aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/core/dst.c10
-rw-r--r--net/core/sock.c6
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/route.c6
-rw-r--r--net/ipv4/sysctl_net_ipv4.c9
-rw-r--r--net/ipv4/tcp_input.c8
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_output.c15
-rw-r--r--net/ipv4/udp.c74
-rw-r--r--net/ipv4/udp_offload.c4
-rw-r--r--net/ipv4/udp_tunnel_core.c2
-rw-r--r--net/ipv4/udplite.c1
-rw-r--r--net/ipv4/xfrm4_input.c4
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/route.c4
-rw-r--r--net/ipv6/udp.c34
-rw-r--r--net/ipv6/udplite.c1
-rw-r--r--net/ipv6/xfrm6_input.c4
-rw-r--r--net/l2tp/l2tp_core.c6
-rw-r--r--net/openvswitch/actions.c4
-rw-r--r--net/sched/cls_route.c37
-rw-r--r--net/sched/sch_frag.c4
-rw-r--r--net/vmw_vsock/af_vsock.c3
-rw-r--r--net/xfrm/xfrm_policy.c2
24 files changed, 129 insertions, 114 deletions
diff --git a/net/core/dst.c b/net/core/dst.c
index 980e2fd2f013..6838d3212c37 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -45,7 +45,7 @@ const struct dst_metrics dst_default_metrics = {
EXPORT_SYMBOL(dst_default_metrics);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
- struct net_device *dev, int initial_ref, int initial_obsolete,
+ struct net_device *dev, int initial_obsolete,
unsigned short flags)
{
dst->dev = dev;
@@ -66,7 +66,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
dst->tclassid = 0;
#endif
dst->lwtstate = NULL;
- rcuref_init(&dst->__rcuref, initial_ref);
+ rcuref_init(&dst->__rcuref, 1);
INIT_LIST_HEAD(&dst->rt_uncached);
dst->__use = 0;
dst->lastuse = jiffies;
@@ -77,7 +77,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
EXPORT_SYMBOL(dst_init);
void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
- int initial_ref, int initial_obsolete, unsigned short flags)
+ int initial_obsolete, unsigned short flags)
{
struct dst_entry *dst;
@@ -90,7 +90,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
if (!dst)
return NULL;
- dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags);
+ dst_init(dst, ops, dev, initial_obsolete, flags);
return dst;
}
@@ -270,7 +270,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst,
struct dst_entry *dst;
dst = &md_dst->dst;
- dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
+ dst_init(dst, &dst_blackhole_ops, NULL, DST_OBSOLETE_NONE,
DST_METADATA | DST_NOCOUNT);
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
md_dst->type = type;
diff --git a/net/core/sock.c b/net/core/sock.c
index 16584e2dd648..bb89b88bc1e8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3001,6 +3001,9 @@ void __sk_flush_backlog(struct sock *sk)
{
spin_lock_bh(&sk->sk_lock.slock);
__release_sock(sk);
+
+ if (sk->sk_prot->release_cb)
+ sk->sk_prot->release_cb(sk);
spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL_GPL(__sk_flush_backlog);
@@ -3519,9 +3522,6 @@ void release_sock(struct sock *sk)
if (sk->sk_backlog.tail)
__release_sock(sk);
- /* Warning : release_cb() might need to release sk ownership,
- * ie call sock_release_ownership(sk) before us.
- */
if (sk->sk_prot->release_cb)
sk->sk_prot->release_cb(sk);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 418e5fb58fd3..76c3ea75b8dd 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2944,8 +2944,6 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l
continue;
state->im = rcu_dereference(state->idev->mc_list);
}
- if (!state->im)
- break;
spin_lock_bh(&state->im->lock);
psf = state->im->sources;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 66f419e7f9a7..fb3045692b99 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1630,7 +1630,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
{
struct rtable *rt;
- rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
+ rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK,
(noxfrm ? DST_NOXFRM : 0));
if (rt) {
@@ -1658,7 +1658,7 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
{
struct rtable *new_rt;
- new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
+ new_rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK,
rt->dst.flags);
if (new_rt) {
@@ -2832,7 +2832,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
struct rtable *ort = (struct rtable *) dst_orig;
struct rtable *rt;
- rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
+ rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0);
if (rt) {
struct dst_entry *new = &rt->dst;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 6ac890b4073f..e7f024d93572 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1367,6 +1367,15 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = SYSCTL_ZERO,
},
{
+ .procname = "tcp_backlog_ack_defer",
+ .data = &init_net.ipv4.sysctl_tcp_backlog_ack_defer,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
.procname = "tcp_reflect_tos",
.data = &init_net.ipv4.sysctl_tcp_reflect_tos,
.maxlen = sizeof(u8),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 06fe1cf645d5..41b471748437 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5553,6 +5553,14 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
tcp_in_quickack_mode(sk) ||
/* Protocol state mandates a one-time immediate ACK */
inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
+ /* If we are running from __release_sock() in user context,
+ * Defer the ack until tcp_release_cb().
