summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2017-03-15 21:59:10 +0300
committerDavid S. Miller <davem@davemloft.net>2017-03-15 21:59:10 +0300
commit101c431492d297dd0d111b461d8d324895676bee (patch)
tree06d8a02a4fd91acdd6c31340452e85feaac4ecb7 /net
parent9c79ddaa0f962d1f26537a670b0652ff509a6fe0 (diff)
parent95422dec6bd4a7c57444743f7b1bb375335a6298 (diff)
downloadlinux-101c431492d297dd0d111b461d8d324895676bee.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts: drivers/net/ethernet/broadcom/genet/bcmgenet.c net/core/sock.c Conflicts were overlapping changes in bcmgenet and the lockdep handling of sockets. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/atm/svc.c5
-rw-r--r--net/ax25/af_ax25.c3
-rw-r--r--net/bluetooth/l2cap_sock.c2
-rw-r--r--net/bluetooth/rfcomm/sock.c3
-rw-r--r--net/bluetooth/sco.c2
-rw-r--r--net/bridge/br_input.c1
-rw-r--r--net/bridge/br_netfilter_hooks.c21
-rw-r--r--net/ceph/ceph_common.c15
-rw-r--r--net/ceph/osd_client.c36
-rw-r--r--net/ceph/osdmap.c4
-rw-r--r--net/core/dev.c1
-rw-r--r--net/core/net-sysfs.c6
-rw-r--r--net/core/skbuff.c30
-rw-r--r--net/core/sock.c109
-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.c24
-rw-r--r--net/decnet/af_decnet.c5
-rw-r--r--net/ipv4/af_inet.c9
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv6/af_inet6.c10
-rw-r--r--net/ipv6/ip6_fib.c2
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/ipv6/ip6_output.c9
-rw-r--r--net/ipv6/ip6_vti.c8
-rw-r--r--net/ipv6/route.c11
-rw-r--r--net/ipv6/tcp_ipv6.c8
-rw-r--r--net/irda/af_irda.c5
-rw-r--r--net/iucv/af_iucv.c2
-rw-r--r--net/llc/af_llc.c4
-rw-r--r--net/mpls/af_mpls.c4
-rw-r--r--net/netrom/af_netrom.c3
-rw-r--r--net/nfc/llcp_sock.c2
-rw-r--r--net/phonet/pep.c6
-rw-r--r--net/phonet/socket.c4
-rw-r--r--net/rds/connection.c1
-rw-r--r--net/rds/ib_cm.c47
-rw-r--r--net/rds/rds.h6
-rw-r--r--net/rds/tcp.c38
-rw-r--r--net/rds/tcp.h2
-rw-r--r--net/rds/tcp_listen.c11
-rw-r--r--net/rose/af_rose.c3
-rw-r--r--net/rxrpc/input.c27
-rw-r--r--net/rxrpc/recvmsg.c4
-rw-r--r--net/rxrpc/sendmsg.c49
-rw-r--r--net/sched/act_connmark.c3
-rw-r--r--net/sched/act_skbmod.c1
-rw-r--r--net/sctp/ipv6.c5
-rw-r--r--net/sctp/protocol.c5
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/smc/af_smc.c2
-rw-r--r--net/socket.c5
-rw-r--r--net/tipc/socket.c8
-rw-r--r--net/unix/af_unix.c5
-rw-r--r--net/vmw_vsock/af_vsock.c3
-rw-r--r--net/x25/af_x25.c3
-rw-r--r--net/xfrm/xfrm_policy.c19
61 files changed, 401 insertions, 240 deletions
diff --git a/net/atm/svc.c b/net/atm/svc.c
index db9794ec61d8..5589de7086af 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -318,7 +318,8 @@ out:
return error;
}
-static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
+static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sk_buff *skb;
@@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
lock_sock(sk);
- error = svc_create(sock_net(sk), newsock, 0, 0);
+ error = svc_create(sock_net(sk), newsock, 0, kern);
if (error)
goto out;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a8e42cedf1db..b7c486752b3a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1320,7 +1320,8 @@ out_release:
return err;
}
-static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f307b145ea54..507b80d59dec 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -301,7 +301,7 @@ done:
}
static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index aa1a814ceddc..ac3c650cb234 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -471,7 +471,8 @@ done:
return err;
}
-static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e4e9a2da1e7e..728e0c8dc8e7 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -627,7 +627,7 @@ done:
}
static int sco_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *ch;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 236f34244dbe..013f2290bfa5 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,6 +30,7 @@ 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 95087e6e8258..fa87fbd62bb7 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ 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)
{
@@ -908,12 +893,6 @@ 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/ceph_common.c b/net/ceph/ceph_common.c
index 464e88599b9d..108533859a53 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -230,6 +230,7 @@ enum {
Opt_osdkeepalivetimeout,
Opt_mount_timeout,
Opt_osd_idle_ttl,
+ Opt_osd_request_timeout,
Opt_last_int,
/* int args above */
Opt_fsid,
@@ -256,6 +257,7 @@ static match_table_t opt_tokens = {
{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
{Opt_mount_timeout, "mount_timeout=%d"},
{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+ {Opt_osd_request_timeout, "osd_request_timeout=%d"},
/* int args above */
{Opt_fsid, "fsid=%s"},
{Opt_name, "name=%s"},
@@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name,
opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+ opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
/* get mon ip(s) */
/* ip1[:port1][,ip2[:port2]...] */
@@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name,
}
opt->mount_timeout = msecs_to_jiffies(intval * 1000);
break;
+ case Opt_osd_request_timeout:
+ /* 0 is "wait forever" (i.e. infinite timeout) */
