summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fou.c4
-rw-r--r--net/ipv4/ip_gre.c15
-rw-r--r--net/ipv4/ip_input.c7
-rw-r--r--net/ipv4/ip_options.c4
-rw-r--r--net/ipv4/route.c16
-rw-r--r--net/ipv4/tcp_dctcp.c81
-rw-r--r--net/ipv4/tcp_input.c10
-rw-r--r--net/ipv4/tcp_ipv4.c3
8 files changed, 75 insertions, 65 deletions
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 79e98e21cdd7..12ce6c526d72 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
struct guehdr *guehdr;
void *data;
u16 doffset = 0;
+ u8 proto_ctype;
if (!fou)
return 1;
@@ -212,13 +213,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
+ proto_ctype = guehdr->proto_ctype;
__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
goto drop;
- return -guehdr->proto_ctype;
+ return -proto_ctype;
drop:
kfree_skb(skb);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index fd219f7bd3ea..4b0526441476 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
struct net *net = dev_net(skb->dev);
struct metadata_dst *tun_dst = NULL;
struct erspan_base_hdr *ershdr;
- struct erspan_metadata *pkt_md;
struct ip_tunnel_net *itn;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
@@ -282,9 +281,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
if (unlikely(!pskb_may_pull(skb, len)))
return PACKET_REJECT;
- ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
- pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
if (__iptunnel_pull_header(skb,
len,
htons(ETH_P_TEB),
@@ -292,8 +288,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
goto drop;
if (tunnel->collect_md) {
+ struct erspan_metadata *pkt_md, *md;
struct ip_tunnel_info *info;
- struct erspan_metadata *md;
+ unsigned char *gh;
__be64 tun_id;
__be16 flags;
@@ -306,6 +303,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
if (!tun_dst)
return PACKET_REJECT;
+ /* skb can be uncloned in __iptunnel_pull_header, so
+ * old pkt_md is no longer valid and we need to reset
+ * it
+ */
+ gh = skb_network_header(skb) +
+ skb_network_header_len(skb);
+ pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+ sizeof(*ershdr));
md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
md->version = ver;
md2 = &md->u.md2;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index ecce2dc78f17..1132d6d1796a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb)
ip_local_deliver_finish);
}
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt;
const struct iphdr *iph;
- struct net_device *dev = skb->dev;
/* It looks as overkill, because not all
IP options require packet mangling.
@@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
}
}
- if (ip_options_rcv_srr(skb))
+ if (ip_options_rcv_srr(skb, dev))
goto drop;
}
@@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
}
#endif
- if (iph->ihl > 5 && ip_rcv_options(skb))
+ if (iph->ihl > 5 && ip_rcv_options(skb, dev))
goto drop;
rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 32a35043c9f5..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
}
}
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt = &(IPCB(skb)->opt);
int srrspace, srrptr;
@@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
orefdst = skb->_skb_refdst;
skb_dst_set(skb, NULL);
- err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+ err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
rt2 = skb_rtable(skb);
if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
skb_dst_drop(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a5da63e5faa2..88ce038dd495 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1185,9 +1185,23 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
static void ipv4_link_failure(struct sk_buff *skb)
{
+ struct ip_options opt;
struct rtable *rt;
+ int res;
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ /* Recompile ip options since IPCB may not be valid anymore.
+ */
+ memset(&opt, 0, sizeof(opt));
+ opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
+ return;
+
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
rt = skb_rtable(skb);
if (rt)
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index cd4814f7e962..477cb4aa456c 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -49,9 +49,8 @@
#define DCTCP_MAX_ALPHA 1024U
struct dctcp {
- u32 acked_bytes_ecn;
- u32 acked_bytes_total;
- u32 prior_snd_una;
+ u32 old_delivered;
+ u32 old_delivered_ce;
u32 prior_rcv_nxt;
u32 dctcp_alpha;
u32 next_seq;
@@ -67,19 +66,14 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
module_param(dctcp_alpha_on_init, uint, 0644);
MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
- "parameter for clamping alpha on loss");
-
static struct tcp_congestion_ops dctcp_reno;
static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
{
ca->next_seq = tp->snd_nxt;
- ca->acked_bytes_ecn = 0;
- ca->acked_bytes_total = 0;
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
}
static void dctcp_init(struct sock *sk)
@@ -91,7 +85,6 @@ static void dctcp_init(struct sock *sk)
sk->sk_state == TCP_CLOSE)) {
struct dctcp *ca = inet_csk_ca(sk);
- ca->prior_snd_una = tp->snd_una;
ca->prior_rcv_nxt = tp->rcv_nxt;
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
@@ -123,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
- u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
- /* If ack did not advance snd_una, count dupack as MSS size.
- * If ack did update window, do not count it at all.
- */
- if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
- acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
- if (acked_bytes) {
- ca->acked_bytes_total += acked_bytes;
- ca->prior_snd_una = tp->snd_una;
-
- if (flags & CA_ACK_ECE)
- ca->acked_bytes_ecn += acked_bytes;
- }
/* Expired RTT */
if (!before(tp->snd_una, ca->next_seq)) {
- u64 bytes_ecn = ca->acked_bytes_ecn;
+ u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
u32 alpha = ca->dctcp_alpha;
/* alpha = (1 - g) * alpha + g * F */
alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
- if (bytes_ecn) {
+ if (delivered_ce) {
+ u32 delivered = tp->delivered - ca->old_delivered;
+
/* If dctcp_shift_g == 1, a 32bit value would overflow
- * after 8 Mbytes.
+ * after 8 M packets.
*/
- bytes_ecn <<= (10 - dctcp_shift_g);
- do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
- alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
}
/* dctcp_alpha can be read from dctcp_get_info() without
* synchro, so we ask compiler to not use dctcp_alpha
@@ -164,21 +145,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
}
}
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
{
- if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
- struct dctcp *ca = inet_csk_ca(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
- /* If this extension is enabled, we clamp dctcp_alpha to
- * max on packet loss; the motivation is that dctcp_alpha
- * is an indicator to the extend of congestion and packet
- * loss is an indicator of extreme congestion; setting
- * this in practice turned out to be beneficial, and
- * effectively assumes total congestion which reduces the
- * window by half.
- */
- ca->dctcp_alpha = DCTCP_MAX_ALPHA;
- }
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != inet_csk(sk)->icsk_ca_state)
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
}
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -190,6 +173,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
default:
/* Don't care for the rest. */
break;
@@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Fill it also in case of VEGASINFO due to req struct limits.
* We can still correctly retrieve it later.
@@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
info->dctcp.dctcp_enabled = 1;
info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
info->dctcp.dctcp_alpha = ca->dctcp_alpha;
- info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+ (tp->delivered_ce - ca->old_delivered_ce);
+ info->dctcp.dctcp_ab_tot = tp->mss_cache *
+ (tp->delivered - ca->old_delivered);
}
*attr = INET_DIAG_DCTCPINFO;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5def3c48870e..731d3045b50a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ int room;
+
+ room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
/* Check #1 */
- if (tp->rcv_ssthresh < tp->window_clamp &&
- (int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_under_memory_pressure(sk)) {
+ if (room > 0 && !tcp_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
@@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
- tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
- tp->window_clamp);
+ tp->rcv_ssthresh += min(room, incr);
inet_csk(sk)->icsk_ack.quick |= 1;
}
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 277d71239d75..2f8039a26b08 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2578,7 +2578,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
{
int cpu;
- module_put(net->ipv4.tcp_congestion_control->owner);
+ if (net->ipv4.tcp_congestion_control)
+ module_put(net->ipv4.tcp_congestion_control->owner);
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-24 12:59:54 +0100