summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c8
-rw-r--r--net/ipv4/ah4.c2
-rw-r--r--net/ipv4/arp.c2
-rw-r--r--net/ipv4/bpf_tcp_ca.c33
-rw-r--r--net/ipv4/devinet.c6
-rw-r--r--net/ipv4/esp4.c16
-rw-r--r--net/ipv4/esp4_offload.c32
-rw-r--r--net/ipv4/fib_lookup.h2
-rw-r--r--net/ipv4/fib_semantics.c26
-rw-r--r--net/ipv4/fib_trie.c10
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/inet_connection_sock.c36
-rw-r--r--net/ipv4/inet_diag.c307
-rw-r--r--net/ipv4/ip_input.c3
-rw-r--r--net/ipv4/ip_output.c4
-rw-r--r--net/ipv4/ip_tunnel.c6
-rw-r--r--net/ipv4/ip_tunnel_core.c4
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/netfilter/nf_log_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_pptp.c4
-rw-r--r--net/ipv4/nexthop.c2
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/raw_diag.c24
-rw-r--r--net/ipv4/route.c61
-rw-r--r--net/ipv4/sysctl_net_ipv4.c33
-rw-r--r--net/ipv4/tcp.c29
-rw-r--r--net/ipv4/tcp_bic.c11
-rw-r--r--net/ipv4/tcp_bpf.c272
-rw-r--r--net/ipv4/tcp_diag.c8
-rw-r--r--net/ipv4/tcp_input.c6
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_minisocks.c9
-rw-r--r--net/ipv4/tcp_scalable.c17
-rw-r--r--net/ipv4/tcp_ulp.c9
-rw-r--r--net/ipv4/tcp_veno.c47
-rw-r--r--net/ipv4/tcp_yeah.c41
-rw-r--r--net/ipv4/udp.c24
-rw-r--r--net/ipv4/udp_bpf.c53
-rw-r--r--net/ipv4/udp_diag.c41
-rw-r--r--net/ipv4/udp_offload.c1
45 files changed, 705 insertions, 515 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 9d97bace13c8..9e1a186a3671 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o
+obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2fe295432c24..cf58e29cf746 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -872,7 +872,7 @@ int inet_shutdown(struct socket *sock, int how)
err = -ENOTCONN;
/* Hack to wake up other listeners, who can poll for
EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
- /* fall through */
+ fallthrough;
default:
sk->sk_shutdown |= how;
if (sk->sk_prot->shutdown)
@@ -886,7 +886,7 @@ int inet_shutdown(struct socket *sock, int how)
case TCP_LISTEN:
if (!(how & RCV_SHUTDOWN))
break;
- /* fall through */
+ fallthrough;
case TCP_SYN_SENT:
err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
@@ -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/ah4.c b/net/ipv4/ah4.c
index 974179b3b314..d99e1be94019 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -107,7 +107,7 @@ static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr)
if (optlen < 6)
return -EINVAL;
memcpy(daddr, optptr+optlen-4, 4);
- /* Fall through */
+ fallthrough;
default:
memset(optptr, 0, optlen);
}
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 05eb42f347e8..687971d83b4e 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1181,7 +1181,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
case SIOCSARP:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
- /* fall through */
+ fallthrough;
case SIOCGARP:
err = copy_from_user(&r, arg, sizeof(struct arpreq));
if (err)
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 2bf3abeb1456..e3939f76b024 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -7,6 +7,7 @@
#include <linux/btf.h>
#include <linux/filter.h>
#include <net/tcp.h>
+#include <net/bpf_sk_storage.h>
static u32 optional_ops[] = {
offsetof(struct tcp_congestion_ops, init),
@@ -27,6 +28,27 @@ static u32 unsupported_ops[] = {
static const struct btf_type *tcp_sock_type;
static u32 tcp_sock_id, sock_id;
+static int btf_sk_storage_get_ids[5];
+static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
+
+static int btf_sk_storage_delete_ids[5];
+static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
+
+static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids,
+ const struct bpf_func_proto *from)
+{
+ int i;
+
+ *to = *from;
+ to->btf_id = to_btf_ids;
+ for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
+ if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
+ to->arg_type[i] = ARG_PTR_TO_BTF_ID;
+ to->btf_id[i] = tcp_sock_id;
+ }
+ }
+}
+
static int bpf_tcp_ca_init(struct btf *btf)
{
s32 type_id;
@@ -42,6 +64,13 @@ static int bpf_tcp_ca_init(struct btf *btf)
tcp_sock_id = type_id;
tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
+ convert_sk_func_proto(&btf_sk_storage_get_proto,
+ btf_sk_storage_get_ids,
+ &bpf_sk_storage_get_proto);
+ convert_sk_func_proto(&btf_sk_storage_delete_proto,
+ btf_sk_storage_delete_ids,
+ &bpf_sk_storage_delete_proto);
+
return 0;
}
@@ -167,6 +196,10 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
switch (func_id) {
case BPF_FUNC_tcp_send_ack:
return &bpf_tcp_send_ack_proto;
+ case BPF_FUNC_sk_storage_get:
+ return &btf_sk_storage_get_proto;
+ case BPF_FUNC_sk_storage_delete:
+ return &btf_sk_storage_delete_proto;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e4632bd2026d..30fa42f5997d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1566,11 +1566,11 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
}
}
ip_mc_up(in_dev);
- /* fall through */
+ fallthrough;
case NETDEV_CHANGEADDR:
if (!IN_DEV_ARP_NOTIFY(in_dev))
break;
- /* fall through */
+ fallthrough;
case NETDEV_NOTIFY_PEERS:
/* Send gratuitous ARP to notify of link change */
inetdev_send_gratuitous_arp(dev, in_dev);
@@ -1588,7 +1588,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
if (inetdev_valid_mtu(dev->mtu))
break;
/* disable IP when MTU is not enough */
- /* fall through */
+ fallthrough;
case NETDEV_UNREGISTER:
inetdev_destroy(in_dev);
break;
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_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 a803cdd9400a..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
@@ -1962,7 +1964,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
nexthop_nh->fib_nh_flags |= RTNH_F_DEAD;
- /* fall through */
+ fallthrough;
case NETDEV_CHANGE:
nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
break;
@@ -1984,7 +1986,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
