summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-04-24 14:16:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-04-24 14:16:40 -0700
commit24cac7009cb1b211f1c793ecb6a462c03dc35818 (patch)
tree3c1e77363ed730b38a9c4bd842a187a8250d34b7 /net
parent6d08b06e67cd117f6992c46611dfb4ce267cd71e (diff)
parentd19efb729f10339f91c35003d480dc718cae3b3c (diff)
downloadlinux-master.tar.gz
linux-master.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netHEADmaster
Pull networking fixes from David Miller: 1) Fix rtnl deadlock in ipvs, from Julian Anastasov. 2) s390 qeth fixes from Julian Wiedmann (control IO completion stalls, bad MAC address update sequence, request side races on command IO timeouts). 3) Handle seq_file overflow properly in l2tp, from Guillaume Nault. 4) Fix VLAN priority mappings in cpsw driver, from Ivan Khoronzhuk. 5) Packet scheduler ife action fixes (malformed TLV lengths, etc.) from Alexander Aring. 6) Fix out of bounds access in tcp md5 option parser, from Jann Horn. 7) Missing netlink attribute policies in rtm_ipv6_policy table, from Eric Dumazet. 8) Missing socket address length checks in l2tp and pppoe connect, from Guillaume Nault. 9) Fix netconsole over team and bonding, from Xin Long. 10) Fix race with AF_PACKET socket state bitfields, from Willem de Bruijn. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (51 commits) ice: Fix insufficient memory issue in ice_aq_manage_mac_read sfc: ARFS filter IDs net: ethtool: Add missing kernel doc for FEC parameters packet: fix bitfield update race ice: Do not check INTEVENT bit for OICR interrupts ice: Fix incorrect comment for action type ice: Fix initialization for num_nodes_added igb: Fix the transmission mode of queue 0 for Qav mode ixgbevf: ensure xdp_ring resources are free'd on error exit team: fix netconsole setup over team amd-xgbe: Only use the SFP supported transceiver signals amd-xgbe: Improve KR auto-negotiation and training amd-xgbe: Add pre/post auto-negotiation phy hooks pppoe: check sockaddr length in pppoe_connect() l2tp: check sockaddr length in pppol2tp_connect() net: phy: marvell: clear wol event before setting it ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy bonding: do not set slave_dev npinfo before slave_enable_netpoll in bond_enslave tcp: don't read out-of-bounds opsize ibmvnic: Clean actual number of RX or TX pools ...
Diffstat (limited to 'net')
-rw-r--r--net/bridge/netfilter/ebtables.c11
-rw-r--r--net/ife/ife.c38
-rw-r--r--net/ipv4/tcp_input.c7
-rw-r--r--net/ipv6/netfilter/Kconfig55
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/seg6_iptunnel.c2
-rw-r--r--net/l2tp/l2tp_debugfs.c5
-rw-r--r--net/l2tp/l2tp_ppp.c12
-rw-r--r--net/llc/af_llc.c21
-rw-r--r--net/llc/llc_c_ac.c9
-rw-r--r--net/llc/llc_conn.c22
-rw-r--r--net/netfilter/Kconfig1
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c155
-rw-r--r--net/netfilter/nf_conntrack_expect.c5
-rw-r--r--net/netfilter/nf_conntrack_extend.c2
-rw-r--r--net/netfilter/nf_conntrack_sip.c16
-rw-r--r--net/netfilter/nf_tables_api.c69
-rw-r--r--net/netfilter/xt_connmark.c49
-rw-r--r--net/packet/af_packet.c60
-rw-r--r--net/packet/internal.h10
-rw-r--r--net/sched/act_ife.c9
-rw-r--r--net/strparser/strparser.c2
23 files changed, 347 insertions, 223 deletions
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 032e0fe45940..28a4c3490359 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info,
{
unsigned int size = info->entries_size;
const void *entries = info->entries;
- int ret;
newinfo->entries_size = size;
-
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
- if (ret)
- return ret;
+ if (info->nentries) {
+ int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+ info->nentries);
+ if (ret)
+ return ret;
+ }
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
@@ -92,12 +95,43 @@ struct meta_tlvhdr {
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 367def6ddeda..e51c644484dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ccbfa83e4bb0..ce77bcc2490c 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6
fields such as the source, destination, flowlabel, hop-limit and
the packet mark.
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+ tristate "IPv6 nf_tables nat chain support"
+ help
+ This option enables the "nat" chain for IPv6 in nf_tables. This
+ chain type is used to perform Network Address Translation (NAT)
+ packet transformations such as the source, destination address and
+ source and destination ports.
+
+config NFT_MASQ_IPV6
+ tristate "IPv6 masquerade support for nf_tables"
+ depends on NFT_MASQ
+ select NF_NAT_MASQUERADE_IPV6
+ help
+ This is the expression that provides IPv4 masquerading support for
+ nf_tables.
+
+config NFT_REDIR_IPV6
+ tristate "IPv6 redirect support for nf_tables"
+ depends on NFT_REDIR
+ select NF_NAT_REDIRECT
+ help
+ This is the expression that provides IPv4 redirect support for
+ nf_tables.
+
+endif # NF_NAT_IPV6
+
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
@@ -107,39 +135,12 @@ config NF_NAT_IPV6
if NF_NAT_IPV6
-config NFT_CHAIN_NAT_IPV6
- depends on NF_TABLES_IPV6
- tristate "IPv6 nf_tables nat chain support"
- help
- This option enables the "nat" chain for IPv6 in nf_tables. This
- chain type is used to perform Network Address Translation (NAT)
- packet transformations such as the source, destination address and
- source and destination ports.
-
config NF_NAT_MASQUERADE_IPV6
tristate "IPv6 masquerade support"
help
This is the kernel functionality to provide NAT in the masquerade
flavour (automatic source address selection) for IPv6.
-config NFT_MASQ_IPV6
- tristate "IPv6 masquerade support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_MASQ
- select NF_NAT_MASQUERADE_IPV6
- help
- This is the expression that provides IPv4 masquerading support for
- nf_tables.
-
-config NFT_REDIR_IPV6
- tristate "IPv6 redirect support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_REDIR
- select NF_NAT_REDIRECT
- help
- This is the expression that provides IPv4 redirect support for
- nf_tables.
-
endif # NF_NAT_IPV6
config IP6_NF_IPTABLES
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 49b954d6d0fa..cde7d8251377 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3975,6 +3975,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
@@ -3986,6 +3987,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..5fe139484919 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b8f9d45bfeb1..7f1e842ef05a 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -106,8 +106,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
return;
/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 7d0c963680e6..1fd9e145076a 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
@@ -1618,8 +1625,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v)
return;
/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 6d29b2b94e84..cb80ebb38311 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
- struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
@@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- sap = llc->sap;
- /* Hold this for release_sock(), so that llc_backlog_rcv() could still
- * use it.
- */
- llc_sap_hold(sap);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
- llc_sap_put(sap);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 163121192aca..4d78375f9872 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 110e32bcb399..c0ac522b48a1 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -961,6 +961,26 @@ out:
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
@@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk)
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 704b3832dbad..44d8a55e9721 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -594,6 +594,7 @@ config NFT_QUOTA
config NFT_REJECT
default m if NETFILTER_ADVANCED=n
tristate "Netfilter nf_tables reject support"
+ depends on !NF_TABLES_INET || (IPV6!=m || m)
help
This option adds the "reject" expression that you can use to
explicitly deny and notify via TCP reset/ICMP informational errors
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5ebde4b15810..f36098887ad0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2384,11 +2384,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn));
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
@@ -3481,12 +3477,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index fbaf3bd05b2e..001501e25625 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -49,6 +49,7 @@
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched/signal.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
@@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
@@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
@@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
@@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
@@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
@@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
@@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
@@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
@@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
@@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
} else {
array = kcalloc(count, sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
@@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
@@ -1932,13 +1927,23 @@ outtinfo:
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 8ef21d9f9a00..4b2b3d53acfc 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
- return a->master == b->master && a->class == b->class &&
+ return a->master == b->master &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
@@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
+ if (i->class != expect->class)
+ return -EALREADY;
+
if (nf_ct_remove_expect(i))
break;
} else if (expect_clash(i, expect)) {
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 9fe0ddc333fb..277bbfe26478 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -9,6 +9,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
+#include <linux/kmemleak.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
@@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
rcu_read_unlock();
alloc = max(newlen, NF_CT_EXT_PREALLOC);
+ kmemleak_not_leak(old);
new = __krealloc(old, alloc, gfp);
if (!new)
return NULL;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4dbb5bad4363..908e51e2dc2b 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
datalen, rtp_exp, rtcp_exp,
mediaoff, medialen, daddr);
else {
- if (nf_ct_expect_related(rtp_exp) == 0) {
- if (nf_ct_expect_related(rtcp_exp) != 0)
- nf_ct_unexpect_related(rtp_exp);
- else
+ /* -EALREADY handling works around end-points that send
+ * SDP messages with identical port but different media type,
+ * we pretend expectation was set up.
