summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2014-03-30 02:48:54 +0400
committerDavid S. Miller <davem@davemloft.net>2014-03-30 02:48:54 +0400
commit64c27237a07129758e33f5f824ba5c33b7f57417 (patch)
tree4c0c0a9b6d282d600f2226e1b3510096b9d789dd /net
parent77a9939426f7a3f35f460afc9b11f1fe45955409 (diff)
parent49d8137a4039c63c834827f4bfe875e27bb9c521 (diff)
downloadlinux-64c27237a07129758e33f5f824ba5c33b7f57417.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts: drivers/net/ethernet/marvell/mvneta.c The mvneta.c conflict is a case of overlapping changes, a conversion to devm_ioremap_resource() vs. a conversion to netdev_alloc_pcpu_stats. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c4
-rw-r--r--net/8021q/vlan_dev.c6
-rw-r--r--net/bridge/br_device.c6
-rw-r--r--net/bridge/br_input.c11
-rw-r--r--net/bridge/br_vlan.c44
-rw-r--r--net/core/dev.c13
-rw-r--r--net/core/skbuff.c30
-rw-r--r--net/ipv4/gre_demux.c8
-rw-r--r--net/ipv4/ip_tunnel.c3
-rw-r--r--net/ipv4/ip_tunnel_core.c1
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv6/addrconf.c193
-rw-r--r--net/netfilter/nfnetlink_queue_core.c9
-rw-r--r--net/openvswitch/datapath.c6
-rw-r--r--net/openvswitch/flow.c26
-rw-r--r--net/unix/af_unix.c17
16 files changed, 257 insertions, 122 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ec9909935fb6..175273f38cb1 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -307,9 +307,11 @@ static void vlan_sync_address(struct net_device *dev,
static void vlan_transfer_features(struct net_device *dev,
struct net_device *vlandev)
{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
vlandev->gso_max_size = dev->gso_max_size;
- if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
vlandev->hard_header_len = dev->hard_header_len;
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index a78bebeca4d9..6f142f03716d 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -578,6 +578,9 @@ static int vlan_dev_init(struct net_device *dev)
dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
dev->gso_max_size = real_dev->gso_max_size;
+ if (dev->features & NETIF_F_VLAN_FEATURES)
+ netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
+
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
@@ -592,7 +595,8 @@ static int vlan_dev_init(struct net_device *dev)
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
+ if (vlan_hw_offload_capable(real_dev->features,
+ vlan_dev_priv(dev)->vlan_proto)) {
dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 0dd01a05bd59..3e2da2cb72db 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -49,14 +49,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
brstats->tx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
- if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
- goto out;
-
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
+ if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+ goto out;
+
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb, false);
else if (is_multicast_ether_addr(dest)) {
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 28d544627422..d0cca3c65f01 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ static int br_pass_frame_up(struct sk_buff *skb)
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+ struct net_port_vlans *pv;
u64_stats_update_begin(&brstats->syncp);
brstats->rx_packets++;
@@ -39,18 +40,18 @@ static int br_pass_frame_up(struct sk_buff *skb)
* packet is allowed except in promisc modue when someone
* may be running packet capture.
*/
+ pv = br_get_vlan_info(br);
if (!(brdev->flags & IFF_PROMISC) &&
- !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+ !br_allowed_egress(br, pv, skb)) {
kfree_skb(skb);
return NET_RX_DROP;
}
- skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
- if (!skb)
- return NET_RX_DROP;
-
indev = skb->dev;
skb->dev = brdev;
+ skb = br_handle_vlan(br, pv, skb);
+ if (!skb)
+ return NET_RX_DROP;
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
netif_receive_skb);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 5d5b101be102..91510712c7a7 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -119,22 +119,6 @@ static void __vlan_flush(struct net_port_vlans *v)
kfree_rcu(v, rcu);
}
-/* Strip the tag from the packet. Will return skb with tci set 0. */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
- if (skb->protocol != htons(ETH_P_8021Q)) {
- skb->vlan_tci = 0;
- return skb;
- }
-
- skb->vlan_tci = 0;
- skb = vlan_untag(skb);
- if (skb)
- skb->vlan_tci = 0;
-
- return skb;
-}
-
struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *pv,
struct sk_buff *skb)
@@ -144,13 +128,27 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
if (!br->vlan_enabled)
goto out;
+ /* Vlan filter table must be configured at this point. The
+ * only exception is the bridge is set in promisc mode and the
+ * packet is destined for the bridge device. In this case
+ * pass the packet as is.