+ if (intval < 0 || intval > INT_MAX / 1000) {
+ pr_err("osd_request_timeout out of range\n");
+ err = -EINVAL;
+ goto out;
+ }
+ opt->osd_request_timeout = msecs_to_jiffies(intval * 1000);
+ break;
case Opt_share:
opt->flags &= ~CEPH_OPT_NOSHARE;
@@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
seq_printf(m, "osdkeepalivetimeout=%d,",
jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
+ if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
+ seq_printf(m, "osd_request_timeout=%d,",
+ jiffies_to_msecs(opt->osd_request_timeout) / 1000);
/* drop redundant comma */
if (m->count != pos)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b65bbf9f45eb..e15ea9e4c495 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req)
req->r_flags |= CEPH_OSD_FLAG_ONDISK;
atomic_inc(&req->r_osdc->num_requests);
+
+ req->r_start_stamp = jiffies;
}
static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req)
ceph_osdc_put_request(req);
}
+static void abort_request(struct ceph_osd_request *req, int err)
+{
+ dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+ cancel_map_check(req);
+ complete_request(req, err);
+}
+
static void check_pool_dne(struct ceph_osd_request *req)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work)
container_of(work, struct ceph_osd_client, timeout_work.work);
struct ceph_options *opts = osdc->client->options;
unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+ unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
LIST_HEAD(slow_osds);
struct rb_node *n, *p;
@@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work)
struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
bool found = false;
- for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+ for (p = rb_first(&osd->o_requests); p; ) {
struct ceph_osd_request *req =
rb_entry(p, struct ceph_osd_request, r_node);
+ p = rb_next(p); /* abort_request() */
+
if (time_before(req->r_stamp, cutoff)) {
dout(" req %p tid %llu on osd%d is laggy\n",
req, req->r_tid, osd->o_osd);
found = true;
}
+ if (opts->osd_request_timeout &&
+ time_before(req->r_start_stamp, expiry_cutoff)) {
+ pr_err_ratelimited("tid %llu on osd%d timeout\n",
+ req->r_tid, osd->o_osd);
+ abort_request(req, -ETIMEDOUT);
+ }
}
for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
struct ceph_osd_linger_request *lreq =
@@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work)
list_move_tail(&osd->o_keepalive_item, &slow_osds);
}
+ if (opts->osd_request_timeout) {
+ for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ p = rb_next(p); /* abort_request() */
+
+ if (time_before(req->r_start_stamp, expiry_cutoff)) {
+ pr_err_ratelimited("tid %llu on osd%d timeout\n",
+ req->r_tid, osdc->homeless_osd.o_osd);
+ abort_request(req, -ETIMEDOUT);
+ }
+ }
+ }
+
if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
maybe_request_map(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6824c0ec8373..ffe9e904d4d1 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
dout("crush decode tunable chooseleaf_stable = %d\n",
c->chooseleaf_stable);
- crush_finalize(c);
-
done:
+ crush_finalize(c);
dout("crush_decode success\n");
return c;
@@ -1380,7 +1379,6 @@ 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 8637b2b71f3d..7869ae3837ca 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1304,6 +1304,7 @@ void netdev_notify_peers(struct net_device *dev)
{
rtnl_lock();
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+ call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 3945821e9c1f..65ea0ff4017c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -953,7 +953,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
while (--i >= new_num) {
struct kobject *kobj = &dev->_rx[i].kobj;
- if (!list_empty(&dev_net(dev)->exit_list))
+ if (!atomic_read(&dev_net(dev)->count))
kobj->uevent_suppress = 1;
if (dev->sysfs_rx_queue_group)
sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1371,7 +1371,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
while (--i >= new_num) {
struct netdev_queue *queue = dev->_tx + i;
- if (!list_empty(&dev_net(dev)->exit_list))
+ if (!atomic_read(&dev_net(dev)->count))
queue->kobj.uevent_suppress = 1;
#ifdef CONFIG_BQL
sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1558,7 +1558,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
{
struct device *dev = &(ndev->dev);
- if (!list_empty(&dev_net(ndev)->exit_list))
+ if (!atomic_read(&dev_net(ndev)->count))
dev_set_uevent_suppress(dev, 1);
kobject_get(&dev->kobj);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f3557958e9bf..cd4ba8c6b609 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3828,13 +3828,14 @@ 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);
@@ -3893,7 +3894,7 @@ 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;
@@ -3903,14 +3904,15 @@ 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 768aedf238f5..a83731c36761 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -197,66 +197,55 @@ EXPORT_SYMBOL(sk_net_capable);
/*
* Each address family might have different locking rules, so we have
- * one slock key per address family:
+ * one slock key per address family and separate keys for internal and
+ * userspace sockets.
