summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-11-14 14:15:53 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-11-14 14:15:53 -0800
commite76d21c40bd6c67fd4e2c1540d77e113df962b4d (patch)
tree26412781fb3f51719cb32d7b031660a7139c1a3b /net
parentd4b9532367c77a35849d6cce491a3ca474c519cf (diff)
parentac571de999e14b87890cb960ad6f03fbdde6abc8 (diff)
downloadlinux-e76d21c40bd6c67fd4e2c1540d77e113df962b4d.tar.gz
linux-e76d21c40bd6c67fd4e2c1540d77e113df962b4d.tar.bz2
linux-e76d21c40bd6c67fd4e2c1540d77e113df962b4d.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) Fix off by one wrt. indexing when dumping /proc/net/route entries, from Alexander Duyck. 2) Fix lockdep splats in iwlwifi, from Johannes Berg. 3) Cure panic when inserting certain netfilter rules when NFT_SET_HASH is disabled, from Liping Zhang. 4) Memory leak when nft_expr_clone() fails, also from Liping Zhang. 5) Disable UFO when path will apply IPSEC tranformations, from Jakub Sitnicki. 6) Don't bogusly double cwnd in dctcp module, from Florian Westphal. 7) skb_checksum_help() should never actually use the value "0" for the resulting checksum, that has a special meaning, use CSUM_MANGLED_0 instead. From Eric Dumazet. 8) Per-tx/rx queue statistic strings are wrong in qed driver, fix from Yuval MIntz. 9) Fix SCTP reference counting of associations and transports in sctp_diag. From Xin Long. 10) When we hit ip6tunnel_xmit() we could have come from an ipv4 path in a previous layer or similar, so explicitly clear the ipv6 control block in the skb. From Eli Cooper. 11) Fix bogus sleeping inside of inet_wait_for_connect(), from WANG Cong. 12) Correct deivce ID of T6 adapter in cxgb4 driver, from Hariprasad Shenai. 13) Fix potential access past the end of the skb page frag array in tcp_sendmsg(). From Eric Dumazet. 14) 'skb' can legitimately be NULL in inet{,6}_exact_dif_match(). Fix from David Ahern. 15) Don't return an error in tcp_sendmsg() if we wronte any bytes successfully, from Eric Dumazet. 16) Extraneous unlocks in netlink_diag_dump(), we removed the locking but forgot to purge these unlock calls. From Eric Dumazet. 17) Fix memory leak in error path of __genl_register_family(). We leak the attrbuf, from WANG Cong. 18) cgroupstats netlink policy table is mis-sized, from WANG Cong. 19) Several XDP bug fixes in mlx5, from Saeed Mahameed. 20) Fix several device refcount leaks in network drivers, from Johan Hovold. 21) icmp6_send() should use skb dst device not skb->dev to determine L3 routing domain. From David Ahern. 22) ip_vs_genl_family sets maxattr incorrectly, from WANG Cong. 23) We leak new macvlan port in some cases of maclan_common_netlink() errors. Fix from Gao Feng. 24) Similar to the icmp6_send() fix, icmp_route_lookup() should determine L3 routing domain using skb_dst(skb)->dev not skb->dev. Also from David Ahern. 25) Several fixes for route offloading and FIB notification handling in mlxsw driver, from Jiri Pirko. 26) Properly cap __skb_flow_dissect()'s return value, from Eric Dumazet. 27) Fix long standing regression in ipv4 redirect handling, wrt. validating the new neighbour's reachability. From Stephen Suryaputra Lin. 28) If sk_filter() trims the packet excessively, handle it reasonably in tcp input instead of exploding. From Eric Dumazet. 29) Fix handling of napi hash state when copying channels in sfc driver, from Bert Kenward. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (121 commits) mlxsw: spectrum_router: Flush FIB tables during fini net: stmmac: Fix lack of link transition for fixed PHYs sctp: change sk state only when it has assocs in sctp_shutdown bnx2: Wait for in-flight DMA to complete at probe stage Revert "bnx2: Reset device during driver initialization" ps3_gelic: fix spelling mistake in debug message net: ethernet: ixp4xx_eth: fix spelling mistake in debug message ibmvnic: Fix size of debugfs name buffer ibmvnic: Unmap ibmvnic_statistics structure sfc: clear napi_hash state when copying channels mlxsw: spectrum_router: Correctly dump neighbour activity mlxsw: spectrum: Fix refcount bug on span entries bnxt_en: Fix VF virtual link state. bnxt_en: Fix ring arithmetic in bnxt_setup_tc(). Revert "include/uapi/linux/atm_zatm.h: include linux/time.h" tcp: take care of truncations done by sk_filter() ipv4: use new_gw for redirect neigh lookup r8152: Fix error path in open function net: bpqether.h: remove if_ether.h guard net: __skb_flow_dissect() must cap its return value ...