+ */
+ if (!pv) {
+ if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+ goto out;
+ } else {
+ kfree_skb(skb);
+ return NULL;
+ }
+ }
+
/* At this point, we know that the frame was filtered and contains
* a valid vlan id. If the vlan id is set in the untagged bitmap,
* send untagged; otherwise, send tagged.
*/
br_vlan_get_tag(skb, &vid);
if (test_bit(vid, pv->untagged_bitmap))
- skb = br_vlan_untag(skb);
+ skb->vlan_tci = 0;
out:
return skb;
@@ -174,6 +172,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
if (!v)
return false;
+ /* If vlan tx offload is disabled on bridge device and frame was
+ * sent from vlan device on the bridge device, it does not have
+ * HW accelerated vlan tag.
+ */
+ if (unlikely(!vlan_tx_tag_present(skb) &&
+ (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)))) {
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ return false;
+ }
+
err = br_vlan_get_tag(skb, vid);
if (!*vid) {
u16 pvid = br_get_pvid(v);
diff --git a/net/core/dev.c b/net/core/dev.c
index 778b2036a9e7..cf92139b229c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2281,7 +2281,7 @@ out:
}
EXPORT_SYMBOL(skb_checksum_help);
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
@@ -2308,6 +2308,8 @@ __be16 skb_network_protocol(struct sk_buff *skb)
vlan_depth += VLAN_HLEN;
}
+ *depth = vlan_depth;
+
return type;
}
@@ -2321,12 +2323,13 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_offload *ptype;
- __be16 type = skb_network_protocol(skb);
+ int vlan_depth = skb->mac_len;
+ __be16 type = skb_network_protocol(skb, &vlan_depth);
if (unlikely(!type))
return ERR_PTR(-EINVAL);
- __skb_pull(skb, skb->mac_len);
+ __skb_pull(skb, vlan_depth);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2493,8 +2496,10 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
const struct net_device *dev,
netdev_features_t features)
{
+ int tmp;
+
if (skb->ip_summed != CHECKSUM_NONE &&
- !can_checksum_protocol(features, skb_network_protocol(skb))) {
+ !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
features &= ~NETIF_F_ALL_CSUM;
} else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3f14c638c2b1..30c7d35dd862 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2127,25 +2127,31 @@ EXPORT_SYMBOL_GPL(skb_zerocopy_headlen);
*
* The `hlen` as calculated by skb_zerocopy_headlen() specifies the
* headroom in the `to` buffer.
+ *
+ * Return value:
+ * 0: everything is OK
+ * -ENOMEM: couldn't orphan frags of @from due to lack of memory
+ * -EFAULT: skb_copy_bits() found some problem with skb geometry
*/
-void
-skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
{
int i, j = 0;
int plen = 0; /* length of skb->head fragment */
+ int ret;
struct page *page;
unsigned int offset;
BUG_ON(!from->head_frag && !hlen);
/* dont bother with small payloads */
- if (len <= skb_tailroom(to)) {
- skb_copy_bits(from, 0, skb_put(to, len), len);
- return;
- }
+ if (len <= skb_tailroom(to))
+ return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
- skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ if (unlikely(ret))
+ return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len);
@@ -2163,6 +2169,11 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
to->len += len + plen;
to->data_len += len + plen;
+ if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+ skb_tx_error(from);
+ return -ENOMEM;
+ }
+
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
if (!len)
break;
@@ -2173,6 +2184,8 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
j++;
}
skb_shinfo(to)->nr_frags = j;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(skb_zerocopy);
@@ -2866,8 +2879,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
int err = -ENOMEM;
int i = 0;
int pos;
+ int dummy;
- proto = skb_network_protocol(head_skb);
+ proto = skb_network_protocol(head_skb, &dummy);
if (unlikely(!proto))
return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 1863422fb7d5..250be7421ab3 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -182,6 +182,14 @@ static int gre_cisco_rcv(struct sk_buff *skb)
int i;
bool csum_err = false;
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ }
+#endif
+
if (parse_gre_header(skb, &tpi, &csum_err) < 0)
goto drop;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 66aaf506fbef..e77381d1df9a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -420,9 +420,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index b86f0a37fa7c..e0c2b1d2ea4e 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -108,6 +108,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
nf_reset(skb);
secpath_reset(skb);
skb_clear_hash_if_not_l4(skb);
+ skb_dst_drop(skb);
