aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fou_core.c29
-rw-r--r--net/ipv4/tcp.c18
-rw-r--r--net/ipv4/tcp_bpf.c2
-rw-r--r--net/ipv4/tcp_input.c28
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/udp_offload.c9
6 files changed, 70 insertions, 30 deletions
diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
index 0abbc413e0fe..78b869b31492 100644
--- a/net/ipv4/fou_core.c
+++ b/net/ipv4/fou_core.c
@@ -50,7 +50,7 @@ struct fou_net {
static inline struct fou *fou_from_sock(struct sock *sk)
{
- return sk->sk_user_data;
+ return rcu_dereference_sk_user_data(sk);
}
static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
@@ -233,9 +233,15 @@ static struct sk_buff *fou_gro_receive(struct sock *sk,
struct sk_buff *skb)
{
const struct net_offload __rcu **offloads;
- u8 proto = fou_from_sock(sk)->protocol;
+ struct fou *fou = fou_from_sock(sk);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
+ u8 proto;
+
+ if (!fou)
+ goto out;
+
+ proto = fou->protocol;
/* We can clear the encap_mark for FOU as we are essentially doing
* one of two possible things. We are either adding an L4 tunnel
@@ -263,14 +269,24 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
int nhoff)
{
const struct net_offload __rcu **offloads;
- u8 proto = fou_from_sock(sk)->protocol;
+ struct fou *fou = fou_from_sock(sk);
const struct net_offload *ops;
- int err = -ENOSYS;
+ u8 proto;
+ int err;
+
+ if (!fou) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ proto = fou->protocol;
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
- if (WARN_ON(!ops || !ops->callbacks.gro_complete))
+ if (WARN_ON(!ops || !ops->callbacks.gro_complete)) {
+ err = -ENOSYS;
goto out;
+ }
err = ops->callbacks.gro_complete(skb, nhoff);
@@ -320,6 +336,9 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
struct gro_remcsum grc;
u8 proto;
+ if (!fou)
+ goto out;
+
skb_gro_remcsum_init(&grc);
off = skb_gro_offset(skb);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e03a342c9162..831a18dc7aa6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4637,6 +4637,13 @@ int tcp_abort(struct sock *sk, int err)
/* Don't race with userspace socket closes such as tcp_close. */
lock_sock(sk);
+ /* Avoid closing the same socket twice. */
+ if (sk->sk_state == TCP_CLOSE) {
+ if (!has_current_bpf_ctx())
+ release_sock(sk);
+ return -ENOENT;
+ }
+
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
inet_csk_listen_stop(sk);
@@ -4646,16 +4653,13 @@ int tcp_abort(struct sock *sk, int err)
local_bh_disable();
bh_lock_sock(sk);
- if (!sock_flag(sk, SOCK_DEAD)) {
- if (tcp_need_reset(sk->sk_state))
- tcp_send_active_reset(sk, GFP_ATOMIC,
- SK_RST_REASON_NOT_SPECIFIED);
- tcp_done_with_error(sk, err);
- }
+ if (tcp_need_reset(sk->sk_state))
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
+ tcp_done_with_error(sk, err);
bh_unlock_sock(sk);
local_bh_enable();
- tcp_write_queue_purge(sk);
if (!has_current_bpf_ctx())
release_sock(sk);
return 0;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 53b0d62fd2c2..fe6178715ba0 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -577,7 +577,7 @@ out_err:
err = sk_stream_error(sk, msg->msg_flags, err);
release_sock(sk);
sk_psock_put(sk, psock);
- return copied ? copied : err;
+ return copied > 0 ? copied : err;
}
enum {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e2b9583ed96a..e37488d3453f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
*/
if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+ u8 old_ratio = tcp_sk(sk)->scaling_ratio;
do_div(val, skb->truesize);
tcp_sk(sk)->scaling_ratio = val ? val : 1;
+
+ if (old_ratio != tcp_sk(sk)->scaling_ratio)
+ WRITE_ONCE(tcp_sk(sk)->window_clamp,
+ tcp_win_from_space(sk, sk->sk_rcvbuf));
}
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
@@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
u64 rcvwin, grow;
int rcvbuf;
@@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk)
rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- if (rcvbuf > sk->sk_rcvbuf) {
- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
-
- /* Make the window clamp follow along. */
- WRITE_ONCE(tp->window_clamp,
- tcp_win_from_space(sk, rcvbuf));
- }
- } else {
- /* Make the window clamp follow along while being bounded
- * by SO_RCVBUF.
- */
- int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
+ if (rcvbuf > sk->sk_rcvbuf) {
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
- if (clamp > tp->window_clamp)
- WRITE_ONCE(tp->window_clamp, clamp);
+ /* Make the window clamp follow along. */
+ WRITE_ONCE(tp->window_clamp,
+ tcp_win_from_space(sk, rcvbuf));
}
}
tp->rcvq_space.space = copied;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd17f25ff288..a4e510846905 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
.bh_lock = INIT_LOCAL_LOCK(bh_lock),
};
+static DEFINE_MUTEX(tcp_exit_batch_mutex);
+
static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
return secure_tcp_seq(ip_hdr(skb)->daddr,
@@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
struct net *net;
+ /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work
+ * and failed setup_net error unwinding path are serialized.
+ *
+ * tcp_twsk_purge() handles twsk in any dead netns, not just those in
+ * net_exit_list, the thread that dismantles a particular twsk must
+ * do so without other thread progressing to refcount_dec_and_test() of
+ * tcp_death_row.tw_refcount.
+ */
+ mutex_lock(&tcp_exit_batch_mutex);
+
tcp_twsk_purge(net_exit_list);
list_for_each_entry(net, net_exit_list, exit_list) {
@@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
tcp_fastopen_ctx_destroy(net);
}
+
+ mutex_unlock(&tcp_exit_batch_mutex);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index bc8a9da750fe..d842303587af 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -279,9 +279,16 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
return ERR_PTR(-EINVAL);
if (unlikely(skb_checksum_start(gso_skb) !=
- skb_transport_header(gso_skb)))
+ skb_transport_header(gso_skb) &&
+ !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)))
return ERR_PTR(-EINVAL);
+ /* We don't know if egress device can segment and checksum the packet
+ * when IPv6 extension headers are present. Fall back to software GSO.
+ */
+ if (gso_skb->ip_summed != CHECKSUM_PARTIAL)
+ features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK);
+
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
Powered by cgit, Gruvboxed by Blaster4385.