aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c26
-rw-r--r--net/core/dev.c120
-rw-r--r--net/core/dev_addr_lists.c210
-rw-r--r--net/core/dst.c9
-rw-r--r--net/core/ethtool.c29
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/filter.c5
-rw-r--r--net/core/flow.c42
-rw-r--r--net/core/flow_dissector.c68
-rw-r--r--net/core/neighbour.c55
-rw-r--r--net/core/net-procfs.c2
-rw-r--r--net/core/netpoll.c22
-rw-r--r--net/core/rtnetlink.c178
-rw-r--r--net/core/scm.c20
-rw-r--r--net/core/secure_seq.c4
-rw-r--r--net/core/skbuff.c93
-rw-r--r--net/core/sock.c22
-rw-r--r--net/core/sock_diag.c33
-rw-r--r--net/core/utils.c5
19 files changed, 635 insertions, 312 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 368f9c3f9dc..b71423db778 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -78,9 +78,10 @@ static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int syn
return autoremove_wake_function(wait, mode, sync, key);
}
/*
- * Wait for a packet..
+ * Wait for the last received packet to be different from skb
*/
-static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
+static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+ const struct sk_buff *skb)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
@@ -92,7 +93,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
if (error)
goto out_err;
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (sk->sk_receive_queue.prev != skb)
goto out;
/* Socket shut down? */
@@ -131,9 +132,9 @@ out_noerr:
* __skb_recv_datagram - Receive a datagram skbuff
* @sk: socket
* @flags: MSG_ flags
+ * @peeked: returns non-zero if this packet has been seen before
* @off: an offset in bytes to peek skb from. Returns an offset
* within an skb where data actually starts
- * @peeked: returns non-zero if this packet has been seen before
* @err: error code returned
*
* Get a datagram skbuff, understands the peeking, nonblocking wakeups
@@ -161,7 +162,7 @@ out_noerr:
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
int *peeked, int *off, int *err)
{
- struct sk_buff *skb;
+ struct sk_buff *skb, *last;
long timeo;
/*
* Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -182,13 +183,17 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
*/
unsigned long cpu_flags;
struct sk_buff_head *queue = &sk->sk_receive_queue;
+ int _off = *off;
+ last = (struct sk_buff *)queue;
spin_lock_irqsave(&queue->lock, cpu_flags);
skb_queue_walk(queue, skb) {
+ last = skb;
*peeked = skb->peeked;
if (flags & MSG_PEEK) {
- if (*off >= skb->len && skb->len) {
- *off -= skb->len;
+ if (_off >= skb->len && (skb->len || _off ||
+ skb->peeked)) {
+ _off -= skb->len;
continue;
}
skb->peeked = 1;
@@ -197,6 +202,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
__skb_unlink(skb, queue);
spin_unlock_irqrestore(&queue->lock, cpu_flags);
+ *off = _off;
return skb;
}
spin_unlock_irqrestore(&queue->lock, cpu_flags);
@@ -206,7 +212,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
if (!timeo)
goto no_packet;
- } while (!wait_for_packet(sk, err, &timeo));
+ } while (!wait_for_more_packets(sk, err, &timeo, last));
return NULL;
@@ -749,7 +755,9 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= POLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
diff --git a/net/core/dev.c b/net/core/dev.c
index b24ab0e98eb..4040673f806 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -200,7 +200,7 @@ static inline void rps_unlock(struct softnet_data *sd)
}
/* Device list insertion */
-static int list_netdevice(struct net_device *dev)
+static void list_netdevice(struct net_device *dev)
{
struct net *net = dev_net(dev);
@@ -214,8 +214,6 @@ static int list_netdevice(struct net_device *dev)
write_unlock_bh(&dev_base_lock);
dev_base_seq_inc(net);
-
- return 0;
}
/* Device list removal
@@ -2210,30 +2208,40 @@ out:
}
EXPORT_SYMBOL(skb_checksum_help);
-/**
