summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/batman-adv/bat_iv_ogm.c30
-rw-r--r--net/batman-adv/hard-interface.c22
-rw-r--r--net/batman-adv/originator.c36
-rw-r--r--net/batman-adv/originator.h4
-rw-r--r--net/batman-adv/routing.c4
-rw-r--r--net/batman-adv/send.c9
-rw-r--r--net/batman-adv/translation-table.c23
-rw-r--r--net/bluetooth/hidp/core.c16
-rw-r--r--net/bluetooth/hidp/hidp.h4
-rw-r--r--net/can/raw.c26
-rw-r--r--net/core/dev.c22
-rw-r--r--net/core/flow_dissector.c20
-rw-r--r--net/core/neighbour.c8
-rw-r--r--net/core/rtnetlink.c19
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/dccp/ccids/lib/tfrc.c2
-rw-r--r--net/dccp/ccids/lib/tfrc.h1
-rw-r--r--net/hsr/hsr_framereg.c2
-rw-r--r--net/ipv4/af_inet.c7
-rw-r--r--net/ipv4/ip_forward.c71
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/ip_tunnel.c53
-rw-r--r--net/ipv4/ip_tunnel_core.c47
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c4
-rw-r--r--net/ipv4/route.c13
-rw-r--r--net/ipv4/tcp.c8
-rw-r--r--net/ipv4/tcp_cong.c3
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_output.c22
-rw-r--r--net/ipv6/Kconfig1
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/exthdrs_core.c2
-rw-r--r--net/ipv6/ip6_offload.c20
-rw-r--r--net/ipv6/ip6_output.c20
-rw-r--r--net/ipv6/ping.c1
-rw-r--r--net/ipv6/sit.c19
-rw-r--r--net/ipv6/udp_offload.c2
-rw-r--r--net/mac80211/ieee80211_i.h10
-rw-r--r--net/mac80211/iface.c6
-rw-r--r--net/mac80211/mlme.c24
-rw-r--r--net/mac80211/rx.c7
-rw-r--r--net/mac80211/sta_info.c66
-rw-r--r--net/mac80211/sta_info.h7
-rw-r--r--net/mac80211/tx.c15
-rw-r--r--net/mac80211/util.c48
-rw-r--r--net/mac80211/wme.c5
-rw-r--r--net/netfilter/nf_conntrack_netlink.c35
-rw-r--r--net/netfilter/nf_nat_core.c56
-rw-r--r--net/netfilter/nft_meta.c4
-rw-r--r--net/netfilter/nft_payload.c3
-rw-r--r--net/netfilter/nft_reject_inet.c4
-rw-r--r--net/netlink/af_netlink.c4
-rw-r--r--net/nfc/nci/core.c2
-rw-r--r--net/packet/af_packet.c26
-rw-r--r--net/sched/sch_pie.c21
-rw-r--r--net/sched/sch_tbf.c24
-rw-r--r--net/sctp/associola.c211
-rw-r--r--net/sctp/sm_sideeffect.c7
-rw-r--r--net/sctp/sm_statefuns.c9
-rw-r--r--net/sctp/socket.c47
-rw-r--r--net/sctp/sysctl.c18
-rw-r--r--net/sctp/ulpevent.c8
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c19
-rw-r--r--net/sunrpc/backchannel_rqst.c6
-rw-r--r--net/sunrpc/xprtsock.c6
-rw-r--r--net/tipc/bearer.c7
-rw-r--r--net/tipc/config.c2
-rw-r--r--net/tipc/core.c109
-rw-r--r--net/tipc/core.h2
-rw-r--r--net/tipc/link.c7
-rw-r--r--net/tipc/name_table.c3
-rw-r--r--net/tipc/netlink.c8
-rw-r--r--net/tipc/ref.c3
-rw-r--r--net/tipc/server.c5
-rw-r--r--net/tipc/server.h2
-rw-r--r--net/tipc/socket.c8
-rw-r--r--net/wireless/reg.c12
-rw-r--r--net/xfrm/xfrm_policy.c2
-rw-r--r--net/xfrm/xfrm_state.c23
-rw-r--r--net/xfrm/xfrm_user.c5
81 files changed, 887 insertions, 563 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 512159b..8323bce 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -241,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr)
size = bat_priv->num_ifaces * sizeof(uint8_t);
orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC);
if (!orig_node->bat_iv.bcast_own_sum)
- goto free_bcast_own;
+ goto free_orig_node;
hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig,
batadv_choose_orig, orig_node,
&orig_node->hash_entry);
if (hash_added != 0)
- goto free_bcast_own;
+ goto free_orig_node;
return orig_node;
-free_bcast_own:
- kfree(orig_node->bat_iv.bcast_own);
free_orig_node:
+ /* free twice, as batadv_orig_node_new sets refcount to 2 */
+ batadv_orig_node_free_ref(orig_node);
batadv_orig_node_free_ref(orig_node);
return NULL;
@@ -266,7 +266,7 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
struct batadv_orig_node *orig_neigh)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- struct batadv_neigh_node *neigh_node;
+ struct batadv_neigh_node *neigh_node, *tmp_neigh_node;
neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node);
if (!neigh_node)
@@ -281,14 +281,24 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
neigh_node->orig_node = orig_neigh;
neigh_node->if_incoming = hard_iface;
- batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
- "Creating new neighbor %pM for orig_node %pM on interface %s\n",
- neigh_addr, orig_node->orig, hard_iface->net_dev->name);
-
spin_lock_bh(&orig_node->neigh_list_lock);
- hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+ tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface,
+ neigh_addr);
+ if (!tmp_neigh_node) {
+ hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+ } else {
+ kfree(neigh_node);
+ batadv_hardif_free_ref(hard_iface);
+ neigh_node = tmp_neigh_node;
+ }
spin_unlock_bh(&orig_node->neigh_list_lock);
+ if (!tmp_neigh_node)
+ batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+ "Creating new neighbor %pM for orig_node %pM on interface %s\n",
+ neigh_addr, orig_node->orig,
+ hard_iface->net_dev->name);
+
out:
return neigh_node;
}
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 3d417d3..b851cc5 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -241,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
{
struct batadv_priv *bat_priv = netdev_priv(soft_iface);
const struct batadv_hard_iface *hard_iface;
- int min_mtu = ETH_DATA_LEN;
+ int min_mtu = INT_MAX;
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -256,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
}
rcu_read_unlock();
- atomic_set(&bat_priv->packet_size_max, min_mtu);
-
if (atomic_read(&bat_priv->fragmentation) == 0)
goto out;
@@ -268,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE);
min_mtu -= sizeof(struct batadv_frag_packet);
min_mtu *= BATADV_FRAG_MAX_FRAGMENTS;
- atomic_set(&bat_priv->packet_size_max, min_mtu);
-
- /* with fragmentation enabled we can fragment external packets easily */
- min_mtu = min_t(int, min_mtu, ETH_DATA_LEN);
out:
- return min_mtu - batadv_max_header_len();
+ /* report to the other components the maximum amount of bytes that
+ * batman-adv can send over the wire (without considering the payload
+ * overhead). For example, this value is used by TT to compute the
+ * maximum local table table size
+ */
+ atomic_set(&bat_priv->packet_size_max, min_mtu);
+
+ /* the real soft-interface MTU is computed by removing the payload
+ * overhead from the maximum amount of bytes that was just computed.
+ *
+ * However batman-adv does not support MTUs bigger than ETH_DATA_LEN
+ */
+ return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN);
}
/* adjusts the MTU if a new interface with a smaller MTU appeared. */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 6df12a2..8539416 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -458,6 +458,42 @@ out:
}
/**
+ * batadv_neigh_node_get - retrieve a neighbour from the list
+ * @orig_node: originator which the neighbour belongs to
+ * @hard_iface: the interface where this neighbour is connected to
+ * @addr: the address of the neighbour
+ *
+ * Looks for and possibly returns a neighbour belonging to this originator list
+ * which is connected through the provided hard interface.
+ * Returns NULL if the neighbour is not found.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+ const struct batadv_hard_iface *hard_iface,
+ const uint8_t *addr)
+{
+ struct batadv_neigh_node *tmp_neigh_node, *res = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) {
+ if (!batadv_compare_eth(tmp_neigh_node->addr, addr))
+ continue;
+
+ if (tmp_neigh_node->if_incoming != hard_iface)
+ continue;
+
+ if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
+ continue;
+
+ res = tmp_neigh_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return res;
+}
+
+/**
* batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
* @rcu: rcu pointer of the orig_ifinfo object
*/
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 37be290..db3a9ed 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -29,6 +29,10 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node);
struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
const uint8_t *addr);
struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+ const struct batadv_hard_iface *hard_iface,
+ const uint8_t *addr);
+struct batadv_neigh_node *
batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
const uint8_t *neigh_addr,
struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 1ed9f7c..a953d5b 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -688,7 +688,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
int is_old_ttvn;
/* check if there is enough data before accessing it */
- if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0)
+ if (!pskb_may_pull(skb, hdr_len + ETH_HLEN))
return 0;
/* create a copy of the skb (in case of for re-routing) to modify it. */
@@ -918,6 +918,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb,
if (ret != NET_RX_SUCCESS)
ret = batadv_route_unicast_packet(skb, recv_if);
+ else
+ consume_skb(skb);
return ret;
}
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 579f5f0..843febd 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -254,9 +254,9 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
unsigned short vid)
{
- struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+ struct ethhdr *ethhdr;
struct batadv_unicast_packet *unicast_packet;
- int ret = NET_XMIT_DROP;
+ int ret = NET_XMIT_DROP, hdr_size;
if (!orig_node)
goto out;
@@ -265,12 +265,16 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
case BATADV_UNICAST:
if (!batadv_send_skb_prepare_unicast(skb, orig_node))
goto out;
+
+ hdr_size = sizeof(*unicast_packet);
break;
case BATADV_UNICAST_4ADDR:
if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb,
orig_node,
packet_subtype))
goto out;
+
+ hdr_size = sizeof(struct batadv_unicast_4addr_packet);
break;
default:
/* this function supports UNICAST and UNICAST_4ADDR only. It
@@ -279,6 +283,7 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
goto out;
}
+ ethhdr = (struct ethhdr *)(skb->data + hdr_size);
unicast_packet = (struct batadv_unicast_packet *)skb->data;
/* inform the destination node that we are still missing a correct route
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b6071f6..959dde7 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1975,6 +1975,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv,
struct hlist_head *head;
uint32_t i, crc_tmp, crc = 0;
uint8_t flags;
+ __be16 tmp_vid;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
@@ -2011,8 +2012,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv,
orig_node))
continue;
- crc_tmp = crc32c(0, &tt_common->vid,
- sizeof(tt_common->vid));
+ /* use network order to read the VID: this ensures that
+ * every node reads the bytes in the same order.