+ */
+ int errp = nf_ct_expect_related(rtp_exp);
+
+ if (errp == 0 || errp == -EALREADY) {
+ int errcp = nf_ct_expect_related(rtcp_exp);
+
+ if (errcp == 0 || errcp == -EALREADY)
ret = NF_ACCEPT;
+ else if (errp == 0)
+ nf_ct_unexpect_related(rtp_exp);
}
}
nf_ct_expect_put(rtcp_exp);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9134cc429ad4..04d4e3772584 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2361,41 +2361,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- if (nft_is_active_next(net, old_rule)) {
- trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
- old_rule);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err2;
- }
- nft_deactivate_next(net, old_rule);
- chain->use--;
- list_add_tail_rcu(&rule->list, &old_rule->list);
- } else {
+ if (!nft_is_active_next(net, old_rule)) {
err = -ENOENT;
goto err2;
}
- } else if (nlh->nlmsg_flags & NLM_F_APPEND)
- if (old_rule)
- list_add_rcu(&rule->list, &old_rule->list);
- else
- list_add_tail_rcu(&rule->list, &chain->rules);
- else {
- if (old_rule)
- list_add_tail_rcu(&rule->list, &old_rule->list);
- else
- list_add_rcu(&rule->list, &chain->rules);
- }
+ trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+ old_rule);
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+ nft_deactivate_next(net, old_rule);
+ chain->use--;
- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
- err = -ENOMEM;
- goto err3;
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ } else {
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_APPEND) {
+ if (old_rule)
+ list_add_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ } else {
+ if (old_rule)
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+ }
}
chain->use++;
return 0;
-err3:
- list_del_rcu(&rule->list);
err2:
nf_tables_rule_destroy(&ctx, rule);
err1:
@@ -3207,18 +3212,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
err = ops->init(set, &desc, nla);
if (err < 0)
- goto err2;
+ goto err3;
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err3;
+ goto err4;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err3:
+err4:
ops->destroy(set);
+err3:
+ kfree(set->name);
err2:
kvfree(set);
err1:
@@ -5738,7 +5745,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
struct nft_base_chain *basechain;
if (nft_trans_chain_name(trans))
- strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+ swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
if (!nft_is_base_chain(trans->ctx.chain))
return;
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 773da82190dc..94df000abb92 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark");
MODULE_ALIAS("ip6t_connmark");
static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
- const struct xt_connmark_tginfo1 *info,
- u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
{
enum ip_conntrack_info ctinfo;
+ u_int32_t new_targetmark;
struct nf_conn *ct;
u_int32_t newmark;
@@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb,
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ newmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ newmark <<= info->shift_bits;
+
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
- newmark = (ct->mark & ~info->ctmask) ^
- (skb->mark & info->nfmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (skb->mark & info->nfmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (ct->mark & ~info->ctmask) ^
+ new_targetmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_RESTORE:
- newmark = (skb->mark & ~info->nfmask) ^
- (ct->mark & info->ctmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (ct->mark & info->ctmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (skb->mark & ~info->nfmask) ^
+ new_targetmark;
skb->mark = newmark;
break;
}
@@ -89,8 +93,14 @@ static unsigned int
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
-
- return connmark_tg_shift(skb, info, 0, 0);
+ const struct xt_connmark_tginfo2 info2 = {
+ .ctmark = info->ctmark,
+ .ctmask = info->ctmask,
+ .nfmask = info->nfmask,
+ .mode = info->mode,
+ };
+
+ return connmark_tg_shift(skb, &info2);
}
static unsigned int
@@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo2 *info = par->targinfo;
- return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
- info->shift_bits, info->shift_dir);
+ return connmark_tg_shift(skb, info);
}
static int connmark_tg_check(const struct xt_tgchk_param *par)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c31b0687396a..01f3515cada0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
skb_set_queue_mapping(skb, queue_index);
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
@@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk)
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
@@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
@@ -3252,7 +3259,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
@@ -3732,12 +3739,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
@@ -3748,7 +3761,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
@@ -3760,7 +3775,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
@@ -3769,15 +3786,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
@@ -3815,11 +3837,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
@@ -125,8 +127,6 @@ struct packet_sock {
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a5994cf0512b..8527cfdc446d 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
@@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 805b139756db..092bebc70048 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}