- * skb_mac_gso_segment - mac layer segmentation handler.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- */
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
+__be16 skb_network_protocol(struct sk_buff *skb)
{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
- while (type == htons(ETH_P_8021Q)) {
+ while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
struct vlan_hdr *vh;
if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
- return ERR_PTR(-EINVAL);
+ return 0;
vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
}
+ return type;
+}
+
+/**
+ * skb_mac_gso_segment - mac layer segmentation handler.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ */
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_offload *ptype;
+ __be16 type = skb_network_protocol(skb);
+
+ if (unlikely(!type))
+ return ERR_PTR(-EINVAL);
+
__skb_pull(skb, skb->mac_len);
rcu_read_lock();
@@ -2400,24 +2408,12 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
return 0;
}
-static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
-{
- return ((features & NETIF_F_GEN_CSUM) ||
- ((features & NETIF_F_V4_CSUM) &&
- protocol == htons(ETH_P_IP)) ||
- ((features & NETIF_F_V6_CSUM) &&
- protocol == htons(ETH_P_IPV6)) ||
- ((features & NETIF_F_FCOE_CRC) &&
- protocol == htons(ETH_P_FCOE)));
-}
-
static netdev_features_t harmonize_features(struct sk_buff *skb,
__be16 protocol, netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
- features &= ~NETIF_F_SG;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
@@ -2433,20 +2429,22 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
- if (protocol == htons(ETH_P_8021Q)) {
+ if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
return harmonize_features(skb, protocol, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);
+ features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
- if (protocol != htons(ETH_P_8021Q)) {
+ if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) {
return harmonize_features(skb, protocol, features);
} else {
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
- NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX;
+ NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX;
return harmonize_features(skb, protocol, features);
}
}
@@ -2487,8 +2485,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
- !(features & NETIF_F_HW_VLAN_TX)) {
- skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
if (unlikely(!skb))
goto out;
@@ -2547,13 +2546,6 @@ gso:
skb->next = nskb->next;
nskb->next = NULL;
- /*
- * If device doesn't need nskb->dst, release it right now while
- * its hot in this cpu cache
- */
- if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
- skb_dst_drop(nskb);
-
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(nskb, dev);
@@ -2573,8 +2565,11 @@ gso:
} while (skb->next);
out_kfree_gso_skb:
- if (likely(skb->next == NULL))
+ if (likely(skb->next == NULL)) {
skb->destructor = DEV_GSO_CB(skb)->destructor;
+ consume_skb(skb);
+ return rc;
+ }
out_kfree_skb:
kfree_skb(skb);
out:
@@ -2592,6 +2587,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
*/
if (shinfo->gso_size) {
unsigned int hdr_len;
+ u16 gso_segs = shinfo->gso_segs;
/* mac layer + network layer */
hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
@@ -2601,7 +2597,12 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
hdr_len += tcp_hdrlen(skb);
else
hdr_len += sizeof(struct udphdr);
- qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len;
+
+ if (shinfo->gso_type & SKB_GSO_DODGY)
+ gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
+ shinfo->gso_size);
+
+ qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
}
}
@@ -3329,7 +3330,7 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
- * Unregister a receive hander from a device.
+ * Unregister a receive handler from a device.
*
* The caller must hold the rtnl_mutex.
*/
@@ -3358,6 +3359,7 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
case __constant_htons(ETH_P_IP):
case __constant_htons(ETH_P_IPV6):
case __constant_htons(ETH_P_8021Q):
+ case __constant_htons(ETH_P_8021AD):
return true;
default:
return false;
@@ -3398,7 +3400,8 @@ another_round:
__this_cpu_inc(softnet_data.processed);
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+ skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
goto unlock;
@@ -4066,6 +4069,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
napi->gro_list = NULL;
napi->skb = NULL;
napi->poll = poll;
+ if (weight > NAPI_POLL_WEIGHT)
+ pr_err_once("netif_napi_add() called with weight %d on device %s\n",
+ weight, dev->name);
napi->weight = weight;
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
@@ -4927,20 +4933,25 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
- /* Fix illegal SG+CSUM combinations. */
- if ((features & NETIF_F_SG) &&
- !(features & NETIF_F_ALL_CSUM)) {
- netdev_dbg(dev,
- "Dropping NETIF_F_SG since no checksum feature.\n");
- features &= ~NETIF_F_SG;
- }
-
/* TSO requires that SG is present as well. */
if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) {
netdev_dbg(dev, "Dropping TSO features since no SG feature.\n");
features &= ~NETIF_F_ALL_TSO;
}
+ if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IP_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO;
+ features &= ~NETIF_F_TSO_ECN;
+ }
+
+ if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IPV6_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO6;
+ }
+
/* TSO ECN requires that TSO is present as well. */
if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
features &= ~NETIF_F_TSO_ECN;
@@ -5171,7 +5182,8 @@ int register_netdevice(struct net_device *dev)
}
}
- if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) &&
+ if (((dev->hw_features | dev->features) &
+ NETIF_F_HW_VLAN_CTAG_FILTER) &&
(!dev->netdev_ops->ndo_vlan_rx_add_vid ||
!dev->netdev_ops->ndo_vlan_rx_kill_vid)) {
netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n");
@@ -5208,6 +5220,10 @@ int register_netdevice(struct net_device *dev)
*/
dev->vlan_features |= NETIF_F_HIGHDMA;
+ /* Make NETIF_F_SG inheritable to tunnel devices.
+ */
+ dev->hw_enc_features |= NETIF_F_SG;
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index abdc9e6ef33..c013f38482a 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -22,7 +22,8 @@
static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
const unsigned char *addr, int addr_len,
- unsigned char addr_type, bool global)
+ unsigned char addr_type, bool global,
+ bool sync)
{
struct netdev_hw_addr *ha;
int alloc_size;
@@ -37,7 +38,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
ha->type = addr_type;
ha->refcount = 1;
ha->global_use = global;
- ha->synced = 0;
+ ha->synced = sync;
list_add_tail_rcu(&ha->list, &list->list);
list->count++;
@@ -46,7 +47,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
const unsigned char *addr, int addr_len,
- unsigned char addr_type, bool global)
+ unsigned char addr_type, bool global, bool sync)
{
struct netdev_hw_addr *ha;
@@ -63,43 +64,62 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
else
ha->global_use = true;
}
+ if (sync) {
+ if (ha->synced)
+ return 0;
+ else
+ ha->synced = true;
+ }
ha->refcount++;
return 0;
}
}
- return __hw_addr_create_ex(list, addr, addr_len, addr_type, global);
+ return __hw_addr_create_ex(list, addr, addr_len, addr_type, global,
+ sync);
}
static int __hw_addr_add(struct netdev_hw_addr_list *list,
const unsigned char *addr, int addr_len,
unsigned char addr_type)
{
- return __hw_addr_add_ex(list, addr, addr_len, addr_type, false);
+ return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false);
+}
+
+static int __hw_addr_del_entry(struct netdev_hw_addr_list *list,
+ struct netdev_hw_addr *ha, bool global,
+ bool sync)
+{
+ if (global && !ha->global_use)
+ return -ENOENT;
+
+ if (sync && !ha->synced)
+ return -ENOENT;
+
+ if (global)
+ ha->global_use = false;
+
+ if (sync)
+ ha->synced = false;
+
+ if (--ha->refcount)
+ return 0;
+ list_del_rcu(&ha->list);
+ kfree_rcu(ha, rcu_head);
+ list->count--;
+ return 0;
}
static int __hw_addr_del_ex(struct netdev_hw_addr_list *list,
