summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/core/neighbour.c4
-rw-r--r--net/core/scm.c2
-rw-r--r--net/dccp/ipv6.c33
-rw-r--r--net/ipv4/ipmr.c15
-rw-r--r--net/ipv4/tcp_input.c23
-rw-r--r--net/ipv4/tcp_ipv4.c3
-rw-r--r--net/ipv4/tcp_timer.c12
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/af_inet6.c13
-rw-r--r--net/ipv6/datagram.c4
-rw-r--r--net/ipv6/exthdrs.c3
-rw-r--r--net/ipv6/inet6_connection_sock.c11
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6mr.c15
-rw-r--r--net/ipv6/ipv6_sockglue.c33
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/ndisc.c10
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c5
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/reassembly.c10
-rw-r--r--net/ipv6/route.c24
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/tcp_ipv6.c28
-rw-r--r--net/ipv6/udp.c8
-rw-r--r--net/l2tp/l2tp_ip6.c8
-rw-r--r--net/openvswitch/dp_notify.c2
-rw-r--r--net/openvswitch/vport-netdev.c8
-rw-r--r--net/packet/af_packet.c86
-rw-r--r--net/rds/connection.c6
-rw-r--r--net/rds/send.c4
-rw-r--r--net/sched/sch_api.c27
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_mq.c4
-rw-r--r--net/sched/sch_mqprio.c4
-rw-r--r--net/sctp/auth.c4
-rw-r--r--net/sctp/socket.c9
-rw-r--r--net/tipc/udp_media.c7
-rw-r--r--net/unix/af_unix.c286
38 files changed, 533 insertions, 196 deletions
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2b515ba7e..c169bba44 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2215,7 +2215,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
ndm->ndm_pad2 = 0;
ndm->ndm_flags = pn->flags | NTF_PROXY;
ndm->ndm_type = RTN_UNICAST;
- ndm->ndm_ifindex = pn->dev->ifindex;
+ ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
ndm->ndm_state = NUD_NONE;
if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2290,7 +2290,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
if (h > s_h)
s_idx = 0;
for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
- if (dev_net(n->dev) != net)
+ if (pneigh_net(n) != net)
continue;
if (idx < s_idx)
goto next;
diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b7d..8a1741b14 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
err = put_user(cmlen, &cm->cmsg_len);
if (!err) {
cmlen = CMSG_SPACE(i*sizeof(int));
+ if (msg->msg_controllen < cmlen)
+ cmlen = msg->msg_controllen;
msg->msg_control += cmlen;
msg->msg_controllen -= cmlen;
}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5165571f3..a0490508d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
&ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6.daddr = ireq->ir_v6_rmt_addr;
- err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ rcu_read_lock();
+ err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
@@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
- if (np->opt != NULL)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt != NULL)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
@@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt != NULL)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8e8203d5c..ef7e2c434 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -350,7 +350,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
static void ipmr_free_table(struct mr_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -1208,7 +1208,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1217,8 +1217,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
/* Shut down all active vif entries */
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif_table[i].flags & VIFF_STATIC))
- vif_delete(mrt, i, 0, &list);
+ if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+ continue;
+ vif_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
@@ -1226,7 +1227,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
for (i = 0; i < MFC_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
list_del_rcu(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1261,7 +1262,7 @@ static void mrtsock_destruct(struct sock *sk)
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
}
}
rtnl_unlock();
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3d12c5e94..194a8ff10 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4501,19 +4501,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_buff *skb;
+ int err = -ENOMEM;
+ int data_len = 0;
bool fragstolen;
if (size == 0)
return 0;
- skb = alloc_skb(size, sk->sk_allocation);
+ if (size > PAGE_SIZE) {
+ int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+ data_len = npages << PAGE_SHIFT;
+ size = data_len + (size & ~PAGE_MASK);
+ }
+ skb = alloc_skb_with_frags(size - data_len, data_len,
+ PAGE_ALLOC_COSTLY_ORDER,
+ &err, sk->sk_allocation);
if (!skb)
goto err;
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+
if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
goto err_free;
- if (memcpy_from_msg(skb_put(skb, size), msg, size))
+ err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+ if (err)
goto err_free;
TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4529,7 +4544,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
err_free:
kfree_skb(skb);
err:
- return -ENOMEM;
+ return err;
+
}
#ifdef CONFIG_TCP_STEALTH
@@ -5729,6 +5745,7 @@ discard:
}
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 42562a7f8..5f46f5bcc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -938,7 +938,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
}
md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
+ sock_owned_by_user(sk) ||
+ lockdep_is_held(&sk->sk_lock.slock));
if (!md5sig) {
md5sig = kmalloc(sizeof(*md5sig), gfp);
if (!md5sig)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 7149ebc82..04f0a052b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
syn_set = true;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+ /* Some middle-boxes may black-hole Fast Open _after_
+ * the handshake. Therefore we conservatively disable
+ * Fast Open on this path on recurring timeouts with
+ * few or zero bytes acked after Fast Open.