Diffstat (limited to 'net')
-rw-r--r--net/can/bcm.c32
-rw-r--r--net/core/dev.c19
-rw-r--r--net/core/filter.c68
-rw-r--r--net/core/flow_dissector.c11
-rw-r--r--net/core/rtnetlink.c1
-rw-r--r--net/core/sock.c6
-rw-r--r--net/dccp/ipv4.c16
-rw-r--r--net/dccp/ipv6.c19
-rw-r--r--net/dccp/proto.c4
-rw-r--r--net/ipv4/af_inet.c9
-rw-r--r--net/ipv4/fib_trie.c21
-rw-r--r--net/ipv4/icmp.c4
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_output.c25
-rw-r--r--net/ipv4/ip_tunnel_core.c11
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/netfilter/nft_dup_ipv4.c6
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_dctcp.c13
-rw-r--r--net/ipv4/tcp_ipv4.c19
-rw-r--r--net/ipv6/icmp.c2
-rw-r--r--net/ipv6/ip6_output.c2
-rw-r--r--net/ipv6/ip6_udp_tunnel.c3
-rw-r--r--net/ipv6/netfilter/nft_dup_ipv6.c6
-rw-r--r--net/ipv6/route.c4
-rw-r--r--net/ipv6/tcp_ipv6.c14
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c7
-rw-r--r--net/netfilter/nf_conntrack_core.c49
-rw-r--r--net/netfilter/nf_conntrack_helper.c11
-rw-r--r--net/netfilter/nf_conntrack_sip.c5
-rw-r--r--net/netfilter/nf_tables_api.c18
-rw-r--r--net/netfilter/nft_dynset.c19
-rw-r--r--net/netfilter/nft_set_hash.c19
-rw-r--r--net/netfilter/nft_set_rbtree.c2
-rw-r--r--net/netfilter/xt_connmark.c4
-rw-r--r--net/netlink/diag.c5
-rw-r--r--net/netlink/genetlink.c4
-rw-r--r--net/sctp/input.c35
-rw-r--r--net/sctp/ipv6.c2
-rw-r--r--net/sctp/socket.c27
-rw-r--r--net/socket.c2
-rw-r--r--net/unix/af_unix.c3
44 files changed, 357 insertions, 184 deletions
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8e999ffdf28b..8af9d25ff988 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1549,24 +1549,31 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
struct sock *sk = sock->sk;
struct bcm_sock *bo = bcm_sk(sk);
+ int ret = 0;
if (len < sizeof(*addr))
return -EINVAL;
- if (bo->bound)
- return -EISCONN;
+ lock_sock(sk);
+
+ if (bo->bound) {
+ ret = -EISCONN;
+ goto fail;
+ }
/* bind a device to this socket */
if (addr->can_ifindex) {
struct net_device *dev;
dev = dev_get_by_index(&init_net, addr->can_ifindex);
- if (!dev)
- return -ENODEV;
-
+ if (!dev) {
+ ret = -ENODEV;
+ goto fail;
+ }
if (dev->type != ARPHRD_CAN) {
dev_put(dev);
- return -ENODEV;
+ ret = -ENODEV;
+ goto fail;
}
bo->ifindex = dev->ifindex;
@@ -1577,17 +1584,24 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
bo->ifindex = 0;
}
- bo->bound = 1;
-
if (proc_dir) {
/* unique socket address as filename */
sprintf(bo->procname, "%lu", sock_i_ino(sk));
bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
proc_dir,
&bcm_proc_fops, sk);
+ if (!bo->bcm_proc_read) {
+ ret = -ENOMEM;
+ goto fail;
+ }
}
- return 0;
+ bo->bound = 1;
+
+fail:
+ release_sock(sk);
+
+ return ret;
}
static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/core/dev.c b/net/core/dev.c
index 820bac239738..6666b28b6815 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1766,19 +1766,14 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
- if (skb_orphan_frags(skb, GFP_ATOMIC) ||
- unlikely(!is_skb_forwardable(dev, skb))) {
- atomic_long_inc(&dev->rx_dropped);
- kfree_skb(skb);
- return NET_RX_DROP;
- }
+ int ret = ____dev_forward_skb(dev, skb);
- skb_scrub_packet(skb, true);
- skb->priority = 0;
- skb->protocol = eth_type_trans(skb, dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ if (likely(!ret)) {
+ skb->protocol = eth_type_trans(skb, dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ }
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(__dev_forward_skb);
@@ -2484,7 +2479,7 @@ int skb_checksum_help(struct sk_buff *skb)
goto out;
}
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
diff --git a/net/core/filter.c b/net/core/filter.c
index 00351cdf7d0c..b391209838ef 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1628,6 +1628,19 @@ static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
return dev_forward_skb(dev, skb);
}
+static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ int ret = ____dev_forward_skb(dev, skb);
+
+ if (likely(!ret)) {
+ skb->dev = dev;
+ ret = netif_rx(skb);
+ }
+
+ return ret;
+}
+
static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
{
int ret;
@@ -1647,6 +1660,51 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
return ret;
}
+static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ /* skb->mac_len is not set on normal egress */
+ unsigned int mlen = skb->network_header - skb->mac_header;
+
+ __skb_pull(skb, mlen);
+
+ /* At ingress, the mac header has already been pulled once.
+ * At egress, skb_pospull_rcsum has to be done in case that
+ * the skb is originated from ingress (i.e. a forwarded skb)
+ * to ensure that rcsum starts at net header.
