summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig34
-rw-r--r--net/ipv4/af_inet.c6
-rw-r--r--net/ipv4/esp4_offload.c1
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/fou.c1
-rw-r--r--net/ipv4/ip_output.c6
-rw-r--r--net/ipv4/ip_tunnel.c14
-rw-r--r--net/ipv4/netfilter/ip_tables.c15
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c1
-rw-r--r--net/ipv4/netfilter/iptable_filter.c10
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c10
-rw-r--r--net/ipv4/netfilter/iptable_nat.c10
-rw-r--r--net/ipv4/netfilter/iptable_raw.c10
-rw-r--r--net/ipv4/netfilter/iptable_security.c11
-rw-r--r--net/ipv4/netfilter/nf_flow_table_ipv4.c1
-rw-r--r--net/ipv4/netfilter/nft_dup_ipv4.c1
-rw-r--r--net/ipv4/netfilter/nft_fib_ipv4.c1
-rw-r--r--net/ipv4/netfilter/nft_reject_ipv4.c1
-rw-r--r--net/ipv4/tcp_cubic.c5
-rw-r--r--net/ipv4/tcp_input.c80
-rw-r--r--net/ipv4/tcp_output.c12
21 files changed, 165 insertions, 67 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 6ecbb0ced177..e64e59b536d3 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -340,29 +340,31 @@ config NET_FOU_IP_TUNNELS
config INET_AH
tristate "IP: AH transformation"
- select XFRM_ALGO
- select CRYPTO
- select CRYPTO_HMAC
- select CRYPTO_MD5
- select CRYPTO_SHA1
+ select XFRM_AH
help
- Support for IPsec AH.
+ Support for IPsec AH (Authentication Header).
+
+ AH can be used with various authentication algorithms. Besides
+ enabling AH support itself, this option enables the generic
+ implementations of the algorithms that RFC 8221 lists as MUST be
+ implemented. If you need any other algorithms, you'll need to enable
+ them in the crypto API. You should also enable accelerated
+ implementations of any needed algorithms when available.
If unsure, say Y.
config INET_ESP
tristate "IP: ESP transformation"
- select XFRM_ALGO
- select CRYPTO
- select CRYPTO_AUTHENC
- select CRYPTO_HMAC
- select CRYPTO_MD5
- select CRYPTO_CBC
- select CRYPTO_SHA1
- select CRYPTO_DES
- select CRYPTO_ECHAINIV
+ select XFRM_ESP
help
- Support for IPsec ESP.
+ Support for IPsec ESP (Encapsulating Security Payload).
+
+ ESP can be used with various encryption and authentication algorithms.
+ Besides enabling ESP support itself, this option enables the generic
+ implementations of the algorithms that RFC 8221 lists as MUST be
+ implemented. If you need any other algorithms, you'll need to enable
+ them in the crypto API. You should also enable accelerated
+ implementations of any needed algorithms when available.
If unsure, say Y.
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 02aa5cb3a4fd..ea6ed6d487ed 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1432,10 +1432,6 @@ static struct sk_buff *ipip_gso_segment(struct sk_buff *skb,
return inet_gso_segment(skb, features);
}
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *,
- struct sk_buff *));
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
- struct sk_buff *));
struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
{
const struct net_offload *ops;
@@ -1608,8 +1604,6 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
return -EINVAL;
}
-INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *, int));
-INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
int inet_gro_complete(struct sk_buff *skb, int nhoff)
{
__be16 newlen = htons(skb->len - nhoff);
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index d14133eac476..5bda5aeda579 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -361,3 +361,4 @@ module_exit(esp4_offload_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP);
+MODULE_DESCRIPTION("IPV4 GSO/GRO offload support");
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e53871e4a097..1f75dc686b6b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1109,7 +1109,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
if (fl4.flowi4_scope < RT_SCOPE_LINK)
fl4.flowi4_scope = RT_SCOPE_LINK;
- if (table)
+ if (table && table != RT_TABLE_MAIN)
tbl = fib_get_table(net, table);
if (tbl)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index dcc79ff54b41..abd083415f89 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -1304,3 +1304,4 @@ module_init(fou_init);
module_exit(fou_fini);
MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Foo over UDP");
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 090d3097ee15..d946356187ed 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -539,6 +539,12 @@ no_route:
}
EXPORT_SYMBOL(__ip_queue_xmit);
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
+{
+ return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+}
