aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ip_gre.c59
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/tcp_input.c43
-rw-r--r--net/ipv4/tcp_output.c22
4 files changed, 67 insertions, 60 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 029b24eeafba..0ce9b91ff55c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -248,6 +248,15 @@ static void gre_err(struct sk_buff *skb, u32 info)
ipgre_err(skb, info, &tpi);
}
+static bool is_erspan_type1(int gre_hdr_len)
+{
+ /* Both ERSPAN type I (version 0) and type II (version 1) use
+ * protocol 0x88BE, but the type I has only 4-byte GRE header,
+ * while type II has 8-byte.
+ */
+ return gre_hdr_len == 4;
+}
+
static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
int gre_hdr_len)
{
@@ -262,17 +271,26 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
int len;
itn = net_generic(net, erspan_net_id);
-
iph = ip_hdr(skb);
- ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
- ver = ershdr->ver;
-
- tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
- tpi->flags | TUNNEL_KEY,
- iph->saddr, iph->daddr, tpi->key);
+ if (is_erspan_type1(gre_hdr_len)) {
+ ver = 0;
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
+ tpi->flags | TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ } else {
+ ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
+ ver = ershdr->ver;
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
+ tpi->flags | TUNNEL_KEY,
+ iph->saddr, iph->daddr, tpi->key);
+ }
if (tunnel) {
- len = gre_hdr_len + erspan_hdr_len(ver);
+ if (is_erspan_type1(gre_hdr_len))
+ len = gre_hdr_len;
+ else
+ len = gre_hdr_len + erspan_hdr_len(ver);
+
if (unlikely(!pskb_may_pull(skb, len)))
return PACKET_REJECT;
@@ -665,7 +683,10 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
}
/* Push ERSPAN header */
- if (tunnel->erspan_ver == 1) {
+ if (tunnel->erspan_ver == 0) {
+ proto = htons(ETH_P_ERSPAN);
+ tunnel->parms.o_flags &= ~TUNNEL_SEQ;
+ } else if (tunnel->erspan_ver == 1) {
erspan_build_header(skb, ntohl(tunnel->parms.o_key),
tunnel->index,
truncate, true);
@@ -1066,7 +1087,11 @@ static int erspan_validate(struct nlattr *tb[], struct nlattr *data[],
if (ret)
return ret;
- /* ERSPAN should only have GRE sequence and key flag */
+ if (data[IFLA_GRE_ERSPAN_VER] &&
+ nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0)
+ return 0;
+
+ /* ERSPAN type II/III should only have GRE sequence and key flag */
if (data[IFLA_GRE_OFLAGS])
flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
if (data[IFLA_GRE_IFLAGS])
@@ -1174,7 +1199,7 @@ static int erspan_netlink_parms(struct net_device *dev,
if (data[IFLA_GRE_ERSPAN_VER]) {
t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
- if (t->erspan_ver != 1 && t->erspan_ver != 2)
+ if (t->erspan_ver > 2)
return -EINVAL;
}
@@ -1259,7 +1284,11 @@ static int erspan_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- tunnel->tun_hlen = 8;
+ if (tunnel->erspan_ver == 0)
+ tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */
+ else
+ tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */
+
tunnel->parms.iph.protocol = IPPROTO_GRE;
tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
erspan_hdr_len(tunnel->erspan_ver);
@@ -1456,8 +1485,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
struct ip_tunnel_parm *p = &t->parms;
__be16 o_flags = p->o_flags;
- if (t->erspan_ver == 1 || t->erspan_ver == 2) {
- if (!t->collect_md)
+ if (t->erspan_ver <= 2) {
+ if (t->erspan_ver != 0 && !t->collect_md)
o_flags |= TUNNEL_KEY;
if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
@@ -1466,7 +1495,7 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
if (t->erspan_ver == 1) {
if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
goto nla_put_failure;
- } else {
+ } else if (t->erspan_ver == 2) {
if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index aa3fd61818c4..8206047d70b6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1492,7 +1492,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
- msg.msg_control = (__force void *) optval;
+ msg.msg_control_is_user = true;
+ msg.msg_control_user = optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d68128a672ab..7529c2816f2f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2183,8 +2183,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
}
/* Detect loss in event "A" above by marking head of queue up as lost.
