addr.svm_port;
if (!info->remote_cid) {
dst_cid = vsk->remote_addr.svm_cid;
@@ -202,7 +215,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
virtio_transport_inc_tx_pkt(vvs, pkt);
- return virtio_transport_get_ops(vsk)->send_pkt(pkt);
+ return t_ops->send_pkt(pkt);
}
static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
@@ -1021,18 +1034,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
int ret;
if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
- virtio_transport_reset(vsk, pkt);
+ virtio_transport_reset_no_sock(t, pkt);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
- virtio_transport_reset(vsk, pkt);
+ virtio_transport_reset_no_sock(t, pkt);
return -ENOMEM;
}
child = vsock_create_connected(sk);
if (!child) {
- virtio_transport_reset(vsk, pkt);
+ virtio_transport_reset_no_sock(t, pkt);
return -ENOMEM;
}
@@ -1054,7 +1067,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
*/
if (ret || vchild->transport != &t->transport) {
release_sock(child);
- virtio_transport_reset(vsk, pkt);
+ virtio_transport_reset_no_sock(t, pkt);
sock_put(child);
return ret;
}