summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c89
1 files changed, 40 insertions, 49 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 84d3d556ed80..b1fcf3e4e1ce 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -65,6 +65,7 @@
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
+#include <net/tcp_ecn.h>
#include <net/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
@@ -74,6 +75,7 @@
#include <net/secure_seq.h>
#include <net/busy_poll.h>
#include <net/rstreason.h>
+#include <net/psp.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
@@ -292,9 +294,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
inet->inet_dport = usin->sin_port;
sk_daddr_set(sk, daddr);
- inet_csk(sk)->icsk_ext_hdr_len = 0;
+ inet_csk(sk)->icsk_ext_hdr_len = psp_sk_overhead(sk);
if (inet_opt)
- inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
+ inet_csk(sk)->icsk_ext_hdr_len += inet_opt->opt.optlen;
tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;
@@ -506,8 +508,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
struct sock *sk;
int err;
- sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
- iph->daddr, th->dest, iph->saddr,
+ sk = __inet_lookup_established(net, iph->daddr, th->dest, iph->saddr,
ntohs(th->source), inet_iif(skb), 0);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
@@ -823,8 +824,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
* Incoming packet is checked with md5 hash with finding key,
* no RST generated if md5 hash doesn't match.
*/
- sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo,
- NULL, 0, ip_hdr(skb)->saddr,
+ sk1 = __inet_lookup_listener(net, NULL, 0, ip_hdr(skb)->saddr,
th->source, ip_hdr(skb)->daddr,
ntohs(th->source), dif, sdif);
/* don't send rst if it can't find key */
@@ -1191,7 +1191,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb)
{
- const struct inet_request_sock *ireq = inet_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct flowi4 fl4;
int err = -1;
struct sk_buff *skb;
@@ -1204,6 +1204,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
+ tcp_rsk(req)->syn_ect_snt = inet_sk(sk)->tos & INET_ECN_MASK;
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
tos = READ_ONCE(inet_sk(sk)->tos);
@@ -1505,9 +1506,9 @@ void tcp_clear_md5_list(struct sock *sk)
md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
- hlist_del_rcu(&key->node);
+ hlist_del(&key->node);
atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
- kfree_rcu(key, rcu);
+ kfree(key);
}
}
@@ -1907,6 +1908,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
enum skb_drop_reason reason;
struct sock *rsk;
+ reason = psp_sk_rx_policy_check(sk, skb);
+ if (reason)
+ goto err_discard;
+
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
struct dst_entry *dst;
@@ -1968,6 +1973,7 @@ csum_err:
reason = SKB_DROP_REASON_TCP_CSUM;
trace_tcp_bad_csum(skb);
TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
+err_discard:
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
goto discard;
}
@@ -1992,8 +1998,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
if (th->doff < sizeof(struct tcphdr) / 4)
return 0;
- sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
- iph->saddr, th->source,
+ sk = __inet_lookup_established(net, iph->saddr, th->source,
iph->daddr, ntohs(th->dest),
skb->skb_iif, inet_sdif(skb));
if (sk) {
@@ -2070,7 +2075,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
(TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)) ||
!tcp_skb_can_collapse_rx(tail, skb) ||
thtail->doff != th->doff ||
- memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
+ memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)) ||
+ /* prior to PSP Rx policy check, retain exact PSP metadata */
+ psp_skb_coalesce_diff(tail, skb))
goto no_coalesce;
__skb_pull(skb, hdrlen);
@@ -2236,8 +2243,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
lookup:
- sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo,
- skb, __tcp_hdrlen(th), th->source,
+ sk = __inet_lookup_skb(skb, __tcp_hdrlen(th), th->source,
th->dest, sdif, &refcounted);
if (!sk)
goto no_tcp_socket;
@@ -2258,7 +2264,7 @@ lookup:
&iph->saddr, &iph->daddr,
AF_INET, dif, sdif);
if (unlikely(drop_reason)) {
- sk_drops_add(sk, skb);
+ sk_drops_skbadd(sk, skb);
reqsk_put(req);
goto discard_it;
}
@@ -2403,7 +2409,7 @@ discard_it:
return 0;
discard_and_relse:
- sk_drops_add(sk, skb);
+ sk_drops_skbadd(sk, skb);
if (refcounted)
sock_put(sk);
goto discard_it;
@@ -2426,9 +2432,7 @@ do_time_wait:
&drop_reason);
switch (tw_status) {
case TCP_TW_SYN: {
- struct sock *sk2 = inet_lookup_listener(net,
- net->ipv4.tcp_death_row.hashinfo,
- skb, __tcp_hdrlen(th),
+ struct sock *sk2 = inet_lookup_listener(net, skb, __tcp_hdrlen(th),
iph->saddr, th->source,
iph->daddr, th->dest,
inet_iif(skb),
@@ -2441,6 +2445,10 @@ do_time_wait:
__this_cpu_write(tcp_tw_isn, isn);
goto process;
}
+
+ drop_reason = psp_twsk_rx_policy_check(inet_twsk(sk), skb);
+ if (drop_reason)
+ break;
}
/* to ACK */
fallthrough;
@@ -2459,7 +2467,6 @@ do_time_wait:
static struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp_timewait_sock),
- .twsk_destructor= tcp_twsk_destructor,
};
void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
@@ -2501,6 +2508,13 @@ static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
.ao_calc_key_sk = tcp_v4_ao_calc_key_sk,
#endif
};
+
+static void tcp4_destruct_sock(struct sock *sk)
+{
+ tcp_md5_destruct_sock(sk);
+ tcp_ao_destroy_sock(sk, false);
+ inet_sock_destruct(sk);
+}
#endif
/* NOTE: A lot of things set to zero explicitly by call to
@@ -2516,23 +2530,12 @@ static int tcp_v4_init_sock(struct sock *sk)
#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific;
+ sk->sk_destruct = tcp4_destruct_sock;
#endif
return 0;
}
-#ifdef CONFIG_TCP_MD5SIG
-static void tcp_md5sig_info_free_rcu(struct rcu_head *head)
-{
- struct tcp_md5sig_info *md5sig;
-
- md5sig = container_of(head, struct tcp_md5sig_info, rcu);
- kfree(md5sig);
- static_branch_slow_dec_deferred(&tcp_md5_needed);
- tcp_md5_release_sigpool();
-}
-#endif
-
static void tcp_release_user_frags(struct sock *sk)
{
#ifdef CONFIG_PAGE_POOL
@@ -2569,19 +2572,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* Cleans up our, hopefully empty, out_of_order_queue. */
skb_rbtree_purge(&tp->out_of_order_queue);
-#ifdef CONFIG_TCP_MD5SIG
- /* Clean up the MD5 key list, if any */
- if (tp->md5sig_info) {
- struct tcp_md5sig_info *md5sig;
-
- md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
- tcp_clear_md5_list(sk);
- call_rcu(&md5sig->rcu, tcp_md5sig_info_free_rcu);
- rcu_assign_pointer(tp->md5sig_info, NULL);
- }
-#endif
- tcp_ao_destroy_sock(sk, false);
-
/* Clean up a referenced TCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash)
inet_put_port(sk);
@@ -2958,9 +2948,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
- icsk->icsk_retransmits,
+ READ_ONCE(icsk->icsk_retransmits),
from_kuid_munged(seq_user_ns(f), sk_uid(sk)),
- icsk->icsk_probes_out,
+ READ_ONCE(icsk->icsk_probes_out),
sock_i_ino(sk),
refcount_read(&sk->sk_refcnt), sk,
jiffies_to_clock_t(icsk->icsk_rto),
@@ -3524,7 +3514,6 @@ struct proto tcp_prot = {
.leave_memory_pressure = tcp_leave_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
- .orphan_count = &tcp_orphan_count,
.memory_allocated = &net_aligned_data.tcp_memory_allocated,
.per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc,
@@ -3583,7 +3572,9 @@ fallback:
static int __net_init tcp_sk_init(struct net *net)
{
- net->ipv4.sysctl_tcp_ecn = 2;
+ net->ipv4.sysctl_tcp_ecn = TCP_ECN_IN_ECN_OUT_NOECN;
+ net->ipv4.sysctl_tcp_ecn_option = TCP_ACCECN_OPTION_FULL;
+ net->ipv4.sysctl_tcp_ecn_option_beacon = TCP_ACCECN_OPTION_BEACON;
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-03 10:40:59 +0000