summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_input.c1
-rw-r--r--net/bridge/br_netfilter_hooks.c21
-rw-r--r--net/ceph/osdmap.c1
-rw-r--r--net/core/dev.c35
-rw-r--r--net/core/skbuff.c30
-rw-r--r--net/core/sock.c16
-rw-r--r--net/dccp/ccids/ccid2.c1
-rw-r--r--net/dccp/ipv4.c3
-rw-r--r--net/dccp/ipv6.c8
-rw-r--r--net/dccp/minisocks.c25
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/route.c1
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv6/addrconf.c61
-rw-r--r--net/ipv6/ip6_fib.c2
-rw-r--r--net/ipv6/ip6_output.c7
-rw-r--r--net/ipv6/ip6_vti.c4
-rw-r--r--net/ipv6/ndisc.c2
-rw-r--r--net/ipv6/tcp_ipv6.c8
-rw-r--r--net/l2tp/l2tp_ip.c2
-rw-r--r--net/mpls/af_mpls.c1
-rw-r--r--net/netfilter/xt_qtaguid.c24
-rw-r--r--net/netlink/Kconfig9
-rw-r--r--net/netlink/af_netlink.c751
-rw-r--r--net/netlink/af_netlink.h15
-rw-r--r--net/netlink/diag.c39
-rw-r--r--net/openvswitch/flow_netlink.c2
-rw-r--r--net/packet/af_packet.c8
-rw-r--r--net/sched/act_api.c5
-rw-r--r--net/sched/act_connmark.c3
-rw-r--r--net/unix/garbage.c17
-rw-r--r--net/wireless/nl80211.c121
-rw-r--r--net/xfrm/xfrm_policy.c10
-rw-r--r--net/xfrm/xfrm_user.c9
37 files changed, 283 insertions, 981 deletions
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index f7fba74108a9..e24754a0e052 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook);
static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ br_drop_fake_rtable(skb);
return netif_receive_skb(skb);
}
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 7ddbe7ec81d6..97fc19f001bf 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -516,21 +516,6 @@ static unsigned int br_nf_pre_routing(void *priv,
}
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one. On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- br_drop_fake_rtable(skb);
- return NF_ACCEPT;
-}
-
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -901,12 +886,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
.priority = NF_BR_PRI_BRNF,
},
{
- .hook = br_nf_local_in,
- .pf = NFPROTO_BRIDGE,
- .hooknum = NF_BR_LOCAL_IN,
- .priority = NF_BR_PRI_BRNF,
- },
- {
.hook = br_nf_forward_ip,
.pf = NFPROTO_BRIDGE,
.hooknum = NF_BR_FORWARD,
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index ddc3573894b0..bc95e48d5cfb 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1265,7 +1265,6 @@ static int decode_new_up_state_weight(void **p, void *end,
if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
(xorstate & CEPH_OSD_EXISTS)) {
pr_info("osd%d does not exist\n", osd);
- map->osd_weight[osd] = CEPH_OSD_IN;
ret = set_primary_affinity(map, osd,
CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
if (ret)
diff --git a/net/core/dev.c b/net/core/dev.c
index 51aed87e8eec..2587d7f30191 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1679,27 +1679,54 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
static void netstamp_clear(struct work_struct *work)
{
int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+ int wanted;
- while (deferred--)
- static_key_slow_dec(&netstamp_needed);
+ wanted = atomic_add_return(deferred, &netstamp_wanted);
+ if (wanted > 0)
+ static_key_enable(&netstamp_needed);
+ else
+ static_key_disable(&netstamp_needed);
}
static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif
void net_enable_timestamp(void)
{
+#ifdef HAVE_JUMP_LABEL
+ int wanted;
+
+ while (1) {
+ wanted = atomic_read(&netstamp_wanted);
+ if (wanted <= 0)
+ break;
+ if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+ return;
+ }
+ atomic_inc(&netstamp_needed_deferred);
+ schedule_work(&netstamp_work);
+#else
static_key_slow_inc(&netstamp_needed);
+#endif
}
EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
- /* net_disable_timestamp() can be called from non process context */
- atomic_inc(&netstamp_needed_deferred);
+ int wanted;
+
+ while (1) {
+ wanted = atomic_read(&netstamp_wanted);
+ if (wanted <= 1)
+ break;
+ if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+ return;
+ }
+ atomic_dec(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
static_key_slow_dec(&netstamp_needed);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5dd643d524d6..fedcee8263b6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3704,13 +3704,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
if (!skb_may_tx_timestamp(sk, false))
return;
- /* take a reference to prevent skb_orphan() from freeing the socket */
- sock_hold(sk);
-
- *skb_hwtstamps(skb) = *hwtstamps;
- __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
- sock_put(sk);
+ /* Take a reference to prevent skb_orphan() from freeing the socket,
+ * but only if the socket refcount is not zero.
+ */
+ if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ *skb_hwtstamps(skb) = *hwtstamps;
+ __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+ sock_put(sk);
+ }
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
@@ -3761,7 +3762,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
{
struct sock *sk = skb->sk;
struct sock_exterr_skb *serr;
- int err;
+ int err = 1;
skb->wifi_acked_valid = 1;
skb->wifi_acked = acked;
@@ -3771,14 +3772,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
- /* take a reference to prevent skb_orphan() from freeing the socket */
- sock_hold(sk);
-
- err = sock_queue_err_skb(sk, skb);
+ /* Take a reference to prevent skb_orphan() from freeing the socket,
+ * but only if the socket refcount is not zero.
+ */
+ if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ err = sock_queue_err_skb(sk, skb);
+ sock_put(sk);
+ }
if (err)
kfree_skb(skb);
-
- sock_put(sk);
}
EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
diff --git a/net/core/sock.c b/net/core/sock.c
index a84a154cdf0c..4efaa3b6633d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1463,6 +1463,11 @@ static void __sk_destruct(struct rcu_head *head)
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
+ if (sk->sk_frag.page) {
+ put_page(sk->sk_frag.page);
+ sk->sk_frag.page = NULL;
+ }
+
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
@@ -1564,6 +1569,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
is_charged = sk_filter_charge(newsk, filter);
if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+ /* We need to make sure that we don't uncharge the new
+ * socket if we couldn't charge it in the first place
+ * as otherwise we uncharge the parent's filter.
+ */
+ if (!is_charged)
+ RCU_INIT_POINTER(newsk->sk_filter, NULL);
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
@@ -2706,11 +2717,6 @@ void sk_common_release(struct sock *sk)
sk_refcnt_debug_release(sk);
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
- sk->sk_frag.page = NULL;
- }
-
sock_put(sk);
}
EXPORT_SYMBOL(sk_common_release);
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198e730c..5e3a7302f774 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
for (i = 0; i < hc->tx_seqbufc; i++)
kfree(hc->tx_seqbuf[i]);
hc->tx_seqbufc = 0;
+ dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
}
static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 0759f5b9180e..6467bf392e1b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
switch (type) {
case ICMP_REDIRECT:
- dccp_do_redirect(skb, sk);
+ if (!sock_owned_by_user(sk))
+ dccp_do_redirect(skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 27c4e81efa24..8113ad58fcb4 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
- struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+ if (!sock_owned_by_user(sk)) {
+ struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
- if (dst)
- dst->ops->redirect(dst, sk, skb);
+ if (dst)
+ dst->ops->redirect(dst, sk, skb);
+ }
goto out;
}
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 1994f8af646b..68eed344b471 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
+ bh_unlock_sock(newsk);
sk_free(newsk);
return NULL;
}
@@ -145,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
struct dccp_request_sock *dreq = dccp_rsk(req);
bool own_req;
+ /* TCP/DCCP listeners became lockless.