+ */
+ if (sock_owned_by_user_nocheck(sk) &&
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_backlog_ack_defer)) {
+ set_bit(TCP_ACK_DEFERRED, &sk->sk_tsq_flags);
+ return;
+ }
send_now:
tcp_send_ack(sk);
return;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 27140e5cdc06..f13eb7e23d03 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3263,6 +3263,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC;
net->ipv4.sysctl_tcp_comp_sack_nr = 44;
+ net->ipv4.sysctl_tcp_backlog_ack_defer = 1;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0;
atomic_set(&net->ipv4.tfo_active_disable_times, 0);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ccfc8bbf7455..1fc1f879cfd6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1077,7 +1077,8 @@ static void tcp_tasklet_func(struct tasklet_struct *t)
#define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \
TCPF_WRITE_TIMER_DEFERRED | \
TCPF_DELACK_TIMER_DEFERRED | \
- TCPF_MTU_REDUCED_DEFERRED)
+ TCPF_MTU_REDUCED_DEFERRED | \
+ TCPF_ACK_DEFERRED)
/**
* tcp_release_cb - tcp release_sock() callback
* @sk: socket
@@ -1101,16 +1102,6 @@ void tcp_release_cb(struct sock *sk)
tcp_tsq_write(sk);
__sock_put(sk);
}
- /* Here begins the tricky part :
- * We are called from release_sock() with :
- * 1) BH disabled
- * 2) sk_lock.slock spinlock held
- * 3) socket owned by us (sk->sk_lock.owned == 1)
- *
- * But following code is meant to be called from BH handlers,
- * so we should keep BH disabled, but early release socket ownership
- */
- sock_release_ownership(sk);
if (flags & TCPF_WRITE_TIMER_DEFERRED) {
tcp_write_timer_handler(sk);
@@ -1124,6 +1115,8 @@ void tcp_release_cb(struct sock *sk)
inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
__sock_put(sk);
}
+ if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk))
+ tcp_send_ack(sk);
}
EXPORT_SYMBOL(tcp_release_cb);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f39b9c844580..c3ff984b6354 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -714,7 +714,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
- if (!sk || udp_sk(sk)->encap_type) {
+ if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) {
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udp_encap_needed_key)) {
sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
@@ -1051,7 +1051,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
u8 tos, scope;
__be16 dport;
int err, is_udplite = IS_UDPLITE(sk);
- int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
+ int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
struct sk_buff *skb;
struct ip_options_data opt_copy;
@@ -1315,11 +1315,11 @@ void udp_splice_eof(struct socket *sock)
struct sock *sk = sock->sk;
struct udp_sock *up = udp_sk(sk);
- if (!up->pending || READ_ONCE(up->corkflag))
+ if (!up->pending || udp_test_bit(CORK, sk))
return;
lock_sock(sk);
- if (up->pending && !READ_ONCE(up->corkflag))
+ if (up->pending && !udp_test_bit(CORK, sk))
udp_push_pending_frames(sk);
release_sock(sk);
}
@@ -1868,7 +1868,7 @@ try_again:
(struct sockaddr *)sin);
}
- if (udp_sk(sk)->gro_enabled)
+ if (udp_test_bit(GRO_ENABLED, sk))
udp_cmsg_recv(msg, sk, skb);
if (inet_cmsg_flags(inet))
@@ -2081,7 +2081,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
}
nf_reset_ct(skb);
- if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
+ if (static_branch_unlikely(&udp_encap_needed_key) &&
+ READ_ONCE(up->encap_type)) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
@@ -2119,7 +2120,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
/*
* UDP-Lite specific tests, ignored on UDP sockets
*/
- if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
+ if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) {
+ u16 pcrlen = READ_ONCE(up->pcrlen);
/*
* MIB statistics other than incrementing the error count are
@@ -2132,7 +2134,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
* delivery of packets with coverage values less than a value
* provided by the application."