*/
static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_kern_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
+static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
+
+#define _sock_locks(x) \
+ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \
+ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \
+ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \
+ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \
+ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \
+ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \
+ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \
+ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \
+ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \
+ x "27" , x "28" , x "AF_CAN" , \
+ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \
+ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \
+ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \
+ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \
+ x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX"
+
static const char *const af_family_key_strings[AF_MAX+1] = {
- "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
- "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
- "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
- "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" ,
- "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
- "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
- "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
- "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
- "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
- "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" ,
- "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
- "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
- "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
- "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" ,
- "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX"
+ _sock_locks("sk_lock-")
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
- "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
- "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
- "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
- "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" ,
- "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
- "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
- "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
- "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" ,
- "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
- "slock-27" , "slock-28" , "slock-AF_CAN" ,
- "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
- "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
- "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
- "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" ,
- "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX"
+ _sock_locks("slock-")
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
- "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
- "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
- "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
- "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" ,
- "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
- "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
- "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
- "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" ,
- "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
- "clock-27" , "clock-28" , "clock-AF_CAN" ,
- "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
- "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
- "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
- "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" ,
- "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX"
+ _sock_locks("clock-")
+};
+
+static const char *const af_family_kern_key_strings[AF_MAX+1] = {
+ _sock_locks("k-sk_lock-")
+};
+static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
+ _sock_locks("k-slock-")
+};
+static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
+ _sock_locks("k-clock-")
};
static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
"rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" ,
@@ -318,6 +307,7 @@ static struct lock_class_key af_callback_keys[AF_MAX];
static struct lock_class_key af_rlock_keys[AF_MAX];
static struct lock_class_key af_wlock_keys[AF_MAX];
static struct lock_class_key af_elock_keys[AF_MAX];
+static struct lock_class_key af_kern_callback_keys[AF_MAX];
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
@@ -1347,7 +1337,16 @@ lenout:
*/
static inline void sock_lock_init(struct sock *sk)
{
- sock_lock_init_class_and_name(sk,
+ if (sk->sk_kern_sock)
+ sock_lock_init_class_and_name(
+ sk,
+ af_family_kern_slock_key_strings[sk->sk_family],
+ af_family_kern_slock_keys + sk->sk_family,
+ af_family_kern_key_strings[sk->sk_family],
+ af_family_kern_keys + sk->sk_family);
+ else
+ sock_lock_init_class_and_name(
+ sk,
af_family_slock_key_strings[sk->sk_family],
af_family_slock_keys + sk->sk_family,
af_family_key_strings[sk->sk_family],
@@ -1453,6 +1452,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
* why we need sk_prot_creator -acme
*/
sk->sk_prot = sk->sk_prot_creator = prot;
+ sk->sk_kern_sock = kern;
sock_lock_init(sk);
sk->sk_net_refcnt = kern ? 0 : 1;
if (likely(sk->sk_net_refcnt))
@@ -2345,7 +2345,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
}
EXPORT_SYMBOL(sock_no_socketpair);
-int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
+int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
return -EOPNOTSUPP;
}
@@ -2545,6 +2546,18 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
}
+ rwlock_init(&sk->sk_callback_lock);
+ if (sk->sk_kern_sock)
+ lockdep_set_class_and_name(
+ &sk->sk_callback_lock,
+ af_kern_callback_keys + sk->sk_family,
+ af_family_kern_clock_key_strings[sk->sk_family]);
+ else
+ lockdep_set_class_and_name(
+ &sk->sk_callback_lock,
+ af_callback_keys + sk->sk_family,
+ af_family_clock_key_strings[sk->sk_family]);
+
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
sk->sk_write_space = sock_def_write_space;
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 409d0cfd3447..b99168b0fabf 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 233b57367758..d9b6a4e403e7 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 e267e6f4c9a5..abd07a443219 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -142,6 +142,13 @@ 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) {
@@ -156,7 +163,7 @@ 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;
@@ -182,20 +189,20 @@ 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);
@@ -246,6 +253,7 @@ 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/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 0ec8cb4363e9..9afa2a5030b2 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1071,7 +1071,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
return skb == NULL ? ERR_PTR(err) : skb;
}
-static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
+static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk, *newsk;
struct sk_buff *skb = NULL;
@@ -1100,7 +1101,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
cb = DN_SKB_CB(skb);
sk->sk_ack_backlog--;
- newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
+ newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
if (newsk == NULL) {
release_sock(sk);
kfree_skb(skb);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 602d40f43687..6b1fc6e4278e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect);
* Accept a pending connection. The TCP layer now gives BSD semantics.