+EXPORT_SYMBOL(ip_queue_xmit);
+
static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
to->pkt_type = from->pkt_type;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index f4f1d11eab50..0c1f36404471 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
__be32 remote, __be32 local,
__be32 key)
{
- unsigned int hash;
struct ip_tunnel *t, *cand = NULL;
struct hlist_head *head;
+ struct net_device *ndev;
+ unsigned int hash;
hash = ip_tunnel_hash(key, remote);
head = &itn->tunnels[hash];
@@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
if (t && t->dev->flags & IFF_UP)
return t;
- if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
- return netdev_priv(itn->fb_tunnel_dev);
+ ndev = READ_ONCE(itn->fb_tunnel_dev);
+ if (ndev && ndev->flags & IFF_UP)
+ return netdev_priv(ndev);
return NULL;
}
@@ -1259,9 +1261,9 @@ void ip_tunnel_uninit(struct net_device *dev)
struct ip_tunnel_net *itn;
itn = net_generic(net, tunnel->ip_tnl_net_id);
- /* fb_tunnel_dev will be unregisted in net-exit call. */
- if (itn->fb_tunnel_dev != dev)
- ip_tunnel_del(itn, netdev_priv(dev));
+ ip_tunnel_del(itn, netdev_priv(dev));
+ if (itn->fb_tunnel_dev == dev)
+ WRITE_ONCE(itn->fb_tunnel_dev, NULL);
dst_cache_reset(&tunnel->dst_cache);
}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c2670eaa74e6..5bf9fa06aee0 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1797,11 +1797,22 @@ out_free:
return ret;
}
+void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops)
+{
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+
+void ipt_unregister_table_exit(struct net *net, struct xt_table *table)
+{
+ __ipt_unregister_table(net, table);
+}
+
void ipt_unregister_table(struct net *net, struct xt_table *table,
const struct nf_hook_ops *ops)
{
if (ops)
- nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ ipt_unregister_table_pre_exit(net, table, ops);
__ipt_unregister_table(net, table);
}
@@ -1958,6 +1969,8 @@ static void __exit ip_tables_fini(void)
EXPORT_SYMBOL(ipt_register_table);
EXPORT_SYMBOL(ipt_unregister_table);
+EXPORT_SYMBOL(ipt_unregister_table_pre_exit);
+EXPORT_SYMBOL(ipt_unregister_table_exit);
EXPORT_SYMBOL(ipt_do_table);
module_init(ip_tables_init);
module_exit(ip_tables_fini);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 748dc3ce58d3..f2984c7eef40 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -118,3 +118,4 @@ module_exit(synproxy_tg4_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Intercept TCP connections and establish them using syncookies");
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 9d54b4017e50..8f7bc1ee7453 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -72,16 +72,24 @@ static int __net_init iptable_filter_net_init(struct net *net)
return 0;
}
+static void __net_exit iptable_filter_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.iptable_filter)
+ ipt_unregister_table_pre_exit(net, net->ipv4.iptable_filter,
+ filter_ops);
+}
+
static void __net_exit iptable_filter_net_exit(struct net *net)
{
if (!net->ipv4.iptable_filter)
return;
- ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops);
+ ipt_unregister_table_exit(net, net->ipv4.iptable_filter);
net->ipv4.iptable_filter = NULL;
}
static struct pernet_operations iptable_filter_net_ops = {
.init = iptable_filter_net_init,
+ .pre_exit = iptable_filter_net_pre_exit,
.exit = iptable_filter_net_exit,
};
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index bb9266ea3785..f703a717ab1d 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -100,15 +100,23 @@ static int __net_init iptable_mangle_table_init(struct net *net)
return ret;
}
+static void __net_exit iptable_mangle_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.iptable_mangle)
+ ipt_unregister_table_pre_exit(net, net->ipv4.iptable_mangle,
+ mangle_ops);
+}
+
static void __net_exit iptable_mangle_net_exit(struct net *net)
{
if (!net->ipv4.iptable_mangle)
return;
- ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops);
+ ipt_unregister_table_exit(net, net->ipv4.iptable_mangle);
net->ipv4.iptable_mangle = NULL;
}
static struct pernet_operations iptable_mangle_net_ops = {
+ .pre_exit = iptable_mangle_net_pre_exit,
.exit = iptable_mangle_net_exit,
};
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index ad33687b7444..b0143b109f25 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -113,16 +113,22 @@ static int __net_init iptable_nat_table_init(struct net *net)
return ret;
}
+static void __net_exit iptable_nat_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.nat_table)
+ ipt_nat_unregister_lookups(net);
+}
+