const unsigned char *addr, int addr_len,
- unsigned char addr_type, bool global)
+ unsigned char addr_type, bool global, bool sync)
{
struct netdev_hw_addr *ha;
list_for_each_entry(ha, &list->list, list) {
if (!memcmp(ha->addr, addr, addr_len) &&
- (ha->type == addr_type || !addr_type)) {
- if (global) {
- if (!ha->global_use)
- break;
- else
- ha->global_use = false;
- }
- if (--ha->refcount)
- return 0;
- list_del_rcu(&ha->list);
- kfree_rcu(ha, rcu_head);
- list->count--;
- return 0;
- }
+ (ha->type == addr_type || !addr_type))
+ return __hw_addr_del_entry(list, ha, global, sync);
}
return -ENOENT;
}
@@ -108,7 +128,57 @@ static int __hw_addr_del(struct netdev_hw_addr_list *list,
const unsigned char *addr, int addr_len,
unsigned char addr_type)
{
- return __hw_addr_del_ex(list, addr, addr_len, addr_type, false);
+ return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false);
+}
+
+static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr *ha,
+ int addr_len)
+{
+ int err;
+
+ err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type,
+ false, true);
+ if (err)
+ return err;
+ ha->sync_cnt++;
+ ha->refcount++;
+
+ return 0;
+}
+
+static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ struct netdev_hw_addr *ha,
+ int addr_len)
+{
+ int err;
+
+ err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type,
+ false, true);
+ if (err)
+ return;
+ ha->sync_cnt--;
+ __hw_addr_del_entry(from_list, ha, false, true);
+}
+
+static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ int addr_len)
+{
+ int err = 0;
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+ if (ha->sync_cnt == ha->refcount) {
+ __hw_addr_unsync_one(to_list, from_list, ha, addr_len);
+ } else {
+ err = __hw_addr_sync_one(to_list, ha, addr_len);
+ if (err)
+ break;
+ }
+ }
+ return err;
}
int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
@@ -152,6 +222,11 @@ void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
}
EXPORT_SYMBOL(__hw_addr_del_multiple);
+/* This function only works where there is a strict 1-1 relationship
+ * between source and destionation of they synch. If you ever need to
+ * sync addresses to more then 1 destination, you need to use
+ * __hw_addr_sync_multiple().
+ */
int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list,
int addr_len)
@@ -160,17 +235,12 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr *ha, *tmp;
list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
- if (!ha->synced) {
- err = __hw_addr_add(to_list, ha->addr,
- addr_len, ha->type);
+ if (!ha->sync_cnt) {
+ err = __hw_addr_sync_one(to_list, ha, addr_len);
if (err)
break;
- ha->synced++;
- ha->refcount++;
- } else if (ha->refcount == 1) {
- __hw_addr_del(to_list, ha->addr, addr_len, ha->type);
- __hw_addr_del(from_list, ha->addr, addr_len, ha->type);
- }
+ } else if (ha->refcount == 1)
+ __hw_addr_unsync_one(to_list, from_list, ha, addr_len);
}
return err;
}
@@ -183,13 +253,8 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr *ha, *tmp;
list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
- if (ha->synced) {
- __hw_addr_del(to_list, ha->addr,
- addr_len, ha->type);
- ha->synced--;
- __hw_addr_del(from_list, ha->addr,
- addr_len, ha->type);
- }
+ if (ha->sync_cnt)
+ __hw_addr_unsync_one(to_list, from_list, ha, addr_len);
}
}
EXPORT_SYMBOL(__hw_addr_unsync);
@@ -406,7 +471,7 @@ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr)
}
}
err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_UNICAST, true);
+ NETDEV_HW_ADDR_T_UNICAST, true, false);
if (!err)
__dev_set_rx_mode(dev);
out:
@@ -469,7 +534,8 @@ EXPORT_SYMBOL(dev_uc_del);
* locked by netif_addr_lock_bh.
*
* This function is intended to be called from the dev->set_rx_mode
- * function of layered software devices.
+ * function of layered software devices. This function assumes that
+ * addresses will only ever be synced to the @to devices and no other.
*/
int dev_uc_sync(struct net_device *to, struct net_device *from)
{
@@ -488,6 +554,36 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
EXPORT_SYMBOL(dev_uc_sync);
/**
+ * dev_uc_sync_multiple - Synchronize device's unicast list to another
+ * device, but allow for multiple calls to sync to multiple devices.