skb->vlan_tci = 0;
skb_set_queue_mapping(skb, 0);
skb->pkt_type = PACKET_HOST;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4555244607d0..6379894ec210 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,7 +2628,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
{
__be32 dest, src;
__u16 destp, srcp;
- long delta = tw->tw_ttd - jiffies;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
dest = tw->tw_daddr;
src = tw->tw_rcv_saddr;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 344e972426df..6c7fa0853fc7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
static DEFINE_SPINLOCK(addrconf_hash_lock);
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
u32 flags, u32 noflags);
static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev)
__in6_dev_put(idev);
}
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
{
- if (del_timer(&ifp->dad_timer))
+ if (cancel_delayed_work(&ifp->dad_work))
__in6_ifa_put(ifp);
}
@@ -261,12 +263,12 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
mod_timer(&idev->rs_timer, jiffies + when);
}
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
- unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+ unsigned long delay)
{
- if (!timer_pending(&ifp->dad_timer))
+ if (!delayed_work_pending(&ifp->dad_work))
in6_ifa_hold(ifp);
- mod_timer(&ifp->dad_timer, jiffies + when);
+ mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
}
static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
in6_dev_put(ifp->idev);
- if (del_timer(&ifp->dad_timer))
- pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+ if (cancel_delayed_work(&ifp->dad_work))
+ pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+ ifp);
if (ifp->state != INET6_IFADDR_STATE_DEAD) {
pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
spin_lock_init(&ifa->lock);
spin_lock_init(&ifa->state_lock);
- setup_timer(&ifa->dad_timer, addrconf_dad_timer,
- (unsigned long)ifa);
+ INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
unsigned long expires;
+ ASSERT_RTNL();
+
spin_lock_bh(&ifp->state_lock);
state = ifp->state;
ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
write_unlock_bh(&ifp->idev->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ipv6_ifa_notify(RTM_DELADDR, ifp);
@@ -1604,7 +1608,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
{
if (ifp->flags&IFA_F_PERMANENT) {
spin_lock_bh(&ifp->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ifp->flags |= IFA_F_TENTATIVE;
if (dad_failed)
ifp->flags |= IFA_F_DADFAILED;
@@ -1625,20 +1629,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
spin_unlock_bh(&ifp->lock);
}
ipv6_del_addr(ifp);
- } else
+ } else {
ipv6_del_addr(ifp);
+ }
}
static int addrconf_dad_end(struct inet6_ifaddr *ifp)
{
int err = -ENOENT;
- spin_lock(&ifp->state_lock);
+ spin_lock_bh(&ifp->state_lock);
if (ifp->state == INET6_IFADDR_STATE_DAD) {
ifp->state = INET6_IFADDR_STATE_POSTDAD;
err = 0;
}
- spin_unlock(&ifp->state_lock);
+ spin_unlock_bh(&ifp->state_lock);
return err;
}
@@ -1671,7 +1676,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
}
}
- addrconf_dad_stop(ifp, 1);
+ spin_lock_bh(&ifp->state_lock);
+ /* transition from _POSTDAD to _ERRDAD */
+ ifp->state = INET6_IFADDR_STATE_ERRDAD;
+ spin_unlock_bh(&ifp->state_lock);
+
+ addrconf_mod_dad_work(ifp, 0);
}
/* Join to solicited addr multicast group. */
@@ -1680,6 +1690,8 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1691,6 +1703,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1701,6 +1715,9 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1712,6 +1729,9 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2271,11 +2291,13 @@ ok:
return;
}
- ifp->flags |= IFA_F_MANAGETEMPADDR;
update_lft = 0;
create = 1;
+ spin_lock_bh(&ifp->lock);
+ ifp->flags |= IFA_F_MANAGETEMPADDR;
ifp->cstamp = jiffies;
ifp->tokenized = tokenized;
+ spin_unlock_bh(&ifp->lock);
addrconf_dad_start(ifp);
}
@@ -2326,7 +2348,7 @@ ok:
create, now);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify();
}
}
inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2475,7 +2497,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
true, jiffies);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -3011,7 +3033,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
hlist_for_each_entry_rcu(ifa, h, addr_lst) {
if (ifa->idev == idev) {
hlist_del_init_rcu(&ifa->addr_lst);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
goto restart;
}
}
@@ -3049,7 +3071,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
while (!list_empty(&idev->addr_list)) {
ifa = list_first_entry(&idev->addr_list,
struct inet6_ifaddr, if_list);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