*/
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk1 = sock->sk;
int err = -EINVAL;
- struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+ struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
if (!sk2)
goto do_err;
@@ -1487,8 +1488,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
int proto = iph->protocol;
int err = -ENOSYS;
- if (skb->encapsulation)
+ if (skb->encapsulation) {
+ skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
skb_set_inner_network_header(skb, nhoff);
+ }
csum_replace2(&iph->check, iph->tot_len, newlen);
iph->tot_len = newlen;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980ade3b..5e313c1ac94f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
/*
* This will accept the next outstanding connection.
*/
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 737ce826d7ec..7a3fd25e8913 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
(sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, transhdrlen,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7b332ed66488..08d870e45658 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -279,10 +279,13 @@ 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;
@@ -428,7 +431,8 @@ 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_timer.c b/net/ipv4/tcp_timer.c
index 40d893556e67..b2ab411c6d37 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ 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)) {
@@ -552,7 +553,8 @@ 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/af_inet6.c b/net/ipv6/af_inet6.c
index 04db40620ea6..a9a9553ee63d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -920,12 +920,12 @@ static int __init inet6_init(void)
err = register_pernet_subsys(&inet6_net_ops);
if (err)
goto register_pernet_fail;
- err = icmpv6_init();
- if (err)
- goto icmp_fail;
err = ip6_mr_init();
if (err)
goto ipmr_fail;
+ err = icmpv6_init();
+ if (err)
+ goto icmp_fail;
err = ndisc_init();
if (err)
goto ndisc_fail;
@@ -1061,10 +1061,10 @@ igmp_fail:
ndisc_cleanup();
ndisc_fail:
ip6_mr_cleanup();
-ipmr_fail:
- icmpv6_cleanup();
icmp_fail:
unregister_pernet_subsys(&inet6_net_ops);
+ipmr_fail:
+ icmpv6_cleanup();
register_pernet_fail:
sock_unregister(PF_INET6);
rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e4266746e4a2..d4bf2c68a545 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -923,6 +923,8 @@ 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_offload.c b/net/ipv6/ip6_offload.c
index 0838e6d01d2e..93e58a5e1837 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
int err = -ENOSYS;
- if (skb->encapsulation)
+ if (skb->encapsulation) {
+ skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
skb_set_inner_network_header(skb, nhoff);
+ }
iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 528b3c1f3fde..58f6288e9ba5 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,13 +768,14 @@ 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)
@@ -819,6 +820,10 @@ 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.
*/
@@ -1385,7 +1390,7 @@ emsgsize:
if ((((length + fragheaderlen) > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 644ba59fbd9d..3d8a3b63b4fd 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -485,11 +485,15 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
if (!skb->ignore_df && skb->len > mtu) {
skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
- if (skb->protocol == htons(ETH_P_IPV6))
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- else
+ } else {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
+ }
return -EMSGSIZE;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 229bfcc451ef..35c58b669ebd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3299,7 +3299,6 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
+ NLA_ALIGN(sizeof(struct rtnexthop))
+ nla_total_size(16) /* RTA_GATEWAY */
- + nla_total_size(4) /* RTA_OIF */
+ lwtunnel_get_encap_size(rt->dst.lwtstate);
nexthop_len *= rt->rt6i_nsiblings;
@@ -3323,7 +3322,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
}
static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
- unsigned int *flags)
+ unsigned int *flags, bool skip_oif)
{
if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
*flags |= RTNH_F_LINKDOWN;
@@ -3336,7 +3335,8 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
goto nla_put_failure;
}
- if (rt->dst.dev &&
+ /* not needed for multipath encoding b/c it has a rtnexthop struct */
+ if (!skip_oif && rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
@@ -3350,6 +3350,7 @@ nla_put_failure:
return -EMSGSIZE;
}
+/* add multipath next hop */
static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
{
struct rtnexthop *rtnh;
@@ -3362,7 +3363,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
rtnh->rtnh_hops = 0;
rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
- if (rt6_nexthop_info(skb, rt, &flags) < 0)
+ if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
goto nla_put_failure;
rtnh->rtnh_flags = flags;
@@ -3515,7 +3516,7 @@ static int rt6_fill_node(struct net *net,
nla_nest_end(skb, mp);
} else {
- if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0)
+ if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0)
goto nla_put_failure;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 56f742fff967..c73a431fd06f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -391,10 +391,12 @@ 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/irda/af_irda.c b/net/irda/af_irda.c
index 81adc29a448d..8d77ad5cadaf 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -828,7 +828,8 @@ out:
* Wait for incoming connection
*
*/
-static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
+static int irda_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct irda_sock *new, *self = irda_sk(sk);
@@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
struct sk_buff *skb = NULL;
int err;
- err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
+ err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern);
if (err)
return err;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 89bbde1081ce..84de7b6326dc 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -938,7 +938,7 @@ done:
/* Accept a pending connection */
static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DECLARE_WAITQUEUE(wait, current);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 06186d608a27..cb4fff785cbf 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
* @sock: Socket which connections arrive on.
* @newsock: Socket to move incoming connection to.
* @flags: User specified operational flags.
