summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig1
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/bpf_tcp_ca.c7
-rw-r--r--net/ipv4/esp4.c16
-rw-r--r--net/ipv4/esp4_offload.c32
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/fib_lookup.h2
-rw-r--r--net/ipv4/fib_semantics.c22
-rw-r--r--net/ipv4/fib_trie.c2
-rw-r--r--net/ipv4/ip_gre.c105
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_tunnel_core.c4
-rw-r--r--net/ipv4/ip_vti.c38
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/route.c13
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_bic.c11
-rw-r--r--net/ipv4/tcp_minisocks.c6
-rw-r--r--net/ipv4/tcp_output.c12
-rw-r--r--net/ipv4/tcp_scalable.c17
-rw-r--r--net/ipv4/tcp_veno.c47
-rw-r--r--net/ipv4/tcp_yeah.c41
-rw-r--r--net/ipv4/udp.c2
25 files changed, 257 insertions, 143 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index f96bd489b362..6490b845e17b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -303,6 +303,7 @@ config SYN_COOKIES
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
+ depends on IPV6 || IPV6=n
select INET_TUNNEL
select NET_IP_TUNNEL
select XFRM
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index bd7b4e92e07f..cf58e29cf746 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1793,6 +1793,10 @@ static __net_exit void ipv4_mib_exit_net(struct net *net)
free_percpu(net->mib.net_statistics);
free_percpu(net->mib.ip_statistics);
free_percpu(net->mib.tcp_statistics);
+#ifdef CONFIG_MPTCP
+ /* allocated on demand, see mptcp_init_sock() */
+ free_percpu(net->mib.mptcp_statistics);
+#endif
}
static __net_initdata struct pernet_operations ipv4_mib_ops = {
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 0fd8bfde2448..e3939f76b024 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -217,7 +217,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
{
const struct tcp_congestion_ops *utcp_ca;
struct tcp_congestion_ops *tcp_ca;
- size_t tcp_ca_name_len;
int prog_fd;
u32 moff;
@@ -232,13 +231,11 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
tcp_ca->flags = utcp_ca->flags;
return 1;
case offsetof(struct tcp_congestion_ops, name):
- tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name));
- if (!tcp_ca_name_len ||
- tcp_ca_name_len == sizeof(utcp_ca->name))
+ if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name,
+ sizeof(tcp_ca->name)) <= 0)
return -EINVAL;
if (tcp_ca_find(utcp_ca->name))
return -EEXIST;
- memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name));
return 1;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 103c7d599a3c..8b07f3a4f2db 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -341,22 +341,6 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
esp_output_done(base, err);
}
-static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
-{
- /* Fill padding... */
- if (tfclen) {
- memset(tail, 0, tfclen);
- tail += tfclen;
- }
- do {
- int i;
- for (i = 0; i < plen - 2; i++)
- tail[i] = i + 1;
- } while (0);
- tail[plen - 2] = plen - 2;
- tail[plen - 1] = proto;
-}
-
static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb,
int encap_type,
struct esp_info *esp,
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index e2e219c7854a..731022cff600 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -132,6 +132,36 @@ static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
return segs;
}
+static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
+ struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct xfrm_offload *xo = xfrm_offload(skb);
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ const struct net_offload *ops;
+ int proto = xo->proto;
+
+ skb->transport_header += x->props.header_len;
+
+ if (proto == IPPROTO_BEETPH) {
+ struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
+
+ skb->transport_header += ph->hdrlen * 8;
+ proto = ph->nexthdr;
+ } else if (x->sel.family != AF_INET6) {
+ skb->transport_header -= IPV4_BEET_PHMAXLEN;
+ } else if (proto == IPPROTO_TCP) {
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+ }
+
+ __skb_pull(skb, skb_transport_offset(skb));
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (likely(ops && ops->callbacks.gso_segment))
+ segs = ops->callbacks.gso_segment(skb, features);
+
+ return segs;
+}
+
static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x,
struct sk_buff *skb,
netdev_features_t features)
@@ -141,6 +171,8 @@ static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x,
return xfrm4_tunnel_gso_segment(x, skb, features);
case XFRM_MODE_TRANSPORT:
return xfrm4_transport_gso_segment(x, skb, features);
+ case XFRM_MODE_BEET:
+ return xfrm4_beet_gso_segment(x, skb, features);
}
return ERR_PTR(-EOPNOTSUPP);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 577db1d50a24..213be9c050ad 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -997,7 +997,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
return -ENOENT;
}
+ rcu_read_lock();
err = fib_table_dump(tb, skb, cb, &filter);