list_del(&ifa->if_list);
@@ -3148,10 +3170,10 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
ifp->dad_probes = idev->cnf.dad_transmits;
- addrconf_mod_dad_timer(ifp, rand_num);
+ addrconf_mod_dad_work(ifp, rand_num);
}
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
@@ -3203,25 +3225,68 @@ out:
read_unlock_bh(&idev->lock);
}
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
{
- struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+ bool begin_dad = false;
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+ ifp->state = INET6_IFADDR_STATE_PREDAD;
+ begin_dad = true;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (begin_dad)
+ addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+ struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+ struct inet6_ifaddr,
+ dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ enum {
+ DAD_PROCESS,
+ DAD_BEGIN,
+ DAD_ABORT,
+ } action = DAD_PROCESS;
+
+ rtnl_lock();
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+ action = DAD_BEGIN;
+ ifp->state = INET6_IFADDR_STATE_DAD;
+ } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+ action = DAD_ABORT;
+ ifp->state = INET6_IFADDR_STATE_POSTDAD;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (action == DAD_BEGIN) {
+ addrconf_dad_begin(ifp);
+ goto out;
+ } else if (action == DAD_ABORT) {
+ addrconf_dad_stop(ifp, 1);
+ goto out;
+ }
+
if (!ifp->dad_probes && addrconf_dad_end(ifp))
goto out;
- write_lock(&idev->lock);
+ write_lock_bh(&idev->lock);
if (idev->dead || !(idev->if_flags & IF_READY)) {
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
spin_lock(&ifp->lock);
if (ifp->state == INET6_IFADDR_STATE_DEAD) {
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
@@ -3232,7 +3297,7 @@ static void addrconf_dad_timer(unsigned long data)
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
addrconf_dad_completed(ifp);
@@ -3240,16 +3305,17 @@ static void addrconf_dad_timer(unsigned long data)
}
ifp->dad_probes--;
- addrconf_mod_dad_timer(ifp,
- NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+ addrconf_mod_dad_work(ifp,
+ NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
/* 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);
out:
in6_ifa_put(ifp);
+ rtnl_unlock();
}
/* ifp->idev must be at least read locked */
@@ -3276,7 +3342,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
struct in6_addr lladdr;
bool send_rs, send_mld;
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
/*
* Configure the address for reception. Now it is valid.
@@ -3517,23 +3583,23 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
* Periodic address status verification
*/
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
{
unsigned long now, next, next_sec, next_sched;
struct inet6_ifaddr *ifp;
int i;
+ ASSERT_RTNL();
+
rcu_read_lock_bh();
- spin_lock(&addrconf_verify_lock);
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
restart:
- hlist_for_each_entry_rcu_bh(ifp,
- &inet6_addr_lst[i], addr_lst) {
+ hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
unsigned long age;
/* When setting preferred_lft to a value not zero or
@@ -3628,13 +3694,22 @@ restart:
ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
now, next, next_sec, next_sched);
-
- addr_chk_timer.expires = next_sched;
- add_timer(&addr_chk_timer);
- spin_unlock(&addrconf_verify_lock);
+ mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
rcu_read_unlock_bh();
}
+static void addrconf_verify_work(struct work_struct *w)
+{
+ rtnl_lock();
+ addrconf_verify_rtnl();
+ rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+ mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
struct in6_addr **peer_pfx)
{
@@ -3691,6 +3766,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
bool was_managetempaddr;
bool had_prefixroute;
+ ASSERT_RTNL();
+
if (!valid_lft || (prefered_lft > valid_lft))
return -EINVAL;
@@ -3756,7 +3833,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
!was_managetempaddr, jiffies);
}
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4386,6 +4463,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
bool update_rs = false;
struct in6_addr ll_addr;
+ ASSERT_RTNL();
+
if (token == NULL)
return -EINVAL;
if (ipv6_addr_any(token))
@@ -4434,7 +4513,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
}
write_unlock_bh(&idev->lock);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4636,6 +4715,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
struct net *net = dev_net(ifp->idev->dev);
+ if (event)
+ ASSERT_RTNL();
+
inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
switch (event) {