fi->fib_flags |= RTNH_F_DEAD;
- /* fall through */
+ fallthrough;
case NETDEV_CHANGE:
fi->fib_flags |= RTNH_F_LINKDOWN;
break;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ff0c24371e33..4f334b425538 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -35,9 +35,6 @@
* Paul E. McKenney <paulmck@us.ibm.com>
* Patrick McHardy <kaber@trash.net>
*/
-
-#define VERSION "0.409"
-
#include <linux/cache.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
@@ -304,8 +301,6 @@ static inline void alias_free_mem_rcu(struct fib_alias *fa)
call_rcu(&fa->rcu, __alias_free_mem);
}
-#define TNODE_KMALLOC_MAX \
- ilog2((PAGE_SIZE - TNODE_SIZE(0)) / sizeof(struct key_vector *))
#define TNODE_VMALLOC_MAX \
ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *))
@@ -1684,7 +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;
@@ -2577,6 +2572,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
" %zd bytes, size of tnode: %zd bytes.\n",
LEAF_SIZE, TNODE_SIZE(0));
+ rcu_read_lock();
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv4.fib_table_hash[h];
struct fib_table *tb;
@@ -2596,7 +2592,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
trie_show_usage(seq, t->stats);
#endif
}
+ cond_resched_rcu();
}
+ rcu_read_unlock();
return 0;
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f369e7ce685b..fc61f51d87a3 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -865,7 +865,7 @@ static bool icmp_unreach(struct sk_buff *skb)
case 3:
if (!icmp_tag_validation(iph->protocol))
goto out;
- /* fall through */
+ fallthrough;
case 0:
info = ntohs(icmph->un.frag.mtu);
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 3b9c7a2725a9..47f0502b2101 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -107,8 +107,6 @@
#ifdef CONFIG_IP_MULTICAST
/* Parameter names and values are taken from igmp-v2-06 draft */
-#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ)
-#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ)
#define IGMP_QUERY_INTERVAL (125*HZ)
#define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d545fb99a8a1..5f34eb951627 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -131,7 +131,7 @@ static int inet_csk_bind_conflict(const struct sock *sk,
{
struct sock *sk2;
bool reuse = sk->sk_reuse;
- bool reuseport = !!sk->sk_reuseport && reuseport_ok;
+ bool reuseport = !!sk->sk_reuseport;
kuid_t uid = sock_i_uid((struct sock *)sk);
/*
@@ -146,17 +146,21 @@ static int inet_csk_bind_conflict(const struct sock *sk,
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
- if ((!reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) &&
- (!reuseport || !sk2->sk_reuseport ||
- rcu_access_pointer(sk->sk_reuseport_cb) ||
- (sk2->sk_state != TCP_TIME_WAIT &&
- !uid_eq(uid, sock_i_uid(sk2))))) {
- if (inet_rcv_saddr_equal(sk, sk2, true))
- break;
- }
- if (!relax && reuse && sk2->sk_reuse &&
+ if (reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN) {
+ if ((!relax ||
+ (!reuseport_ok &&
+ reuseport && sk2->sk_reuseport &&
+ !rcu_access_pointer(sk->sk_reuseport_cb) &&
+ (sk2->sk_state == TCP_TIME_WAIT ||
+ uid_eq(uid, sock_i_uid(sk2))))) &&
+ inet_rcv_saddr_equal(sk, sk2, true))
+ break;
+ } else if (!reuseport_ok ||
+ !reuseport || !sk2->sk_reuseport ||
+ rcu_access_pointer(sk->sk_reuseport_cb) ||
+ (sk2->sk_state != TCP_TIME_WAIT &&
+ !uid_eq(uid, sock_i_uid(sk2)))) {
if (inet_rcv_saddr_equal(sk, sk2, true))
break;
}
@@ -176,12 +180,14 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
int port = 0;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
+ bool relax = false;
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
+ports_exhausted:
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
@@ -219,7 +225,7 @@ other_parity_scan:
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
tb->port == port) {
- if (!inet_csk_bind_conflict(sk, tb, false, false))
+ if (!inet_csk_bind_conflict(sk, tb, relax, false))
goto success;
goto next_port;
}
@@ -239,6 +245,12 @@ next_port:
attempt_half = 2;
goto other_half_scan;
}
+
+ if (net->ipv4.sysctl_ip_autobind_reuse && !relax) {
+ /* We still have a chance to connect to different destinations */
+ relax = true;
+ goto ports_exhausted;
+ }
return NULL;
success:
*port_ret = port;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8c8377568a78..5d50aad3cdbf 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -23,6 +23,7 @@
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/inet6_hashtables.h>
+#include <net/bpf_sk_storage.h>
#include <net/netlink.h>
#include <linux/inet.h>
@@ -170,26 +171,28 @@ errout:
}
EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill);
+#define MAX_DUMP_ALLOC_SIZE (KMALLOC_MAX_SIZE - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
- struct sk_buff *skb, const struct inet_diag_req_v2 *req,
- struct user_namespace *user_ns,
- u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh,
- bool net_admin)
+ struct sk_buff *skb, struct netlink_callback *cb,
+ const struct inet_diag_req_v2 *req,
+ u16 nlmsg_flags, bool net_admin)
{
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
+ struct inet_diag_dump_data *cb_data;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
+ cb_data = cb->data;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
- nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
- nlmsg_flags);
+ nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
@@ -201,7 +204,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
r->idiag_timer = 0;
r->idiag_retrans = 0;
- if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
+ if (inet_diag_msg_attrs_fill(sk, skb, r, ext,
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
+ net_admin))
goto errout;
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
@@ -298,6 +303,48 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
goto errout;
}
+ /* Keep it at the end for potential retry with a larger skb,
+ * or else do best-effort fitting, which is only done for the
+ * first_nlmsg.