*/
- if (up->pcrlen == 0) { /* full coverage was set */
+ if (pcrlen == 0) { /* full coverage was set */
net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
@@ -2143,9 +2145,9 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
* that it wants x while sender emits packets of smaller size y.
* Therefore the above ...()->partial_cov statement is essential.
*/
- if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
+ if (UDP_SKB_CB(skb)->cscov < pcrlen) {
net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n",
- UDP_SKB_CB(skb)->cscov, up->pcrlen);
+ UDP_SKB_CB(skb)->cscov, pcrlen);
goto drop;
}
}
@@ -2618,7 +2620,7 @@ void udp_destroy_sock(struct sock *sk)
if (encap_destroy)
encap_destroy(sk);
}
- if (up->encap_enabled)
+ if (udp_test_bit(ENCAP_ENABLED, sk))
static_branch_dec(&udp_encap_needed_key);
}
}
@@ -2658,9 +2660,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
switch (optname) {
case UDP_CORK:
if (val != 0) {
- WRITE_ONCE(up->corkflag, 1);
+ udp_set_bit(CORK, sk);
} else {
- WRITE_ONCE(up->corkflag, 0);
+ udp_clear_bit(CORK, sk);
lock_sock(sk);
push_pending_frames(sk);
release_sock(sk);
@@ -2675,17 +2677,17 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
case UDP_ENCAP_ESPINUDP_NON_IKE:
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
- up->encap_rcv = ipv6_stub->xfrm6_udp_encap_rcv;
+ WRITE_ONCE(up->encap_rcv,
+ ipv6_stub->xfrm6_udp_encap_rcv);
else
#endif
- up->encap_rcv = xfrm4_udp_encap_rcv;
+ WRITE_ONCE(up->encap_rcv,
+ xfrm4_udp_encap_rcv);
#endif
fallthrough;
case UDP_ENCAP_L2TPINUDP:
- up->encap_type = val;
- lock_sock(sk);
- udp_tunnel_encap_enable(sk->sk_socket);
- release_sock(sk);
+ WRITE_ONCE(up->encap_type, val);
+ udp_tunnel_encap_enable(sk);
break;
default:
err = -ENOPROTOOPT;
@@ -2694,11 +2696,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
break;
case UDP_NO_CHECK6_TX:
- up->no_check6_tx = valbool;
+ udp_set_no_check6_tx(sk, valbool);
break;
case UDP_NO_CHECK6_RX:
- up->no_check6_rx = valbool;
+ udp_set_no_check6_rx(sk, valbool);
break;
case UDP_SEGMENT:
@@ -2708,14 +2710,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
break;
case UDP_GRO:
- lock_sock(sk);
/* when enabling GRO, accept the related GSO packet type */
if (valbool)
- udp_tunnel_encap_enable(sk->sk_socket);
- up->gro_enabled = valbool;
- up->accept_udp_l4 = valbool;
- release_sock(sk);
+ udp_tunnel_encap_enable(sk);
+ udp_assign_bit(GRO_ENABLED, sk, valbool);
+ udp_assign_bit(ACCEPT_L4, sk, valbool);
break;
/*
@@ -2730,8 +2730,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
val = 8;
else if (val > USHRT_MAX)
val = USHRT_MAX;
- up->pcslen = val;
- up->pcflag |= UDPLITE_SEND_CC;
+ WRITE_ONCE(up->pcslen, val);
+ udp_set_bit(UDPLITE_SEND_CC, sk);
break;
/* The receiver specifies a minimum checksum coverage value. To make
@@ -2744,8 +2744,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
val = 8;
else if (val > USHRT_MAX)
val = USHRT_MAX;
- up->pcrlen = val;
- up->pcflag |= UDPLITE_RECV_CC;
+ WRITE_ONCE(up->pcrlen, val);
+ udp_set_bit(UDPLITE_RECV_CC, sk);
break;
default:
@@ -2783,19 +2783,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
switch (optname) {
case UDP_CORK:
- val = READ_ONCE(up->corkflag);
+ val = udp_test_bit(CORK, sk);
break;
case UDP_ENCAP:
- val = up->encap_type;
+ val = READ_ONCE(up->encap_type);
break;
case UDP_NO_CHECK6_TX:
- val = up->no_check6_tx;
+ val = udp_get_no_check6_tx(sk);
break;
case UDP_NO_CHECK6_RX:
- val = up->no_check6_rx;
+ val = udp_get_no_check6_rx(sk);
break;
case UDP_SEGMENT:
@@ -2803,17 +2803,17 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
break;
case UDP_GRO:
- val = up->gro_enabled;
+ val = udp_test_bit(GRO_ENABLED, sk);
break;
/* The following two cannot be changed on UDP sockets, the return is
* always 0 (which corresponds to the full checksum coverage of UDP). */
case UDPLITE_SEND_CSCOV:
- val = up->pcslen;
+ val = READ_ONCE(up->pcslen);
break;
case UDPLITE_RECV_CSCOV:
- val = up->pcrlen;
+ val = READ_ONCE(up->pcrlen);
break;
default:
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0f46b3c2e4ac..6c95d28d0c4a 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -557,10 +557,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
NAPI_GRO_CB(skb)->is_flist = 0;
if (!sk || !udp_sk(sk)->gro_receive) {