@@ -5244,6 +5326,12 @@ int __init addrconf_init(void)
if (err < 0)
goto out_addrlabel;
+ addrconf_wq = create_workqueue("ipv6_addrconf");
+ if (!addrconf_wq) {
+ err = -ENOMEM;
+ goto out_nowq;
+ }
+
/* The addrconf netdev notifier requires that loopback_dev
* has it's ipv6 private information allocated and setup
* before it can bring up and give link-local addresses
@@ -5274,7 +5362,7 @@ int __init addrconf_init(void)
register_netdevice_notifier(&ipv6_dev_notf);
- addrconf_verify(0);
+ addrconf_verify();
rtnl_af_register(&inet6_ops);
@@ -5302,6 +5390,8 @@ errout:
rtnl_af_unregister(&inet6_ops);
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
+ destroy_workqueue(addrconf_wq);
+out_nowq:
unregister_pernet_subsys(&addrconf_ops);
out_addrlabel:
ipv6_addr_label_cleanup();
@@ -5337,7 +5427,8 @@ void addrconf_cleanup(void)
for (i = 0; i < IN6_ADDR_HSIZE; i++)
WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
spin_unlock_bh(&addrconf_hash_lock);
-
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
rtnl_unlock();
+
+ destroy_workqueue(addrconf_wq);
}
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index f072fe803510..108120f216b1 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -354,13 +354,16 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
GFP_ATOMIC);
- if (!skb)
+ if (!skb) {
+ skb_tx_error(entskb);
return NULL;
+ }
nlh = nlmsg_put(skb, 0, 0,
NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
sizeof(struct nfgenmsg), 0);
if (!nlh) {
+ skb_tx_error(entskb);
kfree_skb(skb);
return NULL;
}
@@ -488,13 +491,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
nla->nla_type = NFQA_PAYLOAD;
nla->nla_len = nla_attr_size(data_len);
- skb_zerocopy(skb, entskb, data_len, hlen);
+ if (skb_zerocopy(skb, entskb, data_len, hlen))
+ goto nla_put_failure;
}
nlh->nlmsg_len = skb->len;
return skb;
nla_put_failure:
+ skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
return NULL;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 48bbcd94631e..a3276e3c4feb 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -464,7 +464,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
}
nla->nla_len = nla_attr_size(skb->len);
- skb_zerocopy(user_skb, skb, skb->len, hlen);
+ err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+ if (err)
+ goto out;
/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
@@ -478,6 +480,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
out:
+ if (err)
+ skb_tx_error(skb);
kfree_skb(nskb);
return err;
}
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index dda451f4429c..2998989e76db 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -103,30 +103,24 @@ static void stats_read(struct flow_stats *stats,
void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
unsigned long *used, __be16 *tcp_flags)
{
- int cpu, cur_cpu;
+ int cpu;
*used = 0;
*tcp_flags = 0;
memset(ovs_stats, 0, sizeof(*ovs_stats));
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
} else {
- cur_cpu = get_cpu();
for_each_possible_cpu(cpu) {
struct flow_stats *stats;
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
stats_read(stats, ovs_stats, used, tcp_flags);
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static void stats_reset(struct flow_stats *stats)
@@ -141,25 +135,17 @@ static void stats_reset(struct flow_stats *stats)
void ovs_flow_stats_clear(struct sw_flow *flow)
{
- int cpu, cur_cpu;
+ int cpu;
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_reset(flow->stats.stat);
} else {
- cur_cpu = get_cpu();
-
for_each_possible_cpu(cpu) {
-
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static int check_header(struct sk_buff *skb, int len)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ce6ec6c2f4de..94404f19f9de 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1787,8 +1787,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
goto out;
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
@@ -1913,6 +1916,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
struct unix_sock *u = unix_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
int copied = 0;
+ int noblock = flags & MSG_DONTWAIT;
int check_creds = 0;
int target;
int err = 0;
@@ -1928,7 +1932,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
goto out;
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
- timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+ timeo = sock_rcvtimeo(sk, noblock);
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
@@ -1940,8 +1944,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
}
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(timeo);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}