+ */
+ if (cb_data->bpf_stg_diag) {
+ bool first_nlmsg = ((unsigned char *)nlh == skb->data);
+ unsigned int prev_min_dump_alloc;
+ unsigned int total_nla_size = 0;
+ unsigned int msg_len;
+ int err;
+
+ msg_len = skb_tail_pointer(skb) - (unsigned char *)nlh;
+ err = bpf_sk_storage_diag_put(cb_data->bpf_stg_diag, sk, skb,
+ INET_DIAG_SK_BPF_STORAGES,
+ &total_nla_size);
+
+ if (!err)
+ goto out;
+
+ total_nla_size += msg_len;
+ prev_min_dump_alloc = cb->min_dump_alloc;
+ if (total_nla_size > prev_min_dump_alloc)
+ cb->min_dump_alloc = min_t(u32, total_nla_size,
+ MAX_DUMP_ALLOC_SIZE);
+
+ if (!first_nlmsg)
+ goto errout;
+
+ if (cb->min_dump_alloc > prev_min_dump_alloc)
+ /* Retry with pskb_expand_head() with
+ * __GFP_DIRECT_RECLAIM
+ */
+ goto errout;
+
+ WARN_ON_ONCE(total_nla_size <= prev_min_dump_alloc);
+
+ /* Send what we have for this sk
+ * and move on to the next sk in the following
+ * dump()
+ */
+ }
+
out:
nlmsg_end(skb, nlh);
return 0;
@@ -308,30 +355,19 @@ errout:
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
-static int inet_csk_diag_fill(struct sock *sk,
- struct sk_buff *skb,
- const struct inet_diag_req_v2 *req,
- struct user_namespace *user_ns,
- u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh,
- bool net_admin)
-{
- return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns,
- portid, seq, nlmsg_flags, unlh, net_admin);
-}
-
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
- u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh)
+ struct netlink_callback *cb,
+ u16 nlmsg_flags)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
- nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
- nlmsg_flags);
+ nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type,
+ sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
@@ -355,16 +391,16 @@ static int inet_twsk_diag_fill(struct sock *sk,
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
- u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh, bool net_admin)
+ struct netlink_callback *cb,
+ u16 nlmsg_flags, bool net_admin)
{
struct request_sock *reqsk = inet_reqsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
- nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
- nlmsg_flags);
+ nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+ cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
@@ -393,21 +429,18 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
+ struct netlink_callback *cb,
const struct inet_diag_req_v2 *r,
- struct user_namespace *user_ns,
- u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh, bool net_admin)
+ u16 nlmsg_flags, bool net_admin)
{
if (sk->sk_state == TCP_TIME_WAIT)
- return inet_twsk_diag_fill(sk, skb, portid, seq,
- nlmsg_flags, unlh);
+ return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags);
if (sk->sk_state == TCP_NEW_SYN_RECV)
- return inet_req_diag_fill(sk, skb, portid, seq,
- nlmsg_flags, unlh, net_admin);
+ return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin);
- return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
- nlmsg_flags, unlh, net_admin);
+ return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags,
+ net_admin);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
@@ -455,10 +488,10 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
- struct sk_buff *in_skb,
- const struct nlmsghdr *nlh,
+ struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
+ struct sk_buff *in_skb = cb->skb;
bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN);
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
@@ -475,10 +508,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
goto out;
}
- err = sk_diag_fill(sk, rep, req,
- sk_user_ns(NETLINK_CB(in_skb).sk),
- NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0, nlh, net_admin);
+ err = sk_diag_fill(sk, rep, cb, req, 0, net_admin);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
@@ -505,14 +535,21 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
int err;
handler = inet_diag_lock_handler(req->sdiag_protocol);
- if (IS_ERR(handler))
+ if (IS_ERR(handler)) {
err = PTR_ERR(handler);
- else if (cmd == SOCK_DIAG_BY_FAMILY)
- err = handler->dump_one(in_skb, nlh, req);
- else if (cmd == SOCK_DESTROY && handler->destroy)
+ } else if (cmd == SOCK_DIAG_BY_FAMILY) {
+ struct inet_diag_dump_data empty_dump_data = {};
+ struct netlink_callback cb = {
+ .nlh = nlh,
+ .skb = in_skb,
+ .data = &empty_dump_data,
+ };
+ err = handler->dump_one(&cb, req);
+ } else if (cmd == SOCK_DESTROY && handler->destroy) {
err = handler->destroy(in_skb, req);
- else
+ } else {
err = -EOPNOTSUPP;
+ }
inet_diag_unlock_handler(handler);
return err;
@@ -843,23 +880,6 @@ static int inet_diag_bc_audit(const struct nlattr *attr,
return len == 0 ? 0 : -EINVAL;
}
-static int inet_csk_diag_dump(struct sock *sk,
- struct sk_buff *skb,
- struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r,
- const struct nlattr *bc,
- bool net_admin)
-{
- if (!inet_diag_bc_sk(bc, sk))
- return 0;
-
- return inet_csk_diag_fill(sk, skb, r,
- sk_user_ns(NETLINK_CB(cb->skb).sk),
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh,
- net_admin);
-}
-
static void twsk_build_assert(void)
{
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) !=
@@ -888,14 +908,17 @@ static void twsk_build_assert(void)
void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r, struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
+ struct inet_diag_dump_data *cb_data = cb->data;
struct net *net = sock_net(skb->sk);
u32 idiag_states = r->idiag_states;
int i, num, s_i, s_num;
+ struct nlattr *bc;
struct sock *sk;
+ bc = cb_data->inet_diag_nla_bc;
if (idiag_states & TCPF_SYN_RECV)
idiag_states |= TCPF_NEW_SYN_RECV;
s_i = cb->args[1];
@@ -931,8 +954,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
r->id.idiag_sport)
goto next_listen;
- if (inet_csk_diag_dump(sk, skb, cb, r,
- bc, net_admin) < 0) {
+ if (!inet_diag_bc_sk(bc, sk))
+ goto next_listen;
+
+ if (inet_sk_diag_fill(sk, inet_csk(sk), skb,
+ cb, r, NLM_F_MULTI,
+ net_admin) < 0) {
spin_unlock(&ilb->lock);
goto done;
}
@@ -1010,11 +1037,8 @@ next_normal:
res = 0;
for (idx = 0; idx < accum; idx++) {
if (res >= 0) {
- res = sk_diag_fill(sk_arr[idx], skb, r,
- sk_user_ns(NETLINK_CB(cb->skb).sk),
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI,
- cb->nlh, net_admin);
+ res = sk_diag_fill(sk_arr[idx], skb, cb, r,
+ NLM_F_MULTI, net_admin);
if (res < 0)
num = num_arr[idx];
}
@@ -1038,31 +1062,101 @@ out:
EXPORT_SYMBOL_GPL(inet_diag_dump_icsk);
static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r,
- struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
const struct inet_diag_handler *handler;
+ u32 prev_min_dump_alloc;
int err = 0;
+again:
+ prev_min_dump_alloc = cb->min_dump_alloc;
handler = inet_diag_lock_handler(r->sdiag_protocol);
if (!IS_ERR(handler))
- handler->dump(skb, cb, r, bc);
+ handler->dump(skb, cb, r);
else
err = PTR_ERR(handler);
inet_diag_unlock_handler(handler);
+ /* The skb is not large enough to fit one sk info and
+ * inet_sk_diag_fill() has requested for a larger skb.
+ */
+ if (!skb->len && cb->min_dump_alloc > prev_min_dump_alloc) {
+ err = pskb_expand_head(skb, 0, cb->min_dump_alloc, GFP_KERNEL);
+ if (!err)
+ goto again;
+ }
+
return err ? : skb->len;
}
static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- int hdrlen = sizeof(struct inet_diag_req_v2);
- struct nlattr *bc = NULL;
+ return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh));
+}
- if (nlmsg_attrlen(cb->nlh, hdrlen))
- bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
+static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen)
+{
+ const struct nlmsghdr *nlh = cb->nlh;
+ struct inet_diag_dump_data *cb_data;
+ struct sk_buff *skb = cb->skb;
+ struct nlattr *nla;
+ int rem, err;
+
+ cb_data = kzalloc(sizeof(*cb_data), GFP_KERNEL);
+ if (!cb_data)
+ return -ENOMEM;
+
+ nla_for_each_attr(nla, nlmsg_attrdata(nlh, hdrlen),
+ nlmsg_attrlen(nlh, hdrlen), rem) {
+ int type = nla_type(nla);
+
+ if (type < __INET_DIAG_REQ_MAX)
+ cb_data->req_nlas[type] = nla;
+ }
+
+ nla = cb_data->inet_diag_nla_bc;
+ if (nla) {
+ err = inet_diag_bc_audit(nla, skb);
+ if (err) {
+ kfree(cb_data);
+ return err;
+ }
+ }
+
+ nla = cb_data->inet_diag_nla_bpf_stgs;
+ if (nla) {
+ struct bpf_sk_storage_diag *bpf_stg_diag;
+
+ bpf_stg_diag = bpf_sk_storage_diag_alloc(nla);
+ if (IS_ERR(bpf_stg_diag)) {
+ kfree(cb_data);
+ return PTR_ERR(bpf_stg_diag);
+ }
+ cb_data->bpf_stg_diag = bpf_stg_diag;
+ }
+
+ cb->data = cb_data;
+ return 0;
+}
+
+static int inet_diag_dump_start(struct netlink_callback *cb)
+{
+ return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req_v2));
+}
+
+static int inet_diag_dump_start_compat(struct netlink_callback *cb)
+{
+ return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req));
+}
- return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh), bc);
+static int inet_diag_dump_done(struct netlink_callback *cb)
+{
+ struct inet_diag_dump_data *cb_data = cb->data;
+
+ bpf_sk_storage_diag_free(cb_data->bpf_stg_diag);
+ kfree(cb->data);
+
+ return 0;
}
static int inet_diag_type2proto(int type)
@@ -1081,9 +1175,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb,
struct netlink_callback *cb)
{
struct inet_diag_req *rc = nlmsg_data(cb->nlh);
- int hdrlen = sizeof(struct inet_diag_req);
struct inet_diag_req_v2 req;
- struct nlattr *bc = NULL;
req.sdiag_family = AF_UNSPEC; /* compatibility */
req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type);
@@ -1091,10 +1183,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb,
req.idiag_states = rc->idiag_states;
req.id = rc->id;
- if (nlmsg_attrlen(cb->nlh, hdrlen))
- bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
-
- return __inet_diag_dump(skb, cb, &req, bc);
+ return __inet_diag_dump(skb, cb, &req);
}
static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
@@ -1122,22 +1211,12 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
return -EINVAL;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
- if (nlmsg_attrlen(nlh, hdrlen)) {
- struct nlattr *attr;
- int err;
-
- attr = nlmsg_find_attr(nlh, hdrlen,
- INET_DIAG_REQ_BYTECODE);
- err = inet_diag_bc_audit(attr, skb);
- if (err)
- return err;
- }
- {
- struct netlink_dump_control c = {
- .dump = inet_diag_dump_compat,
- };
- return netlink_dump_start(net->diag_nlsk, skb, nlh, &c);
- }
+ struct netlink_dump_control c = {
+ .start = inet_diag_dump_start_compat,
+ .done = inet_diag_dump_done,
+ .dump = inet_diag_dump_compat,
+ };
+ return netlink_dump_start(net->diag_nlsk, skb, nlh, &c);
}
return inet_diag_get_exact_compat(skb, nlh);
@@ -1153,22 +1232,12 @@ static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h)
if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY &&
h->nlmsg_flags & NLM_F_DUMP) {
- if (nlmsg_attrlen(h, hdrlen)) {
- struct nlattr *attr;
- int err;
-
- attr = nlmsg_find_attr(h, hdrlen,
- INET_DIAG_REQ_BYTECODE);
- err = inet_diag_bc_audit(attr, skb);
- if (err)
- return err;
- }
- {
- struct netlink_dump_control c = {
- .dump = inet_diag_dump,
- };
- return netlink_dump_start(net->diag_nlsk, skb, h, &c);
- }
+ struct netlink_dump_control c = {
+ .start = inet_diag_dump_start,
+ .done = inet_diag_dump_done,
+ .dump = inet_diag_dump,
+ };
+ return netlink_dump_start(net->diag_nlsk, skb, h, &c);
}
return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h));
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index aa438c6758a7..b0c244af1e4d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -509,7 +509,8 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
IPCB(skb)->iif = skb->skb_iif;
/* Must drop socket now because of tproxy. */
- skb_orphan(skb);
+ if (!skb_sk_is_prefetched(skb))
+ skb_orphan(skb);
return skb;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d84819893db9..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);
@@ -333,7 +333,7 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk,
switch (ret) {
case NET_XMIT_CN:
do_cn = true;
- /* fall through */
+ fallthrough;
case NET_XMIT_SUCCESS:
break;
default:
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 74e1d964a615..cd4b84310d92 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -142,11 +142,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
cand = t;
}
- if (flags & TUNNEL_NO_KEY)
- goto skip_key_lookup;
-
hlist_for_each_entry_rcu(t, head, hash_node) {
- if (t->parms.i_key != key ||
+ if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) ||
t->parms.iph.saddr != 0 ||
t->parms.iph.daddr != 0 ||
!(t->dev->flags & IFF_UP))
@@ -158,7 +155,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
cand = t;
}
-skip_key_lookup:
if (cand)
return cand;
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/ipmr.c b/net/ipv4/ipmr.c
index 6e68def66822..9cf83cc85e4a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1465,7 +1465,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
case MRT_ADD_MFC:
case MRT_DEL_MFC:
parent = -1;
- /* fall through */
+ fallthrough;
case MRT_ADD_MFC_PROXY:
case MRT_DEL_MFC_PROXY:
if (optlen != sizeof(mfc)) {
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/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 4b2d49cc9f1a..0c72156130b6 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -173,7 +173,7 @@ static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
case ICMP_REDIRECT:
/* Max length: 24 "GATEWAY=255.255.255.255 " */
nf_log_buf_add(m, "GATEWAY=%pI4 ", &ich->un.gateway);
- /* Fall through */
+ fallthrough;
case ICMP_DEST_UNREACH:
case ICMP_SOURCE_QUENCH:
case ICMP_TIME_EXCEEDED:
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index b2aeb7bf5dac..3c25a467b3ef 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -168,7 +168,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
pptp_msg_name[0]);
- /* fall through */
+ fallthrough;
case PPTP_SET_LINK_INFO:
/* only need to NAT in case PAC is behind NAT box */
case PPTP_START_SESSION_REQUEST:
@@ -271,7 +271,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
pr_debug("unknown inbound packet %s\n",
msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
pptp_msg_name[0]);
- /* fall through */
+ fallthrough;
case PPTP_START_SESSION_REQUEST:
case PPTP_START_SESSION_REPLY:
case PPTP_STOP_SESSION_REQUEST:
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d072c326dd64..fdfca534d094 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1327,7 +1327,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
case AF_UNSPEC:
if (tb[NHA_GROUP])
break;
- /* fallthrough */
+ fallthrough;
default:
NL_SET_ERR_MSG(extack, "Invalid address family");
goto out;
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/raw.c b/net/ipv4/raw.c
index 3183413ebc6c..47665919048f 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1034,6 +1034,7 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
}
void *raw_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(&h->lock)
{
struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
@@ -1056,6 +1057,7 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
EXPORT_SYMBOL_GPL(raw_seq_next);
void raw_seq_stop(struct seq_file *seq, void *v)
+ __releases(&h->lock)
{
struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index a93e7d1e1251..1b5b8af27aaf 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -87,15 +87,16 @@ out_unlock:
return sk ? sk : ERR_PTR(-ENOENT);
}
-static int raw_diag_dump_one(struct sk_buff *in_skb,
- const struct nlmsghdr *nlh,
+static int raw_diag_dump_one(struct netlink_callback *cb,
const struct inet_diag_req_v2 *r)
{
- struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *in_skb = cb->skb;
struct sk_buff *rep;
struct sock *sk;
+ struct net *net;
int err;
+ net = sock_net(in_skb->sk);
sk = raw_sock_get(net, r);
if (IS_ERR(sk))
return PTR_ERR(sk);
@@ -109,10 +110,7 @@ static int raw_diag_dump_one(struct sk_buff *in_skb,
return -ENOMEM;
}
- err = inet_sk_diag_fill(sk, NULL, rep, r,
- sk_user_ns(NETLINK_CB(in_skb).sk),
- NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0, nlh,
+ err = inet_sk_diag_fill(sk, NULL, rep, cb, r, 0,
netlink_net_capable(in_skb, CAP_NET_ADMIN));
sock_put(sk);
@@ -137,25 +135,25 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
if (!inet_diag_bc_sk(bc, sk))
return 0;
- return inet_sk_diag_fill(sk, NULL, skb, r,
- sk_user_ns(NETLINK_CB(cb->skb).sk),
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI,
- cb->nlh, net_admin);
+ return inet_sk_diag_fill(sk, NULL, skb, cb, r, NLM_F_MULTI, net_admin);
}
static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r, struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
struct net *net = sock_net(skb->sk);
+ struct inet_diag_dump_data *cb_data;
int num, s_num, slot, s_slot;
struct sock *sk = NULL;
+ struct nlattr *bc;
if (IS_ERR(hashinfo))
return;
+ cb_data = cb->data;
+ bc = cb_data->inet_diag_nla_bc;
s_slot = cb->args[0];
num = s_num = cb->args[1];
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ebe7060d0fc9..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);
@@ -2774,6 +2771,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
+struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
+ struct net_device *dev,
+ struct net *net, __be32 *saddr,
+ const struct ip_tunnel_info *info,
+ u8 protocol, bool use_cache)
+{
+#ifdef CONFIG_DST_CACHE
+ struct dst_cache *dst_cache;
+#endif
+ struct rtable *rt = NULL;
+ struct flowi4 fl4;
+ __u8 tos;
+
+#ifdef CONFIG_DST_CACHE
+ dst_cache = (struct dst_cache *)&info->dst_cache;
+ if (use_cache) {
+ rt = dst_cache_get_ip4(dst_cache, saddr);
+ if (rt)
+ return rt;
+ }
+#endif
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_mark = skb->mark;
+ fl4.flowi4_proto = protocol;
+ fl4.daddr = info->key.u.ipv4.dst;
+ fl4.saddr = info->key.u.ipv4.src;
+ tos = info->key.tos;
+ fl4.flowi4_tos = RT_TOS(tos);
+
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+ return ERR_PTR(-ENETUNREACH);
+ }
+ if (rt->dst.dev == dev) { /* is this necessary? */
+ netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
+ ip_rt_put(rt);
+ return ERR_PTR(-ELOOP);
+ }
+#ifdef CONFIG_DST_CACHE
+ if (use_cache)
+ dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+#endif
+ *saddr = fl4.saddr;
+ return rt;
+}
+EXPORT_SYMBOL_GPL(ip_route_output_tunnel);
+
/* called with rcu_read_lock held */
static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
struct rtable *rt, u32 table_id, struct flowi4 *fl4,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9684af02e0a5..81b267e990a1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -555,18 +555,6 @@ static struct ctl_table ipv4_table[] = {
},
#endif /* CONFIG_NETLABEL */
{
- .procname = "tcp_available_congestion_control",
- .maxlen = TCP_CA_BUF_MAX,
- .mode = 0444,
- .proc_handler = proc_tcp_available_congestion_control,
- },
- {
- .procname = "tcp_allowed_congestion_control",
- .maxlen = TCP_CA_BUF_MAX,
- .mode = 0644,
- .proc_handler = proc_allowed_congestion_control,
- },
- {
.procname = "tcp_available_ulp",
.maxlen = TCP_ULP_BUF_MAX,
.mode = 0444,
@@ -776,6 +764,15 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "ip_autobind_reuse",
+ .data = &init_net.ipv4.sysctl_ip_autobind_reuse,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
.procname = "fwmark_reflect",
.data = &init_net.ipv4.sysctl_fwmark_reflect,
.maxlen = sizeof(int),
@@ -886,6 +883,18 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_tcp_congestion_control,
},
{
+ .procname = "tcp_available_congestion_control",
+ .maxlen = TCP_CA_BUF_MAX,
+ .mode = 0444,
+ .proc_handler = proc_tcp_available_congestion_control,
+ },
+ {
+ .procname = "tcp_allowed_congestion_control",
+ .maxlen = TCP_CA_BUF_MAX,
+ .mode = 0644,
+ .proc_handler = proc_allowed_congestion_control,
+ },
+ {
.procname = "tcp_keepalive_time",
.data = &init_net.ipv4.sysctl_tcp_keepalive_time,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc77c303e6f7..6d87de434377 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2251,7 +2251,7 @@ void tcp_set_state(struct sock *sk, int state)
if (inet_csk(sk)->icsk_bind_hash &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
inet_put_port(sk);
- /* fall through */
+ fallthrough;
default:
if (oldstate == TCP_ESTABLISHED)
TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
@@ -3346,6 +3346,7 @@ static size_t tcp_opt_stats_get_size(void)
nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */
nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */
0;
}
@@ -3401,6 +3402,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3);
nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash);
+ nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT,
+ max_t(int, 0, tp->write_seq - tp->snd_nxt));
return stats;
}
@@ -3669,13 +3672,35 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
if (get_user(len, optlen))
return -EFAULT;
- if (len != sizeof(zc))
+ if (len < offsetofend(struct tcp_zerocopy_receive, length))
return -EINVAL;
+ if (len > sizeof(zc)) {
+ len = sizeof(zc);
+ if (put_user(len, optlen))
+ return -EFAULT;
+ }
if (copy_from_user(&zc, optval, len))
return -EFAULT;
lock_sock(sk);
err = tcp_zerocopy_receive(sk, &zc);
release_sock(sk);
+ if (len == sizeof(zc))
+ goto zerocopy_rcv_sk_err;
+ switch (len) {
+ case offsetofend(struct tcp_zerocopy_receive, err):
+ goto zerocopy_rcv_sk_err;
+ case offsetofend(struct tcp_zerocopy_receive, inq):
+ goto zerocopy_rcv_inq;
+ case offsetofend(struct tcp_zerocopy_receive, length):
+ default:
+ goto zerocopy_rcv_out;
+ }
+zerocopy_rcv_sk_err:
+ if (!err)
+ zc.err = sock_error(sk);
+zerocopy_rcv_inq:
+ zc.inq = tcp_inq_hint(sk);
+zerocopy_rcv_out:
if (!err && copy_to_user(optval, &zc, len))
err = -EFAULT;
return err;
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_bpf.c b/net/ipv4/tcp_bpf.c
index 8a01428f80c1..5a05327f97c1 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -10,38 +10,6 @@
#include <net/inet_common.h>
#include <net/tls.h>
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
- struct sk_psock *psock;
- bool empty = true;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (likely(psock))
- empty = list_empty(&psock->ingress_msg);
- rcu_read_unlock();
- return !empty;
-}
-
-static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
- int flags, long timeo, int *err)
-{
- DEFINE_WAIT_FUNC(wait, woken_wake_function);
- int ret = 0;
-
- if (!timeo)
- return ret;
-
- add_wait_queue(sk_sleep(sk), &wait);
- sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- ret = sk_wait_event(sk, &timeo,
- !list_empty(&psock->ingress_msg) ||
- !skb_queue_empty(&sk->sk_receive_queue), &wait);
- sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- remove_wait_queue(sk_sleep(sk), &wait);
- return ret;
-}
-
int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
struct msghdr *msg, int len, int flags)
{
@@ -115,49 +83,6 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
}
EXPORT_SYMBOL_GPL(__tcp_bpf_recvmsg);
-int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
- int nonblock, int flags, int *addr_len)
-{
- struct sk_psock *psock;
- int copied, ret;
-
- psock = sk_psock_get(sk);
- if (unlikely(!psock))
- return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
- if (unlikely(flags & MSG_ERRQUEUE))
- return inet_recv_error(sk, msg, len, addr_len);
- if (!skb_queue_empty(&sk->sk_receive_queue) &&
- sk_psock_queue_empty(psock))
- return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
- lock_sock(sk);
-msg_bytes_ready:
- copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
- if (!copied) {
- int data, err = 0;
- long timeo;
-
- timeo = sock_rcvtimeo(sk, nonblock);
- data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
- if (data) {
- if (!sk_psock_queue_empty(psock))
- goto msg_bytes_ready;
- release_sock(sk);
- sk_psock_put(sk, psock);
- return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
- }
- if (err) {
- ret = err;
- goto out;
- }
- copied = -EAGAIN;
- }
- ret = copied;
-out:
- release_sock(sk);
- sk_psock_put(sk, psock);
- return ret;
-}
-
static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
struct sk_msg *msg, u32 apply_bytes, int flags)
{
@@ -298,6 +223,82 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
}
EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
+#ifdef CONFIG_BPF_STREAM_PARSER
+static bool tcp_bpf_stream_read(const struct sock *sk)
+{
+ struct sk_psock *psock;
+ bool empty = true;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (likely(psock))
+ empty = list_empty(&psock->ingress_msg);
+ rcu_read_unlock();
+ return !empty;
+}
+
+static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
+ int flags, long timeo, int *err)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret = 0;
+
+ if (!timeo)
+ return ret;
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ ret = sk_wait_event(sk, &timeo,
+ !list_empty(&psock->ingress_msg) ||
+ !skb_queue_empty(&sk->sk_receive_queue), &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return ret;
+}
+
+static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len)
+{
+ struct sk_psock *psock;
+ int copied, ret;
+
+ psock = sk_psock_get(sk);
+ if (unlikely(!psock))
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ if (unlikely(flags & MSG_ERRQUEUE))
+ return inet_recv_error(sk, msg, len, addr_len);
+ if (!skb_queue_empty(&sk->sk_receive_queue) &&
+ sk_psock_queue_empty(psock))
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ lock_sock(sk);
+msg_bytes_ready:
+ copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
+ if (!copied) {
+ int data, err = 0;
+ long timeo;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+ data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
+ if (data) {
+ if (!sk_psock_queue_empty(psock))
+ goto msg_bytes_ready;
+ release_sock(sk);
+ sk_psock_put(sk, psock);
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ }
+ if (err) {
+ ret = err;
+ goto out;
+ }
+ copied = -EAGAIN;
+ }
+ ret = copied;
+out:
+ release_sock(sk);
+ sk_psock_put(sk, psock);
+ return ret;
+}
+
static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
struct sk_msg *msg, int *copied, int flags)
{
@@ -528,57 +529,6 @@ out_err:
return copied ? copied : err;
}
-static void tcp_bpf_remove(struct sock *sk, struct sk_psock *psock)
-{
- struct sk_psock_link *link;
-
- while ((link = sk_psock_link_pop(psock))) {
- sk_psock_unlink(sk, link);
- sk_psock_free_link(link);
- }
-}
-
-static void tcp_bpf_unhash(struct sock *sk)
-{
- void (*saved_unhash)(struct sock *sk);
- struct sk_psock *psock;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (unlikely(!psock)) {
- rcu_read_unlock();
- if (sk->sk_prot->unhash)
- sk->sk_prot->unhash(sk);
- return;
- }
-
- saved_unhash = psock->saved_unhash;
- tcp_bpf_remove(sk, psock);
- rcu_read_unlock();
- saved_unhash(sk);
-}
-
-static void tcp_bpf_close(struct sock *sk, long timeout)
-{
- void (*saved_close)(struct sock *sk, long timeout);
- struct sk_psock *psock;
-
- lock_sock(sk);
- rcu_read_lock();
- psock = sk_psock(sk);
- if (unlikely(!psock)) {
- rcu_read_unlock();
- release_sock(sk);
- return sk->sk_prot->close(sk, timeout);
- }
-
- saved_close = psock->saved_close;
- tcp_bpf_remove(sk, psock);
- rcu_read_unlock();
- release_sock(sk);
- saved_close(sk, timeout);
-}
-
enum {
TCP_BPF_IPV4,
TCP_BPF_IPV6,
@@ -599,8 +549,8 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
struct proto *base)
{
prot[TCP_BPF_BASE] = *base;
- prot[TCP_BPF_BASE].unhash = tcp_bpf_unhash;
- prot[TCP_BPF_BASE].close = tcp_bpf_close;
+ prot[TCP_BPF_BASE].unhash = sock_map_unhash;
+ prot[TCP_BPF_BASE].close = sock_map_close;
prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg;
prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read;
@@ -629,26 +579,6 @@ static int __init tcp_bpf_v4_build_proto(void)
}
core_initcall(tcp_bpf_v4_build_proto);
-static void tcp_bpf_update_sk_prot(struct sock *sk, struct sk_psock *psock)
-{
- int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
- int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;
-
- sk_psock_update_proto(sk, psock, &tcp_bpf_prots[family][config]);
-}
-
-static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock)
-{
- int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
- int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;
-
- /* Reinit occurs when program types change e.g. TCP_BPF_TX is removed
- * or added requiring sk_prot hook updates. We keep original saved
- * hooks in this case.