+ */
+ if (!skb_at_tc_ingress(skb))
+ skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+ skb_pop_mac_header(skb);
+ skb_reset_mac_len(skb);
+ return flags & BPF_F_INGRESS ?
+ __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ bpf_push_mac_rcsum(skb);
+ return flags & BPF_F_INGRESS ?
+ __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ switch (dev->type) {
+ case ARPHRD_TUNNEL:
+ case ARPHRD_TUNNEL6:
+ case ARPHRD_SIT:
+ case ARPHRD_IPGRE:
+ case ARPHRD_VOID:
+ case ARPHRD_NONE:
+ return __bpf_redirect_no_mac(skb, dev, flags);
+ default:
+ return __bpf_redirect_common(skb, dev, flags);
+ }
+}
+
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
{
struct net_device *dev;
@@ -1675,10 +1733,7 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
return -ENOMEM;
}
- bpf_push_mac_rcsum(clone);
-
- return flags & BPF_F_INGRESS ?
- __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone);
+ return __bpf_redirect(clone, dev, flags);
}
static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1722,10 +1777,7 @@ int skb_do_redirect(struct sk_buff *skb)
return -EINVAL;
}
- bpf_push_mac_rcsum(skb);
-
- return ri->flags & BPF_F_INGRESS ?
- __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+ return __bpf_redirect(skb, dev, ri->flags);
}
static const struct bpf_func_proto bpf_redirect_proto = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ab193e5def07..69e4463a4b1b 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -122,7 +122,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector_key_keyid *key_keyid;
bool skip_vlan = false;
u8 ip_proto = 0;
- bool ret = false;
+ bool ret;
if (!data) {
data = skb->data;
@@ -549,12 +549,17 @@ ip_proto_again:
out_good:
ret = true;
-out_bad:
+ key_control->thoff = (u16)nhoff;
+out:
key_basic->n_proto = proto;
key_basic->ip_proto = ip_proto;
- key_control->thoff = (u16)nhoff;
return ret;
+
+out_bad:
+ ret = false;
+ key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+ goto out;
}
EXPORT_SYMBOL(__skb_flow_dissect);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fb7348f13501..db313ec7af32 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -275,6 +275,7 @@ int rtnl_unregister(int protocol, int msgtype)
rtnl_msg_handlers[protocol][msgindex].doit = NULL;
rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;
+ rtnl_msg_handlers[protocol][msgindex].calcit = NULL;
return 0;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index c73e28fc9c2a..5e3ca414357e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
EXPORT_SYMBOL(sock_queue_rcv_skb);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
- const int nested, unsigned int trim_cap)
+ const int nested, unsigned int trim_cap, bool refcounted)
{
int rc = NET_RX_SUCCESS;
@@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
bh_unlock_sock(sk);
out:
- sock_put(sk);
+ if (refcounted)
+ sock_put(sk);
return rc;
discard_and_relse:
kfree_skb(skb);
@@ -1543,6 +1544,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
newsk->sk_err = 0;
+ newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 345a3aeb8c7e..b567c8725aea 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
- const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+ const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct inet_sock *inet;
const int type = icmp_hdr(skb)->type;
@@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
int err;
struct net *net = dev_net(skb->dev);
- if (skb->len < offset + sizeof(*dh) ||
- skb->len < offset + __dccp_basic_hdr_len(dh)) {
- __ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
- }
+ /* Only need dccph_dport & dccph_sport which are the first
+ * 4 bytes in dccp header.
+ * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+ */
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet_lookup_established(net, &dccp_hashinfo,
iph->daddr, dh->dccph_dport,
@@ -868,7 +870,7 @@ lookup:
goto discard_and_relse;
nf_reset(skb);
- return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4);
+ return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
no_dccp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 3828f94b234c..715e5d1dc107 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
- const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+ const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
@@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
__u64 seq;
struct net *net = dev_net(skb->dev);
- if (skb->len < offset + sizeof(*dh) ||
- skb->len < offset + __dccp_basic_hdr_len(dh)) {
- __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
- ICMP6_MIB_INERRORS);
- return;
- }
+ /* Only need dccph_dport & dccph_sport which are the first
+ * 4 bytes in dccp header.
+ * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+ */
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet6_lookup_established(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
@@ -738,7 +739,8 @@ lookup:
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
- return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0;
+ return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
+ refcounted) ? -1 : 0;
no_dccp_socket:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
@@ -956,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 41e65804ddf5..9fe25bf63296 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout)
__kfree_skb(skb);
}
+ /* If socket has been already reset kill it. */
+ if (sk->sk_state == DCCP_CLOSED)
+ goto adjudge_to_death;
+
if (data_was_unread) {
/* Unread data was tossed, send an appropriate Reset Code */
DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9648c97e541f..5ddf5cda07f4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect);
static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
/* Basic assumption: if someone sets sk->sk_err, he _must_
@@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
*/
while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
return timeo;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31cef3602585..4cff74d4133f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2413,22 +2413,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
struct key_vector *l, **tp = &iter->tnode;
t_key key;
- /* use cache location of next-to-find key */
+ /* use cached location of previously found key */
if (iter->pos > 0 && pos >= iter->pos) {
- pos -= iter->pos;
key = iter->key;
} else {
- iter->pos = 0;
+ iter->pos = 1;
key = 0;
}
- while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+ pos -= iter->pos;
+
+ while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
key = l->key + 1;
iter->pos++;
-
- if (--pos <= 0)
- break;
-
l = NULL;
/* handle unlikely case of a key wrap */
@@ -2437,7 +2434,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
}
if (l)
- iter->key = key; /* remember it */
+ iter->key = l->key; /* remember it */
else
iter->pos = 0; /* forget it */
@@ -2465,7 +2462,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
return fib_route_get_idx(iter, *pos);
iter->pos = 0;
- iter->key = 0;
+ iter->key = KEY_MAX;
return SEQ_START_TOKEN;
}
@@ -2474,7 +2471,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct fib_route_iter *iter = seq->private;
struct key_vector *l = NULL;
- t_key key = iter->key;
+ t_key key = iter->key + 1;
++*pos;
@@ -2483,7 +2480,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
l = leaf_walk_rcu(&iter->tnode, key);
if (l) {
- iter->key = l->key + 1;
+ iter->key = l->key;
iter->pos++;
} else {
iter->pos = 0;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70e595f..48734ee6293f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
- fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+ fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
rt = __ip_route_output_key_hash(net, fl4,
@@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- if (inet_addr_type_dev_table(net, skb_in->dev,
+ if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
fl4_dec.saddr) == RTN_LOCAL) {
rt2 = __ip_route_output_key(net, &fl4_dec);
if (IS_ERR(rt2))
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 8b4ffd216839..9f0a7b96646f 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
if (ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 03e7f7310423..105908d841a3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -239,19 +239,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
struct sk_buff *segs;
int ret = 0;
- /* common case: fragmentation of segments is not allowed,
- * or seglen is <= mtu
+ /* common case: seglen is <= mtu
*/
- if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
- skb_gso_validate_mtu(skb, mtu))
+ if (skb_gso_validate_mtu(skb, mtu))
return ip_finish_output2(net, sk, skb);
- /* Slowpath - GSO segment length is exceeding the dst MTU.
+ /* Slowpath - GSO segment length exceeds the egress MTU.
*
- * This can happen in two cases:
- * 1) TCP GRO packet, DF bit not set
- * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
- * from host network stack.
+ * This can happen in several cases:
+ * - Forwarding of a TCP GRO skb, when DF flag is not set.
+ * - Forwarding of an skb that arrived on a virtualization interface
+ * (virtio-net/vhost/tap) with TSO/GSO size set by other network
+ * stack.
+ * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
+ * interface with a smaller MTU.
+ * - Arriving GRO skb (or GSO skb in a virtualized environment) that is
+ * bridged to a NETIF_F_TSO tunnel stacked over an interface with an
+ * insufficent MTU.
*/
features = netif_skb_features(skb);
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
@@ -1579,7 +1583,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
}
oif = arg->bound_dev_if;
- oif = oif ? : skb->skb_iif;
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
flowi4_init_output(&fl4, oif,
IP4_REPLY_MARK(net, skb->mark),
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 777bc1883870..fed3d29f9eb3 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
- int skb_iif = skb->skb_iif;
struct iphdr *iph;
int err;
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- if (skb_iif && !(df & htons(IP_DF))) {
- /* Arrived from an ingress interface, got encapsulated, with
- * fragmentation of encapulating frames allowed.
- * If skb is gso, the resulting encapsulated network segments
- * may exceed dst mtu.
- * Allow IP Fragmentation of segments.
- */
- IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
- }
-
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f006e13de56..27089f5ebbb1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
vif->dev->stats.tx_bytes += skb->len;
}
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
* not only before forwarding, but after forwarding on all output
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index bf855e64fc45..0c01a270bf9f 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -28,7 +28,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr,
struct in_addr gw = {
.s_addr = (__force __be32)regs->data[priv->sreg_addr],
};
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif);
}
@@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 62d4d90c1389..2a57566e6e91 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -753,7 +753,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
goto reject_redirect;
}
- n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+ n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+ if (!n)
+ n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
if (!(n->nud_state & NUD_VALID)) {
neigh_event_send(n, NULL);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3251fe71f39f..814af89c1bd3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1164,7 +1164,7 @@ restart:
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto out_err;
+ goto do_error;
sg = !!(sk->sk_route_caps & NETIF_F_SG);
@@ -1241,7 +1241,7 @@ new_segment:
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
- if (i == sysctl_max_skb_frags || !sg) {
+ if (i >= sysctl_max_skb_frags || !sg) {
tcp_mark_push(tp, skb);
goto new_segment;
}
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 10d728b6804c..ab37c6775630 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -56,6 +56,7 @@ struct dctcp {
u32 next_seq;
u32 ce_state;
u32 delayed_ack_reserved;
+ u32 loss_cwnd;
};
static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
ca->delayed_ack_reserved = 0;
+ ca->loss_cwnd = 0;
ca->ce_state = 0;
dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
static u32 dctcp_ssthresh(struct sock *sk)
{
- const struct dctcp *ca = inet_csk_ca(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ ca->loss_cwnd = tp->snd_cwnd;
return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
}
@@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
return 0;
}
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
static struct tcp_congestion_ops dctcp __read_mostly = {
.init = dctcp_init,
.in_ack_event = dctcp_update_alpha,
.cwnd_event = dctcp_cwnd_event,
.ssthresh = dctcp_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
+ .undo_cwnd = dctcp_cwnd_undo,
.set_state = dctcp_state,
.get_info = dctcp_get_info,
.flags = TCP_CONG_NEEDS_ECN,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 61b7be303eec..2259114c7242 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1564,6 +1564,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_add_backlog);
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcphdr *th = (struct tcphdr *)skb->data;
+ unsigned int eaten = skb->len;
+ int err;
+
+ err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+ if (!err) {
+ eaten -= skb->len;
+ TCP_SKB_CB(skb)->end_seq -= eaten;
+ }
+ return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
/*
* From tcp_input.c
*/
@@ -1676,8 +1691,10 @@ process:
nf_reset(skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
skb->dev = NULL;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c343d35f..7370ad2e693a 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -448,7 +448,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (__ipv6_addr_needs_scope_id(addr_type))
iif = skb->dev->ifindex;
else
- iif = l3mdev_master_ifindex(skb->dev);
+ iif = l3mdev_master_ifindex(skb_dst(skb)->dev);
/*
* Must not send error if the source does not uniquely
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6001e781164e..59eb4ed99ce8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1366,7 +1366,7 @@ emsgsize:
if (((length > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7520528ecd2..b283f293ee4a 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -88,9 +88,6 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
uh->len = htons(skb->len);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
- | IPSKB_REROUTED);
skb_dst_set(skb, dst);
udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
index 8bfd470cbe72..831f86e1ec08 100644
--- a/net/ipv6/netfilter/nft_dup_ipv6.c
+++ b/net/ipv6/netfilter/nft_dup_ipv6.c
@@ -26,7 +26,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr,
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
struct in6_addr *gw = (struct in6_addr *)&regs->data[priv->sreg_addr];
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif);
}
@@ -57,7 +57,9 @@ static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 947ed1ded026..1b57e11e6e0d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1364,6 +1364,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (rt6->rt6i_flags & RTF_LOCAL)
return;
+ if (dst_metric_locked(dst, RTAX_MTU))
+ return;
+
dst_confirm(dst);
mtu = max_t(u32, mtu, IPV6_MIN_MTU);
if (mtu >= dst_mtu(dst))
@@ -2758,6 +2761,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
+ dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
if (rt->rt6i_flags & RTF_CACHE) {
/* For RTF_CACHE with rt6i_pmtu == 0
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a27ab4eab39..b9f1fee9a886 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -818,8 +818,12 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_proto = IPPROTO_TCP;
if (rt6_need_strict(&fl6.daddr) && !oif)
fl6.flowi6_oif = tcp_v6_iif(skb);
- else
- fl6.flowi6_oif = oif ? : skb->skb_iif;
+ else {
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
+
+ fl6.flowi6_oif = oif;
+ }
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
@@ -1225,7 +1229,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard;
/*
@@ -1453,8 +1457,10 @@ process:
if (tcp_v6_inbound_md5_hash(sk, skb))
goto discard_and_relse;
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ hdr = ipv6_hdr(skb);
skb->dev = NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c3c809b2e712..a6e44ef2ec9a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2845,7 +2845,7 @@ static struct genl_family ip_vs_genl_family = {
.hdrsize = 0,
.name = IPVS_GENL_NAME,
.version = IPVS_GENL_VERSION,
- .maxattr = IPVS_CMD_MAX,
+ .maxattr = IPVS_CMD_ATTR_MAX,
.netnsok = true, /* Make ipvsadm to work on netns */
};
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 1b07578bedf3..9350530c16c1 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -283,6 +283,7 @@ struct ip_vs_sync_buff {
*/
static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
{
+ memset(ho, 0, sizeof(*ho));
ho->init_seq = get_unaligned_be32(&no->init_seq);
ho->delta = get_unaligned_be32(&no->delta);
ho->previous_delta = get_unaligned_be32(&no->previous_delta);
@@ -917,8 +918,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa
kfree(param->pe_data);
}
- if (opt)
- memcpy(&cp->in_seq, opt, sizeof(*opt));
+ if (opt) {
+ cp->in_seq = opt->in_seq;
+ cp->out_seq = opt->out_seq;
+ }
atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs));
cp->state = state;
cp->old_state = cp->state;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index df2f5a3901df..0f87e5d21be7 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -76,6 +76,7 @@ struct conntrack_gc_work {
struct delayed_work dwork;
u32 last_bucket;
bool exiting;
+ long next_gc_run;
};
static __read_mostly struct kmem_cache *nf_conntrack_cachep;
@@ -83,9 +84,11 @@ static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
+/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
#define GC_MAX_BUCKETS_DIV 64u
-#define GC_MAX_BUCKETS 8192u
-#define GC_INTERVAL (5 * HZ)
+/* upper bound of scan intervals */
+#define GC_INTERVAL_MAX (2 * HZ)
+/* maximum conntracks to evict per gc run */
#define GC_MAX_EVICTS 256u
static struct conntrack_gc_work conntrack_gc_work;
@@ -936,13 +939,13 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
static void gc_worker(struct work_struct *work)
{
unsigned int i, goal, buckets = 0, expired_count = 0;
- unsigned long next_run = GC_INTERVAL;
- unsigned int ratio, scanned = 0;
struct conntrack_gc_work *gc_work;
+ unsigned int ratio, scanned = 0;
+ unsigned long next_run;
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
- goal = min(nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV, GC_MAX_BUCKETS);
+ goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
i = gc_work->last_bucket;
do {
@@ -982,17 +985,47 @@ static void gc_worker(struct work_struct *work)
if (gc_work->exiting)
return;
+ /*
+ * Eviction will normally happen from the packet path, and not
+ * from this gc worker.
+ *
+ * This worker is only here to reap expired entries when system went
+ * idle after a busy period.
+ *
+ * The heuristics below are supposed to balance conflicting goals:
+ *
+ * 1. Minimize time until we notice a stale entry
+ * 2. Maximize scan intervals to not waste cycles
+ *
+ * Normally, expired_count will be 0, this increases the next_run time
+ * to priorize 2) above.
+ *
+ * As soon as a timed-out entry is found, move towards 1) and increase
+ * the scan frequency.
+ * In case we have lots of evictions next scan is done immediately.
+ */
ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio >= 90 || expired_count == GC_MAX_EVICTS)
+ if (ratio >= 90 || expired_count == GC_MAX_EVICTS) {
+ gc_work->next_gc_run = 0;
next_run = 0;
+ } else if (expired_count) {
+ gc_work->next_gc_run /= 2U;
+ next_run = msecs_to_jiffies(1);
+ } else {
+ if (gc_work->next_gc_run < GC_INTERVAL_MAX)
+ gc_work->next_gc_run += msecs_to_jiffies(1);
+
+ next_run = gc_work->next_gc_run;
+ }
gc_work->last_bucket = i;
- schedule_delayed_work(&gc_work->dwork, next_run);
+ queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
}
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
+ gc_work->next_gc_run = GC_INTERVAL_MAX;
gc_work->exiting = false;
}
@@ -1885,7 +1918,7 @@ int nf_conntrack_init_start(void)
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
conntrack_gc_work_init(&conntrack_gc_work);
- schedule_delayed_work(&conntrack_gc_work.dwork, GC_INTERVAL);
+ queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX);
return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 336e21559e01..7341adf7059d 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -138,9 +138,14 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum)
for (i = 0; i < nf_ct_helper_hsize; i++) {
hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) {
- if (!strcmp(h->name, name) &&
- h->tuple.src.l3num == l3num &&
- h->tuple.dst.protonum == protonum)
+ if (strcmp(h->name, name))
+ continue;
+
+ if (h->tuple.src.l3num != NFPROTO_UNSPEC &&
+ h->tuple.src.l3num != l3num)
+ continue;
+
+ if (h->tuple.dst.protonum == protonum)
return h;
}
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 621b81c7bddc..c3fc14e021ec 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1436,9 +1436,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff,
handler = &sip_handlers[i];
if (handler->request == NULL)
continue;
- if (*datalen < handler->len ||
+ if (*datalen < handler->len + 2 ||
strncasecmp(*dptr, handler->method, handler->len))
continue;
+ if ((*dptr)[handler->len] != ' ' ||
+ !isalpha((*dptr)[handler->len+1]))
+ continue;
if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ,
&matchoff, &matchlen) <= 0) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 24db22257586..026581b04ea8 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2956,12 +2956,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err2;
+ goto err3;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
+err3:
+ ops->destroy(set);
err2:
kfree(set);
err1:
@@ -3452,14 +3454,15 @@ void *nft_set_elem_init(const struct nft_set *set,
return elem;
}
-void nft_set_elem_destroy(const struct nft_set *set, void *elem)
+void nft_set_elem_destroy(const struct nft_set *set, void *elem,
+ bool destroy_expr)
{
struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE);
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
nft_data_uninit(nft_set_ext_data(ext), set->dtype);
- if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+ if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext));
kfree(elem);
@@ -3565,6 +3568,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
dreg = nft_type_to_reg(set->dtype);
list_for_each_entry(binding, &set->bindings, list) {
struct nft_ctx bind_ctx = {
+ .net = ctx->net,
.afi = ctx->afi,
.table = ctx->table,
.chain = (struct nft_chain *)binding->chain,
@@ -3812,7 +3816,7 @@ void nft_set_gc_batch_release(struct rcu_head *rcu)
gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu);
for (i = 0; i < gcb->head.cnt; i++)
- nft_set_elem_destroy(gcb->head.set, gcb->elems[i]);
+ nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true);
kfree(gcb);
}
EXPORT_SYMBOL_GPL(nft_set_gc_batch_release);
@@ -4030,7 +4034,7 @@ static void nf_tables_commit_release(struct nft_trans *trans)
break;
case NFT_MSG_DELSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
- nft_trans_elem(trans).priv);
+ nft_trans_elem(trans).priv, true);
break;
}
kfree(trans);
@@ -4171,7 +4175,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
break;
case NFT_MSG_NEWSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
- nft_trans_elem(trans).priv);
+ nft_trans_elem(trans).priv, true);
break;
}
kfree(trans);
@@ -4421,7 +4425,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
* Otherwise a 0 is returned and the attribute value is stored in the
* destination variable.
*/
-unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
+int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
{
u32 val;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 517f08767a3c..31ca94793aa9 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -44,18 +44,22 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
&regs->data[priv->sreg_key],
&regs->data[priv->sreg_data],
timeout, GFP_ATOMIC);
- if (elem == NULL) {
- if (set->size)
- atomic_dec(&set->nelems);
- return NULL;
- }
+ if (elem == NULL)
+ goto err1;
ext = nft_set_elem_ext(set, elem);
if (priv->expr != NULL &&
nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0)
- return NULL;
+ goto err2;
return elem;
+
+err2:
+ nft_set_elem_destroy(set, elem, false);
+err1:
+ if (set->size)
+ atomic_dec(&set->nelems);
+ return NULL;
}
static void nft_dynset_eval(const struct nft_expr *expr,
@@ -139,6 +143,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
return PTR_ERR(set);
}
+ if (set->ops->update == NULL)
+ return -EOPNOTSUPP;
+
if (set->flags & NFT_SET_CONSTANT)
return -EBUSY;
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 3794cb2fc788..a3dface3e6e6 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -98,7 +98,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key,
const struct nft_set_ext **ext)
{
struct nft_hash *priv = nft_set_priv(set);
- struct nft_hash_elem *he;
+ struct nft_hash_elem *he, *prev;
struct nft_hash_cmp_arg arg = {
.genmask = NFT_GENMASK_ANY,
.set = set,
@@ -112,15 +112,24 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key,
he = new(set, expr, regs);
if (he == NULL)
goto err1;
- if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
- nft_hash_params))
+
+ prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
+ nft_hash_params);
+ if (IS_ERR(prev))
goto err2;
+
+ /* Another cpu may race to insert the element with the same key */
+ if (prev) {
+ nft_set_elem_destroy(set, he, true);
+ he = prev;
+ }
+
out:
*ext = &he->ext;
return true;
err2:
- nft_set_elem_destroy(set, he);
+ nft_set_elem_destroy(set, he, true);
err1:
return false;
}
@@ -332,7 +341,7 @@ static int nft_hash_init(const struct nft_set *set,
static void nft_hash_elem_destroy(void *ptr, void *arg)
{
- nft_set_elem_destroy((const struct nft_set *)arg, ptr);
+ nft_set_elem_destroy((const struct nft_set *)arg, ptr, true);
}
static void nft_hash_destroy(const struct nft_set *set)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 38b5bda242f8..36493a7cae88 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -266,7 +266,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
- nft_set_elem_destroy(set, rbe);
+ nft_set_elem_destroy(set, rbe, true);
}
}
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 69f78e96fdb4..b83e158e116a 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
u_int32_t newmark;
ct = nf_ct_get(skb, &ctinfo);
- if (ct == NULL)
+ if (ct == NULL || nf_ct_is_untracked(ct))
return XT_CONTINUE;
switch (info->mode) {
@@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
- if (ct == NULL)
+ if (ct == NULL || nf_ct_is_untracked(ct))
return false;
return ((ct->mark & info->mask) == info->mark) ^ info->invert;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index b2f0e986a6f4..a5546249fb10 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -178,11 +178,8 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
}
cb->args[1] = i;
} else {
- if (req->sdiag_protocol >= MAX_LINKS) {
- read_unlock(&nl_table_lock);
- rcu_read_unlock();
+ if (req->sdiag_protocol >= MAX_LINKS)
return -ENOENT;
- }
err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num);
}
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 23cc12639ba7..49c28e8ef01b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -404,7 +404,7 @@ int __genl_register_family(struct genl_family *family)
err = genl_validate_assign_mc_groups(family);
if (err)
- goto errout_locked;
+ goto errout_free;
list_add_tail(&family->family_list, genl_family_chain(family->id));
genl_unlock_all();
@@ -417,6 +417,8 @@ int __genl_register_family(struct genl_family *family)
return 0;
+errout_free:
+ kfree(family->attrbuf);
errout_locked:
genl_unlock_all();
errout:
diff --git a/net/sctp/input.c b/net/sctp/input.c
index a2ea1d1cc06a..a01a56ec8b8c 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -181,9 +181,10 @@ int sctp_rcv(struct sk_buff *skb)
* bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
*/
if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) {
- if (asoc) {
- sctp_association_put(asoc);
+ if (transport) {
+ sctp_transport_put(transport);
asoc = NULL;
+ transport = NULL;
} else {
sctp_endpoint_put(ep);
ep = NULL;
@@ -269,8 +270,8 @@ int sctp_rcv(struct sk_buff *skb)
bh_unlock_sock(sk);
/* Release the asoc/ep ref we took in the lookup calls. */
- if (asoc)
- sctp_association_put(asoc);
+ if (transport)
+ sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
@@ -283,8 +284,8 @@ discard_it:
discard_release:
/* Release the asoc/ep ref we took in the lookup calls. */
- if (asoc)