+ * @kern: If the socket is kernel internal
*
* Accept a new incoming connection.
* Returns 0 upon success, negative otherwise.
*/
-static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags)
+static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk, *newsk;
struct llc_sock *llc, *newllc;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 0c5d111abe36..f7a08e5f9763 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1317,7 +1317,8 @@ static void mpls_ifdown(struct net_device *dev, int event)
/* fall through */
case NETDEV_CHANGE:
nh->nh_flags |= RTNH_F_LINKDOWN;
- ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+ if (event != NETDEV_UNREGISTER)
+ ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
break;
}
if (event == NETDEV_UNREGISTER)
@@ -2110,6 +2111,7 @@ 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/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4bbf4526b885..ebf16f7f9089 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -765,7 +765,8 @@ out_release:
return err;
}
-static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
+static int nr_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 879885b31cce..2ffb18e73df6 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent,
}
static int llcp_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DECLARE_WAITQUEUE(wait, current);
struct sock *sk = sock->sk, *new_sk;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 222bedcd9575..e81537991ddf 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout)
sock_put(sk);
}
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
+ bool kern)
{
struct pep_sock *pn = pep_sk(sk), *newpn;
struct sock *newsk = NULL;
@@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
}
/* Create a new to-be-accepted sock */
- newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
+ newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot,
+ kern);
if (!newsk) {
pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
err = -ENOBUFS;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index a6c8da3ee893..64634e3ec2fc 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -305,7 +305,7 @@ out:
}
static int pn_socket_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
struct sock *sk = sock->sk;
struct sock *newsk;
@@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
if (unlikely(sk->sk_state != TCP_LISTEN))
return -EINVAL;
- newsk = sk->sk_prot->accept(sk, flags, &err);
+ newsk = sk->sk_prot->accept(sk, flags, &err, kern);
if (!newsk)
return err;
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 0e04dcceb1d4..1fa75ab7b733 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -429,6 +429,7 @@ void rds_conn_destroy(struct rds_connection *conn)
*/
rds_cong_remove_conn(conn);
+ put_net(conn->c_net);
kmem_cache_free(rds_conn_slab, conn);
spin_lock_irqsave(&rds_conn_lock, flags);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 11d535b16125..80fb6f63e768 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -442,7 +442,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_send_cq = NULL;
ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
rdsdebug("ib_create_cq send failed: %d\n", ret);
- goto out;
+ goto rds_ibdev_out;
}
ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
@@ -456,19 +456,19 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_recv_cq = NULL;
ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
rdsdebug("ib_create_cq recv failed: %d\n", ret);
- goto out;
+ goto send_cq_out;
}
ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
if (ret) {
rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
if (ret) {
rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
/* XXX negotiate max send/recv with remote? */
@@ -494,7 +494,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
if (ret) {
rdsdebug("rdma_create_qp failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
@@ -504,7 +504,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_send_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent send failed\n");
- goto out;
+ goto qp_out;
}
ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
@@ -514,7 +514,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_recv_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent recv failed\n");
- goto out;
+ goto send_hdrs_dma_out;
}
ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
@@ -522,7 +522,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_ack) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent ack failed\n");
- goto out;
+ goto recv_hdrs_dma_out;
}
ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
@@ -530,7 +530,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_sends) {
ret = -ENOMEM;
rdsdebug("send allocation failed\n");
- goto out;
+ goto ack_dma_out;
}
ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
@@ -538,7 +538,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_recvs) {
ret = -ENOMEM;
rdsdebug("recv allocation failed\n");
- goto out;
+ goto sends_out;
}
rds_ib_recv_init_ack(ic);
@@ -546,8 +546,33 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
-out:
+ return ret;
+
+sends_out:
+ vfree(ic->i_sends);
+ack_dma_out:
+ ib_dma_free_coherent(dev, sizeof(struct rds_header),
+ ic->i_ack, ic->i_ack_dma);
+recv_hdrs_dma_out:
+ ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
+ sizeof(struct rds_header),
+ ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
+send_hdrs_dma_out:
+ ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
+ sizeof(struct rds_header),
+ ic->i_send_hdrs, ic->i_send_hdrs_dma);
+qp_out:
+ rdma_destroy_qp(ic->i_cm_id);
+recv_cq_out:
+ if (!ib_destroy_cq(ic->i_recv_cq))
+ ic->i_recv_cq = NULL;
+send_cq_out:
+ if (!ib_destroy_cq(ic->i_send_cq))
+ ic->i_send_cq = NULL;
+rds_ibdev_out:
+ rds_ib_remove_conn(rds_ibdev, conn);
rds_ib_dev_put(rds_ibdev);
+
return ret;
}
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 39518ef7af4d..82d38ccf5e8b 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -147,7 +147,7 @@ struct rds_connection {
/* Protocol version */
unsigned int c_version;
- possible_net_t c_net;
+ struct net *c_net;
struct list_head c_map_item;
unsigned long c_map_queued;
@@ -162,13 +162,13 @@ struct rds_connection {
static inline
struct net *rds_conn_net(struct rds_connection *conn)
{
- return read_pnet(&conn->c_net);
+ return conn->c_net;
}
static inline
void rds_conn_net_set(struct rds_connection *conn, struct net *net)
{
- write_pnet(&conn->c_net, net);
+ conn->c_net = get_net(net);
}
#define RDS_FLAG_CONG_BITMAP 0x01
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index a973d3b4dff0..225690076773 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -484,9 +484,10 @@ static void __net_exit rds_tcp_exit_net(struct net *net)
* we do need to clean up the listen socket here.