+ rcu_read_unlock();
return skb->len ? : err;
}
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c092e9a55790..818916b2a04d 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -35,7 +35,7 @@ static inline void fib_alias_accessed(struct fib_alias *fa)
void fib_release_info(struct fib_info *);
struct fib_info *fib_create_info(struct fib_config *cfg,
struct netlink_ext_ack *extack);
-int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
+int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack);
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi);
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e4c62b8f57a8..6ed8c9317179 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -570,8 +570,9 @@ static int fib_detect_death(struct fib_info *fi, int order,
return 1;
}
-int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap,
- u16 encap_type, void *cfg, gfp_t gfp_flags,
+int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
+ struct nlattr *encap, u16 encap_type,
+ void *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
int err;
@@ -589,8 +590,9 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap,
err = -EINVAL;
goto lwt_failure;
}
- err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family,
- cfg, &lwtstate, extack);
+ err = lwtunnel_build_state(net, encap_type, encap,
+ nhc->nhc_family, cfg, &lwtstate,
+ extack);
if (err)
goto lwt_failure;
@@ -614,7 +616,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
nh->fib_nh_family = AF_INET;
- err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap,
+ err = fib_nh_common_init(net, &nh->nh_common, cfg->fc_encap,
cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
if (err)
return err;
@@ -814,7 +816,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
-static int fib_encap_match(u16 encap_type,
+static int fib_encap_match(struct net *net, u16 encap_type,
struct nlattr *encap,
const struct fib_nh *nh,
const struct fib_config *cfg,
@@ -826,7 +828,7 @@ static int fib_encap_match(u16 encap_type,
if (encap_type == LWTUNNEL_ENCAP_NONE)
return 0;
- ret = lwtunnel_build_state(encap_type, encap, AF_INET,
+ ret = lwtunnel_build_state(net, encap_type, encap, AF_INET,
cfg, &lwtstate, extack);
if (!ret) {
result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws);
@@ -836,7 +838,7 @@ static int fib_encap_match(u16 encap_type,
return result;
}
-int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
+int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -857,8 +859,8 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
struct fib_nh *nh = fib_info_nh(fi, 0);
if (cfg->fc_encap) {
- if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
- nh, cfg, extack))
+ if (fib_encap_match(net, cfg->fc_encap_type,
+ cfg->fc_encap, nh, cfg, extack))
return 1;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index f4c2ac445b3f..b01b748df9dd 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1679,7 +1679,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
fi->fib_prefsrc == cfg->fc_prefsrc) &&
(!cfg->fc_protocol ||
fi->fib_protocol == cfg->fc_protocol) &&
- fib_nh_match(cfg, fi, extack) == 0 &&
+ fib_nh_match(net, cfg, fi, extack) == 0 &&
fib_metrics_match(cfg, fi)) {
fa_to_delete = fa;
break;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8274f98c511c..029b24eeafba 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1153,6 +1153,24 @@ static int ipgre_netlink_parms(struct net_device *dev,
if (data[IFLA_GRE_FWMARK])
*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
+ return 0;
+}
+
+static int erspan_netlink_parms(struct net_device *dev,
+ struct nlattr *data[],
+ struct nlattr *tb[],
+ struct ip_tunnel_parm *parms,
+ __u32 *fwmark)
+{
+ struct ip_tunnel *t = netdev_priv(dev);
+ int err;
+
+ err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
+ if (err)
+ return err;
+ if (!data)
+ return 0;
+
if (data[IFLA_GRE_ERSPAN_VER]) {
t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
@@ -1276,45 +1294,70 @@ static void ipgre_tap_setup(struct net_device *dev)
ip_tunnel_setup(dev, gre_tap_net_id);
}
-static int ipgre_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
- struct netlink_ext_ack *extack)
+static int
+ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[])
{
- struct ip_tunnel_parm p;
struct ip_tunnel_encap ipencap;
- __u32 fwmark = 0;
- int err;
if (ipgre_netlink_encap_parms(data, &ipencap)) {
struct ip_tunnel *t = netdev_priv(dev);
- err = ip_tunnel_encap_setup(t, &ipencap);
+ int err = ip_tunnel_encap_setup(t, &ipencap);
if (err < 0)
return err;
}
+ return 0;
+}
+
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip_tunnel_parm p;
+ __u32 fwmark = 0;
+ int err;
+
+ err = ipgre_newlink_encap_setup(dev, data);
+ if (err)
+ return err;
+
err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
if (err < 0)
return err;
return ip_tunnel_newlink(dev, tb, &p, fwmark);
}
+static int erspan_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip_tunnel_parm p;
+ __u32 fwmark = 0;
+ int err;