- sctp_association_put(asoc);
+ if (transport)
+ sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
@@ -300,6 +301,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
+ struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = NULL;
int backloged = 0;
@@ -351,7 +353,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
done:
/* Release the refs we took in sctp_add_backlog */
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
- sctp_association_put(sctp_assoc(rcvr));
+ sctp_transport_put(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_put(sctp_ep(rcvr));
else
@@ -363,6 +365,7 @@ done:
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
+ struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = chunk->rcvr;
int ret;
@@ -373,7 +376,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
* from us
*/
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
- sctp_association_hold(sctp_assoc(rcvr));
+ sctp_transport_hold(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_hold(sctp_ep(rcvr));
else
@@ -537,15 +540,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
return sk;
out:
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
return NULL;
}
/* Common cleanup code for icmp/icmpv6 error handler. */
-void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
+void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
{
bh_unlock_sock(sk);
- sctp_association_put(asoc);
+ sctp_transport_put(t);
}
/*
@@ -641,7 +644,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
}
out_unlock:
- sctp_err_finish(sk, asoc);
+ sctp_err_finish(sk, transport);
}
/*
@@ -952,11 +955,8 @@ static struct sctp_association *__sctp_lookup_association(
goto out;
asoc = t->asoc;
- sctp_association_hold(asoc);
*pt = t;
- sctp_transport_put(t);
-
out:
return asoc;
}
@@ -986,7 +986,7 @@ int sctp_has_association(struct net *net,
struct sctp_transport *transport;
if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) {
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
return 1;
}
@@ -1021,7 +1021,6 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
struct sctphdr *sh = sctp_hdr(skb);
union sctp_params params;
sctp_init_chunk_t *init;
- struct sctp_transport *transport;
struct sctp_af *af;
/*
@@ -1052,7 +1051,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
af->from_addr_param(paddr, params.addr, sh->source, 0);
- asoc = __sctp_lookup_association(net, laddr, paddr, &transport);
+ asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
if (asoc)
return asoc;
}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f473779e8b1c..176af3080a2b 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -198,7 +198,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
out_unlock:
- sctp_err_finish(sk, asoc);
+ sctp_err_finish(sk, transport);
out:
if (likely(idev != NULL))
in6_dev_put(idev);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9fbb6feb8c27..f23ad913dc7a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk,
timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
- err = sctp_wait_for_connect(asoc, &timeo);
- if ((err == 0 || err == -EINPROGRESS) && assoc_id)
+ if (assoc_id)
*assoc_id = asoc->assoc_id;
+ err = sctp_wait_for_connect(asoc, &timeo);
+ /* Note: the asoc may be freed after the return of
+ * sctp_wait_for_connect.
+ */
/* Don't free association on exit. */
asoc = NULL;
@@ -4282,19 +4285,18 @@ static void sctp_shutdown(struct sock *sk, int how)
{
struct net *net = sock_net(sk);
struct sctp_endpoint *ep;
- struct sctp_association *asoc;
if (!sctp_style(sk, TCP))
return;
- if (how & SEND_SHUTDOWN) {
+ ep = sctp_sk(sk)->ep;
+ if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
+ struct sctp_association *asoc;
+
sk->sk_state = SCTP_SS_CLOSING;
- ep = sctp_sk(sk)->ep;
- if (!list_empty(&ep->asocs)) {
- asoc = list_entry(ep->asocs.next,
- struct sctp_association, asocs);
- sctp_primitive_SHUTDOWN(net, asoc, NULL);
- }
+ asoc = list_entry(ep->asocs.next,
+ struct sctp_association, asocs);
+ sctp_primitive_SHUTDOWN(net, asoc, NULL);
}
}
@@ -4480,12 +4482,9 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
if (!transport || !sctp_transport_hold(transport))
goto out;
- sctp_association_hold(transport->asoc);
- sctp_transport_put(transport);
-
rcu_read_unlock();
err = cb(transport, p);
- sctp_association_put(transport->asoc);
+ sctp_transport_put(transport);
out:
return err;
diff --git a/net/socket.c b/net/socket.c
index 5a9bf5ee2464..272518b087c8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2038,6 +2038,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
if (err)
break;
++datagrams;
+ if (msg_data_left(&msg_sys))
+ break;
cond_resched();
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 145082e2ba36..5d1c14a2f268 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2812,7 +2812,8 @@ static int unix_seq_show(struct seq_file *seq, void *v)
i++;
}
for ( ; i < len; i++)
- seq_putc(seq, u->addr->name->sun_path[i]);
+ seq_putc(seq, u->addr->name->sun_path[i] ?:
+ '@');
}
unix_state_unlock(s);
seq_putc(seq, '\n');