if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
- NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1;
+ NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1;
if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
- (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
+ (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist)
return call_gro_receive(udp_gro_receive_segment, head, skb);
/* no GRO, be sure flush the current packet */
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 9b18f371af0d..1e7e4aecdc48 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -78,7 +78,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
udp_sk(sk)->gro_receive = cfg->gro_receive;
udp_sk(sk)->gro_complete = cfg->gro_complete;
- udp_tunnel_encap_enable(sock);
+ udp_tunnel_encap_enable(sk);
}
EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 39ecdad1b50c..af37af3ab727 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -21,7 +21,6 @@ EXPORT_SYMBOL(udplite_table);
static int udplite_sk_init(struct sock *sk)
{
udp_init_sock(sk);
- udp_sk(sk)->pcflag = UDPLITE_BIT;
pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
"please contact the netdev mailing list\n");
return 0;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index eac206a290d0..183f6dc37242 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -85,11 +85,11 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
struct udphdr *uh;
struct iphdr *iph;
int iphlen, len;
-
__u8 *udpdata;
__be32 *udpdata32;
- __u16 encap_type = up->encap_type;
+ u16 encap_type;
+ encap_type = READ_ONCE(up->encap_type);
/* if this is not encapsulated socket, then just return now */
if (!encap_type)
return 1;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 5ce25bcb9974..421264a69e97 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -3011,8 +3011,6 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s
continue;
state->im = rcu_dereference(state->idev->mc_list);
}
- if (!state->im)
- break;
psf = rcu_dereference(state->im->mca_sources);
}
out:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c687b357e6a..9d8dfc7423e4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -341,7 +341,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
- 1, DST_OBSOLETE_FORCE_CHK, flags);
+ DST_OBSOLETE_FORCE_CHK, flags);
if (rt) {
rt6_info_init(rt);
@@ -2655,7 +2655,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
struct net_device *loopback_dev = net->loopback_dev;
struct dst_entry *new = NULL;
- rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1,
+ rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev,
DST_OBSOLETE_DEAD, 0);
if (rt) {
rt6_info_init(rt);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 86b5d509a468..f60ba4295435 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -413,7 +413,7 @@ try_again:
(struct sockaddr *)sin6);
}
- if (udp_sk(sk)->gro_enabled)
+ if (udp_test_bit(GRO_ENABLED, sk))
udp_cmsg_recv(msg, sk, skb);
if (np->rxopt.all)
@@ -571,7 +571,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
- if (!sk || udp_sk(sk)->encap_type) {
+ if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) {
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
@@ -688,7 +688,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
}
nf_reset_ct(skb);
- if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
+ if (static_branch_unlikely(&udpv6_encap_needed_key) &&
+ READ_ONCE(up->encap_type)) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
@@ -726,16 +727,17 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
/*
* UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
*/
- if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
+ if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) {
+ u16 pcrlen = READ_ONCE(up->pcrlen);
- if (up->pcrlen == 0) { /* full coverage was set */
+ if (pcrlen == 0) { /* full coverage was set */
net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
}
- if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
+ if (UDP_SKB_CB(skb)->cscov < pcrlen) {
net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
- UDP_SKB_CB(skb)->cscov, up->pcrlen);
+ UDP_SKB_CB(skb)->cscov, pcrlen);
goto drop;
}
}
@@ -858,7 +860,7 @@ start_lookup:
/* If zero checksum and no_check is not on for
* the socket then skip it.
*/
- if (!uh->check && !udp_sk(sk)->no_check6_rx)
+ if (!uh->check && !udp_get_no_check6_rx(sk))
continue;
if (!first) {
first = sk;
@@ -980,7 +982,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp6_sk_rx_dst_set(sk, dst);
- if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+ if (!uh->check && !udp_get_no_check6_rx(sk)) {
if (refcounted)
sock_put(sk);
goto report_csum_error;
@@ -1002,7 +1004,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
/* Unicast */
sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk) {
- if (!uh->check && !udp_sk(sk)->no_check6_rx)
+ if (!uh->check && !udp_get_no_check6_rx(sk))
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
@@ -1241,7 +1243,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
kfree_skb(skb);
return -EINVAL;
}
- if (udp_sk(sk)->no_check6_tx) {
+ if (udp_get_no_check6_tx(sk)) {
kfree_skb(skb);
return -EINVAL;
}
@@ -1262,7 +1264,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
if (is_udplite)
csum = udplite_csum(skb);
- else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */
+ else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */
skb->ip_summed = CHECKSUM_NONE;
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
@@ -1332,7 +1334,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int addr_len = msg->msg_namelen;
bool connected = false;
int ulen = len;
- int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
+ int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
int err;
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
@@ -1644,11 +1646,11 @@ static void udpv6_splice_eof(struct socket *sock)
struct sock *sk = sock->sk;
struct udp_sock *up = udp_sk(sk);
- if (!up->pending || READ_ONCE(up->corkflag))
+ if (!up->pending || udp_test_bit(CORK, sk))
return;
lock_sock(sk);
- if (up->pending && !READ_ONCE(up->corkflag))
+ if (up->pending && !udp_test_bit(CORK, sk))
udp_v6_push_pending_frames(sk);
release_sock(sk);
}
@@ -1670,7 +1672,7 @@ void udpv6_destroy_sock(struct sock *sk)
if (encap_destroy)
encap_destroy(sk);
}
- if (up->encap_enabled) {
+ if (udp_test_bit(ENCAP_ENABLED, sk)) {
static_branch_dec(&udpv6_encap_needed_key);
udp_encap_disable();
}
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 267d491e9707..a60bec9b14f1 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -17,7 +17,6 @@
static int udplitev6_sk_init(struct sock *sk)
{
udpv6_init_sock(sk);
- udp_sk(sk)->pcflag = UDPLITE_BIT;
pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
"please contact the netdev mailing list\n");
return 0;
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4907ab241d6b..4156387248e4 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -81,14 +81,14 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
struct ipv6hdr *ip6h;
int len;
int ip6hlen = sizeof(struct ipv6hdr);
-
__u8 *udpdata;
__be32 *udpdata32;
- __u16 encap_type = up->encap_type;
+ u16 encap_type;
if (skb->protocol == htons(ETH_P_IP))
return xfrm4_udp_encap_rcv(sk, skb);
+ encap_type = READ_ONCE(up->encap_type);
/* if this is not encapsulated socket, then just return now */
if (!encap_type)
return 1;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 03608d3ded4b..8d21ff25f160 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1139,9 +1139,9 @@ static void l2tp_tunnel_destruct(struct sock *sk)
switch (tunnel->encap) {
case L2TP_ENCAPTYPE_UDP:
/* No longer an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = 0;
- (udp_sk(sk))->encap_rcv = NULL;
- (udp_sk(sk))->encap_destroy = NULL;
+ WRITE_ONCE(udp_sk(sk)->encap_type, 0);
+ udp_sk(sk)->encap_rcv = NULL;
+ udp_sk(sk)->encap_destroy = NULL;
break;
case L2TP_ENCAPTYPE_IP:
break;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index fd66014d8a76..5f8094acd056 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -873,7 +873,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
- dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+ dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
@@ -890,7 +890,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