+ */
+ if (tp->syn_data_acked &&
+ tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+ tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+ if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+ }
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index dd0082886..3939dd290 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3628,7 +3628,7 @@ static void addrconf_dad_work(struct work_struct *w)
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
- ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL);
+ ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
out:
in6_ifa_put(ifp);
rtnl_unlock();
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 44bb66bde..38d66ddfb 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -428,9 +428,11 @@ void inet6_destroy_sock(struct sock *sk)
/* Free tx options */
- opt = xchg(&np->opt, NULL);
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
@@ -659,7 +661,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+ &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9aadd5780..a42a673aa 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- opt = flowlabel ? flowlabel->opt : np->opt;
+ rcu_read_lock();
+ opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
final_p = fl6_update_dst(&fl6, opt, &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ce203b040..ea7c4d64a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
*((char **)&opt2->dst1opt) += dif;
if (opt2->srcrt)
*((char **)&opt2->srcrt) += dif;
+ atomic_set(&opt2->refcnt, 1);
}
return opt2;
}
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
return ERR_PTR(-ENOBUFS);
memset(opt2, 0, tot_len);
-
+ atomic_set(&opt2->refcnt, 1);
opt2->tot_len = tot_len;
p = (char *)(opt2 + 1);
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 6927f3fb5..9beed302e 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = IPPROTO_TCP;
fl6->daddr = ireq->ir_v6_rmt_addr;
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
fl6->saddr = ireq->ir_v6_loc_addr;
fl6->flowi6_oif = ireq->ir_iif;
fl6->flowi6_mark = ireq->ir_mark;
@@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->fl6_dport = inet->inet_dport;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = __inet6_csk_dst_check(sk, np->dst_cookie);
if (!dst) {
@@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
/* Restore final destination back after routing done */
fl6.daddr = sk->sk_v6_daddr;
- res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
rcu_read_unlock();
return res;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index eabffbb89..137fca42a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -177,7 +177,7 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t)
int i;
for_each_possible_cpu(i)
- ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL);
+ ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
}
EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0e004cc42..35eee72ab 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
int cmd);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -334,7 +334,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
static void ip6mr_free_table(struct mr6_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -1542,7 +1542,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1552,8 +1552,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
* Shut down all active vif entries
*/
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(mrt, i, &list);
+ if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+ continue;
+ mif6_delete(mrt, i, &list);
}
unregister_netdevice_many(&list);
@@ -1562,7 +1563,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
*/
for (i = 0; i < MFC6_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
write_lock_bh(&mrt_lock);
list_del(&c->list);
@@ -1625,7 +1626,7 @@ int ip6mr_sk_done(struct sock *sk)
net->ipv6.devconf_all);
write_unlock_bh(&mrt_lock);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
err = 0;
break;
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e695691..4449ad1f8 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
}
- opt = xchg(&inet6_sk(sk)->opt, opt);
+ opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+ opt);
sk_dst_reset(sk);
return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
- opt = xchg(&np->opt, NULL);
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+ NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
- opt = ipv6_renew_options(sk, np->opt, optname,
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ opt = ipv6_renew_options(sk, opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
@@ -486,6 +493,7 @@ sticky_done:
break;
memset(opt, 0, sizeof(*opt));
+ atomic_set(&opt->refcnt, 1);
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
+ struct ipv6_txoptions *opt;
lock_sock(sk);
- len = ipv6_getsockopt_sticky(sk, np->opt,
- optname, optval, len);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 083b2927f..41e3b5ee8 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1651,7 +1651,6 @@ out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
} else {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
}
@@ -2014,7 +2013,6 @@ out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
} else
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 64a71354b..9ad46cd79 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -553,8 +553,7 @@ static void ndisc_send_unsol_na(struct net_device *dev)
void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct sk_buff *oskb)
+ const struct in6_addr *daddr, const struct in6_addr *saddr)
{