+ * DCCP stores complex state in its request_sock, so we need
+ * a protection for them, now this code runs without being protected
+ * by the parent (listener) lock.
+ */
+ spin_lock_bh(&dreq->dreq_lock);
+
/* Check for retransmitted REQUEST */
if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
@@ -159,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
inet_rtx_syn_ack(sk, req);
}
/* Network Duplicate, discard packet */
- return NULL;
+ goto out;
}
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -185,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
req, &own_req);
- if (!child)
- goto listen_overflow;
-
- return inet_csk_complete_hashdance(sk, child, req, own_req);
+ if (child) {
+ child = inet_csk_complete_hashdance(sk, child, req, own_req);
+ goto out;
+ }
-listen_overflow:
- dccp_pr_debug("listen_overflow!\n");
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
drop:
if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req);
- return NULL;
+out:
+ spin_unlock_bh(&dreq->dreq_lock);
+ return child;
}
EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -249,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req,
{
struct dccp_request_sock *dreq = dccp_rsk(req);
+ spin_lock_init(&dreq->dreq_lock);
inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport);
inet_rsk(req)->acked = 0;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 7e30c7b50a28..a353d1d92f01 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1081,7 +1081,8 @@ static void nl_fib_input(struct sk_buff *skb)
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
- if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+ if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+ skb->len < nlh->nlmsg_len ||
nlmsg_len(nlh) < sizeof(*frn))
return;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6ace04d14e30..9af0f461b00d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1963,6 +1963,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
{
int res;
+ tos &= IPTOS_RT_MASK;
rcu_read_lock();
/* Multicast recognition logic is moved from route cache to here.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e7e227f6760f..3f87c731477f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5437,6 +5437,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_set_state(sk, TCP_ESTABLISHED);
+ icsk->icsk_ack.lrcvtime = tcp_time_stamp;
if (skb) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5649,7 +5650,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* to stand against the temptation 8) --ANK
*/
inet_csk_schedule_ack(sk);
- icsk->icsk_ack.lrcvtime = tcp_time_stamp;
tcp_enter_quickack_mode(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 51a77e20f6c6..1660613ddae4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -271,10 +271,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
*/
void tcp_v4_mtu_reduced(struct sock *sk)
{
- struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
- u32 mtu = tcp_sk(sk)->mtu_info;
+ struct dst_entry *dst;
+ u32 mtu;
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+ return;
+ mtu = tcp_sk(sk)->mtu_info;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -420,7 +423,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
switch (type) {
case ICMP_REDIRECT:
- do_redirect(icmp_skb, sk);
+ if (!sock_owned_by_user(sk))
+ do_redirect(icmp_skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9475a2748a9a..019db68bdb9f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -472,6 +472,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
newtp->rtt_min[0].rtt = ~0U;
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+ newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
newtp->packets_out = 0;
newtp->retrans_out = 0;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index ce20968de667..4aef80d30fab 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -257,7 +257,8 @@ void tcp_delack_timer_handler(struct sock *sk)
sk_mem_reclaim_partial(sk);
- if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
goto out;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -538,7 +539,8 @@ void tcp_write_timer_handler(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
int event;
- if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !icsk->icsk_pending)
goto out;
if (time_after(icsk->icsk_timeout, jiffies)) {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 01455f492e17..3d72aeffa3f1 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -112,6 +112,27 @@ static inline u32 cstamp_delta(unsigned long cstamp)
return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
}
+static inline s32 rfc3315_s14_backoff_init(s32 irt)
+{
+ /* multiply 'initial retransmission time' by 0.9 .. 1.1 */
+ u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt;
+ do_div(tmp, 1000000);
+ return (s32)tmp;
+}
+
+static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt)
+{
+ /* multiply 'retransmission timeout' by 1.9 .. 2.1 */
+ u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt;
+ do_div(tmp, 1000000);
+ if ((s32)tmp > mrt) {
+ /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */
+ tmp = (900000 + prandom_u32() % 200001) * (u64)mrt;
+ do_div(tmp, 1000000);
+ }
+ return (s32)tmp;
+}
+
#ifdef CONFIG_SYSCTL
static int addrconf_sysctl_register(struct inet6_dev *idev);
static void addrconf_sysctl_unregister(struct inet6_dev *idev);
@@ -187,6 +208,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
+ .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL,
.rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY,
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
@@ -202,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
@@ -233,6 +256,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
+ .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL,
.rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY,
.use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
@@ -248,6 +272,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
@@ -3502,7 +3527,7 @@ static void addrconf_rs_timer(unsigned long data)
if (idev->if_flags & IF_RA_RCVD)
goto out;
- if (idev->rs_probes++ < idev->cnf.rtr_solicits) {
+ if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) {
write_unlock(&idev->lock);
if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE))
ndisc_send_rs(dev, &lladdr,
@@ -3511,11 +3536,13 @@ static void addrconf_rs_timer(unsigned long data)
goto put;
write_lock(&idev->lock);
+ idev->rs_interval = rfc3315_s14_backoff_update(
+ idev->rs_interval, idev->cnf.rtr_solicit_max_interval);
/* The wait after the last probe can be shorter */
addrconf_mod_rs_timer(idev, (idev->rs_probes ==
idev->cnf.rtr_solicits) ?
idev->cnf.rtr_solicit_delay :
- idev->cnf.rtr_solicit_interval);
+ idev->rs_interval);
} else {
/*
* Note: we do not support deprecated "all on-link"
@@ -3743,7 +3770,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp);
send_rs = send_mld &&
ipv6_accept_ra(ifp->idev) &&
- ifp->idev->cnf.rtr_solicits > 0 &&
+ ifp->idev->cnf.rtr_solicits != 0 &&
(dev->flags&IFF_LOOPBACK) == 0;
read_unlock_bh(&ifp->idev->lock);
@@ -3765,10 +3792,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
write_lock_bh(&ifp->idev->lock);
spin_lock(&ifp->lock);
+ ifp->idev->rs_interval = rfc3315_s14_backoff_init(
+ ifp->idev->cnf.rtr_solicit_interval);
ifp->idev->rs_probes = 1;
ifp->idev->if_flags |= IF_RS_SENT;
- addrconf_mod_rs_timer(ifp->idev,
- ifp->idev->cnf.rtr_solicit_interval);
+ addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval);
spin_unlock(&ifp->lock);
write_unlock_bh(&ifp->idev->lock);
}
@@ -4685,6 +4713,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits;
array[DEVCONF_RTR_SOLICIT_INTERVAL] =
jiffies_to_msecs(cnf->rtr_solicit_interval);
+ array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] =
+ jiffies_to_msecs(cnf->rtr_solicit_max_interval);
array[DEVCONF_RTR_SOLICIT_DELAY] =
jiffies_to_msecs(cnf->rtr_solicit_delay);
array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version;
@@ -4706,6 +4736,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_PROBE_INTERVAL] =
jiffies_to_msecs(cnf->rtr_probe_interval);
#ifdef CONFIG_IPV6_ROUTE_INFO
+ array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
@@ -4893,7 +4924,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
return -EINVAL;
if (!ipv6_accept_ra(idev))
return -EINVAL;
- if (idev->cnf.rtr_solicits <= 0)
+ if (idev->cnf.rtr_solicits == 0)
return -EINVAL;
write_lock_bh(&idev->lock);
@@ -4918,8 +4949,10 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
if (update_rs) {
idev->if_flags |= IF_RS_SENT;
+ idev->rs_interval = rfc3315_s14_backoff_init(
+ idev->cnf.rtr_solicit_interval);
idev->rs_probes = 1;
- addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval);
+ addrconf_mod_rs_timer(idev, idev->rs_interval);
}
/* Well, that's kinda nasty ... */
@@ -5557,6 +5590,13 @@ static struct addrconf_sysctl_table
.proc_handler = proc_dointvec_jiffies,
},
{
+ .procname = "router_solicitation_max_interval",
+ .data = &ipv6_devconf.rtr_solicit_max_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
.procname = "router_solicitation_delay",
.data = &ipv6_devconf.rtr_solicit_delay,
.maxlen = sizeof(int),
@@ -5666,6 +5706,13 @@ static struct addrconf_sysctl_table
},
#ifdef CONFIG_IPV6_ROUTE_INFO
{
+ .procname = "accept_ra_rt_info_min_plen",
+ .data = &ipv6_devconf.accept_ra_rt_info_min_plen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_rt_info_max_plen",
.data = &ipv6_devconf.accept_ra_rt_info_max_plen,
.maxlen = sizeof(int),
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 34cf46d74554..85bf86458706 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -903,6 +903,8 @@ add:
ins = &rt->dst.rt6_next;
iter = *ins;
while (iter) {
+ if (iter->rt6i_metric > rt->rt6i_metric)
+ break;
if (rt6_qualify_for_ecmp(iter)) {
*ins = iter->dst.rt6_next;
fib6_purge_rt(iter, fn, info->nl_net);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index cd96a01032a2..cf90a9bf26a3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -742,13 +742,14 @@ slow_path:
* Fragment the datagram.
*/
- *prevhdr = NEXTHDR_FRAGMENT;
troom = rt->dst.dev->needed_tailroom;
/*
* Keep copying data until we run out.
*/
while (left > 0) {
+ u8 *fragnexthdr_offset;
+
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
@@ -793,6 +794,10 @@ slow_path:
*/
skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
+ fragnexthdr_offset = skb_network_header(frag);
+ fragnexthdr_offset += prevhdr - skb_network_header(skb);
+ *fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
/*
* Build fragment header.
*/
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 24fb9c0efd00..5b7433887eda 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -681,6 +681,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
u->link = p->link;
u->i_key = p->i_key;
u->o_key = p->o_key;
+ if (u->i_key)
+ u->i_flags |= GRE_KEY;
+ if (u->o_key)
+ u->o_flags |= GRE_KEY;
u->proto = p->proto;
memcpy(u->name, p->name, sizeof(u->name));
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 84afb9a77278..3452f9037ad4 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1358,6 +1358,8 @@ skip_linkparms:
if (ri->prefix_len == 0 &&
!in6_dev->cnf.accept_ra_defrtr)
continue;
+ if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+ continue;
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 108b39967694..8532768b4eaa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -377,10 +377,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
- struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+ if (!sock_owned_by_user(sk)) {
+ struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
- if (dst)
- dst->ops->redirect(dst, sk, skb);
+ if (dst)
+ dst->ops->redirect(dst, sk, skb);
+ }
goto out;
}
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 445b7cd0826a..48ab93842322 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -383,7 +383,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
drop:
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
kfree_skb(skb);
- return -1;
+ return 0;
}
/* Userspace will call sendmsg() on the tunnel socket to send L2TP
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 881bc2072809..52cfc4478511 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1567,6 +1567,7 @@ static void mpls_net_exit(struct net *net)
for (index = 0; index < platform_labels; index++) {
struct mpls_route *rt = rtnl_dereference(platform_label[index]);
RCU_INIT_POINTER(platform_label[index], NULL);
+ mpls_notify_route(net, index, rt, NULL, NULL);
mpls_rt_free(rt);
}
rtnl_unlock();
diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c
index ececa65868ef..e0d8e9ad315b 100644
--- a/net/netfilter/xt_qtaguid.c
+++ b/net/netfilter/xt_qtaguid.c
@@ -1802,8 +1802,11 @@ ret_res:
}
#ifdef DDEBUG
-/* This function is not in xt_qtaguid_print.c because of locks visibility */
-static void prdebug_full_state(int indent_level, const char *fmt, ...)
+/*
+ * This function is not in xt_qtaguid_print.c because of locks visibility.
+ * The lock of sock_tag_list must be aquired before calling this function
+ */
+static void prdebug_full_state_locked(int indent_level, const char *fmt, ...)
{
va_list args;
char *fmt_buff;
@@ -1824,16 +1827,12 @@ static void prdebug_full_state(int indent_level, const char *fmt, ...)
kfree(buff);
va_end(args);
- spin_lock_bh(&sock_tag_list_lock);
prdebug_sock_tag_tree(indent_level, &sock_tag_tree);
- spin_unlock_bh(&sock_tag_list_lock);
- spin_lock_bh(&sock_tag_list_lock);
spin_lock_bh(&uid_tag_data_tree_lock);
prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree);
prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree);
spin_unlock_bh(&uid_tag_data_tree_lock);
- spin_unlock_bh(&sock_tag_list_lock);
spin_lock_bh(&iface_stat_list_lock);
prdebug_iface_stat_list(indent_level, &iface_stat_list);
@@ -1842,7 +1841,7 @@ static void prdebug_full_state(int indent_level, const char *fmt, ...)
pr_debug("qtaguid: %s(): }\n", __func__);
}
#else
-static void prdebug_full_state(int indent_level, const char *fmt, ...) {}
+static void prdebug_full_state_locked(int indent_level, const char *fmt, ...) {}
#endif
struct proc_ctrl_print_info {
@@ -1965,8 +1964,11 @@ static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v)
(u64)atomic64_read(&qtu_events.match_no_sk),
(u64)atomic64_read(&qtu_events.match_no_sk_file));
- /* Count the following as part of the last item_index */
- prdebug_full_state(0, "proc ctrl");
+ /* Count the following as part of the last item_index. No need
+ * to lock the sock_tag_list here since it is already locked when
+ * starting the seq_file operation
+ */
+ prdebug_full_state_locked(0, "proc ctrl");
}
return 0;
@@ -2875,8 +2877,10 @@ static int qtudev_release(struct inode *inode, struct file *file)
sock_tag_tree_erase(&st_to_free_tree);
- prdebug_full_state(0, "%s(): pid=%u tgid=%u", __func__,
+ spin_lock_bh(&sock_tag_list_lock);
+ prdebug_full_state_locked(0, "%s(): pid=%u tgid=%u", __func__,
current->pid, current->tgid);
+ spin_unlock_bh(&sock_tag_list_lock);
return 0;
}
diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig
index 2c5e95e9bfbd..5d6e8c05b3d4 100644
--- a/net/netlink/Kconfig
+++ b/net/netlink/Kconfig
@@ -2,15 +2,6 @@
# Netlink Sockets
#
-config NETLINK_MMAP
- bool "NETLINK: mmaped IO"
- ---help---
- This option enables support for memory mapped netlink IO. This
- reduces overhead by avoiding copying data between kernel- and
- userspace.
