summaryrefslogtreecommitdiffstats
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 368f9c3..b71423d 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 b24ab0e9..4040673 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 abdc9e6..c013f38 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 35fd12f..df9cc81 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 3e9b2c3..5a934ef 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 58a4ba2..d5a9f8e 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 2e20b55..dad2a17 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 2bfd081..7102f16 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;
@@ -337,22 +355,40 @@ void flow_cache_flush(void)
{
struct flow_flush_info info;
static DEFINE_MUTEX(flow_flush_sem);
+ cpumask_var_t mask;
+ int i, self;
+
+ /* Track which cpus need flushing to avoid disturbing all cores. */
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return;
+ cpumask_clear(mask);
/* Don't want cpus going down or up during this. */
get_online_cpus();
mutex_lock(&flow_flush_sem);
info.cache = &flow_cache_global;
- atomic_set(&info.cpuleft, num_online_cpus());
+ for_each_online_cpu(i)
+ if (!flow_cache_percpu_empty(info.cache, i))
+ cpumask_set_cpu(i, mask);
+ atomic_set(&info.cpuleft, cpumask_weight(mask));
+ if (atomic_read(&info.cpuleft) == 0)
+ goto done;
+
init_completion(&info.completion);
local_bh_disable();
- smp_call_function(flow_cache_flush_per_cpu, &info, 0);
- flow_cache_flush_tasklet((unsigned long)&info);
+ self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
+ on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
+ if (self)
+ flow_cache_flush_tasklet((unsigned long)&info);
local_bh_enable();
wait_for_completion(&info.completion);
+
+done:
mutex_unlock(&flow_flush_sem);
put_online_cpus();
+ free_cpumask_var(mask);
}
static void flow_cache_flush_task(struct work_struct *work)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e187bf0..00ee068 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,10 @@
#include <linux/if_vlan.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <linux/igmp.h>
+#include <linux/icmp.h>
+#include <linux/sctp.h>
+#include <linux/dccp.h>
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
@@ -119,6 +123,17 @@ ipv6:
nhoff += 4;
if (hdr->flags & GRE_SEQ)
nhoff += 4;
+ if (proto == htons(ETH_P_TEB)) {
+ const struct ethhdr *eth;
+ struct ethhdr _eth;
+
+ eth = skb_header_pointer(skb, nhoff,
+ sizeof(_eth), &_eth);
+ if (!eth)
+ return false;
+ proto = eth->h_proto;
+ nhoff += sizeof(*eth);
+ }
goto again;
}
break;
@@ -217,6 +232,59 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
}
EXPORT_SYMBOL(__skb_tx_hash);
+/* __skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 __skb_get_poff(const struct sk_buff *skb)
+{
+ struct flow_keys keys;
+ u32 poff = 0;
+
+ if (!skb_flow_dissect(skb, &keys))
+ return 0;
+
+ poff += keys.thoff;
+ switch (keys.ip_proto) {
+ case IPPROTO_TCP: {
+ const struct tcphdr *tcph;
+ struct tcphdr _tcph;
+
+ tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+ if (!tcph)
+ return poff;
+
+ poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4);
+ break;
+ }
+ case IPPROTO_UDP:
+ case IPPROTO_UDPLITE:
+ poff += sizeof(struct udphdr);
+ break;
+ /* For the rest, we do not really care about header
+ * extensions at this point for now.