memset(&ovs_rt, 0, sizeof(ovs_rt));
- dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+ dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 1e20bbd687f1..1424bfeaca73 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -375,9 +375,9 @@ out:
static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = {
[TCA_ROUTE4_CLASSID] = { .type = NLA_U32 },
- [TCA_ROUTE4_TO] = { .type = NLA_U32 },
- [TCA_ROUTE4_FROM] = { .type = NLA_U32 },
- [TCA_ROUTE4_IIF] = { .type = NLA_U32 },
+ [TCA_ROUTE4_TO] = NLA_POLICY_MAX(NLA_U32, 0xFF),
+ [TCA_ROUTE4_FROM] = NLA_POLICY_MAX(NLA_U32, 0xFF),
+ [TCA_ROUTE4_IIF] = NLA_POLICY_MAX(NLA_U32, 0x7FFF),
};
static int route4_set_parms(struct net *net, struct tcf_proto *tp,
@@ -397,33 +397,37 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
return err;
if (tb[TCA_ROUTE4_TO]) {
- if (new && handle & 0x8000)
+ if (new && handle & 0x8000) {
+ NL_SET_ERR_MSG(extack, "Invalid handle");
return -EINVAL;
+ }
to = nla_get_u32(tb[TCA_ROUTE4_TO]);
- if (to > 0xFF)
- return -EINVAL;
nhandle = to;
}
+ if (tb[TCA_ROUTE4_FROM] && tb[TCA_ROUTE4_IIF]) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_ROUTE4_FROM],
+ "'from' and 'fromif' are mutually exclusive");
+ return -EINVAL;
+ }
+
if (tb[TCA_ROUTE4_FROM]) {
- if (tb[TCA_ROUTE4_IIF])
- return -EINVAL;
id = nla_get_u32(tb[TCA_ROUTE4_FROM]);
- if (id > 0xFF)
- return -EINVAL;
nhandle |= id << 16;
} else if (tb[TCA_ROUTE4_IIF]) {
id = nla_get_u32(tb[TCA_ROUTE4_IIF]);
- if (id > 0x7FFF)
- return -EINVAL;
nhandle |= (id | 0x8000) << 16;
} else
nhandle |= 0xFFFF << 16;
if (handle && new) {
nhandle |= handle & 0x7F00;
- if (nhandle != handle)
+ if (nhandle != handle) {
+ NL_SET_ERR_MSG_FMT(extack,
+ "Handle mismatch constructed: %x (expected: %x)",
+ handle, nhandle);
return -EINVAL;
+ }
}
if (!nhandle) {
@@ -478,7 +482,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
struct route4_filter __rcu **fp;
struct route4_filter *fold, *f1, *pfp, *f = NULL;
struct route4_bucket *b;
- struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_ROUTE4_MAX + 1];
unsigned int h, th;
int err;
@@ -489,10 +492,12 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
- if (opt == NULL)
+ if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing options");
return -EINVAL;
+ }
- err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, opt,
+ err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, tca[TCA_OPTIONS],
route4_policy, NULL);
if (err < 0)
return err;
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
index a9bd0a235890..ce63414185fd 100644
--- a/net/sched/sch_frag.c
+++ b/net/sched/sch_frag.c
@@ -96,7 +96,7 @@ static int sch_fragment(struct net *net, struct sk_buff *skb,
unsigned long orig_dst;
sch_frag_prepare_frag(skb, xmit);
- dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
+ dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
sch_frag_rt.dst.dev = skb->dev;
@@ -112,7 +112,7 @@ static int sch_fragment(struct net *net, struct sk_buff *skb,
sch_frag_prepare_frag(skb, xmit);
memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
- dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
+ dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
sch_frag_rt.dst.dev = skb->dev;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 020cf17ab7e4..013b65241b65 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1921,6 +1921,9 @@ out_err:
err = total_written;
}
out:
+ if (sk->sk_type == SOCK_STREAM)
+ err = sk_stream_error(sk, msg->msg_flags, err);
+
release_sock(sk);
return err;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d6b405782b63..c4c4fc29ccf5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2561,7 +2561,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
default:
BUG();
}
- xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+ xdst = dst_alloc(dst_ops, NULL, DST_OBSOLETE_NONE, 0);
if (likely(xdst)) {
memset_after(xdst, 0, u.dst);
Copyright © 1990 – 2022 jet tsang zeon-git.
All Rights Reverse Engineered.