summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c3
-rw-r--r--net/ipv4/inet_hashtables.c16
-rw-r--r--net/ipv4/ip_gre.c4
-rw-r--r--net/ipv4/ip_tunnel.c2
-rw-r--r--net/ipv4/ip_vti.c6
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c8
-rw-r--r--net/ipv4/tcp_bbr.c3
-rw-r--r--net/ipv4/tcp_ipv4.c7
-rw-r--r--net/ipv4/tcp_output.c20
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv4/xfrm4_policy.c5
13 files changed, 52 insertions, 35 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e4c6e8b40490..18c0d5bffe12 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
if (!dst)
goto out;
}
- dst->ops->update_pmtu(dst, sk, NULL, mtu);
+ dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
dst = __sk_dst_check(sk, 0);
if (!dst)
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/ip_gre.c b/net/ipv4/ip_gre.c
index 572b6307a2df..8274f98c511c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1464,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
[IFLA_GRE_OFLAGS] = { .type = NLA_U16 },
[IFLA_GRE_IKEY] = { .type = NLA_U32 },
[IFLA_GRE_OKEY] = { .type = NLA_U32 },
- [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
- [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) },
+ [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) },
[IFLA_GRE_TTL] = { .type = NLA_U8 },
[IFLA_GRE_TOS] = { .type = NLA_U8 },
[IFLA_GRE_PMTUDISC] = { .type = NLA_U8 },
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 38c02bb62e2c..0fe2a5d3e258 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_valid_dst(skb))
- skb_dst_update_pmtu(skb, mtu);
+ skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index cfb025606793..e90b600c7a25 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
mtu = dst_mtu(dst);
if (skb->len > mtu) {
- skb_dst_update_pmtu(skb, mtu);
+ skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
@@ -580,8 +580,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = {
[IFLA_VTI_LINK] = { .type = NLA_U32 },
[IFLA_VTI_IKEY] = { .type = NLA_U32 },
[IFLA_VTI_OKEY] = { .type = NLA_U32 },
- [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
- [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) },
+ [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) },
[IFLA_VTI_FWMARK] = { .type = NLA_U32 },
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f88c93c38f11..87e979f2b74a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu);
+ struct sk_buff *skb, u32 mtu,
+ bool confirm_neigh);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static void ipv4_dst_destroy(struct dst_entry *dst);
@@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
}
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+ struct sk_buff *skb, u32 mtu,
+ bool confirm_neigh)
{
struct rtable *rt = (struct rtable *) dst;
struct flowi4 fl4;
@@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
}
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+ struct sk_buff *skb, u32 mtu,
+ bool confirm_neigh)
{
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8a39ee794891..d885ba868822 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);
}
@@ -3949,7 +3947,7 @@ void __init tcp_init(void)
BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
- FIELD_SIZEOF(struct sk_buff, cb));
+ sizeof_field(struct sk_buff, cb));
percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 32772d6ded4e..a6545ef0d27b 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
/* Sort of tcp_tso_autosize() but ignoring
* driver provided sk_gso_max_size.
*/
- bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift,
+ bytes = min_t(unsigned long,
+ sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
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..58c92a7d671c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
__skb_unlink(skb, &sk->sk_write_queue);
tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
+ if (tp->highest_sack == NULL)
+ tp->highest_sack = skb;
+
tp->packets_out += tcp_skb_pcount(skb);
if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
@@ -1725,7 +1728,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
u32 bytes, segs;
bytes = min_t(unsigned long,
- sk->sk_pacing_rate >> sk->sk_pacing_shift,
+ sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
/* Goal is to send at least one packet per ms,
@@ -2260,7 +2263,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
limit = max_t(unsigned long,
2 * skb->truesize,
- sk->sk_pacing_rate >> sk->sk_pacing_shift);
+ sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
@@ -2438,6 +2441,14 @@ 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 +3132,7 @@ 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 +3140,7 @@ 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 +3148,7 @@ 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/ipv4/udp.c b/net/ipv4/udp.c
index 4da5758cc718..93a355b6b092 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
* queue contains some other skb
*/
rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
- if (rmem > (size + sk->sk_rcvbuf))
+ if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
goto uncharge_drop;
spin_lock(&list->lock);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 35b84b52b702..9ebd54752e03 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
}
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+ struct sk_buff *skb, u32 mtu,
+ bool confirm_neigh)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
- path->ops->update_pmtu(path, sk, skb, mtu);
+ path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
}
static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-09 22:10:07 +0300