- * For non-SACK(Reno) senders, the first "packets" number of segments
- * are considered lost. For RFC3517 SACK, a segment is considered lost if it
+ * For RFC3517 SACK, a segment is considered lost if it
* has at least tp->reordering SACKed seqments above it; "packets" refers to
* the maximum SACKed segments to pass before reaching this limit.
*/
@@ -2192,10 +2191,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt, oldcnt, lost;
- unsigned int mss;
+ int cnt;
/* Use SACK to deduce losses of new sequences sent during recovery */
- const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
+ const u32 loss_high = tp->snd_nxt;
WARN_ON(packets > tp->packets_out);
skb = tp->lost_skb_hint;
@@ -2218,26 +2216,11 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
break;
- oldcnt = cnt;
- if (tcp_is_reno(tp) ||
- (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
cnt += tcp_skb_pcount(skb);
- if (cnt > packets) {
- if (tcp_is_sack(tp) ||
- (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
- (oldcnt >= packets))
- break;
-
- mss = tcp_skb_mss(skb);
- /* If needed, chop off the prefix to mark as lost. */
- lost = (packets - oldcnt) * mss;
- if (lost < skb->len &&
- tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
- lost, mss, GFP_ATOMIC) < 0)
- break;
- cnt = packets;
- }
+ if (cnt > packets)
+ break;
tcp_skb_mark_lost(tp, skb);
@@ -2849,8 +2832,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
if (tcp_try_undo_partial(sk, prior_snd_una))
return;
/* Partial ACK arrived. Force fast retransmit. */
- do_lost = tcp_is_reno(tp) ||
- tcp_force_fast_retransmit(sk);
+ do_lost = tcp_force_fast_retransmit(sk);
}
if (tcp_try_undo_dsack(sk)) {
tcp_try_keep_open(sk);
@@ -3014,7 +2996,7 @@ void tcp_rearm_rto(struct sock *sk)
rto = usecs_to_jiffies(max_t(int, delta_us, 1));
}
tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
- TCP_RTO_MAX, tcp_rtx_queue_head(sk));
+ TCP_RTO_MAX);
}
}
@@ -3291,7 +3273,7 @@ static void tcp_ack_probe(struct sock *sk)
unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
- when, TCP_RTO_MAX, NULL);
+ when, TCP_RTO_MAX);
}
}
@@ -3926,10 +3908,6 @@ void tcp_parse_options(const struct net *net,
*/
break;
#endif
- case TCPOPT_MPTCP:
- mptcp_parse_option(skb, ptr, opsize, opt_rx);
- break;
-
case TCPOPT_FASTOPEN:
tcp_parse_fastopen_option(
opsize - TCPOLEN_FASTOPEN_BASE,
@@ -6019,9 +5997,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
- if (sk_is_mptcp(sk))
- mptcp_rcv_synsent(sk);
-
/* Remember, tcp_poll() does not lock socket!
* Change state from SYN-SENT only after copied_seq
* is initialized. */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c414aeb1efa9..a50e1990a845 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2593,8 +2593,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
if (rto_delta_us > 0)
timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
- tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
- TCP_RTO_MAX, NULL);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX);
return true;
}
@@ -3113,6 +3112,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
const struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb, *rtx_head, *hole = NULL;
struct tcp_sock *tp = tcp_sk(sk);
+ bool rearm_timer = false;
u32 max_segs;
int mib_idx;
@@ -3135,7 +3135,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
if (segs <= 0)
- return;
+ break;
sacked = TCP_SKB_CB(skb)->sacked;
/* In case tcp_shift_skb_data() have aggregated large skbs,
* we need to make sure not sending too bigs TSO packets
@@ -3160,10 +3160,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
continue;
if (tcp_small_queue_check(sk, skb, 1))
- return;
+ break;
if (tcp_retransmit_skb(sk, skb, segs))
- return;
+ break;
NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb));
@@ -3172,11 +3172,13 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
if (skb == rtx_head &&
icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
- tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- inet_csk(sk)->icsk_rto,
- TCP_RTO_MAX,
- skb);
+ rearm_timer = true;
+
}
+ if (rearm_timer)
+ tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto,
+ TCP_RTO_MAX);
}
/* We allow to exceed memory limits for FIN packets to expedite
@@ -3907,7 +3909,7 @@ void tcp_send_probe0(struct sock *sk)
*/
timeout = TCP_RESOURCE_PROBE_INTERVAL;
}
- tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL);
+ tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX);
}
int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.