+ * @to: destination device
+ * @from: source device
+ *
+ * Add newly added addresses to the destination device and release
+ * addresses that have been deleted from the source. The source device
+ * must be locked by netif_addr_lock_bh.
+ *
+ * This function is intended to be called from the dev->set_rx_mode
+ * function of layered software devices. It allows for a single source
+ * device to be synced to multiple destination devices.
+ */
+int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
+{
+ int err = 0;
+
+ if (to->addr_len != from->addr_len)
+ return -EINVAL;
+
+ netif_addr_lock_nested(to);
+ err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
+ if (!err)
+ __dev_set_rx_mode(to);
+ netif_addr_unlock(to);
+ return err;
+}
+EXPORT_SYMBOL(dev_uc_sync_multiple);
+
+/**
* dev_uc_unsync - Remove synchronized addresses from the destination device
* @to: destination device
* @from: source device
@@ -559,7 +655,7 @@ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr)
}
}
err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_MULTICAST, true);
+ NETDEV_HW_ADDR_T_MULTICAST, true, false);
if (!err)
__dev_set_rx_mode(dev);
out:
@@ -575,7 +671,7 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr,
netif_addr_lock_bh(dev);
err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_MULTICAST, global);
+ NETDEV_HW_ADDR_T_MULTICAST, global, false);
if (!err)
__dev_set_rx_mode(dev);
netif_addr_unlock_bh(dev);
@@ -615,7 +711,7 @@ static int __dev_mc_del(struct net_device *dev, const unsigned char *addr,
netif_addr_lock_bh(dev);
err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_MULTICAST, global);
+ NETDEV_HW_ADDR_T_MULTICAST, global, false);
if (!err)
__dev_set_rx_mode(dev);
netif_addr_unlock_bh(dev);
@@ -679,6 +775,36 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
EXPORT_SYMBOL(dev_mc_sync);
/**
+ * dev_mc_sync_multiple - Synchronize device's unicast list to another
+ * device, but allow for multiple calls to sync to multiple devices.
+ * @to: destination device
+ * @from: source device
+ *
+ * Add newly added addresses to the destination device and release
+ * addresses that have no users left. The source device must be
+ * locked by netif_addr_lock_bh.
+ *
+ * This function is intended to be called from the ndo_set_rx_mode
+ * function of layered software devices. It allows for a single
+ * source device to be synced to multiple destination devices.
+ */
+int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
+{
+ int err = 0;
+
+ if (to->addr_len != from->addr_len)
+ return -EINVAL;
+
+ netif_addr_lock_nested(to);
+ err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
+ if (!err)
+ __dev_set_rx_mode(to);
+ netif_addr_unlock(to);
+ return err;
+}
+EXPORT_SYMBOL(dev_mc_sync_multiple);
+
+/**
* dev_mc_unsync - Remove synchronized addresses from the destination device
* @to: destination device
* @from: source device
diff --git a/net/core/dst.c b/net/core/dst.c
index 35fd12f1a69..df9cc810ec8 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -320,27 +320,28 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
EXPORT_SYMBOL(__dst_destroy_metrics_generic);
/**
- * skb_dst_set_noref - sets skb dst, without a reference
+ * __skb_dst_set_noref - sets skb dst, without a reference
* @skb: buffer
* @dst: dst entry
+ * @force: if force is set, use noref version even for DST_NOCACHE entries
*
* Sets skb dst, assuming a reference was not taken on dst
* skb_dst_drop() should not dst_release() this dst
*/
-void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
+void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
{
WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
/* If dst not in cache, we must take a reference, because
* dst_release() will destroy dst as soon as its refcount becomes zero
*/
- if (unlikely(dst->flags & DST_NOCACHE)) {
+ if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
dst_hold(dst);
skb_dst_set(skb, dst);
} else {
skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
}
}
-EXPORT_SYMBOL(skb_dst_set_noref);
+EXPORT_SYMBOL(__skb_dst_set_noref);
/* Dirty hack. We did it in 2.2 (in __dst_free),
* we have _very_ good reasons not to repeat
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 3e9b2c3e30f..5a934ef90f8 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -60,10 +60,13 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6",
[NETIF_F_HIGHDMA_BIT] = "highdma",
[NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist",
- [NETIF_F_HW_VLAN_TX_BIT] = "tx-vlan-hw-insert",