+ */
+ case IPPROTO_ICMP:
+ poff += sizeof(struct icmphdr);
+ break;
+ case IPPROTO_ICMPV6:
+ poff += sizeof(struct icmp6hdr);
+ break;
+ case IPPROTO_IGMP:
+ poff += sizeof(struct igmphdr);
+ break;
+ case IPPROTO_DCCP:
+ poff += sizeof(struct dccp_hdr);
+ break;
+ case IPPROTO_SCTP:
+ poff += sizeof(struct sctphdr);
+ break;
+ }
+
+ return poff;
+}
+
static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3863b8f..89a3a07 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -39,21 +39,13 @@
#include <linux/string.h>
#include <linux/log2.h>
+#define DEBUG
#define NEIGH_DEBUG 1
-
-#define NEIGH_PRINTK(x...) printk(x)
-#define NEIGH_NOPRINTK(x...) do { ; } while(0)
-#define NEIGH_PRINTK1 NEIGH_NOPRINTK
-#define NEIGH_PRINTK2 NEIGH_NOPRINTK
-
-#if NEIGH_DEBUG >= 1
-#undef NEIGH_PRINTK1
-#define NEIGH_PRINTK1 NEIGH_PRINTK
-#endif
-#if NEIGH_DEBUG >= 2
-#undef NEIGH_PRINTK2
-#define NEIGH_PRINTK2 NEIGH_PRINTK
-#endif
+#define neigh_dbg(level, fmt, ...) \
+do { \
+ if (level <= NEIGH_DEBUG) \
+ pr_debug(fmt, ##__VA_ARGS__); \
+} while (0)
#define PNEIGH_HASHMASK 0xF
@@ -246,7 +238,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
n->nud_state = NUD_NOARP;
else
n->nud_state = NUD_NONE;
- NEIGH_PRINTK2("neigh %p is stray.\n", n);
+ neigh_dbg(2, "neigh %p is stray\n", n);
}
write_unlock(&n->lock);
neigh_cleanup_and_release(n);
@@ -542,7 +534,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
lockdep_is_held(&tbl->lock)));
rcu_assign_pointer(nht->hash_buckets[hash_val], n);
write_unlock_bh(&tbl->lock);
- NEIGH_PRINTK2("neigh %p is created.\n", n);
+ neigh_dbg(2, "neigh %p is created\n", n);
rc = n;
out:
return rc;
@@ -725,7 +717,7 @@ void neigh_destroy(struct neighbour *neigh)
dev_put(dev);
neigh_parms_put(neigh->parms);
- NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);
+ neigh_dbg(2, "neigh %p is destroyed\n", neigh);
atomic_dec(&neigh->tbl->entries);
kfree_rcu(neigh, rcu);
@@ -739,7 +731,7 @@ EXPORT_SYMBOL(neigh_destroy);
*/
static void neigh_suspect(struct neighbour *neigh)
{
- NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
+ neigh_dbg(2, "neigh %p is suspected\n", neigh);
neigh->output = neigh->ops->output;
}
@@ -751,7 +743,7 @@ static void neigh_suspect(struct neighbour *neigh)
*/
static void neigh_connect(struct neighbour *neigh)
{
- NEIGH_PRINTK2("neigh %p is connected.\n", neigh);
+ neigh_dbg(2, "neigh %p is connected\n", neigh);
neigh->output = neigh->ops->connected_output;
}
@@ -852,7 +844,7 @@ static void neigh_invalidate(struct neighbour *neigh)
struct sk_buff *skb;
NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed);
- NEIGH_PRINTK2("neigh %p is failed.\n", neigh);
+ neigh_dbg(2, "neigh %p is failed\n", neigh);
neigh->updated = jiffies;
/* It is very thin place. report_unreachable is very complicated
@@ -904,17 +896,17 @@ static void neigh_timer_handler(unsigned long arg)
if (state & NUD_REACHABLE) {
if (time_before_eq(now,
neigh->confirmed + neigh->parms->reachable_time)) {
- NEIGH_PRINTK2("neigh %p is still alive.\n", neigh);
+ neigh_dbg(2, "neigh %p is still alive\n", neigh);
next = neigh->confirmed + neigh->parms->reachable_time;
} else if (time_before_eq(now,
neigh->used + neigh->parms->delay_probe_time)) {
- NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
+ neigh_dbg(2, "neigh %p is delayed\n", neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
neigh_suspect(neigh);
next = now + neigh->parms->delay_probe_time;
} else {
- NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
+ neigh_dbg(2, "neigh %p is suspected\n", neigh);
neigh->nud_state = NUD_STALE;
neigh->updated = jiffies;
neigh_suspect(neigh);
@@ -923,14 +915,14 @@ static void neigh_timer_handler(unsigned long arg)
} else if (state & NUD_DELAY) {
if (time_before_eq(now,
neigh->confirmed + neigh->parms->delay_probe_time)) {
- NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh);
+ neigh_dbg(2, "neigh %p is now reachable\n", neigh);
neigh->nud_state = NUD_REACHABLE;
neigh->updated = jiffies;
neigh_connect(neigh);
notify = 1;
next = neigh->confirmed + neigh->parms->reachable_time;
} else {
- NEIGH_PRINTK2("neigh %p is probed.\n", neigh);
+ neigh_dbg(2, "neigh %p is probed\n", neigh);
neigh->nud_state = NUD_PROBE;
neigh->updated = jiffies;
atomic_set(&neigh->probes, 0);
@@ -997,7 +989,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
return 1;
}
} else if (neigh->nud_state & NUD_STALE) {
- NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
+ neigh_dbg(2, "neigh %p is delayed\n", neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
neigh_add_timer(neigh,
@@ -1320,8 +1312,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
out:
return rc;
discard:
- NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
- dst, neigh);
+ neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh);
out_kfree_skb:
rc = -EINVAL;
kfree_skb(skb);
@@ -1498,7 +1489,7 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
}
}
write_unlock_bh(&tbl->lock);
- NEIGH_PRINTK1("neigh_parms_release: not found\n");
+ neigh_dbg(1, "%s: not found\n", __func__);
}
EXPORT_SYMBOL(neigh_parms_release);
@@ -1613,7 +1604,7 @@ int neigh_table_clear(struct neigh_table *tbl)
}
EXPORT_SYMBOL(neigh_table_clear);
-static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -1677,7 +1668,7 @@ out:
return err;
}
-static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -1955,7 +1946,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
[NDTPA_LOCKTIME] = { .type = NLA_U64 },
};
-static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct neigh_table *tbl;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 3174f19..569d355 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -271,7 +271,7 @@ static int ptype_seq_show(struct seq_file *seq, void *v)
else
seq_printf(seq, "%04x", ntohs(pt->type));
- seq_printf(seq, " %-8s %pF\n",
+ seq_printf(seq, " %-8s %pf\n",
pt->dev ? pt->dev->name : "", pt->func);
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index fa32899..a5802a8 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -47,7 +47,7 @@ static struct sk_buff_head skb_pool;
static atomic_t trapped;
-static struct srcu_struct netpoll_srcu;
+DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
#define NETPOLL_RX_ENABLED 1
@@ -206,17 +206,17 @@ static void netpoll_poll_dev(struct net_device *dev)
* the dev_open/close paths use this to block netpoll activity
* while changing device state
*/
- if (!mutex_trylock(&ni->dev_lock))
+ if (!down_trylock(&ni->dev_lock))
return;
if (!netif_running(dev)) {
- mutex_unlock(&ni->dev_lock);
+ up(&ni->dev_lock);
return;
}
ops = dev->netdev_ops;
if (!ops->ndo_poll_controller) {
- mutex_unlock(&ni->dev_lock);
+ up(&ni->dev_lock);
return;
}
@@ -225,7 +225,7 @@ static void netpoll_poll_dev(struct net_device *dev)
poll_napi(dev);
- mutex_unlock(&ni->dev_lock);
+ up(&ni->dev_lock);
if (dev->flags & IFF_SLAVE) {
if (ni) {
@@ -255,7 +255,7 @@ int netpoll_rx_disable(struct net_device *dev)
idx = srcu_read_lock(&netpoll_srcu);
ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
if (ni)
- mutex_lock(&ni->dev_lock);
+ down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
return 0;
}
@@ -267,7 +267,7 @@ void netpoll_rx_enable(struct net_device *dev)
rcu_read_lock();
ni = rcu_dereference(dev->npinfo);
if (ni)
- mutex_unlock(&ni->dev_lock);
+ up(&ni->dev_lock);
rcu_read_unlock();
}
EXPORT_SYMBOL(netpoll_rx_enable);
@@ -383,8 +383,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
if (__netif_tx_trylock(txq)) {
if (!netif_xmit_stopped(txq)) {
if (vlan_tx_tag_present(skb) &&
- !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) {
- skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+ !vlan_hw_offload_capable(netif_skb_features(skb),
+ skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
if (unlikely(!skb))
break;
skb->vlan_tci = 0;
@@ -1046,7 +1047,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
INIT_LIST_HEAD(&npinfo->rx_np);
spin_lock_init(&npinfo->rx_lock);
- mutex_init(&npinfo->dev_lock);
+ sema_init(&npinfo->dev_lock, 1);
skb_queue_head_init(&npinfo->neigh_tx);
skb_queue_head_init(&npinfo->txq);
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -1212,7 +1213,6 @@ EXPORT_SYMBOL(netpoll_setup);
static int __init netpoll_init(void)
{
skb_queue_head_init(&skb_pool);
- init_srcu_struct(&netpoll_srcu);
return 0;
}
core_initcall(netpoll_init);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 23854b5..a08bd2b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -517,32 +517,6 @@ out:
return err;
}
-static const int rtm_min[RTM_NR_FAMILIES] =
-{
- [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
- [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
- [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)),
- [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)),
- [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)),
- [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
- [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
-};
-
-static const int rta_max[RTM_NR_FAMILIES] =
-{
- [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX,
- [RTM_FAM(RTM_NEWADDR)] = IFA_MAX,
- [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX,
- [RTM_FAM(RTM_NEWRULE)] = FRA_MAX,
- [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX,
- [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX,
- [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX,
- [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX,
-};
-
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
struct sock *rtnl = net->rtnl;
@@ -1539,7 +1513,7 @@ errout:
return err;
}
-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -1580,7 +1554,7 @@ errout:
return err;
}
-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
@@ -1711,7 +1685,7 @@ static int rtnl_group_changelink(struct net *net, int group,
return 0;
}
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
@@ -1866,7 +1840,7 @@ out:
}
}
-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -1957,8 +1931,11 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
if (rtnl_msg_handlers[idx] == NULL ||
rtnl_msg_handlers[idx][type].dumpit == NULL)
continue;
- if (idx > s_idx)
+ if (idx > s_idx) {
memset(&cb->args[0], 0, sizeof(cb->args));
+ cb->prev_seq = 0;
+ cb->seq = 0;
+ }
if (rtnl_msg_handlers[idx][type].dumpit(skb, cb))
break;
}
@@ -2051,7 +2028,39 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+/**
+ * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry
+ */
+int ndo_dflt_fdb_add(struct ndmsg *ndm,
+ struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr,
+ u16 flags)
+{
+ int err = -EINVAL;
+
+ /* If aging addresses are supported device will need to
+ * implement its own handler for this.
+ */
+ if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+ pr_info("%s: FDB only supports static addresses\n", dev->name);
+ return err;
+ }
+
+ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+ err = dev_uc_add_excl(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_add_excl(dev, addr);
+
+ /* Only return duplicate errors if NLM_F_EXCL is set */
+ if (err == -EEXIST && !(flags & NLM_F_EXCL))
+ err = 0;
+
+ return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_add);
+
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -2082,7 +2091,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (!is_valid_ether_addr(addr)) {
+ if (is_zero_ether_addr(addr)) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
return -EINVAL;
}
@@ -2103,10 +2112,13 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
/* Embedded bridge, macvlan, and any other device support */
- if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) {
- err = dev->netdev_ops->ndo_fdb_add(ndm, tb,
- dev, addr,
- nlh->nlmsg_flags);
+ if ((ndm->ndm_flags & NTF_SELF)) {
+ if (dev->netdev_ops->ndo_fdb_add)
+ err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+ nlh->nlmsg_flags);
+ else
+ err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+ nlh->nlmsg_flags);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
@@ -2117,7 +2129,36 @@ out:
return err;
}
-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+/**
+ * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry
+ */
+int ndo_dflt_fdb_del(struct ndmsg *ndm,
+ struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr)
+{
+ int err = -EOPNOTSUPP;
+
+ /* If aging addresses are supported device will need to
+ * implement its own handler for this.
+ */
+ if (ndm->ndm_state & NUD_PERMANENT) {
+ pr_info("%s: FDB only supports static addresses\n", dev->name);
+ return -EINVAL;
+ }
+
+ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+ err = dev_uc_del(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_del(dev, addr);
+ else
+ err = -EINVAL;
+
+ return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_del);
+
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -2151,7 +2192,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (!is_valid_ether_addr(addr)) {
+ if (is_zero_ether_addr(addr)) {
pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n");
return -EINVAL;
}
@@ -2174,8 +2215,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
/* Embedded bridge, macvlan, and any other device support */
- if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
- err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+ if (ndm->ndm_flags & NTF_SELF) {
+ if (dev->netdev_ops->ndo_fdb_del)
+ err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+ else
+ err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2220,7 +2264,7 @@ skip:
* @dev: netdevice
*
* Default netdevice operation to dump the existing unicast address list.
- * Returns zero on success.
+ * Returns number of addresses from list put in skb.
*/
int ndo_dflt_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
@@ -2260,6 +2304,8 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (dev->netdev_ops->ndo_fdb_dump)
idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
+ else
+ idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
}
rcu_read_unlock();
@@ -2411,8 +2457,7 @@ errout:
return err;
}
-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -2482,8 +2527,7 @@ out:
return err;
}
-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -2553,10 +2597,6 @@ out:
return err;
}
-/* Protected by RTNL sempahore. */
-static struct rtattr **rta_buf;
-static int rtattr_max;
-
/* Process one rtnetlink message. */
static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -2564,7 +2604,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
rtnl_doit_func doit;
int sz_idx, kind;
- int min_len;
int family;
int type;
int err;
@@ -2576,10 +2615,10 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
type -= RTM_BASE;
/* All the messages must have at least 1 byte length */
- if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg)))
+ if (nlmsg_len(nlh) < sizeof(struct rtgenmsg))
return 0;
- family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family;
+ family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
sz_idx = type>>2;
kind = type&3;
@@ -2612,32 +2651,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
}
- memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *)));
-
- min_len = rtm_min[sz_idx];
- if (nlh->nlmsg_len < min_len)
- return -EINVAL;
-
- if (nlh->nlmsg_len > min_len) {
- int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
- struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
-
- while (RTA_OK(attr, attrlen)) {
- unsigned int flavor = attr->rta_type & NLA_TYPE_MASK;
- if (flavor) {
- if (flavor > rta_max[sz_idx])
- return -EINVAL;
- rta_buf[flavor-1] = attr;
- }
- attr = RTA_NEXT(attr, attrlen);
- }
- }
-
doit = rtnl_get_doit(family, type);
if (doit == NULL)
return -EOPNOTSUPP;
- return doit(skb, nlh, (void *)&rta_buf[0]);
+ return doit(skb, nlh);
}
static void rtnetlink_rcv(struct sk_buff *skb)
@@ -2707,16 +2725,6 @@ static struct pernet_operations rtnetlink_net_ops = {
void __init rtnetlink_init(void)
{
- int i;
-
- rtattr_max = 0;
- for (i = 0; i < ARRAY_SIZE(rta_max); i++)
- if (rta_max[i] > rtattr_max)
- rtattr_max = rta_max[i];
- rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL);
- if (!rta_buf)
- panic("rtnetlink_init: cannot allocate rta_buf\n");
-
if (register_pernet_subsys(&rtnetlink_net_ops))
panic("rtnetlink_init: cannot initialize rtnetlink\n");
diff --git a/net/core/scm.c b/net/core/scm.c
index 2dc6cda..03795d0 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -187,22 +187,6 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
p->creds.uid = uid;
p->creds.gid = gid;
-
- if (!p->cred ||
- !uid_eq(p->cred->euid, uid) ||
- !gid_eq(p->cred->egid, gid)) {
- struct cred *cred;
- err = -ENOMEM;
- cred = prepare_creds();
- if (!cred)
- goto error;
-
- cred->uid = cred->euid = uid;
- cred->gid = cred->egid = gid;
- if (p->cred)
- put_cred(p->cred);
- p->cred = cred;
- }
break;
}
default:
@@ -306,8 +290,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
/* Bump the usage count and install the file. */
sock = sock_from_file(fp[i], &err);
if (sock) {
- sock_update_netprioidx(sock->sk, current);
- sock_update_classid(sock->sk, current);
+ sock_update_netprioidx(sock->sk);
+ sock_update_classid(sock->sk);
}
fd_install(new_fd, get_file(fp[i]));
}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index e61a8bb..6a2f13c 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -12,12 +12,10 @@
static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-static int __init net_secret_init(void)
+void net_secret_init(void)
{
get_random_bytes(net_secret, sizeof(net_secret));
- return 0;
}
-late_initcall(net_secret_init);
#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 33245ef..af9185d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -179,6 +179,33 @@ out:
*
*/
+struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node)
+{
+ struct sk_buff *skb;
+
+ /* Get the HEAD */
+ skb = kmem_cache_alloc_node(skbuff_head_cache,
+ gfp_mask & ~__GFP_DMA, node);
+ if (!skb)
+ goto out;
+
+ /*
+ * Only clear those fields we need to clear, not those that we will
+ * actually initialise below. Hence, don't put any more fields after
+ * the tail pointer in struct sk_buff!