+
+ err = ipgre_newlink_encap_setup(dev, data);
+ if (err)
+ return err;
+
+ err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+ if (err)
+ return err;
+ return ip_tunnel_newlink(dev, tb, &p, fwmark);
+}
+
static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip_tunnel *t = netdev_priv(dev);
- struct ip_tunnel_encap ipencap;
__u32 fwmark = t->fwmark;
struct ip_tunnel_parm p;
int err;
- if (ipgre_netlink_encap_parms(data, &ipencap)) {
- err = ip_tunnel_encap_setup(t, &ipencap);
-
- if (err < 0)
- return err;
- }
+ err = ipgre_newlink_encap_setup(dev, data);
+ if (err)
+ return err;
err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
if (err < 0)
@@ -1327,8 +1370,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
t->parms.i_flags = p.i_flags;
t->parms.o_flags = p.o_flags;
- if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
- ipgre_link_update(dev, !tb[IFLA_MTU]);
+ ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+ return 0;
+}
+
+static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip_tunnel *t = netdev_priv(dev);
+ __u32 fwmark = t->fwmark;
+ struct ip_tunnel_parm p;
+ int err;
+
+ err = ipgre_newlink_encap_setup(dev, data);
+ if (err)
+ return err;
+
+ err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+ if (err < 0)
+ return err;
+
+ err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+ if (err < 0)
+ return err;
+
+ t->parms.i_flags = p.i_flags;
+ t->parms.o_flags = p.o_flags;
return 0;
}
@@ -1519,8 +1588,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
.priv_size = sizeof(struct ip_tunnel),
.setup = erspan_setup,
.validate = erspan_validate,
- .newlink = ipgre_newlink,
- .changelink = ipgre_changelink,
+ .newlink = erspan_newlink,
+ .changelink = erspan_changelink,
.dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index aaaaf907e0d8..090d3097ee15 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -263,7 +263,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
* insufficent MTU.
*/
features = netif_skb_features(skb);
- BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
+ BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs)) {
kfree_skb(skb);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 47f8b947eef1..181b7a2a0247 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -432,7 +432,7 @@ static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
return ip_tun_parse_opts(attr, info, extack);
}
-static int ip_tun_build_state(struct nlattr *attr,
+static int ip_tun_build_state(struct net *net, struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
@@ -719,7 +719,7 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
[LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED },
};
-static int ip6_tun_build_state(struct nlattr *attr,
+static int ip6_tun_build_state(struct net *net, struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 37cddd18f282..1b4e6f298648 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -187,17 +187,39 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
int mtu;
if (!dst) {
- struct rtable *rt;
-
- fl->u.ip4.flowi4_oif = dev->ifindex;
- fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
- rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
- if (IS_ERR(rt)) {
+ switch (skb->protocol) {
+ case htons(ETH_P_IP): {
+ struct rtable *rt;
+
+ fl->u.ip4.flowi4_oif = dev->ifindex;
+ fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+ rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
+ if (IS_ERR(rt)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error_icmp;
+ }
+ dst = &rt->dst;
+ skb_dst_set(skb, dst);
+ break;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ fl->u.ip6.flowi6_oif = dev->ifindex;
+ fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+ dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
+ if (dst->error) {
+ dst_release(dst);
+ dst = NULL;
+ dev->stats.tx_carrier_errors++;
+ goto tx_error_icmp;
+ }
+ skb_dst_set(skb, dst);
+ break;
+#endif
+ default:
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
- dst = &rt->dst;
- skb_dst_set(skb, dst);
}
dst_hold(dst);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index f1f78a742b36..b167f4a5b684 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1057,7 +1057,7 @@ struct compat_arpt_replace {
u32 underflow[NF_ARP_NUMHOOKS];
u32 num_counters;
compat_uptr_t counters;
- struct compat_arpt_entry entries[0];
+ struct compat_arpt_entry entries[];
};
static inline void compat_release_entry(struct compat_arpt_entry *e)
@@ -1383,7 +1383,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
struct compat_arpt_get_entries {
char name[XT_TABLE_MAXNAMELEN];
compat_uint_t size;
- struct compat_arpt_entry entrytable[0];
+ struct compat_arpt_entry entrytable[];
};
static int compat_get_entries(struct net *net,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 10b91ebdf213..c2670eaa74e6 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1211,7 +1211,7 @@ struct compat_ipt_replace {
u32 underflow[NF_INET_NUMHOOKS];
u32 num_counters;
compat_uptr_t counters; /* struct xt_counters * */
- struct compat_ipt_entry entries[0];
+ struct compat_ipt_entry entries[];
};
static int
@@ -1562,7 +1562,7 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user,
struct compat_ipt_get_entries {
char name[XT_TABLE_MAXNAMELEN];
compat_uint_t size;
- struct compat_ipt_entry entrytable[0];
+ struct compat_ipt_entry entrytable[];
};
static int
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 2580303249e2..75545a829a2b 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -32,6 +32,7 @@
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <linux/bottom_half.h>
@@ -485,6 +486,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
offsetof(struct ipstats_mib, syncp)));
seq_putc(seq, '\n');
+ mptcp_seq_show(seq);
return 0;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 042599cc691d..788c69d9bfe0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1621,12 +1621,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
struct rtable *rt_dst_alloc(struct net_device *dev,
unsigned int flags, u16 type,
- bool nopolicy, bool noxfrm, bool will_cache)
+ bool nopolicy, bool noxfrm)
{
struct rtable *rt;
rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
- (will_cache ? 0 : DST_HOST) |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
@@ -1674,7 +1673,6 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
new_rt->rt_gw6 = rt->rt_gw6;
INIT_LIST_HEAD(&new_rt->rt_uncached);
- new_rt->dst.flags |= DST_HOST;
new_rt->dst.input = rt->dst.input;
new_rt->dst.output = rt->dst.output;
new_rt->dst.error = rt->dst.error;
@@ -1734,7 +1732,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
flags |= RTCF_LOCAL;
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
return -ENOBUFS;
@@ -1851,7 +1849,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth = rt_dst_alloc(out_dev->dev, 0, res->type,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache);
+ IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
@@ -2219,7 +2217,7 @@ local_input:
rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
flags | RTCF_LOCAL, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
@@ -2443,8 +2441,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
add:
rth = rt_dst_alloc(dev_out, flags, type,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(in_dev, NOXFRM),
- do_cache);
+ IN_DEV_CONF_GET(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5c57850fab4b..6d87de434377 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2948,8 +2948,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = -EPERM;
else if (tp->repair_queue == TCP_SEND_QUEUE)
WRITE_ONCE(tp->write_seq, val);
- else if (tp->repair_queue == TCP_RECV_QUEUE)
+ else if (tp->repair_queue == TCP_RECV_QUEUE) {
WRITE_ONCE(tp->rcv_nxt, val);
+ WRITE_ONCE(tp->copied_seq, val);
+ }
else
err = -EINVAL;
break;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 645cc3009e64..f5f588b1f6e9 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -145,12 +145,13 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
if (!tcp_is_cwnd_limited(sk))
return;
- if (tcp_in_slow_start(tp))
- tcp_slow_start(tp, acked);
- else {
- bictcp_update(ca, tp->snd_cwnd);
- tcp_cong_avoid_ai(tp, ca->cnt, 1);
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
}
+ bictcp_update(ca, tp->snd_cwnd);
+ tcp_cong_avoid_ai(tp, ca->cnt, acked);
}
/*
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 03af7c3e75ef..7e40322cc5ec 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -774,6 +774,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
+ if (own_req && sk_is_mptcp(child) && mptcp_sk_is_subflow(child)) {
+ reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ return child;
+ }
+
sock_rps_save_rxhash(child, skb);
tcp_synack_rtt_meas(child, req);
*req_stolen = !own_req;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 306e25d743e8..2f45cde168c4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1109,6 +1109,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
if (unlikely(!skb))
return -ENOBUFS;
+ /* retransmit skbs might have a non zero value in skb->dev
+ * because skb->dev is aliased with skb->rbnode.rb_left
+ */
+ skb->dev = NULL;
}
inet = inet_sk(sk);
@@ -3037,8 +3041,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
tcp_skb_tsorted_save(skb) {
nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
- err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
- -ENOBUFS;
+ if (nskb) {
+ nskb->dev = NULL;
+ err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC);
+ } else {
+ err = -ENOBUFS;
+ }
} tcp_skb_tsorted_restore(skb);
if (!err) {
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 471571e1ab26..6cebf412d590 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -10,10 +10,9 @@
#include <net/tcp.h>
/* These factors derived from the recommended values in the aer:
- * .01 and and 7/8. We use 50 instead of 100 to account for
- * delayed ack.
+ * .01 and and 7/8.
*/
-#define TCP_SCALABLE_AI_CNT 50U
+#define TCP_SCALABLE_AI_CNT 100U
#define TCP_SCALABLE_MD_SCALE 3
static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
@@ -23,11 +22,13 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
if (!tcp_is_cwnd_limited(sk))
return;
- if (tcp_in_slow_start(tp))
- tcp_slow_start(tp, acked);
- else
- tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
- 1);
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+ acked);
}
static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 3b36bb1a0dda..50a9a6e2c4cd 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -153,31 +153,34 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd;
if (tcp_in_slow_start(tp)) {
- /* Slow start. */
- tcp_slow_start(tp, acked);
+ /* Slow start. */
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ goto done;
+ }
+
+ /* Congestion avoidance. */
+ if (veno->diff < beta) {
+ /* In the "non-congestive state", increase cwnd
+ * every rtt.
+ */
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
} else {
- /* Congestion avoidance. */
- if (veno->diff < beta) {
- /* In the "non-congestive state", increase cwnd
- * every rtt.
- */
- tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
- } else {
- /* In the "congestive state", increase cwnd
- * every other rtt.
- */
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- if (veno->inc &&
- tp->snd_cwnd < tp->snd_cwnd_clamp) {
- tp->snd_cwnd++;
- veno->inc = 0;
- } else
- veno->inc = 1;
- tp->snd_cwnd_cnt = 0;
+ /* In the "congestive state", increase cwnd
+ * every other rtt.
+ */
+ if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
+ if (veno->inc &&
+ tp->snd_cwnd < tp->snd_cwnd_clamp) {
+ tp->snd_cwnd++;
+ veno->inc = 0;
} else
- tp->snd_cwnd_cnt++;
- }
+ veno->inc = 1;
+ tp->snd_cwnd_cnt = 0;
+ } else
+ tp->snd_cwnd_cnt += acked;
}
+done:
if (tp->snd_cwnd < 2)
tp->snd_cwnd = 2;
else if (tp->snd_cwnd > tp->snd_cwnd_clamp)
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index e00570dd0a69..3bb448761ca3 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -36,8 +36,6 @@ struct yeah {
u32 reno_count;
u32 fast_count;
-
- u32 pkts_acked;
};
static void tcp_yeah_init(struct sock *sk)
@@ -57,18 +55,6 @@ static void tcp_yeah_init(struct sock *sk)
tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
}
-static void tcp_yeah_pkts_acked(struct sock *sk,
- const struct ack_sample *sample)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
- struct yeah *yeah = inet_csk_ca(sk);
-
- if (icsk->icsk_ca_state == TCP_CA_Open)
- yeah->pkts_acked = sample->pkts_acked;
-
- tcp_vegas_pkts_acked(sk, sample);
-}
-
static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -77,24 +63,19 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
if (!tcp_is_cwnd_limited(sk))
return;
- if (tcp_in_slow_start(tp))
- tcp_slow_start(tp, acked);
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ goto do_vegas;
+ }
- else if (!yeah->doing_reno_now) {
+ if (!yeah->doing_reno_now) {
/* Scalable */
-
- tp->snd_cwnd_cnt += yeah->pkts_acked;
- if (tp->snd_cwnd_cnt > min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- tp->snd_cwnd_cnt = 0;
- }
-
- yeah->pkts_acked = 1;
-
+ tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+ acked);
} else {
/* Reno */
- tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
}
/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
@@ -118,7 +99,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
* of bytes we send in an RTT is often less than our cwnd will allow.
* So we keep track of our cwnd separately, in v_beg_snd_cwnd.
*/
-
+do_vegas:
if (after(ack, yeah->vegas.beg_snd_nxt)) {
/* We do the Vegas calculations only if we got enough RTT
* samples that we can be reasonably sure that we got
@@ -232,7 +213,7 @@ static struct tcp_congestion_ops tcp_yeah __read_mostly = {
.set_state = tcp_vegas_state,
.cwnd_event = tcp_vegas_cwnd_event,
.get_info = tcp_vegas_get_info,
- .pkts_acked = tcp_yeah_pkts_acked,
+ .pkts_acked = tcp_vegas_pkts_acked,
.owner = THIS_MODULE,
.name = "yeah",
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b4035021bbd3..32564b350823 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2109,7 +2109,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (likely(!udp_unexpected_gso(sk, skb)))
return udp_queue_rcv_one_skb(sk, skb);
- BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
+ BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_GSO_CB_OFFSET);
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, true);
skb_list_walk_safe(segs, skb, next) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-27 12:02:50 +0300