static void __net_exit iptable_nat_net_exit(struct net *net)
{
if (!net->ipv4.nat_table)
return;
- ipt_nat_unregister_lookups(net);
- ipt_unregister_table(net, net->ipv4.nat_table, NULL);
+ ipt_unregister_table_exit(net, net->ipv4.nat_table);
net->ipv4.nat_table = NULL;
}
static struct pernet_operations iptable_nat_net_ops = {
+ .pre_exit = iptable_nat_net_pre_exit,
.exit = iptable_nat_net_exit,
};
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 69697eb4bfc6..9abfe6bf2cb9 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -67,15 +67,23 @@ static int __net_init iptable_raw_table_init(struct net *net)
return ret;
}
+static void __net_exit iptable_raw_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.iptable_raw)
+ ipt_unregister_table_pre_exit(net, net->ipv4.iptable_raw,
+ rawtable_ops);
+}
+
static void __net_exit iptable_raw_net_exit(struct net *net)
{
if (!net->ipv4.iptable_raw)
return;
- ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops);
+ ipt_unregister_table_exit(net, net->ipv4.iptable_raw);
net->ipv4.iptable_raw = NULL;
}
static struct pernet_operations iptable_raw_net_ops = {
+ .pre_exit = iptable_raw_net_pre_exit,
.exit = iptable_raw_net_exit,
};
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index ac633c1db97e..415c1975d770 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -62,16 +62,23 @@ static int __net_init iptable_security_table_init(struct net *net)
return ret;
}
+static void __net_exit iptable_security_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.iptable_security)
+ ipt_unregister_table_pre_exit(net, net->ipv4.iptable_security,
+ sectbl_ops);
+}
+
static void __net_exit iptable_security_net_exit(struct net *net)
{
if (!net->ipv4.iptable_security)
return;
-
- ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops);
+ ipt_unregister_table_exit(net, net->ipv4.iptable_security);
net->ipv4.iptable_security = NULL;
}
static struct pernet_operations iptable_security_net_ops = {
+ .pre_exit = iptable_security_net_pre_exit,
.exit = iptable_security_net_exit,
};
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index e32e41b99f0f..aba65fe90345 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -34,3 +34,4 @@ module_exit(nf_flow_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NF_FLOWTABLE(AF_INET);
+MODULE_DESCRIPTION("Netfilter flow table support");
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index abf89b972094..bcdb37f86a94 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -107,3 +107,4 @@ module_exit(nft_dup_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup");
+MODULE_DESCRIPTION("IPv4 nftables packet duplication support");
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index ce294113dbcd..03df986217b7 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -210,3 +210,4 @@ module_exit(nft_fib4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_ALIAS_NFT_AF_EXPR(2, "fib");
+MODULE_DESCRIPTION("nftables fib / ip route lookup support");
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index 7e6fd5cde50f..e408f813f5d8 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -71,3 +71,4 @@ module_exit(nft_reject_ipv4_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");
+MODULE_DESCRIPTION("IPv4 packet rejection for nftables");
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 8f8eefd3a3ce..c7bf5b26bf0c 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -432,10 +432,9 @@ static void hystart_update(struct sock *sk, u32 delay)
if (hystart_detect & HYSTART_DELAY) {
/* obtain the minimum delay of more than sampling packets */
+ if (ca->curr_rtt > delay)
+ ca->curr_rtt = delay;
if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
- if (ca->curr_rtt > delay)
- ca->curr_rtt = delay;
-
ca->sample_cnt++;
} else {
if (ca->curr_rtt > ca->delay_min +
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12fda8f27b08..12c26c9565b7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -261,7 +261,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
* cwnd may be very low (even just 1 packet), so we should ACK
* immediately.
*/
- inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+ if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq)
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
}
}
@@ -961,6 +962,15 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
}
}
+/* Updates the delivered and delivered_ce counts */
+static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
+ bool ece_ack)
+{
+ tp->delivered += delivered;
+ if (ece_ack)
+ tp->delivered_ce += delivered;
+}
+
/* This procedure tags the retransmission queue when SACKs arrive.