- */
- sk->sk_prot = &tcp_bpf_prots[family][config];
-}
-
static int tcp_bpf_assert_proto_ops(struct proto *ops)
{
/* In order to avoid retpoline, we make assumptions when we call
@@ -660,34 +590,34 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
}
-void tcp_bpf_reinit(struct sock *sk)
+struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
{
- struct sk_psock *psock;
+ int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
+ int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;
- sock_owned_by_me(sk);
+ if (!psock->sk_proto) {
+ struct proto *ops = READ_ONCE(sk->sk_prot);
- rcu_read_lock();
- psock = sk_psock(sk);
- tcp_bpf_reinit_sk_prot(sk, psock);
- rcu_read_unlock();
+ if (tcp_bpf_assert_proto_ops(ops))
+ return ERR_PTR(-EINVAL);
+
+ tcp_bpf_check_v6_needs_rebuild(sk, ops);
+ }
+
+ return &tcp_bpf_prots[family][config];
}
-int tcp_bpf_init(struct sock *sk)
+/* If a child got cloned from a listening socket that had tcp_bpf
+ * protocol callbacks installed, we need to restore the callbacks to
+ * the default ones because the child does not inherit the psock state
+ * that tcp_bpf callbacks expect.
+ */
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
{
- struct proto *ops = READ_ONCE(sk->sk_prot);
- struct sk_psock *psock;
-
- sock_owned_by_me(sk);
+ int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
+ struct proto *prot = newsk->sk_prot;
- rcu_read_lock();
- psock = sk_psock(sk);
- if (unlikely(!psock || psock->sk_proto ||
- tcp_bpf_assert_proto_ops(ops))) {
- rcu_read_unlock();
- return -EINVAL;
- }
- tcp_bpf_check_v6_needs_rebuild(sk, ops);
- tcp_bpf_update_sk_prot(sk, psock);
- rcu_read_unlock();
- return 0;
+ if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
+ newsk->sk_prot = sk->sk_prot_creator;
}
+#endif /* CONFIG_BPF_STREAM_PARSER */
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 0d08f9e2d8d0..75a1c985f49a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -179,15 +179,15 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
}
static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r, struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
- inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
+ inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r);
}
-static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+static int tcp_diag_dump_one(struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
- return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
+ return inet_diag_dump_one_icsk(&tcp_hashinfo, cb, req);
}
#ifdef CONFIG_INET_DIAG_DESTROY
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6b6b57000dad..bf4ced9273e8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2865,7 +2865,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
(*ack_flag & FLAG_LOST_RETRANS)))
return;
/* Change state if cwnd is undone or retransmits are lost */
- /* fall through */
+ fallthrough;
default:
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
@@ -6367,7 +6367,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
mptcp_incoming_options(sk, skb, &tp->rx_opt);
break;
}
- /* fall through */
+ fallthrough;
case TCP_FIN_WAIT1:
case TCP_FIN_WAIT2:
/* RFC 793 says to queue data in these states,
@@ -6382,7 +6382,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
return 1;
}
}
- /* Fall through */
+ fallthrough;
case TCP_ESTABLISHED:
tcp_data_queue(sk, skb);
queued = 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index df1166b76126..83a5d24e13b8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1019,7 +1019,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
if (!md5sig)
return NULL;
- hlist_for_each_entry_rcu(key, &md5sig->head, node) {
+ hlist_for_each_entry_rcu(key, &md5sig->head, node,
+ lockdep_sock_is_held(sk)) {
if (key->family != family)
continue;
if (key->l3index && key->l3index != l3index)
@@ -1064,7 +1065,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
if (family == AF_INET6)
size = sizeof(struct in6_addr);
#endif
- hlist_for_each_entry_rcu(key, &md5sig->head, node) {
+ hlist_for_each_entry_rcu(key, &md5sig->head, node,
+ lockdep_sock_is_held(sk)) {
if (key->family != family)
continue;
if (key->l3index && key->l3index != l3index)
@@ -2070,7 +2072,7 @@ do_time_wait:
}
}
/* to ACK */
- /* fall through */
+ fallthrough;
case TCP_TW_ACK:
tcp_v4_timewait_ack(sk, skb);
break;
@@ -2366,7 +2368,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
break;
st->bucket = 0;
st->state = TCP_SEQ_STATE_ESTABLISHED;
- /* Fallthrough */
+ fallthrough;
case TCP_SEQ_STATE_ESTABLISHED:
if (st->bucket > tcp_hashinfo.ehash_mask)
break;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ad3b56d9fa71..7e40322cc5ec 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,6 +548,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->fastopen_req = NULL;
RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
+ tcp_bpf_clone(sk, newsk);
+
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
return newsk;
@@ -772,6 +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;
@@ -817,6 +825,7 @@ EXPORT_SYMBOL(tcp_check_req);
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb)
+ __releases(&((child)->sk_lock.slock))
{
int ret = 0;
int state = child->sk_state;
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_ulp.c b/net/ipv4/tcp_ulp.c
index 38d3ad141161..7c27aa629af1 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -22,7 +22,8 @@ static struct tcp_ulp_ops *tcp_ulp_find(const char *name)
{
struct tcp_ulp_ops *e;
- list_for_each_entry_rcu(e, &tcp_ulp_list, list) {
+ list_for_each_entry_rcu(e, &tcp_ulp_list, list,
+ lockdep_is_held(&tcp_ulp_list_lock)) {
if (strcmp(e->name, name) == 0)
return e;
}
@@ -104,12 +105,6 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto,
{
struct inet_connection_sock *icsk = inet_csk(sk);
- if (!icsk->icsk_ulp_ops) {
- sk->sk_write_space = write_space;
- sk->sk_prot = proto;
- return;
- }
-
if (icsk->icsk_ulp_ops->update)
icsk->icsk_ulp_ops->update(sk, proto, write_space);
}
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 08a41f1e1cd2..32564b350823 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1671,10 +1671,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
error = -EAGAIN;
do {
spin_lock_bh(&queue->lock);
- skb = __skb_try_recv_from_queue(sk, queue, flags,
- udp_skb_destructor,
- off, err, &last);
+ skb = __skb_try_recv_from_queue(sk, queue, flags, off,
+ err, &last);
if (skb) {
+ if (!(flags & MSG_PEEK))
+ udp_skb_destructor(sk, skb);
spin_unlock_bh(&queue->lock);
return skb;
}
@@ -1692,9 +1693,10 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
spin_lock(&sk_queue->lock);
skb_queue_splice_tail_init(sk_queue, queue);
- skb = __skb_try_recv_from_queue(sk, queue, flags,
- udp_skb_dtor_locked,
- off, err, &last);
+ skb = __skb_try_recv_from_queue(sk, queue, flags, off,
+ err, &last);
+ if (skb && !(flags & MSG_PEEK))
+ udp_skb_dtor_locked(sk, skb);
spin_unlock(&sk_queue->lock);
spin_unlock_bh(&queue->lock);
if (skb)
@@ -2107,7 +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) {
@@ -2286,6 +2288,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
struct rtable *rt = skb_rtable(skb);
__be32 saddr, daddr;
struct net *net = dev_net(skb->dev);
+ bool refcounted;
/*
* Validate the packet.
@@ -2311,7 +2314,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
- sk = skb_steal_sock(skb);
+ sk = skb_steal_sock(skb, &refcounted);
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -2320,7 +2323,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
udp_sk_rx_dst_set(sk, dst);
ret = udp_unicast_rcv_skb(sk, skb, uh);
- sock_put(sk);
+ if (refcounted)
+ sock_put(sk);
return ret;
}
@@ -2561,7 +2565,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
case UDP_ENCAP_ESPINUDP_NON_IKE:
up->encap_rcv = xfrm4_udp_encap_rcv;
#endif
- /* FALLTHROUGH */
+ fallthrough;
case UDP_ENCAP_L2TPINUDP:
up->encap_type = val;
lock_sock(sk);
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
new file mode 100644
index 000000000000..eddd973e6575
--- /dev/null
+++ b/net/ipv4/udp_bpf.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */
+
+#include <linux/skmsg.h>
+#include <net/sock.h>
+#include <net/udp.h>
+
+enum {
+ UDP_BPF_IPV4,
+ UDP_BPF_IPV6,
+ UDP_BPF_NUM_PROTS,
+};
+
+static struct proto *udpv6_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(udpv6_prot_lock);
+static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
+
+static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+ *prot = *base;
+ prot->unhash = sock_map_unhash;
+ prot->close = sock_map_close;
+}
+
+static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+{
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+ spin_lock_bh(&udpv6_prot_lock);
+ if (likely(ops != udpv6_prot_saved)) {
+ udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
+ smp_store_release(&udpv6_prot_saved, ops);
+ }
+ spin_unlock_bh(&udpv6_prot_lock);
+ }
+}
+
+static int __init udp_bpf_v4_build_proto(void)
+{
+ udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
+ return 0;
+}
+core_initcall(udp_bpf_v4_build_proto);
+
+struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
+{
+ int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
+
+ if (!psock->sk_proto)
+ udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot));
+
+ return &udp_bpf_prots[family];
+}
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index dccd2286bc28..1dbece34496e 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -21,16 +21,15 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
if (!inet_diag_bc_sk(bc, sk))
return 0;
- return inet_sk_diag_fill(sk, NULL, skb, req,
- sk_user_ns(NETLINK_CB(cb->skb).sk),
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin);
+ return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI,
+ net_admin);
}
-static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
- const struct nlmsghdr *nlh,
+static int udp_dump_one(struct udp_table *tbl,
+ struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
+ struct sk_buff *in_skb = cb->skb;
int err = -EINVAL;
struct sock *sk = NULL;
struct sk_buff *rep;
@@ -71,11 +70,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
if (!rep)
goto out;
- err = inet_sk_diag_fill(sk, NULL, rep, req,
- sk_user_ns(NETLINK_CB(in_skb).sk),
- NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0, nlh,
- netlink_net_capable(in_skb, CAP_NET_ADMIN));
+ err = inet_sk_diag_fill(sk, NULL, rep, cb, req, 0,
+ netlink_net_capable(in_skb, CAP_NET_ADMIN));
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(rep);
@@ -94,12 +90,16 @@ out_nosk:
static void udp_dump(struct udp_table *table, struct sk_buff *skb,
struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r, struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
struct net *net = sock_net(skb->sk);
+ struct inet_diag_dump_data *cb_data;
int num, s_num, slot, s_slot;
+ struct nlattr *bc;
+ cb_data = cb->data;
+ bc = cb_data->inet_diag_nla_bc;
s_slot = cb->args[0];
num = s_num = cb->args[1];
@@ -147,15 +147,15 @@ done:
}
static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r, struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
- udp_dump(&udp_table, skb, cb, r, bc);
+ udp_dump(&udp_table, skb, cb, r);
}
-static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+static int udp_diag_dump_one(struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
- return udp_dump_one(&udp_table, in_skb, nlh, req);
+ return udp_dump_one(&udp_table, cb, req);
}
static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
@@ -250,16 +250,15 @@ static const struct inet_diag_handler udp_diag_handler = {
};
static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- const struct inet_diag_req_v2 *r,
- struct nlattr *bc)
+ const struct inet_diag_req_v2 *r)
{
- udp_dump(&udplite_table, skb, cb, r, bc);
+ udp_dump(&udplite_table, skb, cb, r);
}
-static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+static int udplite_diag_dump_one(struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
- return udp_dump_one(&udplite_table, in_skb, nlh, req);
+ return udp_dump_one(&udplite_table, cb, req);
}
static const struct inet_diag_handler udplite_diag_handler = {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 1a98583a79f4..e67a66fbf27b 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -453,6 +453,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
unsigned int off = skb_gro_offset(skb);
int flush = 1;
+ NAPI_GRO_CB(skb)->is_flist = 0;
if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;