+ */
+ memset(skb, 0, offsetof(struct sk_buff, tail));
+ skb->data = NULL;
+ skb->truesize = sizeof(struct sk_buff);
+ atomic_set(&skb->users, 1);
+
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ skb->mac_header = ~0U;
+#endif
+out:
+ return skb;
+}
+
/**
* __alloc_skb - allocate a network buffer
* @size: size to allocate
@@ -584,7 +611,8 @@ static void skb_release_head_state(struct sk_buff *skb)
static void skb_release_all(struct sk_buff *skb)
{
skb_release_head_state(skb);
- skb_release_data(skb);
+ if (likely(skb->data))
+ skb_release_data(skb);
}
/**
@@ -673,6 +701,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->mac_header = old->mac_header;
new->inner_transport_header = old->inner_transport_header;
new->inner_network_header = old->inner_network_header;
+ new->inner_mac_header = old->inner_mac_header;
skb_dst_copy(new, old);
new->rxhash = old->rxhash;
new->ooo_okay = old->ooo_okay;
@@ -706,6 +735,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->tc_verd = old->tc_verd;
#endif
#endif
+ new->vlan_proto = old->vlan_proto;
new->vlan_tci = old->vlan_tci;
skb_copy_secmark(new, old);
@@ -867,6 +897,18 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
}
EXPORT_SYMBOL(skb_clone);
+static void skb_headers_offset_update(struct sk_buff *skb, int off)
+{
+ /* {transport,network,mac}_header and tail are relative to skb->head */
+ skb->transport_header += off;
+ skb->network_header += off;
+ if (skb_mac_header_was_set(skb))
+ skb->mac_header += off;
+ skb->inner_transport_header += off;
+ skb->inner_network_header += off;
+ skb->inner_mac_header += off;
+}
+
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
#ifndef NET_SKBUFF_DATA_USES_OFFSET
@@ -879,13 +921,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
__copy_skb_header(new, old);
#ifndef NET_SKBUFF_DATA_USES_OFFSET
- /* {transport,network,mac}_header are relative to skb->head */
- new->transport_header += offset;
- new->network_header += offset;
- if (skb_mac_header_was_set(new))
- new->mac_header += offset;
- new->inner_transport_header += offset;
- new->inner_network_header += offset;
+ skb_headers_offset_update(new, offset);
#endif
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
@@ -1077,14 +1113,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
#else
skb->end = skb->head + size;
#endif
- /* {transport,network,mac}_header and tail are relative to skb->head */
skb->tail += off;
- skb->transport_header += off;
- skb->network_header += off;
- if (skb_mac_header_was_set(skb))
- skb->mac_header += off;
- skb->inner_transport_header += off;
- skb->inner_network_header += off;
+ skb_headers_offset_update(skb, off);
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += nhead;
@@ -1180,12 +1210,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
if (n->ip_summed == CHECKSUM_PARTIAL)
n->csum_start += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- n->transport_header += off;
- n->network_header += off;
- if (skb_mac_header_was_set(skb))
- n->mac_header += off;
- n->inner_transport_header += off;
- n->inner_network_header += off;
+ skb_headers_offset_update(n, off);
#endif
return n;
@@ -2741,12 +2766,19 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
unsigned int tnl_hlen = skb_tnl_header_len(skb);
unsigned int headroom;
unsigned int len;
+ __be16 proto;
+ bool csum;
int sg = !!(features & NETIF_F_SG);
int nfrags = skb_shinfo(skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
int pos;
+ proto = skb_network_protocol(skb);
+ if (unlikely(!proto))
+ return ERR_PTR(-EINVAL);
+
+ csum = !!can_checksum_protocol(features, proto);
__skb_push(skb, doffset);
headroom = skb_headroom(skb);
pos = skb_headlen(skb);
@@ -2884,6 +2916,12 @@ skip_fraglist:
nskb->data_len = len - hsize;
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
+
+ if (!csum) {
+ nskb->csum = skb_checksum(nskb, doffset,
+ nskb->len - doffset, 0);
+ nskb->ip_summed = CHECKSUM_NONE;
+ }
} while ((offset += len) < skb->len);
return segs;
@@ -3289,12 +3327,8 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,