+ */
+ tmp_vid = htons(tt_common->vid);
+ crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
/* compute the CRC on flags that have to be kept in sync
* among nodes
@@ -2046,6 +2050,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv,
struct hlist_head *head;
uint32_t i, crc_tmp, crc = 0;
uint8_t flags;
+ __be16 tmp_vid;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
@@ -2064,8 +2069,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv,
if (tt_common->flags & BATADV_TT_CLIENT_NEW)
continue;
- crc_tmp = crc32c(0, &tt_common->vid,
- sizeof(tt_common->vid));
+ /* use network order to read the VID: this ensures that
+ * every node reads the bytes in the same order.
+ */
+ tmp_vid = htons(tt_common->vid);
+ crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
/* compute the CRC on flags that have to be kept in sync
* among nodes
@@ -2262,6 +2270,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
{
struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp;
struct batadv_orig_node_vlan *vlan;
+ uint32_t crc;
int i;
/* check if each received CRC matches the locally stored one */
@@ -2281,7 +2290,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
if (!vlan)
return false;
- if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc))
+ crc = vlan->tt.crc;
+ batadv_orig_node_vlan_free_ref(vlan);
+
+ if (crc != ntohl(tt_vlan_tmp->crc))
return false;
}
@@ -3218,7 +3230,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
spin_lock_bh(&orig_node->tt_lock);
- tt_change = (struct batadv_tvlv_tt_change *)tt_buff;
batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes,
ttvn, tt_change);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 292e619..d9fb934 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -430,6 +430,16 @@ static void hidp_del_timer(struct hidp_session *session)
del_timer(&session->timer);
}
+static void hidp_process_report(struct hidp_session *session,
+ int type, const u8 *data, int len, int intr)
+{
+ if (len > HID_MAX_BUFFER_SIZE)
+ len = HID_MAX_BUFFER_SIZE;
+
+ memcpy(session->input_buf, data, len);
+ hid_input_report(session->hid, type, session->input_buf, len, intr);
+}
+
static void hidp_process_handshake(struct hidp_session *session,
unsigned char param)
{
@@ -502,7 +512,8 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb,
hidp_input_report(session, skb);
if (session->hid)
- hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0);
+ hidp_process_report(session, HID_INPUT_REPORT,
+ skb->data, skb->len, 0);
break;
case HIDP_DATA_RTYPE_OTHER:
@@ -584,7 +595,8 @@ static void hidp_recv_intr_frame(struct hidp_session *session,
hidp_input_report(session, skb);
if (session->hid) {
- hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1);
+ hidp_process_report(session, HID_INPUT_REPORT,
+ skb->data, skb->len, 1);
BT_DBG("report len %d", skb->len);
}
} else {
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index ab52414..8798492 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -24,6 +24,7 @@
#define __HIDP_H
#include <linux/types.h>
+#include <linux/hid.h>
#include <linux/kref.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/l2cap.h>
@@ -179,6 +180,9 @@ struct hidp_session {
/* Used in hidp_output_raw_report() */
int output_report_success; /* boolean */
+
+ /* temporary input buffer */
+ u8 input_buf[HID_MAX_BUFFER_SIZE];
};
/* HIDP init defines */
diff --git a/net/can/raw.c b/net/can/raw.c
index 8be757c..081e81f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -121,13 +121,9 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
if (!ro->recv_own_msgs && oskb->sk == sk)
return;
- /* do not pass frames with DLC > 8 to a legacy socket */
- if (!ro->fd_frames) {
- struct canfd_frame *cfd = (struct canfd_frame *)oskb->data;
-
- if (unlikely(cfd->len > CAN_MAX_DLEN))
- return;
- }
+ /* do not pass non-CAN2.0 frames to a legacy socket */
+ if (!ro->fd_frames && oskb->len != CAN_MTU)
+ return;
/* clone the given skb to be able to enqueue it into the rcv queue */
skb = skb_clone(oskb, GFP_ATOMIC);
@@ -738,9 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct raw_sock *ro = raw_sk(sk);
struct sk_buff *skb;
- int rxmtu;
int err = 0;
int noblock;
@@ -751,20 +745,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
if (!skb)
return err;
- /*
- * when serving a legacy socket the DLC <= 8 is already checked inside
- * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy
- * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU
- */
- if (!ro->fd_frames)
- rxmtu = CAN_MTU;
- else
- rxmtu = skb->len;
-
- if (size < rxmtu)
+ if (size < skb->len)
msg->msg_flags |= MSG_TRUNC;
else
- size = rxmtu;
+ size = skb->len;
err = memcpy_toiovec(msg->msg_iov, skb->data, size);
if (err < 0) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 4ad1b78..b1b0c8d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2420,7 +2420,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
* 2. No high memory really exists on this machine.
*/
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
@@ -2495,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
- netdev_features_t features)
+ const struct net_device *dev,
+ netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, skb_network_protocol(skb))) {
features &= ~NETIF_F_ALL_CSUM;
- } else if (illegal_highdma(skb->dev, skb)) {
+ } else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev)
{
__be16 protocol = skb->protocol;
- netdev_features_t features = skb->dev->features;
+ netdev_features_t features = dev->features;
- if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
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, features);
+ return harmonize_features(skb, dev, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2530,9 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
- return harmonize_features(skb, features);
+ return harmonize_features(skb, dev, features);
}
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 87577d4..e29e810 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb)
return poff;
}
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
- if (unlikely(queue_index >= dev->real_num_tx_queues)) {
- net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
- return 0;
- }
- return queue_index;
-}
-
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
@@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
#endif
}
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
{
struct sock *sk = skb->sk;
int queue_index = sk_tx_queue_get(sk);
@@ -392,7 +381,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
return queue_index;
}
-EXPORT_SYMBOL(__netdev_pick_tx);
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
@@ -403,13 +391,13 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb,
- accel_priv);
+ queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ __netdev_pick_tx);
else
queue_index = __netdev_pick_tx(dev, skb);
if (!accel_priv)
- queue_index = dev_cap_txqueue(dev, queue_index);
+ queue_index = netdev_cap_txqueue(dev, queue_index);
}
skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b9e9e0d..e161290 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -766,9 +766,6 @@ static void neigh_periodic_work(struct work_struct *work)
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
- goto out;
-
/*
* periodically recompute ReachableTime from random function
*/
@@ -781,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work)
neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
}
+ if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+ goto out;
+
for (i = 0 ; i < (1 << nht->hash_shift); i++) {
np = &nht->hash_buckets[i];
@@ -3046,7 +3046,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
if (!t)
goto err;
- for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+ for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) {
t->neigh_vars[i].data += (long) p;
t->neigh_vars[i].extra1 = dev;
t->neigh_vars[i].extra2 = p;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 048dc8d..1a0dac2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1963,16 +1963,21 @@ replay:
dev->ifindex = ifm->ifi_index;
- if (ops->newlink)
+ if (ops->newlink) {
err = ops->newlink(net, dev, tb, data);
- else
+ /* Drivers should call free_netdev() in ->destructor
+ * and unregister it on failure so that device could be
+ * finally freed in rtnl_unlock.
+ */
+ if (err < 0)
+ goto out;
+ } else {
err = register_netdevice(dev);
-
- if (err < 0) {
- free_netdev(dev);
- goto out;
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
+ }
}
-
err = rtnl_configure_link(dev, ifm);
if (err < 0)
unregister_netdevice(dev);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0..5d6236d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->mark = old->mark;
new->skb_iif = old->skb_iif;
__nf_copy(new, old);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- new->nf_trace = old->nf_trace;
-#endif
#ifdef CONFIG_NET_SCHED
new->tc_index = old->tc_index;
#ifdef CONFIG_NET_CLS_ACT
diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c
index c073b81..62b5828 100644
--- a/net/dccp/ccids/lib/tfrc.c
+++ b/net/dccp/ccids/lib/tfrc.c
@@ -8,7 +8,7 @@
#include "tfrc.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-static bool tfrc_debug;
+bool tfrc_debug;
module_param(tfrc_debug, bool, 0644);
MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages");
#endif
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
index a3d8f7c..40ee7d6 100644
--- a/net/dccp/ccids/lib/tfrc.h
+++ b/net/dccp/ccids/lib/tfrc.h
@@ -21,6 +21,7 @@
#include "packet_history.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
+extern bool tfrc_debug;
#define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a)
#else
#define tfrc_pr_debug(format, a...)
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 327060c..7ae0d7f6 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -297,7 +297,7 @@ static bool seq_nr_after(u16 a, u16 b)
void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
{
- if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+ if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) {
WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
return;
}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ecd2c3f..19ab78a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
segs = ERR_PTR(-EPROTONOSUPPORT);
- /* Note : following gso_segment() might change skb->encapsulation */
- udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
ops = rcu_dereference(inet_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217..f3869c1 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
@@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb)
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8971780..73c6b63 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
to->ipvs_property = from->ipvs_property;
#endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 50228be..78a89e6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t)
tunnel_dst_set(t, NULL);
}
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
{
int i;
for_each_possible_cpu(i)
__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
}
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
{
@@ -119,52 +120,6 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
return (struct rtable *)dst;
}
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_sw_netstats *tstats =
- per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
-
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- tot->collisions = dev->stats.collisions;
-
- return tot;
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
{
@@ -759,7 +714,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
if (set_mtu)
dev->mtu = mtu;
}
- tunnel_dst_reset_all(t);
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(dev);
}
@@ -1088,7 +1043,7 @@ void ip_tunnel_uninit(struct net_device *dev)
if (itn->fb_tunnel_dev != dev)
ip_tunnel_del(netdev_priv(dev));
- tunnel_dst_reset_all(tunnel);
+ ip_tunnel_dst_reset_all(tunnel);
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6156f4e..6f847dd 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -108,7 +108,6 @@ 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;
@@ -148,3 +147,49 @@ error:
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_sw_netstats *tstats =
+ per_cpu_ptr(dev->tstats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ }
+
+ tot->multicast = dev->stats.multicast;
+
+ tot->rx_crc_errors = dev->stats.rx_crc_errors;
+ tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+ tot->rx_length_errors = dev->stats.rx_length_errors;
+ tot->rx_frame_errors = dev->stats.rx_frame_errors;
+ tot->rx_errors = dev->stats.rx_errors;
+
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+ tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+ tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+ tot->tx_errors = dev->stats.tx_errors;
+
+ tot->collisions = dev->stats.collisions;
+
+ return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138..b3e86ea 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@ static int __init ic_open_devs(void)
msleep(1);
- if time_before(jiffies, next_msg)
+ if (time_before(jiffies, next_msg))
continue;
elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d551e31..7c67667 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct,
map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
} else {
/* DNAT replies */
- map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
- map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+ map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+ map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
}
if (map.from == map.to)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25071b4..4c011ec 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1597,6 +1597,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1695,10 +1696,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0)
+ if (err != 0) {
+ if (!IN_DEV_FORWARD(in_dev))
+ err = -EHOSTUNREACH;
goto no_route;
-
- RT_CACHE_STAT_INC(in_slow_tot);
+ }
if (res.type == RTN_BROADCAST)
goto brd_input;
@@ -1712,8 +1714,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto local_input;
}
- if (!IN_DEV_FORWARD(in_dev))
+ if (!IN_DEV_FORWARD(in_dev)) {
+ err = -EHOSTUNREACH;
goto no_route;
+ }
if (res.type != RTN_UNICAST)
goto martian_destination;
@@ -1768,6 +1772,7 @@ local_input:
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9f3a2db..97c8f56 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
}
}
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+ int *copied, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
int err, flags;
@@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
if (unlikely(tp->fastopen_req == NULL))
return -ENOBUFS;
tp->fastopen_req->data = msg;
+ tp->fastopen_req->size = size;
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
msg->msg_namelen, flags);
- *size = tp->fastopen_req->copied;
+ *copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
return err;
}
@@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
flags = msg->msg_flags;
if (flags & MSG_FASTOPEN) {
- err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+ err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
else if (err)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf1..2388275 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
left = tp->snd_cwnd - in_flight;
if (sk_can_gso(sk) &&
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
- left * tp->mss_cache < sk->sk_gso_max_size &&
- left < sk->sk_gso_max_segs)
+ left < tp->xmit_size_goal_segs)
return true;
return left <= tcp_max_tso_deferred_mss(tp);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba7..eeaac39 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1945,8 +1945,9 @@ void tcp_enter_loss(struct sock *sk, int how)
if (skb == tcp_send_head(sk))
break;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->undo_marker = 0;
+
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3be1672..f0eb4e3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -864,8 +864,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
fclone->fclone == SKB_FCLONE_CLONE))
- NET_INC_STATS_BH(sock_net(sk),
- LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
if (unlikely(skb_cloned(skb)))
skb = pskb_copy(skb, gfp_mask);
@@ -2337,6 +2337,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned int cur_mss;
+ int err;
/* Inconslusive MTU probe */
if (icsk->icsk_mtup.probe_size) {
@@ -2400,11 +2401,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
skb_headroom(skb) >= 0xFFFF)) {
struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
GFP_ATOMIC);
- return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
- -ENOBUFS;
+ err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+ -ENOBUFS;
} else {
- return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
+
+ if (likely(!err))
+ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+ return err;
}
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2908,7 +2913,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
- syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+ space = min_t(size_t, space, fo->size);
+
+ /* limit to order-0 allocations */
+ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+ syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
sk->sk_allocation);
if (syn_data == NULL)
goto fallback;
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e558..438a73a 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
config IPV6_VTI
tristate "Virtual (secure) IPv6: tunneling"
select IPV6_TUNNEL
+ select NET_IP_TUNNEL
depends on INET6_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad23569..fdbfeca 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2783,6 +2783,8 @@ static void addrconf_gre_config(struct net_device *dev)
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
addrconf_add_linklocal(idev, &addr);
+ else
+ addrconf_prefix_route(&addr, 64, dev, 0, 0);
}
#endif
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748d..8af3eb5 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
found = (nexthdr == target);
if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
- if (target < 0)
+ if (target < 0 || found)
break;
return -ENOENT;
}
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1e8683b..59f95af 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
unsigned int unfrag_ip6hlen;
u8 *prevhdr;
int offset = 0;
- bool tunnel;
+ bool encap, udpfrag;
int nhoff;
if (unlikely(skb_shinfo(skb)->gso_type &
@@ -110,8 +110,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
- tunnel = SKB_GSO_CB(skb)->encap_level > 0;
- if (tunnel)
+ encap = SKB_GSO_CB(skb)->encap_level > 0;
+ if (encap)
features = skb->dev->hw_enc_features & netif_skb_features(skb);
SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
@@ -121,6 +121,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
skb_reset_transport_header(skb);
@@ -133,13 +139,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
for (skb = segs; skb; skb = skb->next) {
ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
- if (tunnel) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
skb->network_header = (u8 *)ipv6h - skb->head;
- if (!tunnel && proto == IPPROTO_UDP) {
+ if (udpfrag) {
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
fptr->frag_off = htons(offset);
@@ -148,6 +150,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
offset += (ntohs(ipv6h->payload_len) -
sizeof(struct frag_hdr));
}
+ if (encap)
+ skb_reset_inner_headers(skb);
}
out:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef02b26..16f91a2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
return mtu;
}
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+ return true;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb)
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
- (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+ if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -517,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
skb_copy_secmark(to, from);
}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index fb9beb7..587bbdc 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -135,6 +135,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
+ fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1..b4d74c8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
ipip6_tunnel_unlink(sitn, tunnel);
ipip6_tunnel_del_prl(tunnel, NULL);
}
+ ip_tunnel_dst_reset_all(tunnel);
dev_put(dev);
}
@@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
t->parms.link = p->link;
ipip6_tunnel_bind_dev(t->dev);
}
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(t->dev);
}
@@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
t->ip6rd.relay_prefix = relay_prefix;
t->ip6rd.prefixlen = ip6rd->prefixlen;
t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(t->dev);
return 0;
}
@@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
break;
}
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(dev);
break;
@@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = {
static void ipip6_dev_free(struct net_device *dev)
{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+
+ free_percpu(tunnel->dst_cache);
free_percpu(dev->tstats);
free_netdev(dev);
}
@@ -1375,6 +1382,12 @@ static int ipip6_tunnel_init(struct net_device *dev)
u64_stats_init(&ipip6_tunnel_stats->syncp);
}
+ tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+ if (!tunnel->dst_cache) {
+ free_percpu(dev->tstats);
+ return -ENOMEM;
+ }
+
return 0;
}
@@ -1405,6 +1418,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
u64_stats_init(&ipip6_fb_stats->syncp);
}
+ tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+ if (!tunnel->dst_cache) {
+ free_percpu(dev->tstats);
+ return -ENOMEM;
+ }
+
dev_hold(dev);
rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
return 0;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9..b261ee8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -113,7 +113,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
fptr->nexthdr = nexthdr;
fptr->reserved = 0;
- ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+ fptr->identification = skb_shinfo(skb)->ip6_frag_id;
/* Fragment the skb. ipv6 header and the remaining fields of the
* fragment header are updated in ipv6_gso_segment()
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 3701930..5e44e317 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1692,14 +1692,8 @@ void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue,
void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue);
void ieee80211_add_pending_skb(struct ieee80211_local *local,
struct sk_buff *skb);
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
- struct sk_buff_head *skbs,
- void (*fn)(void *data), void *data);
-static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local,
- struct sk_buff_head *skbs)
-{
- ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL);
-}
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+ struct sk_buff_head *skbs);
void ieee80211_flush_queues(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d6d1f1d..ce1c443 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev)
static u16 ieee80211_netdev_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv,
+ select_queue_fallback_t fallback)
{
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
}
@@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = {
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv,
+ select_queue_fallback_t fallback)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fc1d824..245dce9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -222,6 +222,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
switch (vht_oper->chan_width) {
case IEEE80211_VHT_CHANWIDTH_USE_HT:
vht_chandef.width = chandef->width;
+ vht_chandef.center_freq1 = chandef->center_freq1;
break;
case IEEE80211_VHT_CHANWIDTH_80MHZ:
vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -271,6 +272,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
ret = 0;
out:
+ /*
+ * When tracking the current AP, don't do any further checks if the
+ * new chandef is identical to the one we're currently using for the
+ * connection. This keeps us from playing ping-pong with regulatory,
+ * without it the following can happen (for example):
+ * - connect to an AP with 80 MHz, world regdom allows 80 MHz
+ * - AP advertises regdom US
+ * - CRDA loads regdom US with 80 MHz prohibited (old database)
+ * - the code below detects an unsupported channel, downgrades, and
+ * we disconnect from the AP in the caller
+ * - disconnect causes CRDA to reload world regdomain and the game
+ * starts anew.
+ * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+ *
+ * It seems possible that there are still scenarios with CSA or real
+ * bandwidth changes where a this could happen, but those cases are
+ * less common and wouldn't completely prevent using the AP.
+ */
+ if (tracking &&
+ cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+ return ret;
+
/* don't print the message below for VHT mismatch if VHT is disabled */
if (ret & IEEE80211_STA_DISABLE_VHT)
vht_chandef = *chandef;
@@ -3753,6 +3776,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
if (WARN_ON(!chanctx_conf)) {
rcu_read_unlock();
+ sta_info_free(local, new_sta);
return -EINVAL;
}
rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c24ca0d..3e57f96 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1128,6 +1128,13 @@ static void sta_ps_end(struct sta_info *sta)
sta->sta.addr, sta->sta.aid);
if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+ /*
+ * Clear the flag only if the other one is still set
+ * so that the TX path won't start TX'ing new frames
+ * directly ... In the case that the driver flag isn't
+ * set ieee80211_sta_ps_deliver_wakeup() will clear it.
+ */
+ clear_sta_flag(sta, WLAN_STA_PS_STA);
ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n",
sta->sta.addr, sta->sta.aid);
return;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index decd30c..a023b43 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -91,7 +91,7 @@ static int sta_info_hash_del(struct ieee80211_local *local,
return -ENOENT;
}
-static void cleanup_single_sta(struct sta_info *sta)
+static void __cleanup_single_sta(struct sta_info *sta)
{
int ac, i;
struct tid_ampdu_tx *tid_tx;
@@ -99,7 +99,8 @@ static void cleanup_single_sta(struct sta_info *sta)
struct ieee80211_local *local = sdata->local;
struct ps_data *ps;
- if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+ if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
+ test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
ps = &sdata->bss->ps;
@@ -109,6 +110,7 @@ static void cleanup_single_sta(struct sta_info *sta)
return;
clear_sta_flag(sta, WLAN_STA_PS_STA);
+ clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
atomic_dec(&ps->num_sta_ps);
sta_info_recalc_tim(sta);
@@ -139,7 +141,14 @@ static void cleanup_single_sta(struct sta_info *sta)
ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending);
kfree(tid_tx);
}
+}
+static void cleanup_single_sta(struct sta_info *sta)
+{
+ struct ieee80211_sub_if_data *sdata = sta->sdata;
+ struct ieee80211_local *local = sdata->local;
+
+ __cleanup_single_sta(sta);
sta_info_free(local, sta);
}
@@ -330,6 +339,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
rcu_read_unlock();
spin_lock_init(&sta->lock);
+ spin_lock_init(&sta->ps_lock);
INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
mutex_init(&sta->ampdu_mlme.mtx);
@@ -487,21 +497,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
goto out_err;
}
- /* notify driver */
- err = sta_info_insert_drv_state(local, sdata, sta);
- if (err)
- goto out_err;
-
local->num_sta++;
local->sta_generation++;
smp_mb();
+ /* simplify things and don't accept BA sessions yet */
+ set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
/* make the station visible */
sta_info_hash_add(local, sta);
list_add_rcu(&sta->list, &local->sta_list);
+ /* notify driver */
+ err = sta_info_insert_drv_state(local, sdata, sta);
+ if (err)
+ goto out_remove;
+
set_sta_flag(sta, WLAN_STA_INSERTED);
+ /* accept BA sessions now */
+ clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
ieee80211_recalc_min_chandef(sdata);
ieee80211_sta_debugfs_add(sta);
@@ -522,6 +537,12 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
mesh_accept_plinks_update(sdata);
return 0;
+ out_remove:
+ sta_info_hash_del(local, sta);
+ list_del_rcu(&sta->list);
+ local->num_sta--;
+ synchronize_net();
+ __cleanup_single_sta(sta);
out_err:
mutex_unlock(&local->sta_mtx);
rcu_read_lock();
@@ -1071,10 +1092,14 @@ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif,
}
EXPORT_SYMBOL(ieee80211_find_sta);
-static void clear_sta_ps_flags(void *_sta)
+/* powersave support code */
+void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
{
- struct sta_info *sta = _sta;
struct ieee80211_sub_if_data *sdata = sta->sdata;
+ struct ieee80211_local *local = sdata->local;
+ struct sk_buff_head pending;
+ int filtered = 0, buffered = 0, ac;
+ unsigned long flags;
struct ps_data *ps;
if (sdata->vif.type == NL80211_IFTYPE_AP ||
@@ -1085,20 +1110,6 @@ static void clear_sta_ps_flags(void *_sta)
else
return;
- clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
- if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA))
- atomic_dec(&ps->num_sta_ps);
-}
-
-/* powersave support code */
-void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
-{
- struct ieee80211_sub_if_data *sdata = sta->sdata;
- struct ieee80211_local *local = sdata->local;
- struct sk_buff_head pending;
- int filtered = 0, buffered = 0, ac;
- unsigned long flags;
-
clear_sta_flag(sta, WLAN_STA_SP);
BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
@@ -1109,6 +1120,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
skb_queue_head_init(&pending);
+ /* sync with ieee80211_tx_h_unicast_ps_buf */
+ spin_lock(&sta->ps_lock);
/* Send all buffered frames to the station */
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
int count = skb_queue_len(&pending), tmp;
@@ -1127,7 +1140,12 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
buffered += tmp - count;
}
- ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+ ieee80211_add_pending_skbs(local, &pending);
+ clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
+ clear_sta_flag(sta, WLAN_STA_PS_STA);
+ spin_unlock(&sta->ps_lock);
+
+ atomic_dec(&ps->num_sta_ps);
/* This station just woke up and isn't aware of our SMPS state */
if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d77ff70..d3a6d82 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -267,6 +267,7 @@ struct ieee80211_tx_latency_stat {
* @drv_unblock_wk: used for driver PS unblocking
* @listen_interval: listen interval of this station, when we're acting as AP
* @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
* @ps_tx_buf: buffers (per AC) of frames to transmit to this station
* when it leaves power saving state or polls
* @tx_filtered: buffers (per AC) of frames we already tried to
@@ -356,10 +357,8 @@ struct sta_info {
/* use the accessors defined below */
unsigned long _flags;
- /*
- * STA powersave frame queues, no more than the internal
- * locking required.
- */
+ /* STA powersave lock and frame queues */
+ spinlock_t ps_lock;
struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
unsigned long driver_buffered_tids;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 97a02d3..4080c61 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -478,6 +478,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
sta->sta.addr, sta->sta.aid, ac);
if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
purge_old_ps_buffers(tx->local);
+
+ /* sync with ieee80211_sta_ps_deliver_wakeup */
+ spin_lock(&sta->ps_lock);
+ /*
+ * STA woke up the meantime and all the frames on ps_tx_buf have
+ * been queued to pending queue. No reordering can happen, go
+ * ahead and Tx the packet.
+ */
+ if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+ !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+ spin_unlock(&sta->ps_lock);
+ return TX_CONTINUE;
+ }
+
if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
ps_dbg(tx->sdata,
@@ -492,6 +506,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+ spin_unlock(&sta->ps_lock);
if (!timer_pending(&local->sta_cleanup))
mod_timer(&local->sta_cleanup,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 676dc09..b8700d4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -435,9 +435,8 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local,
spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
}
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
- struct sk_buff_head *skbs,
- void (*fn)(void *data), void *data)
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+ struct sk_buff_head *skbs)
{
struct ieee80211_hw *hw = &local->hw;
struct sk_buff *skb;
@@ -461,9 +460,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
__skb_queue_tail(&local->pending[queue], skb);
}
- if (fn)
- fn(data);
-
for (i = 0; i < hw->queues; i++)
__ieee80211_wake_queue(hw, i,
IEEE80211_QUEUE_STOP_REASON_SKB_ADD);
@@ -1741,6 +1737,26 @@ int ieee80211_reconfig(struct ieee80211_local *local)
IEEE80211_QUEUE_STOP_REASON_SUSPEND);
/*
+ * Reconfigure sched scan if it was interrupted by FW restart or
+ * suspend.
+ */
+ mutex_lock(&local->mtx);
+ sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
+ lockdep_is_held(&local->mtx));
+ if (sched_scan_sdata && local->sched_scan_req)
+ /*
+ * Sched scan stopped, but we don't want to report it. Instead,
+ * we're trying to reschedule.
+ */
+ if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
+ local->sched_scan_req))
+ sched_scan_stopped = true;
+ mutex_unlock(&local->mtx);
+
+ if (sched_scan_stopped)
+ cfg80211_sched_scan_stopped(local->hw.wiphy);
+
+ /*
* If this is for hw restart things are still running.
* We may want to change that later, however.
*/
@@ -1768,26 +1784,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
WARN_ON(1);
#endif
- /*
- * Reconfigure sched scan if it was interrupted by FW restart or
- * suspend.
- */
- mutex_lock(&local->mtx);
- sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
- lockdep_is_held(&local->mtx));
- if (sched_scan_sdata && local->sched_scan_req)
- /*
- * Sched scan stopped, but we don't want to report it. Instead,
- * we're trying to reschedule.
- */
- if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
- local->sched_scan_req))
- sched_scan_stopped = true;
- mutex_unlock(&local->mtx);
-
- if (sched_scan_stopped)
- cfg80211_sched_scan_stopped(local->hw.wiphy);
-
return 0;
}
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 21211c6..d51422c 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -154,6 +154,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
return IEEE80211_AC_BE;
}
+ if (skb->protocol == sdata->control_port_protocol) {
+ skb->priority = 7;
+ return ieee80211_downgrade_queue(sdata, skb);
+ }
+
/* use the data classifier to determine what 802.1d tag the
* data frame has */
rcu_read_lock();
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index bb322d0..b9f0e03 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1310,27 +1310,22 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
}
static int
-ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
+ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
{
#ifdef CONFIG_NF_NAT_NEEDED
int ret;
- if (cda[CTA_NAT_DST]) {
- ret = ctnetlink_parse_nat_setup(ct,
- NF_NAT_MANIP_DST,
- cda[CTA_NAT_DST]);
- if (ret < 0)
- return ret;
- }
- if (cda[CTA_NAT_SRC]) {
- ret = ctnetlink_parse_nat_setup(ct,
- NF_NAT_MANIP_SRC,
- cda[CTA_NAT_SRC]);
- if (ret < 0)
- return ret;
- }
- return 0;
+ ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
+ cda[CTA_NAT_DST]);
+ if (ret < 0)
+ return ret;
+
+ ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+ cda[CTA_NAT_SRC]);
+ return ret;
#else
+ if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+ return 0;
return -EOPNOTSUPP;
#endif
}
@@ -1659,11 +1654,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
goto err2;
}
- if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
- err = ctnetlink_change_nat(ct, cda);
- if (err < 0)
- goto err2;
- }
+ err = ctnetlink_setup_nat(ct, cda);
+ if (err < 0)
+ goto err2;
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d3f5cd6..52ca952 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -432,15 +432,15 @@ nf_nat_setup_info(struct nf_conn *ct,
}
EXPORT_SYMBOL(nf_nat_setup_info);
-unsigned int
-nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+static unsigned int
+__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
{
/* Force range to this IP; let proto decide mapping for
* per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
* Use reply in case it's already been mangled (eg local packet).
*/
union nf_inet_addr ip =
- (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+ (manip == NF_NAT_MANIP_SRC ?
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
struct nf_nat_range range = {
@@ -448,7 +448,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
.min_addr = ip,
.max_addr = ip,
};
- return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+ return nf_nat_setup_info(ct, &range, manip);
+}
+
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+ return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
}
EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
@@ -702,9 +708,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
static int
nfnetlink_parse_nat(const struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range)
+ const struct nf_conn *ct, struct nf_nat_range *range,
+ const struct nf_nat_l3proto *l3proto)
{
- const struct nf_nat_l3proto *l3proto;
struct nlattr *tb[CTA_NAT_MAX+1];
int err;
@@ -714,38 +720,46 @@ nfnetlink_parse_nat(const struct nlattr *nat,
if (err < 0)
return err;
- rcu_read_lock();
- l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
- if (l3proto == NULL) {
- err = -EAGAIN;
- goto out;
- }
err = l3proto->nlattr_to_range(tb, range);
if (err < 0)
- goto out;
+ return err;
if (!tb[CTA_NAT_PROTO])
- goto out;
+ return 0;
- err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
-out:
- rcu_read_unlock();
- return err;
+ return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
}
+/* This function is called under rcu_read_lock() */
static int
nfnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
struct nf_nat_range range;
+ const struct nf_nat_l3proto *l3proto;
int err;
- err = nfnetlink_parse_nat(attr, ct, &range);
+ /* Should not happen, restricted to creating new conntracks
+ * via ctnetlink.
+ */
+ if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
+ return -EEXIST;
+
+ /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
+ * attach the null binding, otherwise this may oops.
+ */
+ l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
+ if (l3proto == NULL)
+ return -EAGAIN;
+
+ /* No NAT information has been passed, allocate the null-binding */
+ if (attr == NULL)
+ return __nf_nat_alloc_null_binding(ct, manip);
+
+ err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
if (err < 0)
return err;
- if (nf_nat_initialized(ct, manip))
- return -EEXIST;
return nf_nat_setup_info(ct, &range, manip);
}
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e8254ad..425cf39 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -116,7 +116,7 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
skb->sk->sk_socket->file->f_cred->fsgid);
read_unlock_bh(&skb->sk->sk_callback_lock);
break;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
case NFT_META_RTCLASSID: {
const struct dst_entry *dst = skb_dst(skb);
@@ -199,7 +199,7 @@ static int nft_meta_init_validate_get(uint32_t key)
case NFT_META_OIFTYPE:
case NFT_META_SKUID:
case NFT_META_SKGID:
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
case NFT_META_RTCLASSID:
#endif
#ifdef CONFIG_NETWORK_SECMARK
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a2aeb31..85daa84 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
return ERR_PTR(-EINVAL);
- if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+ if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
+ base != NFT_PAYLOAD_LL_HEADER)
return &nft_payload_fast_ops;
else
return &nft_payload_ops;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 8a310f2..b718a52 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -21,9 +21,9 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
{
switch (pkt->ops->pf) {
case NFPROTO_IPV4:
- nft_reject_ipv4_eval(expr, data, pkt);
+ return nft_reject_ipv4_eval(expr, data, pkt);
case NFPROTO_IPV6:
- nft_reject_ipv6_eval(expr, data, pkt);
+ return nft_reject_ipv6_eval(expr, data, pkt);
}
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fdf5135..04748ab6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1489,8 +1489,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
- /* Only superuser is allowed to send multicasts */
- if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ if ((nladdr->nl_groups || nladdr->nl_pid) &&
+ !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
if (!nlk->portid)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 46bda01..56db888 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -301,7 +301,7 @@ static int nci_open_device(struct nci_dev *ndev)
rc = __nci_request(ndev, nci_reset_req, 0,
msecs_to_jiffies(NCI_RESET_TIMEOUT));
- if (ndev->ops->setup(ndev))
+ if (ndev->ops->setup)
ndev->ops->setup(ndev);
if (!rc) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6a2bb37..48a6a93 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -308,11 +308,27 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
return po->xmit == packet_direct_xmit;
}
-static u16 packet_pick_tx_queue(struct net_device *dev)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
{
return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
}
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ u16 queue_index;
+
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb, NULL,
+ __packet_pick_tx_queue);
+ queue_index = netdev_cap_txqueue(dev, queue_index);
+ } else {
+ queue_index = __packet_pick_tx_queue(dev, skb);
+ }
+
+ skb_set_queue_mapping(skb, queue_index);
+}
+
/* register_prot_hook must be invoked with the po->bind_lock held,
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
@@ -2285,7 +2301,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
}
}
- skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+ packet_pick_tx_queue(dev, skb);
+
skb->destructor = tpacket_destruct_skb;
__packet_set_status(po, ph, TP_STATUS_SENDING);
packet_inc_pending(&po->tx_ring);
@@ -2499,7 +2516,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+
+ packet_pick_tx_queue(dev, skb);
if (po->has_vnet_hdr) {
if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -3786,7 +3804,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
*/
if (!tx_ring)
init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
- break;
+ break;
default:
break;
}
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index a255d02..fefeeb7 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -15,6 +15,11 @@
*
* ECN support is added by Naeem Khademi <naeemk@ifi.uio.no>
* University of Oslo, Norway.
+ *
+ * References:
+ * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00
+ * IEEE Conference on High Performance Switching and Routing 2013 :
+ * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem"
*/
#include <linux/module.h>
@@ -36,7 +41,7 @@ struct pie_params {
psched_time_t target; /* user specified target delay in pschedtime */
u32 tupdate; /* timer frequency (in jiffies) */
u32 limit; /* number of packets that can be enqueued */
- u32 alpha; /* alpha and beta are between -4 and 4 */
+ u32 alpha; /* alpha and beta are between 0 and 32 */
u32 beta; /* and are used for shift relative to 1 */
bool ecn; /* true if ecn is enabled */
bool bytemode; /* to scale drop early prob based on pkt size */
@@ -326,10 +331,16 @@ static void calculate_probability(struct Qdisc *sch)
if (qdelay == 0 && qlen != 0)
update_prob = false;
- /* Add ranges for alpha and beta, more aggressive for high dropping
- * mode and gentle steps for light dropping mode
- * In light dropping mode, take gentle steps; in medium dropping mode,
- * take medium steps; in high dropping mode, take big steps.
+ /* In the algorithm, alpha and beta are between 0 and 2 with typical
+ * value for alpha as 0.125. In this implementation, we use values 0-32
+ * passed from user space to represent this. Also, alpha and beta have
+ * unit of HZ and need to be scaled before they can used to update
+ * probability. alpha/beta are updated locally below by 1) scaling them
+ * appropriately 2) scaling down by 16 to come to 0-2 range.
+ * Please see paper for details.
+ *
+ * We scale alpha and beta differently depending on whether we are in
+ * light, medium or high dropping mode.
*/
if (q->vars.prob < MAX_PROB / 100) {
alpha =
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1cb413f..4f505a0 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -334,18 +334,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
tb[TCA_TBF_PTAB]));
- if (q->qdisc != &noop_qdisc) {
- err = fifo_set_limit(q->qdisc, qopt->limit);
- if (err)
- goto done;
- } else if (qopt->limit > 0) {
- child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
- if (IS_ERR(child)) {
- err = PTR_ERR(child);
- goto done;
- }
- }
-
buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
@@ -390,6 +378,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
goto done;
}
+ if (q->qdisc != &noop_qdisc) {
+ err = fifo_set_limit(q->qdisc, qopt->limit);
+ if (err)
+ goto done;
+ } else if (qopt->limit > 0) {
+ child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
+ if (IS_ERR(child)) {
+ err = PTR_ERR(child);
+ goto done;
+ }
+ }
+
sch_tree_lock(sch);
if (child) {
qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5ae6092..ee13d28 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1239,78 +1239,107 @@ void sctp_assoc_update(struct sctp_association *asoc,
}
/* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ * When there is outbound data to send and the primary path
+ * becomes inactive (e.g., due to failures), or where the
+ * SCTP user explicitly requests to send data to an
+ * inactive destination transport address, before reporting
+ * an error to its ULP, the SCTP endpoint should try to send
+ * the data to an alternate active destination transport
+ * address if one exists.
+ *
+ * When retransmitting data that timed out, if the endpoint
+ * is multihomed, it should consider each source-destination
+ * address pair in its retransmission selection policy.
+ * When retransmitting timed-out data, the endpoint should
+ * attempt to pick the most divergent source-destination
+ * pair from the original source-destination pair to which
+ * the packet was transmitted.
+ *
+ * Note: Rules for picking the most divergent source-destination
+ * pair are an implementation decision and are not specified
+ * within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
*/
-void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+static const u8 sctp_trans_state_to_prio_map[] = {
+ [SCTP_ACTIVE] = 3, /* best case */
+ [SCTP_UNKNOWN] = 2,
+ [SCTP_PF] = 1,
+ [SCTP_INACTIVE] = 0, /* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
{
- struct sctp_transport *t, *next;
- struct list_head *head = &asoc->peer.transport_addr_list;
- struct list_head *pos;
+ return sctp_trans_state_to_prio_map[trans->state];
+}
- if (asoc->peer.transport_count == 1)
- return;
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+ struct sctp_transport *best)
+{
+ if (best == NULL)
+ return curr;
- /* Find the next transport in a round-robin fashion. */
- t = asoc->peer.retran_path;
- pos = &t->transports;
- next = NULL;
+ return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+}
- while (1) {
- /* Skip the head. */
- if (pos->next == head)
- pos = head->next;
- else
- pos = pos->next;
+void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+{
+ struct sctp_transport *trans = asoc->peer.retran_path;
+ struct sctp_transport *trans_next = NULL;
- t = list_entry(pos, struct sctp_transport, transports);
+ /* We're done as we only have the one and only path. */
+ if (asoc->peer.transport_count == 1)
+ return;
+ /* If active_path and retran_path are the same and active,
+ * then this is the only active path. Use it.
+ */
+ if (asoc->peer.active_path == asoc->peer.retran_path &&
+ asoc->peer.active_path->state == SCTP_ACTIVE)
+ return;
- /* We have exhausted the list, but didn't find any
- * other active transports. If so, use the next
- * transport.
- */
- if (t == asoc->peer.retran_path) {
- t = next;
+ /* Iterate from retran_path's successor back to retran_path. */
+ for (trans = list_next_entry(trans, transports); 1;
+ trans = list_next_entry(trans, transports)) {
+ /* Manually skip the head element. */
+ if (&trans->transports == &asoc->peer.transport_addr_list)
+ continue;
+ if (trans->state == SCTP_UNCONFIRMED)
+ continue;
+ trans_next = sctp_trans_elect_best(trans, trans_next);
+ /* Active is good enough for immediate return. */
+ if (trans_next->state == SCTP_ACTIVE)
break;
- }
-
- /* Try to find an active transport. */
-
- if ((t->state == SCTP_ACTIVE) ||
- (t->state == SCTP_UNKNOWN)) {
+ /* We've reached the end, time to update path. */
+ if (trans == asoc->peer.retran_path)
break;
- } else {
- /* Keep track of the next transport in case
- * we don't find any active transport.
- */
- if (t->state != SCTP_UNCONFIRMED && !next)
- next = t;
- }
}
- if (t)
- asoc->peer.retran_path = t;
- else
- t = asoc->peer.retran_path;
+ if (trans_next != NULL)
+ asoc->peer.retran_path = trans_next;
- pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
- &t->ipaddr.sa);
+ pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+ __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
}
-/* Choose the transport for sending retransmit packet. */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
- struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+ struct sctp_transport *last_sent_to)
{
/* If this is the first time packet is sent, use the active path,
* else use the retran path. If the last packet was sent over the
* retran path, update the retran path and use it.
*/
- if (!last_sent_to)
+ if (last_sent_to == NULL) {
return asoc->peer.active_path;
- else {
+ } else {
if (last_sent_to == asoc->peer.retran_path)
sctp_assoc_update_retran_path(asoc);
+
return asoc->peer.retran_path;
}
}
@@ -1367,44 +1396,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc)
return false;
}
-/* Increase asoc's rwnd by len and send any window update SACK if needed. */
-void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
+/* Update asoc's rwnd for the approximated state in the buffer,
+ * and check whether SACK needs to be sent.
+ */
+void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
{
+ int rx_count;
struct sctp_chunk *sack;
struct timer_list *timer;
- if (asoc->rwnd_over) {
- if (asoc->rwnd_over >= len) {
- asoc->rwnd_over -= len;
- } else {
- asoc->rwnd += (len - asoc->rwnd_over);
- asoc->rwnd_over = 0;
- }
- } else {
- asoc->rwnd += len;
- }
+ if (asoc->ep->rcvbuf_policy)
+ rx_count = atomic_read(&asoc->rmem_alloc);
+ else
+ rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
- /* If we had window pressure, start recovering it
- * once our rwnd had reached the accumulated pressure
- * threshold. The idea is to recover slowly, but up
- * to the initial advertised window.
- */
- if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
- int change = min(asoc->pathmtu, asoc->rwnd_press);
- asoc->rwnd += change;
- asoc->rwnd_press -= change;
- }
+ if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
+ asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
+ else
+ asoc->rwnd = 0;
- pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
- __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
- asoc->a_rwnd);
+ pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
+ __func__, asoc, asoc->rwnd, rx_count,
+ asoc->base.sk->sk_rcvbuf);
/* Send a window update SACK if the rwnd has increased by at least the
* minimum of the association's PMTU and half of the receive buffer.
* The algorithm used is similar to the one described in
* Section 4.2.3.3 of RFC 1122.
*/
- if (sctp_peer_needs_update(asoc)) {
+ if (update_peer && sctp_peer_needs_update(asoc)) {
asoc->a_rwnd = asoc->rwnd;
pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1426,45 +1446,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
}
}
-/* Decrease asoc's rwnd by len. */
-void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
-{
- int rx_count;
- int over = 0;
-
- if (unlikely(!asoc->rwnd || asoc->rwnd_over))
- pr_debug("%s: association:%p has asoc->rwnd:%u, "
- "asoc->rwnd_over:%u!\n", __func__, asoc,
- asoc->rwnd, asoc->rwnd_over);
-
- if (asoc->ep->rcvbuf_policy)
- rx_count = atomic_read(&asoc->rmem_alloc);
- else
- rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
-
- /* If we've reached or overflowed our receive buffer, announce
- * a 0 rwnd if rwnd would still be positive. Store the
- * the potential pressure overflow so that the window can be restored
- * back to original value.
- */
- if (rx_count >= asoc->base.sk->sk_rcvbuf)
- over = 1;
-
- if (asoc->rwnd >= len) {
- asoc->rwnd -= len;
- if (over) {
- asoc->rwnd_press += asoc->rwnd;
- asoc->rwnd = 0;
- }
- } else {
- asoc->rwnd_over = len - asoc->rwnd;
- asoc->rwnd = 0;
- }
-
- pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
- __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
- asoc->rwnd_press);
-}
/* Build the bind address list for the association based on info from the
* local endpoint and the remote peer.
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index bd85915..5d6883f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -495,11 +495,12 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
}
/* If the transport error count is greater than the pf_retrans
- * threshold, and less than pathmaxrtx, then mark this transport
- * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
- * point 1
+ * threshold, and less than pathmaxrtx, and if the current state
+ * is not SCTP_UNCONFIRMED, then mark this transport as Partially
+ * Failed, see SCTP Quick Failover Draft, section 5.1
*/
if ((transport->state != SCTP_PF) &&
+ (transport->state != SCTP_UNCONFIRMED) &&
(asoc->pf_retrans < transport->pathmaxrxt) &&
(transport->error_count > asoc->pf_retrans)) {
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 483dcd7..ae65b6b 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -758,6 +758,13 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
struct sctp_chunk auth;
sctp_ierror_t ret;
+ /* Make sure that we and the peer are AUTH capable */
+ if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+ kfree_skb(chunk->auth_chunk);
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ }
+
/* set-up our fake chunk so that we can process it */
auth.skb = chunk->auth_chunk;
auth.asoc = chunk->asoc;
@@ -6176,7 +6183,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
* PMTU. In cases, such as loopback, this might be a rather
* large spill over.
*/
- if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
+ if ((!chunk->data_accepted) && (!asoc->rwnd ||
(datalen > asoc->rwnd + asoc->frag_point))) {
/* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e91d6e..981aaf8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,6 +64,7 @@
#include <linux/crypto.h>
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/compat.h>
#include <net/ip.h>
#include <net/icmp.h>
@@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk,
/*
* New (hopefully final) interface for the API.
* We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations. The only defferent part
+ * can avoid any unnecessary allocations. The only different part
* is that we store the actual length of the address buffer into the
- * addrs_num structure member. That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
* code.
*/
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+ sctp_assoc_t assoc_id;
+ s32 addr_num;
+ compat_uptr_t addrs; /* struct sockaddr * */
+};
+#endif
+
static int sctp_getsockopt_connectx3(struct sock *sk, int len,
char __user *optval,
int __user *optlen)
@@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len,
sctp_assoc_t assoc_id = 0;
int err = 0;
- if (len < sizeof(param))
- return -EINVAL;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ struct compat_sctp_getaddrs_old param32;
- if (copy_from_user(&param, optval, sizeof(param)))
- return -EFAULT;
+ if (len < sizeof(param32))
+ return -EINVAL;
+ if (copy_from_user(&param32, optval, sizeof(param32)))
+ return -EFAULT;
- err = __sctp_setsockopt_connectx(sk,
- (struct sockaddr __user *)param.addrs,
- param.addr_num, &assoc_id);
+ param.assoc_id = param32.assoc_id;
+ param.addr_num = param32.addr_num;
+ param.addrs = compat_ptr(param32.addrs);
+ } else
+#endif
+ {
+ if (len < sizeof(param))
+ return -EINVAL;
+ if (copy_from_user(&param, optval, sizeof(param)))
+ return -EFAULT;
+ }
+ err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+ param.addrs, param.addr_num,
+ &assoc_id);
if (err == 0 || err == -EINPROGRESS) {
if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
return -EFAULT;
@@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
sctp_skb_pull(skb, copied);
skb_queue_head(&sk->sk_receive_queue, skb);
- /* When only partial message is copied to the user, increase
- * rwnd by that amount. If all the data in the skb is read,
- * rwnd is updated when the event is freed.
- */
- if (!sctp_ulpevent_is_notification(event))
- sctp_assoc_rwnd_increase(event->asoc, copied);
goto out;
} else if ((event->msg_flags & MSG_NOTIFICATION) ||
(event->msg_flags & MSG_EOR))
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7135e61..35c8923 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = {
},
{
.procname = "cookie_hmac_alg",
+ .data = &init_net.sctp.sctp_hmac_alg,
.maxlen = 8,
.mode = 0644,
.proc_handler = proc_sctp_do_hmac_alg,
@@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
int sctp_sysctl_net_register(struct net *net)
{
- struct ctl_table *table;
- int i;
+ struct ctl_table *table = sctp_net_table;
+
+ if (!net_eq(net, &init_net)) {
+ int i;
- table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
- if (!table)
- return -ENOMEM;
+ table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
- for (i = 0; table[i].data; i++)
- table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ for (i = 0; table[i].data; i++)
+ table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ }
net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
return 0;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c6465..8d198ae 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
skb = sctp_event2skb(event);
/* Set the owner and charge rwnd for bytes received. */
sctp_ulpevent_set_owner(event, asoc);
- sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+ sctp_assoc_rwnd_update(asoc, false);
if (!skb->data_len)
return;
@@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
{
struct sk_buff *skb, *frag;
unsigned int len;
+ struct sctp_association *asoc;
/* Current stack structures assume that the rcv buffer is
* per socket. For UDP style sockets this is not true as
@@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
}
done:
- sctp_assoc_rwnd_increase(event->asoc, len);
+ asoc = event->asoc;
+ sctp_association_hold(asoc);
sctp_ulpevent_release_owner(event);
+ sctp_assoc_rwnd_update(asoc, true);
+ sctp_association_put(asoc);
}
static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 6c0513a..36e431e 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -108,6 +108,7 @@ struct gss_auth {
static DEFINE_SPINLOCK(pipe_version_lock);
static struct rpc_wait_queue pipe_version_rpc_waitqueue;
static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
+static void gss_put_auth(struct gss_auth *gss_auth);
static void gss_free_ctx(struct gss_cl_ctx *);
static const struct rpc_pipe_ops gss_upcall_ops_v0;
@@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg)
if (gss_msg->ctx != NULL)
gss_put_ctx(gss_msg->ctx);
rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue);
+ gss_put_auth(gss_msg->auth);
kfree(gss_msg);
}
@@ -498,9 +500,12 @@ gss_alloc_msg(struct gss_auth *gss_auth,
default:
err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
if (err)
- goto err_free_msg;
+ goto err_put_pipe_version;
};
+ kref_get(&gss_auth->kref);
return gss_msg;
+err_put_pipe_version:
+ put_pipe_version(gss_auth->net);
err_free_msg:
kfree(gss_msg);
err:
@@ -991,6 +996,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor);
if (gss_auth->service == 0)
goto err_put_mech;
+ if (!gssd_running(gss_auth->net))
+ goto err_put_mech;
auth = &gss_auth->rpc_auth;
auth->au_cslack = GSS_CRED_SLACK >> 2;
auth->au_rslack = GSS_VERF_SLACK >> 2;
@@ -1062,6 +1069,12 @@ gss_free_callback(struct kref *kref)
}
static void
+gss_put_auth(struct gss_auth *gss_auth)
+{
+ kref_put(&gss_auth->kref, gss_free_callback);
+}
+
+static void
gss_destroy(struct rpc_auth *auth)
{
struct gss_auth *gss_auth = container_of(auth,
@@ -1082,7 +1095,7 @@ gss_destroy(struct rpc_auth *auth)
gss_auth->gss_pipe[1] = NULL;
rpcauth_destroy_credcache(auth);
- kref_put(&gss_auth->kref, gss_free_callback);
+ gss_put_auth(gss_auth);
}
/*
@@ -1253,7 +1266,7 @@ gss_destroy_nullcred(struct rpc_cred *cred)
call_rcu(&cred->cr_rcu, gss_free_cred_callback);
if (ctx)
gss_put_ctx(ctx);
- kref_put(&gss_auth->kref, gss_free_callback);
+ gss_put_auth(gss_auth);
}
static void
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 890a299..e860d4f 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req)
free_page((unsigned long)xbufp->head[0].iov_base);
xbufp = &req->rq_snd_buf;
free_page((unsigned long)xbufp->head[0].iov_base);
- list_del(&req->rq_bc_pa_list);
kfree(req);
}
@@ -168,8 +167,10 @@ out_free:
/*
* Memory allocation failed, free the temporary list
*/
- list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+ list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+ list_del(&req->rq_bc_pa_list);
xprt_free_allocation(req);
+ }
dprintk("RPC: setup backchannel transport failed\n");
return -ENOMEM;
@@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs)
xprt_dec_alloc_count(xprt, max_reqs);
list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
dprintk("RPC: req=%p\n", req);
+ list_del(&req->rq_bc_pa_list);
xprt_free_allocation(req);
if (--max_reqs == 0)
break;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 817a1e5..0addefc 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -510,6 +510,7 @@ static int xs_nospace(struct rpc_task *task)
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
int ret = -EAGAIN;
dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -527,7 +528,7 @@ static int xs_nospace(struct rpc_task *task)
* window size
*/
set_bit(SOCK_NOSPACE, &transport->sock->flags);
- transport->inet->sk_write_pending++;
+ sk->sk_write_pending++;
/* ...and wait for more buffer space */
xprt_wait_for_buffer_space(task, xs_nospace_callback);
}
@@ -537,6 +538,9 @@ static int xs_nospace(struct rpc_task *task)
}
spin_unlock_bh(&xprt->transport_lock);
+
+ /* Race breaker in case memory is freed before above code is called */
+ sk->sk_write_space(sk);
return ret;
}
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index a38c899..574b861 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -610,8 +610,13 @@ static struct notifier_block notifier = {
int tipc_bearer_setup(void)
{
+ int err;
+
+ err = register_netdevice_notifier(&notifier);
+ if (err)
+ return err;
dev_add_pack(&tipc_packet_type);
- return register_netdevice_notifier(&notifier);
+ return 0;
}
void tipc_bearer_cleanup(void)
diff --git a/net/tipc/config.c b/net/tipc/config.c
index c301a9a..e74eef2 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -181,7 +181,7 @@ static struct sk_buff *cfg_set_own_addr(void)
if (tipc_own_addr)
return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (cannot change node address once assigned)");
- tipc_core_start_net(addr);
+ tipc_net_start(addr);
return tipc_cfg_reply_none();
}
diff --git a/net/tipc/core.c b/net/tipc/core.c
index f9e88d8..80c2064 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -77,37 +77,13 @@ struct sk_buff *tipc_buf_acquire(u32 size)
}
/**
- * tipc_core_stop_net - shut down TIPC networking sub-systems
- */
-static void tipc_core_stop_net(void)
-{
- tipc_net_stop();
- tipc_bearer_cleanup();
-}
-
-/**
- * start_net - start TIPC networking sub-systems
- */
-int tipc_core_start_net(unsigned long addr)
-{
- int res;
-
- tipc_net_start(addr);
- res = tipc_bearer_setup();
- if (res < 0)
- goto err;
- return res;
-
-err:
- tipc_core_stop_net();
- return res;
-}
-
-/**
* tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
*/
static void tipc_core_stop(void)
{
+ tipc_handler_stop();
+ tipc_net_stop();
+ tipc_bearer_cleanup();
tipc_netlink_stop();
tipc_cfg_stop();
tipc_subscr_stop();
@@ -122,30 +98,65 @@ static void tipc_core_stop(void)
*/
static int tipc_core_start(void)
{
- int res;
+ int err;
get_random_bytes(&tipc_random, sizeof(tipc_random));
- res = tipc_handler_start();
- if (!res)
- res = tipc_ref_table_init(tipc_max_ports, tipc_random);
- if (!res)
- res = tipc_nametbl_init();
- if (!res)
- res = tipc_netlink_start();
- if (!res)
- res = tipc_socket_init();
- if (!res)
- res = tipc_register_sysctl();
- if (!res)
- res = tipc_subscr_start();
- if (!res)
- res = tipc_cfg_init();
- if (res) {
- tipc_handler_stop();
- tipc_core_stop();
- }
- return res;
+ err = tipc_handler_start();
+ if (err)
+ goto out_handler;
+
+ err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+ if (err)
+ goto out_reftbl;
+
+ err = tipc_nametbl_init();
+ if (err)
+ goto out_nametbl;
+
+ err = tipc_netlink_start();
+ if (err)
+ goto out_netlink;
+
+ err = tipc_socket_init();
+ if (err)
+ goto out_socket;
+
+ err = tipc_register_sysctl();
+ if (err)
+ goto out_sysctl;
+
+ err = tipc_subscr_start();
+ if (err)
+ goto out_subscr;
+
+ err = tipc_cfg_init();
+ if (err)
+ goto out_cfg;
+
+ err = tipc_bearer_setup();
+ if (err)
+ goto out_bearer;
+
+ return 0;
+out_bearer:
+ tipc_cfg_stop();
+out_cfg:
+ tipc_subscr_stop();
+out_subscr:
+ tipc_unregister_sysctl();
+out_sysctl:
+ tipc_socket_stop();
+out_socket:
+ tipc_netlink_stop();
+out_netlink:
+ tipc_nametbl_stop();
+out_nametbl:
+ tipc_ref_table_stop();
+out_reftbl:
+ tipc_handler_stop();
+out_handler:
+ return err;
}
static int __init tipc_init(void)
@@ -174,8 +185,6 @@ static int __init tipc_init(void)
static void __exit tipc_exit(void)
{
- tipc_handler_stop();
- tipc_core_stop_net();
tipc_core_stop();
pr_info("Deactivated\n");
}
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 1ff477b..4dfe137 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -90,7 +90,6 @@ extern int tipc_random __read_mostly;
/*
* Routines available to privileged subsystems
*/
-int tipc_core_start_net(unsigned long);
int tipc_handler_start(void);
void tipc_handler_stop(void);
int tipc_netlink_start(void);
@@ -192,6 +191,7 @@ static inline void k_term_timer(struct timer_list *timer)
struct tipc_skb_cb {
void *handle;
+ bool deferred;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/link.c b/net/tipc/link.c
index d4b5de4..da6018b 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1391,6 +1391,12 @@ static int link_recv_buf_validate(struct sk_buff *buf)
u32 hdr_size;
u32 min_hdr_size;
+ /* If this packet comes from the defer queue, the skb has already
+ * been validated
+ */
+ if (unlikely(TIPC_SKB_CB(buf)->deferred))
+ return 1;
+
if (unlikely(buf->len < MIN_H_SIZE))
return 0;
@@ -1703,6 +1709,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
&l_ptr->newest_deferred_in, buf)) {
l_ptr->deferred_inqueue_sz++;
l_ptr->stats.deferred_recv++;
+ TIPC_SKB_CB(buf)->deferred = true;
if ((l_ptr->deferred_inqueue_sz % 16) == 1)
tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
} else
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 92a1533..48302be 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -945,9 +945,6 @@ void tipc_nametbl_stop(void)
{
u32 i;
- if (!table.types)
- return;
-
/* Verify name table is empty, then release it */
write_lock_bh(&tipc_nametbl_lock);
for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9f72a63..3aaf73d 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -83,8 +83,6 @@ static struct genl_ops tipc_genl_ops[] = {
},
};
-static int tipc_genl_family_registered;
-
int tipc_netlink_start(void)
{
int res;
@@ -94,16 +92,10 @@ int tipc_netlink_start(void)
pr_err("Failed to register netlink interface\n");
return res;
}
-
- tipc_genl_family_registered = 1;
return 0;
}
void tipc_netlink_stop(void)
{
- if (!tipc_genl_family_registered)
- return;
-
genl_unregister_family(&tipc_genl_family);
- tipc_genl_family_registered = 0;
}
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
index 2a2a938..de3d593 100644
--- a/net/tipc/ref.c
+++ b/net/tipc/ref.c
@@ -126,9 +126,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start)
*/
void tipc_ref_table_stop(void)
{
- if (!tipc_ref_table.entries)
- return;
-
vfree(tipc_ref_table.entries);
tipc_ref_table.entries = NULL;
}
diff --git a/net/tipc/server.c b/net/tipc/server.c
index b635ca3..3739797 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -573,7 +573,6 @@ int tipc_server_start(struct tipc_server *s)
kmem_cache_destroy(s->rcvbuf_cache);
return ret;
}
- s->enabled = 1;
return ret;
}
@@ -583,10 +582,6 @@ void tipc_server_stop(struct tipc_server *s)
int total = 0;
int id;
- if (!s->enabled)
- return;
-
- s->enabled = 0;
spin_lock_bh(&s->idr_lock);
for (id = 0; total < s->idr_in_use; id++) {
con = idr_find(&s->conn_idr, id);
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 98b23f2..be817b0 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -56,7 +56,6 @@
* @name: server name
* @imp: message importance
* @type: socket type
- * @enabled: identify whether server is launched or not
*/
struct tipc_server {
struct idr conn_idr;
@@ -74,7 +73,6 @@ struct tipc_server {
const char name[TIPC_SERVER_NAME_LEN];
int imp;
int type;
- int enabled;
};
int tipc_conn_sendmsg(struct tipc_server *s, int conid,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index aab4948..a4cf274 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -70,8 +70,6 @@ static const struct proto_ops msg_ops;
static struct proto tipc_proto;
static struct proto tipc_proto_kern;
-static int sockets_enabled;
-
/*
* Revised TIPC socket locking policy:
*
@@ -2027,8 +2025,6 @@ int tipc_socket_init(void)
proto_unregister(&tipc_proto);
goto out;
}
-
- sockets_enabled = 1;
out:
return res;
}
@@ -2038,10 +2034,6 @@ int tipc_socket_init(void)
*/
void tipc_socket_stop(void)
{
- if (!sockets_enabled)
- return;
-
- sockets_enabled = 0;
sock_unregister(tipc_family_ops.family);
proto_unregister(&tipc_proto);
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 9b897fc..f054137 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1700,7 +1700,7 @@ static void reg_process_hint(struct regulatory_request *reg_request)
return;
case NL80211_REGDOM_SET_BY_USER:
treatment = reg_process_hint_user(reg_request);
- if (treatment == REG_REQ_OK ||
+ if (treatment == REG_REQ_IGNORE ||
treatment == REG_REQ_ALREADY_SET)
return;
schedule_delayed_work(&reg_timeout, msecs_to_jiffies(3142));
@@ -2373,6 +2373,7 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd,
int set_regdom(const struct ieee80211_regdomain *rd)
{
struct regulatory_request *lr;
+ bool user_reset = false;
int r;
if (!reg_is_valid_request(rd->alpha2)) {
@@ -2389,6 +2390,7 @@ int set_regdom(const struct ieee80211_regdomain *rd)
break;
case NL80211_REGDOM_SET_BY_USER:
r = reg_set_rd_user(rd, lr);
+ user_reset = true;
break;
case NL80211_REGDOM_SET_BY_DRIVER:
r = reg_set_rd_driver(rd, lr);
@@ -2402,8 +2404,14 @@ int set_regdom(const struct ieee80211_regdomain *rd)
}
if (r) {
- if (r == -EALREADY)
+ switch (r) {
+ case -EALREADY:
reg_set_request_processed();
+ break;
+ default:
+ /* Back to world regulatory in case of errors */
+ restore_regulatory_settings(user_reset);
+ }
kfree(rd);
return r;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4b98b25..1d5c7bf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1158,7 +1158,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
if (hlist_unhashed(&pol->bydst))
return NULL;
- hlist_del(&pol->bydst);
+ hlist_del_init(&pol->bydst);
hlist_del(&pol->byidx);
list_del(&pol->walk.all);
net->xfrm.policy_count[dir]--;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a26b7aa..40f1b3e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1159,6 +1159,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
}
x->props.aalgo = orig->props.aalgo;
+ if (orig->aead) {
+ x->aead = xfrm_algo_aead_clone(orig->aead);
+ if (!x->aead)
+ goto error;
+ }
if (orig->ealg) {
x->ealg = xfrm_algo_clone(orig->ealg);
if (!x->ealg)
@@ -1201,6 +1206,9 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
x->props.flags = orig->props.flags;
x->props.extra_flags = orig->props.extra_flags;
+ x->tfcpad = orig->tfcpad;
+ x->replay_maxdiff = orig->replay_maxdiff;
+ x->replay_maxage = orig->replay_maxage;
x->curlft.add_time = orig->curlft.add_time;
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
@@ -1215,11 +1223,12 @@ out:
return NULL;
}
-/* net->xfrm.xfrm_state_lock is held */
struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
{
unsigned int h;
- struct xfrm_state *x;
+ struct xfrm_state *x = NULL;
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (m->reqid) {
h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1236,7 +1245,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
m->old_family))
continue;
xfrm_state_hold(x);
- return x;
+ break;
}
} else {
h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1251,11 +1260,13 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
m->old_family))
continue;
xfrm_state_hold(x);
- return x;
+ break;
}
}
- return NULL;
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+ return x;
}
EXPORT_SYMBOL(xfrm_migrate_state_find);
@@ -1451,7 +1462,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
- struct net *net = xs_net(*dst);
+ struct net *net = xs_net(*src);
if (!afinfo)
return -EAFNOSUPPORT;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1ae3ec7..c274179 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -32,11 +32,6 @@
#include <linux/in6.h>
#endif
-static inline int aead_len(struct xfrm_algo_aead *alg)
-{
- return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
-}
-
static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
{
struct nlattr *rt = attrs[type];