*
* We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
@@ -1137,6 +1147,7 @@ struct tcp_sacktag_state {
struct rate_sample *rate;
int flag;
unsigned int mss_now;
+ u32 sack_delivered;
};
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1257,7 +1268,8 @@ static u8 tcp_sacktag_one(struct sock *sk,
sacked |= TCPCB_SACKED_ACKED;
state->flag |= FLAG_DATA_SACKED;
tp->sacked_out += pcount;
- tp->delivered += pcount; /* Out-of-order packets delivered */
+ /* Out-of-order packets delivered */
+ state->sack_delivered += pcount;
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
if (tp->lost_skb_hint &&
@@ -1683,7 +1695,8 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
num_sacks, prior_snd_una);
if (found_dup_sack) {
state->flag |= FLAG_DSACKING_ACK;
- tp->delivered++; /* A spurious retransmission is delivered */
+ /* A spurious retransmission is delivered */
+ state->sack_delivered++;
}
/* Eliminate too old ACKs, but take into
@@ -1892,7 +1905,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
/* Emulate SACKs for SACKless connection: account for a new dupack. */
-static void tcp_add_reno_sack(struct sock *sk, int num_dupack)
+static void tcp_add_reno_sack(struct sock *sk, int num_dupack, bool ece_ack)
{
if (num_dupack) {
struct tcp_sock *tp = tcp_sk(sk);
@@ -1903,20 +1916,21 @@ static void tcp_add_reno_sack(struct sock *sk, int num_dupack)
tcp_check_reno_reordering(sk, 0);
delivered = tp->sacked_out - prior_sacked;
if (delivered > 0)
- tp->delivered += delivered;
+ tcp_count_delivered(tp, delivered, ece_ack);
tcp_verify_left_out(tp);
}
}
/* Account for ACK, ACKing some data in Reno Recovery phase. */
-static void tcp_remove_reno_sacks(struct sock *sk, int acked)
+static void tcp_remove_reno_sacks(struct sock *sk, int acked, bool ece_ack)
{
struct tcp_sock *tp = tcp_sk(sk);
if (acked > 0) {
/* One ACK acked hole. The rest eat duplicate ACKs. */
- tp->delivered += max_t(int, acked - tp->sacked_out, 1);
+ tcp_count_delivered(tp, max_t(int, acked - tp->sacked_out, 1),
+ ece_ack);
if (acked - 1 >= tp->sacked_out)
tp->sacked_out = 0;
else
@@ -2696,7 +2710,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
* delivered. Lower inflight to clock out (re)tranmissions.
*/
if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
- tcp_add_reno_sack(sk, num_dupack);
+ tcp_add_reno_sack(sk, num_dupack, flag & FLAG_ECE);
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
@@ -2778,6 +2792,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int fast_rexmit = 0, flag = *ack_flag;
+ bool ece_ack = flag & FLAG_ECE;
bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) &&
tcp_force_fast_retransmit(sk));
@@ -2786,7 +2801,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
/* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
- if (flag & FLAG_ECE)
+ if (ece_ack)
tp->prior_ssthresh = 0;
/* B. In all the states check for reneging SACKs. */
@@ -2827,7 +2842,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
case TCP_CA_Recovery:
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (tcp_is_reno(tp))
- tcp_add_reno_sack(sk, num_dupack);
+ tcp_add_reno_sack(sk, num_dupack, ece_ack);
} else {
if (tcp_try_undo_partial(sk, prior_snd_una))
return;
@@ -2852,7 +2867,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
- tcp_add_reno_sack(sk, num_dupack);
+ tcp_add_reno_sack(sk, num_dupack, ece_ack);
}
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
@@ -2876,7 +2891,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
}
/* Otherwise enter Recovery state */
- tcp_enter_recovery(sk, (flag & FLAG_ECE));
+ tcp_enter_recovery(sk, ece_ack);
fast_rexmit = 1;
}
@@ -3052,7 +3067,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
*/
static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
u32 prior_snd_una,
- struct tcp_sacktag_state *sack)
+ struct tcp_sacktag_state *sack, bool ece_ack)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u64 first_ackt, last_ackt;
@@ -3077,8 +3092,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
u8 sacked = scb->sacked;
u32 acked_pcount;
- tcp_ack_tstamp(sk, skb, prior_snd_una);
-
/* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) == 1 ||
@@ -3113,7 +3126,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