-
- If unsure, say N.
-
config NETLINK_DIAG
tristate "NETLINK: socket monitoring interface"
default n
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f4dd706c6cd1..96fe1c103bf9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -225,7 +225,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
dev_hold(dev);
- if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+ if (is_vmalloc_addr(skb->head))
nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
else
nskb = skb_clone(skb, GFP_ATOMIC);
@@ -300,610 +300,8 @@ static void netlink_rcv_wake(struct sock *sk)
wake_up_interruptible(&nlk->wait);
}
-#ifdef CONFIG_NETLINK_MMAP
-static bool netlink_rx_is_mmaped(struct sock *sk)
-{
- return nlk_sk(sk)->rx_ring.pg_vec != NULL;
-}
-
-static bool netlink_tx_is_mmaped(struct sock *sk)
-{
- return nlk_sk(sk)->tx_ring.pg_vec != NULL;
-}
-
-static __pure struct page *pgvec_to_page(const void *addr)
-{
- if (is_vmalloc_addr(addr))
- return vmalloc_to_page(addr);
- else
- return virt_to_page(addr);
-}
-
-static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len)
-{
- unsigned int i;
-
- for (i = 0; i < len; i++) {
- if (pg_vec[i] != NULL) {
- if (is_vmalloc_addr(pg_vec[i]))
- vfree(pg_vec[i]);
- else
- free_pages((unsigned long)pg_vec[i], order);
- }
- }
- kfree(pg_vec);
-}
-
-static void *alloc_one_pg_vec_page(unsigned long order)
-{
- void *buffer;
- gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO |
- __GFP_NOWARN | __GFP_NORETRY;
-
- buffer = (void *)__get_free_pages(gfp_flags, order);
- if (buffer != NULL)
- return buffer;
-
- buffer = vzalloc((1 << order) * PAGE_SIZE);
- if (buffer != NULL)
- return buffer;
-
- gfp_flags &= ~__GFP_NORETRY;
- return (void *)__get_free_pages(gfp_flags, order);
-}
-
-static void **alloc_pg_vec(struct netlink_sock *nlk,
- struct nl_mmap_req *req, unsigned int order)
-{
- unsigned int block_nr = req->nm_block_nr;
- unsigned int i;
- void **pg_vec;
-
- pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL);
- if (pg_vec == NULL)
- return NULL;
-
- for (i = 0; i < block_nr; i++) {
- pg_vec[i] = alloc_one_pg_vec_page(order);
- if (pg_vec[i] == NULL)
- goto err1;
- }
-
- return pg_vec;
-err1:
- free_pg_vec(pg_vec, order, block_nr);
- return NULL;
-}
-
-
-static void
-__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
- unsigned int order)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
- struct sk_buff_head *queue;
- struct netlink_ring *ring;
-
- queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
- ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
- spin_lock_bh(&queue->lock);
-
- ring->frame_max = req->nm_frame_nr - 1;
- ring->head = 0;
- ring->frame_size = req->nm_frame_size;
- ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE;
-
- swap(ring->pg_vec_len, req->nm_block_nr);
- swap(ring->pg_vec_order, order);
- swap(ring->pg_vec, pg_vec);
-
- __skb_queue_purge(queue);
- spin_unlock_bh(&queue->lock);
-
- WARN_ON(atomic_read(&nlk->mapped));
-
- if (pg_vec)
- free_pg_vec(pg_vec, order, req->nm_block_nr);
-}
-
-static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
- bool tx_ring)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
- struct netlink_ring *ring;
- void **pg_vec = NULL;
- unsigned int order = 0;
-
- ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
- if (atomic_read(&nlk->mapped))
- return -EBUSY;
- if (atomic_read(&ring->pending))
- return -EBUSY;
-
- if (req->nm_block_nr) {
- if (ring->pg_vec != NULL)
- return -EBUSY;
-
- if ((int)req->nm_block_size <= 0)
- return -EINVAL;
- if (!PAGE_ALIGNED(req->nm_block_size))
- return -EINVAL;
- if (req->nm_frame_size < NL_MMAP_HDRLEN)
- return -EINVAL;
- if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT))
- return -EINVAL;
-
- ring->frames_per_block = req->nm_block_size /
- req->nm_frame_size;
- if (ring->frames_per_block == 0)
- return -EINVAL;
- if (ring->frames_per_block * req->nm_block_nr !=
- req->nm_frame_nr)
- return -EINVAL;
-
- order = get_order(req->nm_block_size);
- pg_vec = alloc_pg_vec(nlk, req, order);
- if (pg_vec == NULL)
- return -ENOMEM;
- } else {
- if (req->nm_frame_nr)
- return -EINVAL;
- }
-
- mutex_lock(&nlk->pg_vec_lock);
- if (atomic_read(&nlk->mapped) == 0) {
- __netlink_set_ring(sk, req, tx_ring, pg_vec, order);
- mutex_unlock(&nlk->pg_vec_lock);
- return 0;
- }
-
- mutex_unlock(&nlk->pg_vec_lock);
-
- if (pg_vec)
- free_pg_vec(pg_vec, order, req->nm_block_nr);
-
- return -EBUSY;
-}
-
-static void netlink_mm_open(struct vm_area_struct *vma)
-{
- struct file *file = vma->vm_file;
- struct socket *sock = file->private_data;
- struct sock *sk = sock->sk;
-
- if (sk)
- atomic_inc(&nlk_sk(sk)->mapped);
-}
-
-static void netlink_mm_close(struct vm_area_struct *vma)
-{
- struct file *file = vma->vm_file;
- struct socket *sock = file->private_data;
- struct sock *sk = sock->sk;
-
- if (sk)
- atomic_dec(&nlk_sk(sk)->mapped);
-}
-
-static const struct vm_operations_struct netlink_mmap_ops = {
- .open = netlink_mm_open,
- .close = netlink_mm_close,
-};
-
-static int netlink_mmap(struct file *file, struct socket *sock,
- struct vm_area_struct *vma)
-{
- struct sock *sk = sock->sk;
- struct netlink_sock *nlk = nlk_sk(sk);
- struct netlink_ring *ring;
- unsigned long start, size, expected;
- unsigned int i;
- int err = -EINVAL;
-
- if (vma->vm_pgoff)
- return -EINVAL;
-
- mutex_lock(&nlk->pg_vec_lock);
-
- expected = 0;
- for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
- if (ring->pg_vec == NULL)
- continue;
- expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE;
- }
-
- if (expected == 0)
- goto out;
-
- size = vma->vm_end - vma->vm_start;
- if (size != expected)
- goto out;
-
- start = vma->vm_start;
- for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
- if (ring->pg_vec == NULL)
- continue;
-
- for (i = 0; i < ring->pg_vec_len; i++) {
- struct page *page;
- void *kaddr = ring->pg_vec[i];
- unsigned int pg_num;
-
- for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) {
- page = pgvec_to_page(kaddr);
- err = vm_insert_page(vma, start, page);
- if (err < 0)
- goto out;
- start += PAGE_SIZE;
- kaddr += PAGE_SIZE;
- }
- }
- }
-
- atomic_inc(&nlk->mapped);
- vma->vm_ops = &netlink_mmap_ops;
- err = 0;
-out:
- mutex_unlock(&nlk->pg_vec_lock);
- return err;
-}
-
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
-{
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
- struct page *p_start, *p_end;
-
- /* First page is flushed through netlink_{get,set}_status */
- p_start = pgvec_to_page(hdr + PAGE_SIZE);
- p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
- while (p_start <= p_end) {
- flush_dcache_page(p_start);
- p_start++;
- }
-#endif
-}
-
-static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
-{
- smp_rmb();
- flush_dcache_page(pgvec_to_page(hdr));
- return hdr->nm_status;
-}
-
-static void netlink_set_status(struct nl_mmap_hdr *hdr,
- enum nl_mmap_status status)
-{
- smp_mb();
- hdr->nm_status = status;
- flush_dcache_page(pgvec_to_page(hdr));
-}
-
-static struct nl_mmap_hdr *
-__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos)
-{
- unsigned int pg_vec_pos, frame_off;
-
- pg_vec_pos = pos / ring->frames_per_block;
- frame_off = pos % ring->frames_per_block;
-
- return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size);
-}
-
-static struct nl_mmap_hdr *
-netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos,
- enum nl_mmap_status status)
-{
- struct nl_mmap_hdr *hdr;
-
- hdr = __netlink_lookup_frame(ring, pos);
- if (netlink_get_status(hdr) != status)
- return NULL;
-
- return hdr;
-}
-
-static struct nl_mmap_hdr *
-netlink_current_frame(const struct netlink_ring *ring,
- enum nl_mmap_status status)
-{
- return netlink_lookup_frame(ring, ring->head, status);
-}
-
-static void netlink_increment_head(struct netlink_ring *ring)
-{
- ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0;
-}
-
-static void netlink_forward_ring(struct netlink_ring *ring)
-{
- unsigned int head = ring->head;
- const struct nl_mmap_hdr *hdr;
-
- do {
- hdr = __netlink_lookup_frame(ring, ring->head);
- if (hdr->nm_status == NL_MMAP_STATUS_UNUSED)
- break;
- if (hdr->nm_status != NL_MMAP_STATUS_SKIP)
- break;
- netlink_increment_head(ring);
- } while (ring->head != head);
-}
-
-static bool netlink_has_valid_frame(struct netlink_ring *ring)
-{
- unsigned int head = ring->head, pos = head;
- const struct nl_mmap_hdr *hdr;
-
- do {
- hdr = __netlink_lookup_frame(ring, pos);
- if (hdr->nm_status == NL_MMAP_STATUS_VALID)
- return true;
- pos = pos != 0 ? pos - 1 : ring->frame_max;
- } while (pos != head);
-
- return false;
-}
-
-static bool netlink_dump_space(struct netlink_sock *nlk)
-{
- struct netlink_ring *ring = &nlk->rx_ring;
- struct nl_mmap_hdr *hdr;
- unsigned int n;
-
- hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
- if (hdr == NULL)
- return false;
-
- n = ring->head + ring->frame_max / 2;
- if (n > ring->frame_max)
- n -= ring->frame_max;
-
- hdr = __netlink_lookup_frame(ring, n);
-
- return hdr->nm_status == NL_MMAP_STATUS_UNUSED;
-}
-
-static unsigned int netlink_poll(struct file *file, struct socket *sock,
- poll_table *wait)
-{
- struct sock *sk = sock->sk;
- struct netlink_sock *nlk = nlk_sk(sk);
- unsigned int mask;
- int err;
-
- if (nlk->rx_ring.pg_vec != NULL) {
- /* Memory mapped sockets don't call recvmsg(), so flow control
- * for dumps is performed here. A dump is allowed to continue
- * if at least half the ring is unused.
- */
- while (nlk->cb_running && netlink_dump_space(nlk)) {
- err = netlink_dump(sk);
- if (err < 0) {
- sk->sk_err = -err;
- sk->sk_error_report(sk);
- break;
- }
- }
- netlink_rcv_wake(sk);
- }
-
- mask = datagram_poll(file, sock, wait);
-
- /* We could already have received frames in the normal receive
- * queue, that will show up as NL_MMAP_STATUS_COPY in the ring,
- * so if mask contains pollin/etc already, there's no point
- * walking the ring.
- */
- if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) {
- spin_lock_bh(&sk->sk_receive_queue.lock);
- if (nlk->rx_ring.pg_vec) {
- if (netlink_has_valid_frame(&nlk->rx_ring))
- mask |= POLLIN | POLLRDNORM;
- }
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- }
-
- spin_lock_bh(&sk->sk_write_queue.lock);
- if (nlk->tx_ring.pg_vec) {
- if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED))
- mask |= POLLOUT | POLLWRNORM;
- }
- spin_unlock_bh(&sk->sk_write_queue.lock);
-
- return mask;
-}
-
-static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb)
-{
- return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN);
-}
-
-static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
- struct netlink_ring *ring,
- struct nl_mmap_hdr *hdr)
-{
- unsigned int size;
- void *data;
-
- size = ring->frame_size - NL_MMAP_HDRLEN;
- data = (void *)hdr + NL_MMAP_HDRLEN;
-
- skb->head = data;
- skb->data = data;
- skb_reset_tail_pointer(skb);
- skb->end = skb->tail + size;
- skb->len = 0;
-
- skb->destructor = netlink_skb_destructor;
- NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED;
- NETLINK_CB(skb).sk = sk;
-}
-
-static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
- u32 dst_portid, u32 dst_group,
- struct scm_cookie *scm)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
- struct netlink_ring *ring;
- struct nl_mmap_hdr *hdr;
- struct sk_buff *skb;
- unsigned int maxlen;
- int err = 0, len = 0;
-
- mutex_lock(&nlk->pg_vec_lock);
-
- ring = &nlk->tx_ring;
- maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-
- do {
- unsigned int nm_len;
-
- hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
- if (hdr == NULL) {
- if (!(msg->msg_flags & MSG_DONTWAIT) &&
- atomic_read(&nlk->tx_ring.pending))
- schedule();
- continue;
- }
-
- nm_len = ACCESS_ONCE(hdr->nm_len);
- if (nm_len > maxlen) {
- err = -EINVAL;
- goto out;
- }
-
- netlink_frame_flush_dcache(hdr, nm_len);
-
- skb = alloc_skb(nm_len, GFP_KERNEL);
- if (skb == NULL) {
- err = -ENOBUFS;
- goto out;
- }
- __skb_put(skb, nm_len);
- memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
- netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
-
- netlink_increment_head(ring);
-
- NETLINK_CB(skb).portid = nlk->portid;
- NETLINK_CB(skb).dst_group = dst_group;
- NETLINK_CB(skb).creds = scm->creds;
-
- err = security_netlink_send(sk, skb);
- if (err) {
- kfree_skb(skb);
- goto out;
- }
-
- if (unlikely(dst_group)) {
- atomic_inc(&skb->users);
- netlink_broadcast(sk, skb, dst_portid, dst_group,
- GFP_KERNEL);
- }
- err = netlink_unicast(sk, skb, dst_portid,
- msg->msg_flags & MSG_DONTWAIT);
- if (err < 0)
- goto out;
- len += err;
-
- } while (hdr != NULL ||
- (!(msg->msg_flags & MSG_DONTWAIT) &&
- atomic_read(&nlk->tx_ring.pending)));
-
- if (len > 0)
- err = len;
-out:
- mutex_unlock(&nlk->pg_vec_lock);
- return err;
-}
-
-static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
-{
- struct nl_mmap_hdr *hdr;
-
- hdr = netlink_mmap_hdr(skb);
- hdr->nm_len = skb->len;
- hdr->nm_group = NETLINK_CB(skb).dst_group;
- hdr->nm_pid = NETLINK_CB(skb).creds.pid;
- hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
- hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
- netlink_frame_flush_dcache(hdr, hdr->nm_len);
- netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
-
- NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
- kfree_skb(skb);
-}
-
-static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
- struct netlink_ring *ring = &nlk->rx_ring;
- struct nl_mmap_hdr *hdr;
-
- spin_lock_bh(&sk->sk_receive_queue.lock);
- hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
- if (hdr == NULL) {
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- kfree_skb(skb);
- netlink_overrun(sk);
- return;
- }
- netlink_increment_head(ring);
- __skb_queue_tail(&sk->sk_receive_queue, skb);
- spin_unlock_bh(&sk->sk_receive_queue.lock);
-
- hdr->nm_len = skb->len;
- hdr->nm_group = NETLINK_CB(skb).dst_group;
- hdr->nm_pid = NETLINK_CB(skb).creds.pid;
- hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
- hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
- netlink_set_status(hdr, NL_MMAP_STATUS_COPY);
-}
-
-#else /* CONFIG_NETLINK_MMAP */
-#define netlink_rx_is_mmaped(sk) false
-#define netlink_tx_is_mmaped(sk) false
-#define netlink_mmap sock_no_mmap
-#define netlink_poll datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm) 0
-#endif /* CONFIG_NETLINK_MMAP */
-
static void netlink_skb_destructor(struct sk_buff *skb)
{
-#ifdef CONFIG_NETLINK_MMAP
- struct nl_mmap_hdr *hdr;
- struct netlink_ring *ring;
- struct sock *sk;
-
- /* If a packet from the kernel to userspace was freed because of an
- * error without being delivered to userspace, the kernel must reset
- * the status. In the direction userspace to kernel, the status is
- * always reset here after the packet was processed and freed.
- */
- if (netlink_skb_is_mmaped(skb)) {
- hdr = netlink_mmap_hdr(skb);
- sk = NETLINK_CB(skb).sk;
-
- if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) {
- netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
- ring = &nlk_sk(sk)->tx_ring;
- } else {
- if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) {
- hdr->nm_len = 0;
- netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
- }
- ring = &nlk_sk(sk)->rx_ring;
- }
-
- WARN_ON(atomic_read(&ring->pending) == 0);
- atomic_dec(&ring->pending);
- sock_put(sk);
-
- skb->head = NULL;
- }
-#endif
if (is_vmalloc_addr(skb->head)) {
if (!skb->cloned ||
!atomic_dec_return(&(skb_shinfo(skb)->dataref)))
@@ -927,18 +325,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
static void netlink_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_receive_queue);
-#ifdef CONFIG_NETLINK_MMAP
- if (1) {
- struct nl_mmap_req req;
-
- memset(&req, 0, sizeof(req));
- if (nlk->rx_ring.pg_vec)
- __netlink_set_ring(sk, &req, false, NULL, 0);
- memset(&req, 0, sizeof(req));
- if (nlk->tx_ring.pg_vec)
- __netlink_set_ring(sk, &req, true, NULL, 0);
- }
-#endif /* CONFIG_NETLINK_MMAP */
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
@@ -1185,9 +571,6 @@ static int __netlink_create(struct net *net, struct socket *sock,
mutex_init(nlk->cb_mutex);
}
init_waitqueue_head(&nlk->wait);
-#ifdef CONFIG_NETLINK_MMAP
- mutex_init(&nlk->pg_vec_lock);
-#endif
sock_set_flag(sk, SOCK_RCU_FREE);
sk->sk_destruct = netlink_sock_destruct;
@@ -1725,8 +1108,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
nlk = nlk_sk(sk);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
- !netlink_skb_is_mmaped(skb)) {
+ test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
DECLARE_WAITQUEUE(wait, current);
if (!*timeo) {
if (!ssk || netlink_is_kernel(ssk))
@@ -1764,14 +1146,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
netlink_deliver_tap(skb);
-#ifdef CONFIG_NETLINK_MMAP
- if (netlink_skb_is_mmaped(skb))
- netlink_queue_mmaped_skb(sk, skb);
- else if (netlink_rx_is_mmaped(sk))
- netlink_ring_set_copied(sk, skb);
- else
-#endif /* CONFIG_NETLINK_MMAP */
- skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk);
return len;
}
@@ -1795,9 +1170,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
int delta;
WARN_ON(skb->sk != NULL);
- if (netlink_skb_is_mmaped(skb))
- return skb;
-
delta = skb->end - skb->tail;
if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize)
return skb;
@@ -1877,71 +1249,6 @@ struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size,
unsigned int ldiff, u32 dst_portid,
gfp_t gfp_mask)
{
-#ifdef CONFIG_NETLINK_MMAP
- unsigned int maxlen, linear_size;
- struct sock *sk = NULL;
- struct sk_buff *skb;
- struct netlink_ring *ring;
- struct nl_mmap_hdr *hdr;
-
- sk = netlink_getsockbyportid(ssk, dst_portid);
- if (IS_ERR(sk))
- goto out;
-
- ring = &nlk_sk(sk)->rx_ring;
- /* fast-path without atomic ops for common case: non-mmaped receiver */
- if (ring->pg_vec == NULL)
- goto out_put;
-
- /* We need to account the full linear size needed as a ring
- * slot cannot have non-linear parts.
- */
- linear_size = size + ldiff;
- if (ring->frame_size - NL_MMAP_HDRLEN < linear_size)
- goto out_put;
-
- skb = alloc_skb_head(gfp_mask);
- if (skb == NULL)
- goto err1;
-
- spin_lock_bh(&sk->sk_receive_queue.lock);
- /* check again under lock */
- if (ring->pg_vec == NULL)
- goto out_free;
-
- /* check again under lock */
- maxlen = ring->frame_size - NL_MMAP_HDRLEN;
- if (maxlen < linear_size)
- goto out_free;
-
- netlink_forward_ring(ring);
- hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
- if (hdr == NULL)
- goto err2;
-
- netlink_ring_setup_skb(skb, sk, ring, hdr);
- netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
- atomic_inc(&ring->pending);
- netlink_increment_head(ring);
-
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- return skb;
-
-err2:
- kfree_skb(skb);
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- netlink_overrun(sk);
-err1:
- sock_put(sk);
- return NULL;
-
-out_free:
- kfree_skb(skb);
- spin_unlock_bh(&sk->sk_receive_queue.lock);
-out_put:
- sock_put(sk);
-out:
-#endif
return alloc_skb(size, gfp_mask);
}
EXPORT_SYMBOL_GPL(__netlink_alloc_skb);
@@ -2222,8 +1529,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
if (level != SOL_NETLINK)
return -ENOPROTOOPT;
- if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING &&
- optlen >= sizeof(int) &&
+ if (optlen >= sizeof(int) &&
get_user(val, (unsigned int __user *)optval))
return -EFAULT;
@@ -2276,25 +1582,6 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
}
err = 0;
break;
-#ifdef CONFIG_NETLINK_MMAP
- case NETLINK_RX_RING:
- case NETLINK_TX_RING: {
- struct nl_mmap_req req;
-
- /* Rings might consume more memory than queue limits, require
- * CAP_NET_ADMIN.
- */
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- if (optlen < sizeof(req))
- return -EINVAL;
- if (copy_from_user(&req, optval, sizeof(req)))
- return -EFAULT;
- err = netlink_set_ring(sk, &req,
- optname == NETLINK_TX_RING);
- break;
- }
-#endif /* CONFIG_NETLINK_MMAP */
case NETLINK_LISTEN_ALL_NSID:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
return -EPERM;
@@ -2464,18 +1751,6 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
smp_rmb();
}
- /* It's a really convoluted way for userland to ask for mmaped
- * sendmsg(), but that's what we've got...
- */
- if (netlink_tx_is_mmaped(sk) &&
- iter_is_iovec(&msg->msg_iter) &&
- msg->msg_iter.nr_segs == 1 &&
- msg->msg_iter.iov->iov_base == NULL) {
- err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
- &scm);
- goto out;
- }
-
err = -EMSGSIZE;
if (len > sk->sk_sndbuf - 32)
goto out;
@@ -2792,8 +2067,7 @@ static int netlink_dump(struct sock *sk)
goto errout_skb;
}
- if (!netlink_rx_is_mmaped(sk) &&
- atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto errout_skb;
/* NLMSG_GOODSIZE is small to avoid high order allocations being
@@ -2882,16 +2156,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
struct netlink_sock *nlk;
int ret;
- /* Memory mapped dump requests need to be copied to avoid looping
- * on the pending state in netlink_mmap_sendmsg() while the CB hold
- * a reference to the skb.
- */
- if (netlink_skb_is_mmaped(skb)) {
- skb = skb_copy(skb, GFP_KERNEL);
- if (skb == NULL)
- return -ENOBUFS;
- } else
- atomic_inc(&skb->users);
+ atomic_inc(&skb->users);
sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
if (sk == NULL) {
@@ -3235,7 +2500,7 @@ static const struct proto_ops netlink_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
- .poll = netlink_poll,
+ .poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -3243,7 +2508,7 @@ static const struct proto_ops netlink_ops = {
.getsockopt = netlink_getsockopt,
.sendmsg = netlink_sendmsg,
.recvmsg = netlink_recvmsg,
- .mmap = netlink_mmap,
+ .mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b0c1ddc97260..15e62973cfc6 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -45,12 +45,6 @@ struct netlink_sock {
int (*netlink_bind)(struct net *net, int group);
void (*netlink_unbind)(struct net *net, int group);
struct module *module;
-#ifdef CONFIG_NETLINK_MMAP
- struct mutex pg_vec_lock;
- struct netlink_ring rx_ring;
- struct netlink_ring tx_ring;
- atomic_t mapped;
-#endif /* CONFIG_NETLINK_MMAP */
struct rhash_head node;
struct work_struct work;
@@ -61,15 +55,6 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
return container_of(sk, struct netlink_sock, sk);
}
-static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-#ifdef CONFIG_NETLINK_MMAP
- return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-#else
- return false;
-#endif /* CONFIG_NETLINK_MMAP */
-}
-
struct netlink_table {
struct rhashtable hash;
struct hlist_head mc_list;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 3ee63a3cff30..8dd836a8dd60 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -8,41 +8,6 @@
#include "af_netlink.h"
-#ifdef CONFIG_NETLINK_MMAP
-static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type,
- struct sk_buff *nlskb)
-{
- struct netlink_diag_ring ndr;
-
- ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT;
- ndr.ndr_block_nr = ring->pg_vec_len;
- ndr.ndr_frame_size = ring->frame_size;
- ndr.ndr_frame_nr = ring->frame_max + 1;
-
- return nla_put(nlskb, nl_type, sizeof(ndr), &ndr);
-}
-
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
- int ret;
-
- mutex_lock(&nlk->pg_vec_lock);
- ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb);
- if (!ret)
- ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING,
- nlskb);
- mutex_unlock(&nlk->pg_vec_lock);
-
- return ret;
-}
-#else
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
- return 0;
-}
-#endif
-
static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -87,10 +52,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
goto out_nlmsg_trim;
- if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) &&
- sk_diag_put_rings_cfg(sk, skb))
- goto out_nlmsg_trim;
-
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index d1bd4a45ca2d..d26b28def310 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
ipv4 = true;
break;
case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
- SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
nla_get_in6_addr(a), is_mask);
ipv6 = true;
break;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d805cd577a60..3975ac809934 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3021,7 +3021,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
int addr_len)
{
struct sock *sk = sock->sk;
- char name[15];
+ char name[sizeof(uaddr->sa_data) + 1];
/*
* Check legality
@@ -3029,7 +3029,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
if (addr_len != sizeof(struct sockaddr))
return -EINVAL;
- strlcpy(name, uaddr->sa_data, sizeof(name));
+ /* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+ * zero-terminated.
+ */
+ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+ name[sizeof(uaddr->sa_data)] = 0;
return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 06e7c4a37245..694a06f1e0d5 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -820,10 +820,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
goto out_module_put;
err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a);
- if (err < 0)
+ if (err <= 0)
goto out_module_put;
- if (err == 0)
- goto noflush_out;
nla_nest_end(skb, nest);
@@ -840,7 +838,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
out_module_put:
module_put(a.ops->owner);
err_out:
-noflush_out:
kfree_skb(skb);
return err;
}
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index bb41699c6c49..7ecb14f3db54 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -109,6 +109,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
if (ret < 0)
return ret;
+ if (!tb[TCA_CONNMARK_PARMS])
+ return -EINVAL;
+
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
if (!tcf_hash_check(parm->index, a, bind)) {
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d48525fcf..c36757e72844 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
if (s) {
struct unix_sock *u = unix_sk(s);
+ BUG_ON(!atomic_long_read(&u->inflight));
BUG_ON(list_empty(&u->link));
if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
}
list_del(&cursor);
+ /* Now gc_candidates contains only garbage. Restore original
+ * inflight counters for these as well, and remove the skbuffs
+ * which are creating the cycle(s).
+ */
+ skb_queue_head_init(&hitlist);
+ list_for_each_entry(u, &gc_candidates, link)
+ scan_children(&u->sk, inc_inflight, &hitlist);
+
/* not_cycle_list contains those sockets which do not make up a
* cycle. Restore these to the inflight list.
*/
@@ -350,14 +359,6 @@ void unix_gc(void)
list_move_tail(&u->link, &gc_inflight_list);
}
- /* Now gc_candidates contains only garbage. Restore original
- * inflight counters for these as well, and remove the skbuffs
- * which are creating the cycle(s).
- */
- skb_queue_head_init(&hitlist);
- list_for_each_entry(u, &gc_candidates, link)
- scan_children(&u->sk, inc_inflight, &hitlist);
-
spin_unlock(&unix_gc_lock);
/* Here we are. Hitlist is filled. Die. */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index adc62ec5507a..074cf0d25558 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -509,21 +509,17 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
{
int err;
- rtnl_lock();
-
if (!cb->args[0]) {
err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
nl80211_fam.attrbuf, nl80211_fam.maxattr,
nl80211_policy);
if (err)
- goto out_unlock;
+ return err;
*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk),
nl80211_fam.attrbuf);
- if (IS_ERR(*wdev)) {
- err = PTR_ERR(*wdev);
- goto out_unlock;
- }
+ if (IS_ERR(*wdev))
+ return PTR_ERR(*wdev);
*rdev = wiphy_to_rdev((*wdev)->wiphy);
/* 0 is the first index - add 1 to parse only once */
cb->args[0] = (*rdev)->wiphy_idx + 1;
@@ -533,10 +529,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
- if (!wiphy) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!wiphy)
+ return -ENODEV;
*rdev = wiphy_to_rdev(wiphy);
*wdev = NULL;
@@ -547,21 +541,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
}
}
- if (!*wdev) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!*wdev)
+ return -ENODEV;
}
return 0;
- out_unlock:
- rtnl_unlock();
- return err;
-}
-
-static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev)
-{
- rtnl_unlock();
}
/* IE validation */
@@ -4278,9 +4262,10 @@ static int nl80211_dump_station(struct sk_buff *skb,
int sta_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!wdev->netdev) {
err = -EINVAL;
@@ -4316,7 +4301,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
cb->args[2] = sta_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -5033,9 +5018,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
int path_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!rdev->ops->dump_mpath) {
err = -EOPNOTSUPP;
@@ -5069,7 +5055,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
cb->args[2] = path_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -5229,9 +5215,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
int path_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!rdev->ops->dump_mpp) {
err = -EOPNOTSUPP;
@@ -5264,7 +5251,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
cb->args[2] = path_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -7333,9 +7320,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
int start = cb->args[2], idx = 0;
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
- if (err)
+ if (err) {
+ rtnl_unlock();
return err;
+ }
wdev_lock(wdev);
spin_lock_bh(&rdev->bss_lock);
@@ -7358,7 +7348,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
wdev_unlock(wdev);
cb->args[2] = idx;
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return skb->len;
}
@@ -7442,9 +7432,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
int res;
bool radio_stats;
+ rtnl_lock();
res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (res)
- return res;
+ goto out_err;
/* prepare_wdev_dump parsed the attributes */
radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
@@ -7485,7 +7476,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
cb->args[2] = survey_idx;
res = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return res;
}
@@ -10561,17 +10552,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
void *data = NULL;
unsigned int data_len = 0;
- rtnl_lock();
-
if (cb->args[0]) {
/* subtract the 1 again here */
struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
- if (!wiphy) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!wiphy)
+ return -ENODEV;
*rdev = wiphy_to_rdev(wiphy);
*wdev = NULL;
@@ -10592,13 +10579,11 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
nl80211_fam.attrbuf, nl80211_fam.maxattr,
nl80211_policy);
if (err)
- goto out_unlock;
+ return err;
if (!nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID] ||
- !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) {
- err = -EINVAL;
- goto out_unlock;
- }
+ !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD])
+ return -EINVAL;
*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk),
nl80211_fam.attrbuf);
@@ -10607,10 +10592,8 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
*rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk),
nl80211_fam.attrbuf);
- if (IS_ERR(*rdev)) {
- err = PTR_ERR(*rdev);
- goto out_unlock;
- }
+ if (IS_ERR(*rdev))
+ return PTR_ERR(*rdev);
vid = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID]);
subcmd = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]);
@@ -10623,19 +10606,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
continue;
- if (!vcmd->dumpit) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
+ if (!vcmd->dumpit)
+ return -EOPNOTSUPP;
vcmd_idx = i;
break;
}
- if (vcmd_idx < 0) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
+ if (vcmd_idx < 0)
+ return -EOPNOTSUPP;
if (nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]) {
data = nla_data(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]);
@@ -10652,9 +10631,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
/* keep rtnl locked in successful case */
return 0;
- out_unlock:
- rtnl_unlock();
- return err;
}
static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
@@ -10669,9 +10645,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
int err;
struct nlattr *vendor_data;
+ rtnl_lock();
err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out;
vcmd_idx = cb->args[2];
data = (void *)cb->args[3];
@@ -10680,18 +10657,26 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_NETDEV)) {
- if (!wdev)
- return -EINVAL;
+ if (!wdev) {
+ err = -EINVAL;
+ goto out;
+ }
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
- !wdev->netdev)
- return -EINVAL;
+ !wdev->netdev) {
+ err = -EINVAL;
+ goto out;
+ }
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
if (wdev->netdev &&
- !netif_running(wdev->netdev))
- return -ENETDOWN;
- if (!wdev->netdev && !wdev->p2p_started)
- return -ENETDOWN;
+ !netif_running(wdev->netdev)) {
+ err = -ENETDOWN;
+ goto out;
+ }
+ if (!wdev->netdev && !wdev->p2p_started) {
+ err = -ENETDOWN;
+ goto out;
+ }
}
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index cf0193b74ae3..d5b4ac7bf0d8 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3027,6 +3027,11 @@ static int __net_init xfrm_net_init(struct net *net)
{
int rv;
+ /* Initialize the per-net locks here */
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
+ rwlock_init(&net->xfrm.xfrm_policy_lock);
+ mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
rv = xfrm_statistics_init(net);
if (rv < 0)
goto out_statistics;
@@ -3043,11 +3048,6 @@ static int __net_init xfrm_net_init(struct net *net)
if (rv < 0)
goto out;
- /* Initialize the per-net locks here */
- spin_lock_init(&net->xfrm.xfrm_state_lock);
- rwlock_init(&net->xfrm.xfrm_policy_lock);
- mutex_init(&net->xfrm.xfrm_cfg_mutex);
-
return 0;
out:
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 805681a7d356..7a5a64e70b4d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -412,7 +412,14 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
up = nla_data(rp);
ulen = xfrm_replay_state_esn_len(up);
- if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen)
+ /* Check the overall length and the internal bitmap length to avoid
+ * potential overflow. */
+ if (nla_len(rp) < ulen ||
+ xfrm_replay_state_esn_len(replay_esn) != ulen ||
+ replay_esn->bmp_len != up->bmp_len)
+ return -EINVAL;
+
+ if (up->replay_window > up->bmp_len * sizeof(__u32) * 8)
return -EINVAL;
return 0;