if (!sk)
return;
- skb = skb_clone(orig_skb, GFP_ATOMIC);
- if (!skb)
- return;
-
if (hwtstamps) {
- *skb_hwtstamps(skb) =
+ *skb_hwtstamps(orig_skb) =
*hwtstamps;
} else {
/*
@@ -3302,9 +3336,13 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,
* so keep the shared tx_flags and only
* store software time stamp
*/
- skb->tstamp = ktime_get_real();
+ orig_skb->tstamp = ktime_get_real();
}
+ skb = skb_clone(orig_skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
@@ -3361,6 +3399,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_headroom(skb) + start;
skb->csum_offset = off;
+ skb_set_transport_header(skb, start);
return true;
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
diff --git a/net/core/sock.c b/net/core/sock.c
index b261a79..d4f4cea 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -907,6 +907,10 @@ set_rcvbuf:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
+ case SO_SELECT_ERR_QUEUE:
+ sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1160,6 +1164,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
break;
+ case SO_SELECT_ERR_QUEUE:
+ v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -1298,13 +1306,12 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
-#ifdef CONFIG_CGROUPS
#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
-void sock_update_classid(struct sock *sk, struct task_struct *task)
+void sock_update_classid(struct sock *sk)
{
u32 classid;
- classid = task_cls_classid(task);
+ classid = task_cls_classid(current);
if (classid != sk->sk_classid)
sk->sk_classid = classid;
}
@@ -1312,16 +1319,15 @@ EXPORT_SYMBOL(sock_update_classid);
#endif
#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
-void sock_update_netprioidx(struct sock *sk, struct task_struct *task)
+void sock_update_netprioidx(struct sock *sk)
{
if (in_interrupt())
return;
- sk->sk_cgrp_prioidx = task_netprioidx(task);
+ sk->sk_cgrp_prioidx = task_netprioidx(current);
}
EXPORT_SYMBOL_GPL(sock_update_netprioidx);
#endif
-#endif
/**
* sk_alloc - All socket objects are allocated here
@@ -1347,8 +1353,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sock_net_set(sk, get_net(net));
atomic_set(&sk->sk_wmem_alloc, 1);
- sock_update_classid(sk, current);
- sock_update_netprioidx(sk, current);
+ sock_update_classid(sk);
+ sock_update_netprioidx(sk);
}
return sk;
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a29e90c..d5bef0b0 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,6 +49,39 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
}
EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
+int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+ struct sk_buff *skb, int attrtype)
+{
+ struct nlattr *attr;
+ struct sk_filter *filter;
+ unsigned int len;
+ int err = 0;
+
+ if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+ nla_reserve(skb, attrtype, 0);
+ return 0;
+ }
+
+ rcu_read_lock();
+
+ filter = rcu_dereference(sk->sk_filter);
+ len = filter ? filter->len * sizeof(struct sock_filter) : 0;
+
+ attr = nla_reserve(skb, attrtype, len);
+ if (attr == NULL) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ if (filter)
+ memcpy(nla_data(attr), filter->insns, len);
+
+out:
+ rcu_read_unlock();
+ return err;
+}
+EXPORT_SYMBOL(sock_diag_put_filterinfo);
+
void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
{
mutex_lock(&sock_diag_table_mutex);
diff --git a/net/core/utils.c b/net/core/utils.c
index e3487e46..3c7f5b5 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
+#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/mm.h>
#include <linux/net.h>
@@ -348,9 +349,7 @@ int mac_pton(const char *s, u8 *mac)
/* Don't dirty result unless string is valid MAC. */
for (i = 0; i < ETH_ALEN; i++) {
- if (!strchr("0123456789abcdefABCDEF", s[i * 3]))
- return 0;
- if (!strchr("0123456789abcdefABCDEF", s[i * 3 + 1]))
+ if (!isxdigit(s[i * 3]) || !isxdigit(s[i * 3 + 1]))
return 0;
if (i != ETH_ALEN - 1 && s[i * 3 + 2] != ':')
return 0;
OpenPOWER on IntegriCloud