if (sacked & TCPCB_SACKED_ACKED) {
tp->sacked_out -= acked_pcount;
} else if (tcp_is_sack(tp)) {
- tp->delivered += acked_pcount;
+ tcp_count_delivered(tp, acked_pcount, ece_ack);
if (!tcp_skb_spurious_retrans(tp, skb))
tcp_rack_advance(tp, sacked, scb->end_seq,
tcp_skb_timestamp_us(skb));
@@ -3142,6 +3155,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
if (!fully_acked)
break;
+ tcp_ack_tstamp(sk, skb, prior_snd_una);
+
next = skb_rb_next(skb);
if (unlikely(skb == tp->retransmit_skb_hint))
tp->retransmit_skb_hint = NULL;
@@ -3157,8 +3172,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
tp->snd_up = tp->snd_una;
- if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
- flag |= FLAG_SACK_RENEGING;
+ if (skb) {
+ tcp_ack_tstamp(sk, skb, prior_snd_una);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+ flag |= FLAG_SACK_RENEGING;
+ }
if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
@@ -3190,7 +3208,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
}
if (tcp_is_reno(tp)) {
- tcp_remove_reno_sacks(sk, pkts_acked);
+ tcp_remove_reno_sacks(sk, pkts_acked, ece_ack);
/* If any of the cumulatively ACKed segments was
* retransmitted, non-SACK case cannot confirm that
@@ -3557,10 +3575,9 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
delivered = tp->delivered - prior_delivered;
NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
- if (flag & FLAG_ECE) {
- tp->delivered_ce += delivered;
+ if (flag & FLAG_ECE)
NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
- }
+
return delivered;
}
@@ -3584,6 +3601,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
sack_state.first_sackt = 0;
sack_state.rate = &rs;
+ sack_state.sack_delivered = 0;
/* We very likely will need to access rtx queue. */
prefetch(sk->tcp_rtx_queue.rb_node);
@@ -3659,12 +3677,25 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
ack_ev_flags |= CA_ACK_ECE;
}
+ if (sack_state.sack_delivered)
+ tcp_count_delivered(tp, sack_state.sack_delivered,
+ flag & FLAG_ECE);
+
if (flag & FLAG_WIN_UPDATE)
ack_ev_flags |= CA_ACK_WIN_UPDATE;
tcp_in_ack_event(sk, ack_ev_flags);
}
+ /* This is a deviation from RFC3168 since it states that:
+ * "When the TCP data sender is ready to set the CWR bit after reducing
+ * the congestion window, it SHOULD set the CWR bit only on the first
+ * new data packet that it transmits."
+ * We accept CWR on pure ACKs to be more robust
+ * with widely-deployed TCP implementations that do this.
+ */
+ tcp_ecn_accept_cwr(sk, skb);
+
/* We passed data and got it acked, remove any soft error
* log. Something worked...
*/
@@ -3675,7 +3706,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state);
+ flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state,
+ flag & FLAG_ECE);
tcp_rack_update_reo_wnd(sk, &rs);
@@ -4800,8 +4832,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
- tcp_ecn_accept_cwr(sk, skb);
-
tp->rx_opt.dsack = 0;
/* Queue data for delivery to the user.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a50e1990a845..04b70fe31fa2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1064,6 +1064,10 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb,
list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
}
+INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
+INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
+INDIRECT_CALLABLE_DECLARE(void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb));
+
/* This routine actually transmits TCP packets queued in by
* tcp_do_sendmsg(). This is used by both the initial
* transmission and possible later retransmissions.
@@ -1207,7 +1211,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
}
#endif
- icsk->icsk_af_ops->send_check(sk, skb);
+ INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
+ tcp_v6_send_check, tcp_v4_send_check,
+ sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
@@ -1235,7 +1241,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
tcp_add_tx_delay(skb, tp);
- err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+ err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit,
+ inet6_csk_xmit, ip_queue_xmit,
+ sk, skb, &inet->cork.fl);
if (unlikely(err > 0)) {
tcp_enter_cwr(sk);
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-09 03:29:49 +0000