+ [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-ctag-hw-insert",
- [NETIF_F_HW_VLAN_RX_BIT] = "rx-vlan-hw-parse",
- [NETIF_F_HW_VLAN_FILTER_BIT] = "rx-vlan-filter",
+ [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-ctag-hw-parse",
+ [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-ctag-filter",
+ [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert",
+ [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse",
+ [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter",
[NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged",
[NETIF_F_GSO_BIT] = "tx-generic-segmentation",
[NETIF_F_LLTX_BIT] = "tx-lockless",
@@ -78,6 +81,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation",
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
+ [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
@@ -266,18 +270,19 @@ static int ethtool_set_one_feature(struct net_device *dev,
#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \
ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH)
-#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_RX | \
- NETIF_F_HW_VLAN_TX | NETIF_F_NTUPLE | NETIF_F_RXHASH)
+#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_CTAG_RX | \
+ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_NTUPLE | \
+ NETIF_F_RXHASH)
static u32 __ethtool_get_flags(struct net_device *dev)
{
u32 flags = 0;
- if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO;
- if (dev->features & NETIF_F_HW_VLAN_RX) flags |= ETH_FLAG_RXVLAN;
- if (dev->features & NETIF_F_HW_VLAN_TX) flags |= ETH_FLAG_TXVLAN;
- if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE;
- if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH;
+ if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO;
+ if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN;
+ if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN;
+ if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE;
+ if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH;
return flags;
}
@@ -290,8 +295,8 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
return -EINVAL;
if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO;
- if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_RX;
- if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_TX;
+ if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_CTAG_RX;
+ if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_CTAG_TX;
if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE;
if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 58a4ba27dfe..d5a9f8ead0d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -266,7 +266,7 @@ errout:
return err;
}
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -415,7 +415,7 @@ errout:
return err;
}
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
diff --git a/net/core/filter.c b/net/core/filter.c
index 2e20b55a783..dad2a178f9f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -348,6 +348,9 @@ load_b:
case BPF_S_ANC_VLAN_TAG_PRESENT:
A = !!vlan_tx_tag_present(skb);
continue;
+ case BPF_S_ANC_PAY_OFFSET:
+ A = __skb_get_poff(skb);
+ continue;
case BPF_S_ANC_NLATTR: {
struct nlattr *nla;
@@ -612,6 +615,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
ANCILLARY(ALU_XOR_X);
ANCILLARY(VLAN_TAG);
ANCILLARY(VLAN_TAG_PRESENT);
+ ANCILLARY(PAY_OFFSET);
}
/* ancillary operation unknown or unsupported */
@@ -814,6 +818,7 @@ static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
[BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN,
[BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND,
[BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND,
diff --git a/net/core/flow.c b/net/core/flow.c
index 2bfd081c59f..7102f166482 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -323,6 +323,24 @@ static void flow_cache_flush_tasklet(unsigned long data)
complete(&info->completion);
}
+/*
+ * Return whether a cpu needs flushing. Conservatively, we assume
+ * the presence of any entries means the core may require flushing,
+ * since the flow_cache_ops.check() function may assume it's running
+ * on the same core as the per-cpu cache component.
+ */
+static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
+{
+ struct flow_cache_percpu *fcp;
+ int i;
+
+ fcp = per_cpu_ptr(fc->percpu, cpu);
+ for (i = 0; i < flow_cache_hash_size(fc); i++)
+ if (!hlist_empty(&fcp->hash_table[i]))
+ return 0;
+ return 1;
+}
+
static void flow_cache_flush_per_cpu(void *data)
{
struct flow_flush_info *info = data;
@@ -337