struct sk_buff *skb;
struct in6_addr addr_buf;
@@ -590,9 +589,6 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr);
- if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb)
- skb_dst_copy(skb, oskb);
-
ndisc_send_skb(skb, daddr, saddr);
}
@@ -679,12 +675,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
- ndisc_send_ns(dev, neigh, target, target, saddr, skb);
+ ndisc_send_ns(dev, neigh, target, target, saddr);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
neigh_app_ns(neigh);
} else {
addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb);
+ ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
}
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c7196ad1d..dc50143f5 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
/* Creation primitives. */
static inline struct frag_queue *fq_find(struct net *net, __be32 id,
u32 user, struct in6_addr *src,
- struct in6_addr *dst, u8 ecn)
+ struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
arg.user = user;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
local_bh_disable();
@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
fhdr = (struct frag_hdr *)skb_transport_header(clone);
fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
goto ret_orig;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index fdbada156..fe9772995 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -732,6 +732,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions opt_space;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
@@ -838,8 +839,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
- if (!opt)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -905,6 +908,7 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err < 0 ? err : len;
do_confirm:
dst_confirm(dst);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f1159bb76..04013a910 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
return fq->id == arg->id &&
fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst);
+ ipv6_addr_equal(&fq->daddr, arg->dst) &&
+ (arg->iif == fq->iif ||
+ !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)));
}
EXPORT_SYMBOL(ip6_frag_match);
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
static struct frag_queue *
fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, u8 ecn)
+ const struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
}
fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq) {
int ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 946880ad4..fd0e6746d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -403,6 +403,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
}
}
+static bool __rt6_check_expired(const struct rt6_info *rt)
+{
+ if (rt->rt6i_flags & RTF_EXPIRES)
+ return time_after(jiffies, rt->dst.expires);
+ else
+ return false;
+}
+
static bool rt6_check_expired(const struct rt6_info *rt)
{
if (rt->rt6i_flags & RTF_EXPIRES) {
@@ -538,7 +546,7 @@ static void rt6_probe_deferred(struct work_struct *w)
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
- ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
+ ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
dev_put(work->dev);
kfree(work);
}
@@ -1270,7 +1278,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
{
- if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+ if (!__rt6_check_expired(rt) &&
+ rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
rt6_check((struct rt6_info *)(rt->dst.from), cookie))
return &rt->dst;
else
@@ -1290,7 +1299,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
rt6_dst_from_metrics_check(rt);
- if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+ if (rt->rt6i_flags & RTF_PCPU ||
+ (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
return rt6_dst_from_check(rt, cookie);
else
return rt6_check(rt, cookie);
@@ -1340,6 +1350,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
+static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
+{
+ return !(rt->rt6i_flags & RTF_CACHE) &&
+ (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+}
+
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
const struct ipv6hdr *iph, u32 mtu)
{
@@ -1353,7 +1369,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (mtu >= dst_mtu(dst))
return;
- if (rt6->rt6i_flags & RTF_CACHE) {
+ if (!rt6_cache_allowed_for_pmtu(rt6)) {
rt6_do_update_pmtu(rt6, mtu);
} else {
const struct in6_addr *daddr, *saddr;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 0909f4e0d..f30bfdcde 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -225,7 +225,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = ireq->ir_v6_rmt_addr;
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0b959b0c0..2db08b042 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -121,6 +121,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -236,7 +237,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -264,9 +266,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen +
+ opt->opt_nflen;
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
@@ -477,7 +479,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
skb_set_queue_mapping(skb, queue_mapping);
- err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+ err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+ np->tclass);
err = net_xmit_eval(err);
}
@@ -1007,6 +1010,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct tcp6_sock *newtcp6sk;
+ struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
@@ -1142,13 +1146,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
but we make one more one thing there: reattach optmem
to newsk.
*/
- if (np->opt)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
tcp_ca_openreq_child(newsk, dst);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0aba654f5..8379fc2f4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_txoptions *opt = NULL;
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct flowi6 fl6;
struct dst_entry *dst;
@@ -1260,8 +1261,10 @@ do_udp_sendmsg:
opt = NULL;
connected = 0;
}
- if (!opt)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -1370,6 +1373,7 @@ release_dst:
out:
dst_release(dst);
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
if (!err)
return len;
/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d1ded3777..0ce9da948 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
opt = NULL;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err < 0 ? err : len;
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index a7a80a6b7..653d073ba 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -58,7 +58,7 @@ void ovs_dp_notify_wq(struct work_struct *work)
struct hlist_node *n;
hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
- if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+ if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
continue;
if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index f7e8dcce7..ac14c4886 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -180,9 +180,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
ovs_netdev_detach_dev(vport);
- /* Early release so we can unregister the device */
+ /* We can be invoked by both explicit vport deletion and
+ * underlying netdev deregistration; delete the link only
+ * if it's not already shutting down.
+ */
+ if (vport->dev->reg_state == NETREG_REGISTERED)
+ rtnl_delete_link(vport->dev);
dev_put(vport->dev);
- rtnl_delete_link(vport->dev);
vport->dev = NULL;
rtnl_unlock();
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 27b2898f2..4695a36ee 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1741,6 +1741,20 @@ static void fanout_release(struct sock *sk)
kfree_rcu(po->rollover, rcu);
}
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+ struct sk_buff *skb)
+{
+ /* Earlier code assumed this would be a VLAN pkt, double-check
+ * this now that we have the actual packet in hand. We can only
+ * do this check on Ethernet devices.
+ */
+ if (unlikely(dev->type != ARPHRD_ETHER))
+ return false;
+
+ skb_reset_mac_header(skb);
+ return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
static const struct proto_ops packet_ops;
static const struct proto_ops packet_ops_spkt;
@@ -1902,18 +1916,10 @@ retry:
goto retry;
}
- if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
- /* Earlier code assumed this would be a VLAN pkt,
- * double-check this now that we have the actual
- * packet in hand.
- */
- struct ethhdr *ehdr;
- skb_reset_mac_header(skb);
- ehdr = eth_hdr(skb);
- if (ehdr->h_proto != htons(ETH_P_8021Q)) {
- err = -EMSGSIZE;
- goto out_unlock;
- }
+ if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+ !packet_extra_vlan_len_allowed(dev, skb)) {
+ err = -EMSGSIZE;
+ goto out_unlock;
}
skb->protocol = proto;
@@ -2332,6 +2338,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len)
return false;
}
+static void tpacket_set_protocol(const struct net_device *dev,
+ struct sk_buff *skb)
+{
+ if (dev->type == ARPHRD_ETHER) {
+ skb_reset_mac_header(skb);
+ skb->protocol = eth_hdr(skb)->h_proto;
+ }
+}
+
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
void *frame, struct net_device *dev, int size_max,
__be16 proto, unsigned char *addr, int hlen)
@@ -2368,8 +2383,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
skb_reserve(skb, hlen);
skb_reset_network_header(skb);
- if (!packet_use_direct_xmit(po))
- skb_probe_transport_header(skb, 0);
if (unlikely(po->tp_tx_has_off)) {
int off_min, off_max, off;
off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2415,6 +2428,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
dev->hard_header_len);
if (unlikely(err))
return err;
+ if (!skb->protocol)
+ tpacket_set_protocol(dev, skb);
data += dev->hard_header_len;
to_write -= dev->hard_header_len;
@@ -2449,6 +2464,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
len = ((to_write > len_max) ? len_max : to_write);
}
+ skb_probe_transport_header(skb, 0);
+
return tp_len;
}
@@ -2493,12 +2510,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
- reserve = dev->hard_header_len + VLAN_HLEN;
+ if (po->sk.sk_socket->type == SOCK_RAW)
+ reserve = dev->hard_header_len;
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
- if (size_max > dev->mtu + reserve)
- size_max = dev->mtu + reserve;
+ if (size_max > dev->mtu + reserve + VLAN_HLEN)
+ size_max = dev->mtu + reserve + VLAN_HLEN;
do {
ph = packet_current_frame(po, &po->tx_ring,
@@ -2525,18 +2543,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
addr, hlen);
if (likely(tp_len >= 0) &&
- tp_len > dev->mtu + dev->hard_header_len) {
- struct ethhdr *ehdr;
- /* Earlier code assumed this would be a VLAN pkt,
- * double-check this now that we have the actual
- * packet in hand.