*/
if (rtn->rds_tcp_listen_sock) {
- rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
+
rtn->rds_tcp_listen_sock = NULL;
- flush_work(&rtn->rds_tcp_accept_w);
+ rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
}
}
@@ -523,13 +524,13 @@ static void rds_tcp_kill_sock(struct net *net)
struct rds_tcp_connection *tc, *_tc;
LIST_HEAD(tmp_list);
struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
- rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
rtn->rds_tcp_listen_sock = NULL;
- flush_work(&rtn->rds_tcp_accept_w);
+ rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
spin_lock_irq(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
- struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+ struct net *c_net = tc->t_cpath->cp_conn->c_net;
if (net != c_net || !tc->t_sock)
continue;
@@ -546,8 +547,12 @@ static void rds_tcp_kill_sock(struct net *net)
void *rds_tcp_listen_sock_def_readable(struct net *net)
{
struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
+
+ if (!lsock)
+ return NULL;
- return rtn->rds_tcp_listen_sock->sk->sk_user_data;
+ return lsock->sk->sk_user_data;
}
static int rds_tcp_dev_event(struct notifier_block *this,
@@ -584,7 +589,7 @@ static void rds_tcp_sysctl_reset(struct net *net)
spin_lock_irq(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
- struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+ struct net *c_net = tc->t_cpath->cp_conn->c_net;
if (net != c_net || !tc->t_sock)
continue;
@@ -638,19 +643,19 @@ static int rds_tcp_init(void)
goto out;
}
- ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
- if (ret) {
- pr_warn("could not register rds_tcp_dev_notifier\n");
+ ret = rds_tcp_recv_init();
+ if (ret)
goto out_slab;
- }
ret = register_pernet_subsys(&rds_tcp_net_ops);
if (ret)
- goto out_notifier;
+ goto out_recv;
- ret = rds_tcp_recv_init();
- if (ret)
+ ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+ if (ret) {
+ pr_warn("could not register rds_tcp_dev_notifier\n");
goto out_pernet;
+ }
rds_trans_register(&rds_tcp_transport);
@@ -660,9 +665,8 @@ static int rds_tcp_init(void)
out_pernet:
unregister_pernet_subsys(&rds_tcp_net_ops);
-out_notifier:
- if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
- pr_warn("could not unregister rds_tcp_dev_notifier\n");
+out_recv:
+ rds_tcp_recv_exit();
out_slab:
kmem_cache_destroy(rds_tcp_conn_slab);
out:
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 9a1cc8906576..56ea6620fcf9 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk);
/* tcp_listen.c */
struct socket *rds_tcp_listen_init(struct net *);
-void rds_tcp_listen_stop(struct socket *);
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
void rds_tcp_listen_data_ready(struct sock *sk);
int rds_tcp_accept_one(struct socket *sock);
int rds_tcp_keepalive(struct socket *sock);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 67d0929c7d3d..507678853e6c 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock)
new_sock->type = sock->type;
new_sock->ops = sock->ops;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+ ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
if (ret < 0)
goto out;
@@ -223,6 +223,9 @@ void rds_tcp_listen_data_ready(struct sock *sk)
* before it has been accepted and the accepter has set up their
* data_ready.. we only want to queue listen work for our listening
* socket
+ *
+ * (*ready)() may be null if we are racing with netns delete, and
+ * the listen socket is being torn down.