- */
+ tp_len > dev->mtu + reserve &&
+ !packet_extra_vlan_len_allowed(dev, skb))
+ tp_len = -EMSGSIZE;
- skb_reset_mac_header(skb);
- ehdr = eth_hdr(skb);
- if (ehdr->h_proto != htons(ETH_P_8021Q))
- tp_len = -EMSGSIZE;
- }
if (unlikely(tp_len < 0)) {
if (po->tp_loss) {
__packet_set_status(po, ph,
@@ -2757,18 +2767,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
- if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
- /* Earlier code assumed this would be a VLAN pkt,
- * double-check this now that we have the actual
- * packet in hand.
- */
- struct ethhdr *ehdr;
- skb_reset_mac_header(skb);
- ehdr = eth_hdr(skb);
- if (ehdr->h_proto != htons(ETH_P_8021Q)) {
- err = -EMSGSIZE;
- goto out_free;
- }
+ if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+ !packet_extra_vlan_len_allowed(dev, skb)) {
+ err = -EMSGSIZE;
+ goto out_free;
}
skb->protocol = proto;
@@ -2799,8 +2801,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
len += vnet_hdr_len;
}
- if (!packet_use_direct_xmit(po))
- skb_probe_transport_header(skb, reserve);
+ skb_probe_transport_header(skb, reserve);
+
if (unlikely(extra_len == 4))
skb->no_fcs = 1;
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 49adeef80..9b2de5e67 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -190,12 +190,6 @@ new_conn:
}
}
- if (trans == NULL) {
- kmem_cache_free(rds_conn_slab, conn);
- conn = ERR_PTR(-ENODEV);
- goto out;
- }
-
conn->c_trans = trans;
ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index 4df61a515..859de6f32 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,11 +1009,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
release_sock(sk);
}
- /* racing with another thread binding seems ok here */
+ lock_sock(sk);
if (daddr == 0 || rs->rs_bound_addr == 0) {
+ release_sock(sk);
ret = -ENOTCONN; /* XXX not a great errno */
goto out;
}
+ release_sock(sk);
if (payload_len > rds_sk_sndbuf(rs)) {
ret = -EMSGSIZE;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f43c8f33f..7ec667dd4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
}
/* We know handle. Find qdisc among all qdisc's attached to device
- (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
*/
static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
root->handle == handle)
return root;
- list_for_each_entry(q, &root->list, list) {
+ list_for_each_entry_rcu(q, &root->list, list) {
if (q->handle == handle)
return q;
}
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
struct Qdisc *root = qdisc_dev(q)->qdisc;
WARN_ON_ONCE(root == &noop_qdisc);
- list_add_tail(&q->list, &root->list);
+ ASSERT_RTNL();
+ list_add_tail_rcu(&q->list, &root->list);
}
}
EXPORT_SYMBOL(qdisc_list_add);
void qdisc_list_del(struct Qdisc *q)
{
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
- list_del(&q->list);
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+ ASSERT_RTNL();
+ list_del_rcu(&q->list);
+ }
}
EXPORT_SYMBOL(qdisc_list_del);
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
if (n == 0)
return;
drops = max_t(int, n, 0);
+ rcu_read_lock();
while ((parentid = sch->parent)) {
if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
- return;
+ break;
+ if (sch->flags & TCQ_F_NOPARENT)
+ break;
+ /* TODO: perform the search on a per txq basis */
sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
if (sch == NULL) {
- WARN_ON(parentid != TC_H_ROOT);
- return;
+ WARN_ON_ONCE(parentid != TC_H_ROOT);
+ break;
}
cops = sch->ops->cl_ops;
if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
sch->q.qlen -= n;
__qdisc_qstats_drop(sch, drops);
}
+ rcu_read_unlock();
}
EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
}
lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
if (!netif_is_multiqueue(dev))
- sch->flags |= TCQ_F_ONETXQUEUE;
+ sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index cb5d4ad32..e82a1ad80 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -737,7 +737,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
return;
}
if (!netif_is_multiqueue(dev))
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
dev_queue->qdisc_sleeping = qdisc;
}
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaecd2..3e82f047c 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
if (qdisc == NULL)
goto err;
priv->qdiscs[ntx] = qdisc;
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
*old = dev_graft_qdisc(dev_queue, new);
if (new)
- new->flags |= TCQ_F_ONETXQUEUE;
+ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a7454..ad70ecf57 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
goto err;
}
priv->qdiscs[i] = qdisc;
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
/* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
*old = dev_graft_qdisc(dev_queue, new);
if (new)
- new->flags |= TCQ_F_ONETXQUEUE;
+ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 4f15b7d73..1543e39f4 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
if (!has_sha1)
return -EINVAL;
- memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
- hmacs->shmac_num_idents * sizeof(__u16));
+ for (i = 0; i < hmacs->shmac_num_idents; i++)
+ ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
hmacs->shmac_num_idents * sizeof(__u16));
return 0;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 17bef01b9..3ec88be0f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7375,6 +7375,13 @@ struct proto sctp_prot = {
#if IS_ENABLED(CONFIG_IPV6)
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+ sctp_destroy_sock(sk);
+ inet6_destroy_sock(sk);
+}
+
struct proto sctpv6_prot = {
.name = "SCTPv6",
.owner = THIS_MODULE,
@@ -7384,7 +7391,7 @@ struct proto sctpv6_prot = {
.accept = sctp_accept,
.ioctl = sctp_ioctl,
.init = sctp_init_sock,
- .destroy = sctp_destroy_sock,
+ .destroy = sctp_v6_destroy_sock,
.shutdown = sctp_shutdown,
.setsockopt = sctp_setsockopt,
.getsockopt = sctp_getsockopt,
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index cd7c5f131..86f2e7c44 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -159,8 +159,11 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
struct sk_buff *clone;
struct rtable *rt;
- if (skb_headroom(skb) < UDP_MIN_HEADROOM)
- pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+ if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
+ err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+ if (err)
+ goto tx_error;
+ }
clone = skb_clone(skb, GFP_ATOMIC);
skb_set_inner_protocol(clone, htons(ETH_P_TIPC));
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 94f658235..128b0982c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
return s;
}
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+ void *key)
+{
+ struct unix_sock *u;
+ wait_queue_head_t *u_sleep;
+
+ u = container_of(q, struct unix_sock, peer_wake);
+
+ __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+ q);
+ u->peer_wake.private = NULL;
+
+ /* relaying can only happen while the wq still exists */
+ u_sleep = sk_sleep(&u->sk);
+ if (u_sleep)
+ wake_up_interruptible_poll(u_sleep, key);
+
+ return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+ int rc;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ rc = 0;
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (!u->peer_wake.private) {
+ u->peer_wake.private = other;
+ __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+ rc = 1;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+ return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+ struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (u->peer_wake.private == other) {
+ __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+ u->peer_wake.private = NULL;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+ struct sock *other)
+{
+ unix_dgram_peer_wake_disconnect(sk, other);
+ wake_up_interruptible_poll(sk_sleep(sk),
+ POLLOUT |
+ POLLWRNORM |
+ POLLWRBAND);
+}
+
+/* preconditions:
+ * - unix_peer(sk) == other
+ * - association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+ int connected;
+
+ connected = unix_dgram_peer_wake_connect(sk, other);
+
+ if (unix_recvq_full(other))
+ return 1;
+
+ if (connected)
+ unix_dgram_peer_wake_disconnect(sk, other);
+
+ return 0;
+}
+
static inline int unix_writable(struct sock *sk)
{
return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -430,6 +542,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
skpair->sk_state_change(skpair);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
}
+
+ unix_dgram_peer_wake_disconnect(sk, skpair);
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
}
@@ -440,6 +554,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
if (state == TCP_LISTEN)
unix_release_sock(skb->sk, 1);
/* passed fds are erased in the kfree_skb hook */
+ UNIXCB(skb).consumed = skb->len;
kfree_skb(skb);
}
@@ -664,6 +779,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
+ init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -1031,6 +1147,8 @@ restart:
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
unix_peer(sk) = other;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
unix_state_double_unlock(sk, other);
if (other != old_peer)
@@ -1432,6 +1550,14 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
return err;
}
+static bool unix_passcred_enabled(const struct socket *sock,
+ const struct sock *other)
+{
+ return test_bit(SOCK_PASSCRED, &sock->flags) ||
+ !other->sk_socket ||
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+}
+
/*
* Some apps rely on write() giving SCM_CREDENTIALS
* We include credentials if source or destination socket
@@ -1442,14 +1568,41 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
{
if (UNIXCB(skb).pid)
return;
- if (test_bit(SOCK_PASSCRED, &sock->flags) ||
- !other->sk_socket ||
- test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+ if (unix_passcred_enabled(sock, other)) {
UNIXCB(skb).pid = get_pid(task_tgid(current));
current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
}
}
+static int maybe_init_creds(struct scm_cookie *scm,
+ struct socket *socket,
+ const struct sock *other)
+{
+ int err;
+ struct msghdr msg = { .msg_controllen = 0 };
+
+ err = scm_send(socket, &msg, scm, false);
+ if (err)
+ return err;
+
+ if (unix_passcred_enabled(socket, other)) {
+ scm->pid = get_pid(task_tgid(current));
+ current_uid_gid(&scm->creds.uid, &scm->creds.gid);
+ }
+ return err;
+}
+
+static bool unix_skb_scm_eq(struct sk_buff *skb,
+ struct scm_cookie *scm)
+{
+ const struct unix_skb_parms *u = &UNIXCB(skb);
+
+ return u->pid == scm->pid &&
+ uid_eq(u->uid, scm->creds.uid) &&
+ gid_eq(u->gid, scm->creds.gid) &&
+ unix_secdata_eq(scm, skb);
+}
+
/*
* Send AF_UNIX data.
*/
@@ -1470,6 +1623,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
struct scm_cookie scm;
int max_level;
int data_len = 0;
+ int sk_locked;
wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
@@ -1548,12 +1702,14 @@ restart:
goto out_free;
}
+ sk_locked = 0;
unix_state_lock(other);
+restart_locked:
err = -EPERM;
if (!unix_may_send(sk, other))
goto out_unlock;
- if (sock_flag(other, SOCK_DEAD)) {
+ if (unlikely(sock_flag(other, SOCK_DEAD))) {
/*
* Check with 1003.1g - what should
* datagram error
@@ -1561,10 +1717,14 @@ restart:
unix_state_unlock(other);
sock_put(other);
+ if (!sk_locked)
+ unix_state_lock(sk);
+
err = 0;
- unix_state_lock(sk);
if (unix_peer(sk) == other) {
unix_peer(sk) = NULL;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
unix_state_unlock(sk);
unix_dgram_disconnected(sk, other);
@@ -1590,21 +1750,38 @@ restart:
goto out_unlock;
}
- if (unix_peer(other) != sk && unix_recvq_full(other)) {
- if (!timeo) {
- err = -EAGAIN;
- goto out_unlock;
+ if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+ if (timeo) {
+ timeo = unix_wait_for_peer(other, timeo);
+
+ err = sock_intr_errno(timeo);
+ if (signal_pending(current))
+ goto out_free;
+
+ goto restart;
}
- timeo = unix_wait_for_peer(other, timeo);
+ if (!sk_locked) {
+ unix_state_unlock(other);
+ unix_state_double_lock(sk, other);
+ }
- err = sock_intr_errno(timeo);
- if (signal_pending(current))
- goto out_free;
+ if (unix_peer(sk) != other ||
+ unix_dgram_peer_wake_me(sk, other)) {
+ err = -EAGAIN;
+ sk_locked = 1;
+ goto out_unlock;
+ }
- goto restart;
+ if (!sk_locked) {
+ sk_locked = 1;
+ goto restart_locked;
+ }
}
+ if (unlikely(sk_locked))
+ unix_state_unlock(sk);
+
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
maybe_add_creds(skb, sock, other);
@@ -1618,6 +1795,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -1739,8 +1918,10 @@ out_err:
static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
int offset, size_t size, int flags)
{
- int err = 0;
- bool send_sigpipe = true;
+ int err;
+ bool send_sigpipe = false;
+ bool init_scm = true;
+ struct scm_cookie scm;
struct sock *other, *sk = socket->sk;
struct sk_buff *skb, *newskb = NULL, *tail = NULL;
@@ -1758,7 +1939,7 @@ alloc_skb:
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
&err, 0);
if (!newskb)
- return err;
+ goto err;
}
/* we must acquire readlock as we modify already present
@@ -1767,12 +1948,12 @@ alloc_skb:
err = mutex_lock_interruptible(&unix_sk(other)->readlock);
if (err) {
err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
- send_sigpipe = false;
goto err;
}
if (sk->sk_shutdown & SEND_SHUTDOWN) {
err = -EPIPE;
+ send_sigpipe = true;
goto err_unlock;
}
@@ -1781,23 +1962,34 @@ alloc_skb:
if (sock_flag(other, SOCK_DEAD) ||
other->sk_shutdown & RCV_SHUTDOWN) {
err = -EPIPE;
+ send_sigpipe = true;
goto err_state_unlock;
}
+ if (init_scm) {
+ err = maybe_init_creds(&scm, socket, other);
+ if (err)
+ goto err_state_unlock;
+ init_scm = false;
+ }
+
skb = skb_peek_tail(&other->sk_receive_queue);
if (tail && tail == skb) {
skb = newskb;
- } else if (!skb) {
- if (newskb)
+ } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
+ if (newskb) {
skb = newskb;
- else
+ } else {
+ tail = skb;
goto alloc_skb;
+ }
} else if (newskb) {
/* this is fast path, we don't necessarily need to
* call to kfree_skb even though with newskb == NULL
* this - does no harm
*/
consume_skb(newskb);
+ newskb = NULL;
}
if (skb_append_pagefrags(skb, page, offset, size)) {
@@ -1810,14 +2002,20 @@ alloc_skb:
skb->truesize += size;
atomic_add(size, &sk->sk_wmem_alloc);
- if (newskb)
+ if (newskb) {
+ err = unix_scm_to_skb(&scm, skb, false);
+ if (err)
+ goto err_state_unlock;
+ spin_lock(&other->sk_receive_queue.lock);
__skb_queue_tail(&other->sk_receive_queue, newskb);
+ spin_unlock(&other->sk_receive_queue.lock);
+ }
unix_state_unlock(other);
mutex_unlock(&unix_sk(other)->readlock);
other->sk_data_ready(other);
-
+ scm_destroy(&scm);
return size;
err_state_unlock:
@@ -1828,6 +2026,8 @@ err:
kfree_skb(newskb);
if (send_sigpipe && !(flags & MSG_NOSIGNAL))
send_sig(SIGPIPE, current, 0);
+ if (!init_scm)
+ scm_destroy(&scm);
return err;
}
@@ -2071,6 +2271,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
do {
int chunk;
+ bool drop_skb;
struct sk_buff *skb, *last;
unix_state_lock(sk);
@@ -2130,10 +2331,7 @@ unlock:
if (check_creds) {
/* Never glue messages from different writers */
- if ((UNIXCB(skb).pid != scm.pid) ||
- !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
- !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
- !unix_secdata_eq(&scm, skb))
+ if (!unix_skb_scm_eq(skb, &scm))
break;
} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
/* Copy credentials */
@@ -2151,7 +2349,11 @@ unlock:
}
chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
+ skb_get(skb);
chunk = state->recv_actor(skb, skip, chunk, state);
+ drop_skb = !unix_skb_len(skb);
+ /* skb is only safe to use if !drop_skb */
+ consume_skb(skb);
if (chunk < 0) {
if (copied == 0)
copied = -EFAULT;
@@ -2160,6 +2362,18 @@ unlock:
copied += chunk;
size -= chunk;
+ if (drop_skb) {
+ /* the skb was touched by a concurrent reader;
+ * we should not expect anything from this skb
+ * anymore and assume it invalid - we can be
+ * sure it was dropped from the socket queue
+ *
+ * let's report a short read
+ */
+ err = 0;
+ break;
+ }
+
/* Mark read part of skb as used */
if (!(flags & MSG_PEEK)) {
UNIXCB(skb).consumed += chunk;
@@ -2453,14 +2667,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
return mask;
writable = unix_writable(sk);
- other = unix_peer_get(sk);
- if (other) {
- if (unix_peer(other) != sk) {
- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
- if (unix_recvq_full(other))
- writable = 0;
- }
- sock_put(other);
+ if (writable) {
+ unix_state_lock(sk);
+
+ other = unix_peer(sk);
+ if (other && unix_peer(other) != sk &&
+ unix_recvq_full(other) &&
+ unix_dgram_peer_wake_me(sk, other))
+ writable = 0;
+
+ unix_state_unlock(sk);
}
if (writable)