*/
if (sk->sk_state == TCP_LISTEN)
rds_tcp_accept_work(sk);
@@ -231,7 +234,8 @@ void rds_tcp_listen_data_ready(struct sock *sk)
out:
read_unlock_bh(&sk->sk_callback_lock);
- ready(sk);
+ if (ready)
+ ready(sk);
}
struct socket *rds_tcp_listen_init(struct net *net)
@@ -271,7 +275,7 @@ out:
return NULL;
}
-void rds_tcp_listen_stop(struct socket *sock)
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor)
{
struct sock *sk;
@@ -292,5 +296,6 @@ void rds_tcp_listen_stop(struct socket *sock)
/* wait for accepts to stop and close the socket */
flush_workqueue(rds_wq);
+ flush_work(acceptor);
sock_release(sock);
}
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index b8a1df2c9785..4a9729257023 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -871,7 +871,8 @@ out_release:
return err;
}
-static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rose_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9f4cfa25af7c..18b2ad8be8e2 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -420,6 +420,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
u16 skew)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ enum rxrpc_call_state state;
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int ix;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
@@ -434,14 +435,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
_proto("Rx DATA %%%u { #%u f=%02x }",
sp->hdr.serial, seq, sp->hdr.flags);
- if (call->state >= RXRPC_CALL_COMPLETE)
+ state = READ_ONCE(call->state);
+ if (state >= RXRPC_CALL_COMPLETE)
return;
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
- if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
- call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
+ if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
+ state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
!rxrpc_receiving_reply(call))
return;
@@ -650,6 +652,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_peer *peer;
unsigned int mtu;
+ bool wake = false;
u32 rwind = ntohl(ackinfo->rwind);
_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
@@ -657,9 +660,14 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
rwind, ntohl(ackinfo->jumbo_max));
- if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
- rwind = RXRPC_RXTX_BUFF_SIZE - 1;
- call->tx_winsize = rwind;
+ if (call->tx_winsize != rwind) {
+ if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+ rwind = RXRPC_RXTX_BUFF_SIZE - 1;
+ if (rwind > call->tx_winsize)
+ wake = true;
+ call->tx_winsize = rwind;
+ }
+
if (call->cong_ssthresh > rwind)
call->cong_ssthresh = rwind;
@@ -673,6 +681,9 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
spin_unlock_bh(&peer->lock);
_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
}
+
+ if (wake)
+ wake_up(&call->waitq);
}
/*
@@ -799,7 +810,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
return rxrpc_proto_abort("AK0", call, 0);
/* Ignore ACKs unless we are or have just been transmitting. */
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
@@ -940,7 +951,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
struct rxrpc_call *call)
{
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
break;
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6491ca46a03f..3e2f1a8e9c5b 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -527,7 +527,7 @@ try_again:
msg->msg_namelen = len;
}
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_ACCEPTING:
ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
break;
@@ -640,7 +640,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
mutex_lock(&call->user_mutex);
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index bc2d3dcff9de..97ab214ca411 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -488,6 +488,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
__releases(&rx->sk.sk_lock.slock)
{
+ enum rxrpc_call_state state;
enum rxrpc_command cmd;
struct rxrpc_call *call;
unsigned long user_call_ID = 0;
@@ -526,13 +527,17 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
return PTR_ERR(call);
/* ... and we have the call lock. */
} else {
- ret = -EBUSY;
- if (call->state == RXRPC_CALL_UNINITIALISED ||
- call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
- call->state == RXRPC_CALL_SERVER_PREALLOC ||
- call->state == RXRPC_CALL_SERVER_SECURING ||
- call->state == RXRPC_CALL_SERVER_ACCEPTING)
+ switch (READ_ONCE(call->state)) {
+ case RXRPC_CALL_UNINITIALISED:
+ case RXRPC_CALL_CLIENT_AWAIT_CONN:
+ case RXRPC_CALL_SERVER_PREALLOC:
+ case RXRPC_CALL_SERVER_SECURING:
+ case RXRPC_CALL_SERVER_ACCEPTING:
+ ret = -EBUSY;
goto error_release_sock;
+ default:
+ break;
+ }
ret = mutex_lock_interruptible(&call->user_mutex);
release_sock(&rx->sk);
@@ -542,10 +547,11 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
}
}
+ state = READ_ONCE(call->state);
_debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, call->state, call->conn);
+ call->debug_id, call->user_call_ID, state, call->conn);
- if (call->state >= RXRPC_CALL_COMPLETE) {
+ if (state >= RXRPC_CALL_COMPLETE) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (cmd == RXRPC_CMD_SEND_ABORT) {
@@ -555,12 +561,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
} else if (cmd != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else if (rxrpc_is_client_call(call) &&
- call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+ state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
/* request phase complete for this client call */
ret = -EPROTO;
} else if (rxrpc_is_service_call(call) &&
- call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+ state != RXRPC_CALL_SERVER_SEND_REPLY) {
/* Reply phase not begun or not complete for service call. */
ret = -EPROTO;
} else {
@@ -605,14 +611,21 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
- if (call->state >= RXRPC_CALL_COMPLETE) {
- ret = -ESHUTDOWN; /* it's too late for this call */
- } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
- call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
- ret = -EPROTO; /* request phase complete for this client call */
- } else {
+ switch (READ_ONCE(call->state)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ case RXRPC_CALL_SERVER_ACK_REQUEST:
+ case RXRPC_CALL_SERVER_SEND_REPLY:
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
+ break;
+ case RXRPC_CALL_COMPLETE:
+ read_lock_bh(&call->state_lock);
+ ret = -call->error;
+ read_unlock_bh(&call->state_lock);
+ break;
+ default:
+ /* Request phase complete for this client call */
+ ret = -EPROTO;
+ break;
}
mutex_unlock(&call->user_mutex);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ab8062909962..f9bb43c25697 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -113,6 +113,9 @@ 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(tn, parm->index, a, bind)) {
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 3b7074e23024..c736627f8f4a 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
return skb->len;
nla_put_failure:
- rcu_read_unlock();
nlmsg_trim(skb, b);
return -1;
}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 063baac5b9fe..961ee59f696a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr)
/* Create and initialize a new sk for the socket to be returned by accept(). */
static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
- struct sctp_association *asoc)
+ struct sctp_association *asoc,
+ bool kern)
{
struct sock *newsk;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct sctp6_sock *newsctp6sk;
struct ipv6_txoptions *opt;
- newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
+ newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
if (!newsk)
goto out;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 1b6d4574d2b0..989a900383b5 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb)
/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
- struct sctp_association *asoc)
+ struct sctp_association *asoc,
+ bool kern)
{
struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
- sk->sk_prot, 0);
+ sk->sk_prot, kern);
struct inet_sock *newinet;
if (!newsk)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 24e28cfb542b..72cc3ecf6516 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4152,7 +4152,7 @@ static int sctp_disconnect(struct sock *sk, int flags)
* descriptor will be returned from accept() to represent the newly
* formed association.
*/
-static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
+static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct sctp_sock *sp;
struct sctp_endpoint *ep;
@@ -4187,7 +4187,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
*/
asoc = list_entry(ep->asocs.next, struct sctp_association, asocs);
- newsk = sp->pf->create_accept_sk(sk, asoc);
+ newsk = sp->pf->create_accept_sk(sk, asoc, kern);
if (!newsk) {
error = -ENOMEM;
goto out;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 85837ab90e89..093803786eac 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -944,7 +944,7 @@ out:
}
static int smc_accept(struct socket *sock, struct socket *new_sock,
- int flags)
+ int flags, bool kern)
{
struct sock *sk = sock->sk, *nsk;
DECLARE_WAITQUEUE(wait, current);
diff --git a/net/socket.c b/net/socket.c
index 2c1e8677ff2d..e034fe4164be 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1506,7 +1506,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
if (err)
goto out_fd;
- err = sock->ops->accept(sock, newsock, sock->file->f_flags);
+ err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
if (err < 0)
goto out_fd;
@@ -1731,6 +1731,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
/* We assume all kernel code knows the size of sockaddr_storage */
msg.msg_namelen = 0;
msg.msg_iocb = NULL;
+ msg.msg_flags = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, flags);
@@ -3238,7 +3239,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
if (err < 0)
goto done;
- err = sock->ops->accept(sock, *newsock, flags);
+ err = sock->ops->accept(sock, *newsock, flags, true);
if (err < 0) {
sock_release(*newsock);
*newsock = NULL;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43e4045e72bc..7130e73bd42c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
static void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+ bool kern);
static void tipc_sk_timeout(unsigned long data);
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
@@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
*
* Returns 0 on success, errno otherwise
*/
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+ bool kern)
{
struct sock *new_sk, *sk = sock->sk;
struct sk_buff *buf;
@@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
buf = skb_peek(&sk->sk_receive_queue);
- res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
+ res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
if (res)
goto exit;
security_sk_clone(sock->sk, new_sock->sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ee37b390260a..928691c43408 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
static int unix_stream_connect(struct socket *, struct sockaddr *,
int addr_len, int flags);
static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int);
+static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
static unsigned int unix_dgram_poll(struct file *, struct socket *,
@@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
set_bit(SOCK_PASSSEC, &new->flags);
}
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
+static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sock *tsk;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9192ead66751..9f770f33c100 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1250,7 +1250,8 @@ out:
return err;
}
-static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *listener;
int err;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index fd28a49dbe8f..8b911c29860e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
return rc;
}
-static int x25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int x25_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sock *newsk;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0806dccdf507..236cbbc0ab9c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1243,7 +1243,7 @@ static inline int policy_to_flow_dir(int dir)
}
static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
- const struct flowi *fl)
+ const struct flowi *fl, u16 family)
{
struct xfrm_policy *pol;
@@ -1251,8 +1251,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
again:
pol = rcu_dereference(sk->sk_policy[dir]);
if (pol != NULL) {
- bool match = xfrm_selector_match(&pol->selector, fl,
- sk->sk_family);
+ bool match = xfrm_selector_match(&pol->selector, fl, family);
int err = 0;
if (match) {
@@ -2239,7 +2238,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
sk = sk_const_to_full_sk(sk);
if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
num_pols = 1;
- pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+ pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
err = xfrm_expand_policies(fl, family, pols,
&num_pols, &num_xfrms);
if (err < 0)
@@ -2518,7 +2517,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
pol = NULL;
sk = sk_to_full_sk(sk);
if (sk && sk->sk_policy[dir]) {
- pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+ pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
if (IS_ERR(pol)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
return 0;
@@ -3069,6 +3068,11 @@ 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);
+ spin_lock_init(&net->xfrm.xfrm_policy_lock);
+ mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
rv = xfrm_statistics_init(net);
if (rv < 0)
goto out_statistics;
@@ -3085,11 +3089,6 @@ 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);
- spin_lock_init(&net->xfrm.xfrm_policy_lock);
- mutex_init(&net->xfrm.xfrm_cfg_mutex);
-
return 0;
out: