summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c158
-rw-r--r--net/core/ethtool.c3
-rw-r--r--net/core/fib_rules.c27
-rw-r--r--net/core/filter.c483
-rw-r--r--net/core/gen_stats.c15
-rw-r--r--net/core/link_watch.c4
-rw-r--r--net/core/neighbour.c112
-rw-r--r--net/core/net-sysfs.c125
-rw-r--r--net/core/net_namespace.c119
-rw-r--r--net/core/pktgen.c3
-rw-r--r--net/core/request_sock.c45
-rw-r--r--net/core/rtnetlink.c166
-rw-r--r--net/core/skbuff.c80
-rw-r--r--net/core/sock.c132
-rw-r--r--net/core/sock_diag.c37
-rw-r--r--net/core/sysctl_net_core.c12
17 files changed, 1075 insertions, 448 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index df493d68330c..b80fb91bb3f7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -673,7 +673,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
if (!chunk)
return 0;
- if (iov_iter_count(&msg->msg_iter) < chunk) {
+ if (msg_data_left(msg) < chunk) {
if (__skb_checksum_complete(skb))
goto csum_error;
if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
diff --git a/net/core/dev.c b/net/core/dev.c
index 8f9710c62e20..1796cef55ab5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -660,6 +660,27 @@ __setup("netdev=", netdev_boot_setup);
*******************************************************************************/
/**
+ * dev_get_iflink - get 'iflink' value of a interface
+ * @dev: targeted interface
+ *
+ * Indicates the ifindex the interface is linked to.
+ * Physical interfaces have the same 'ifindex' and 'iflink' values.
+ */
+
+int dev_get_iflink(const struct net_device *dev)
+{
+ if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
+ return dev->netdev_ops->ndo_get_iflink(dev);
+
+ /* If dev->rtnl_link_ops is set, it's a virtual interface. */
+ if (dev->rtnl_link_ops)
+ return 0;
+
+ return dev->ifindex;
+}
+EXPORT_SYMBOL(dev_get_iflink);
+
+/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
@@ -946,7 +967,7 @@ bool dev_valid_name(const char *name)
return false;
while (*name) {
- if (*name == '/' || isspace(*name))
+ if (*name == '/' || *name == ':' || isspace(*name))
return false;
name++;
}
@@ -1385,7 +1406,7 @@ static int __dev_close(struct net_device *dev)
return retval;
}
-static int dev_close_many(struct list_head *head)
+int dev_close_many(struct list_head *head, bool unlink)
{
struct net_device *dev, *tmp;
@@ -1399,11 +1420,13 @@ static int dev_close_many(struct list_head *head)
list_for_each_entry_safe(dev, tmp, head, close_list) {
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
call_netdevice_notifiers(NETDEV_DOWN, dev);
- list_del_init(&dev->close_list);
+ if (unlink)
+ list_del_init(&dev->close_list);
}
return 0;
}
+EXPORT_SYMBOL(dev_close_many);
/**
* dev_close - shutdown an interface.
@@ -1420,7 +1443,7 @@ int dev_close(struct net_device *dev)
LIST_HEAD(single);
list_add(&dev->close_list, &single);
- dev_close_many(&single);
+ dev_close_many(&single, true);
list_del(&single);
}
return 0;
@@ -1607,6 +1630,22 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
}
EXPORT_SYMBOL(call_netdevice_notifiers);
+#ifdef CONFIG_NET_CLS_ACT
+static struct static_key ingress_needed __read_mostly;
+
+void net_inc_ingress_queue(void)
+{
+ static_key_slow_inc(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
+
+void net_dec_ingress_queue(void)
+{
+ static_key_slow_dec(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
+#endif
+
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
/* We are not allowed to call static_key_slow_dec() from irq context
@@ -1694,6 +1733,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
}
skb_scrub_packet(skb, true);
+ skb->priority = 0;
skb->protocol = eth_type_trans(skb, dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
@@ -1737,7 +1777,8 @@ static inline int deliver_skb(struct sk_buff *skb,
static inline void deliver_ptype_list_skb(struct sk_buff *skb,
struct packet_type **pt,
- struct net_device *dev, __be16 type,
+ struct net_device *orig_dev,
+ __be16 type,
struct list_head *ptype_list)
{
struct packet_type *ptype, *pt_prev = *pt;
@@ -1746,7 +1787,7 @@ static inline void deliver_ptype_list_skb(struct sk_buff *skb,
if (ptype->type != type)
continue;
if (pt_prev)
- deliver_skb(skb, pt_prev, dev);
+ deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
*pt = pt_prev;
@@ -2559,12 +2600,26 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
return features;
}
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features)
+{
+ return features;
+}
+EXPORT_SYMBOL(passthru_features_check);
+
+static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features)
+{
+ return vlan_features_check(skb, features);
+}
+
netdev_features_t netif_skb_features(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
netdev_features_t features = dev->features;
u16 gso_segs = skb_shinfo(skb)->gso_segs;
- __be16 protocol = skb->protocol;
if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
features &= ~NETIF_F_GSO_MASK;
@@ -2576,34 +2631,17 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
if (skb->encapsulation)
features &= dev->hw_enc_features;
- if (!skb_vlan_tag_present(skb)) {
- if (unlikely(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 {
- goto finalize;
- }
- }
-
- features = netdev_intersect_features(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))
+ if (skb_vlan_tagged(skb))
features = netdev_intersect_features(features,
- NETIF_F_SG |
- NETIF_F_HIGHDMA |
- NETIF_F_FRAGLIST |
- NETIF_F_GEN_CSUM |
+ dev->vlan_features |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
-finalize:
if (dev->netdev_ops->ndo_features_check)
features &= dev->netdev_ops->ndo_features_check(skb, dev,
features);
+ else
+ features &= dflt_features_check(skb, dev, features);
return harmonize_features(skb, features);
}
@@ -2675,7 +2713,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
if (unlikely(!skb))
goto out_null;
- if (netif_needs_gso(dev, skb, features)) {
+ if (netif_needs_gso(skb, features)) {
struct sk_buff *segs;
segs = skb_gso_segment(skb, features);
@@ -2848,14 +2886,16 @@ static void skb_update_prio(struct sk_buff *skb)
#define skb_update_prio(skb)
#endif
-static DEFINE_PER_CPU(int, xmit_recursion);
+DEFINE_PER_CPU(int, xmit_recursion);
+EXPORT_SYMBOL(xmit_recursion);
+
#define RECURSION_LIMIT 10
/**
* dev_loopback_xmit - loop back @skb
* @skb: buffer to transmit
*/
-int dev_loopback_xmit(struct sk_buff *skb)
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
{
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
@@ -2993,11 +3033,11 @@ out:
return rc;
}
-int dev_queue_xmit(struct sk_buff *skb)
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb)
{
return __dev_queue_xmit(skb, NULL);
}
-EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_queue_xmit_sk);
int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
{
@@ -3523,7 +3563,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
- goto out;
+ return skb;
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
@@ -3537,8 +3577,6 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
return NULL;
}
-out:
- skb->tc_verd = 0;
return skb;
}
#endif
@@ -3674,12 +3712,15 @@ another_round:
skip_taps:
#ifdef CONFIG_NET_CLS_ACT
- skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
- if (!skb)
- goto unlock;
+ if (static_key_false(&ingress_needed)) {
+ skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
+ goto unlock;
+ }
+
+ skb->tc_verd = 0;
ncls:
#endif
-
if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
@@ -3829,13 +3870,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
* NET_RX_SUCCESS: no congestion
* NET_RX_DROP: packet was dropped
*/
-int netif_receive_skb(struct sk_buff *skb)
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb)
{
trace_netif_receive_skb_entry(skb);
return netif_receive_skb_internal(skb);
}
-EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_receive_skb_sk);
/* Network device is going away, flush any packets still pending
* Called with irqs disabled.
@@ -5912,6 +5953,24 @@ int dev_get_phys_port_id(struct net_device *dev,
EXPORT_SYMBOL(dev_get_phys_port_id);
/**
+ * dev_get_phys_port_name - Get device physical port name
+ * @dev: device
+ * @name: port name
+ *
+ * Get device physical port name
+ */
+int dev_get_phys_port_name(struct net_device *dev,
+ char *name, size_t len)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_get_phys_port_name)
+ return -EOPNOTSUPP;
+ return ops->ndo_get_phys_port_name(dev, name, len);
+}
+EXPORT_SYMBOL(dev_get_phys_port_name);
+
+/**
* dev_new_index - allocate an ifindex
* @net: the applicable net namespace
*
@@ -5968,7 +6027,7 @@ static void rollback_registered_many(struct list_head *head)
/* If device is running, close it first. */
list_for_each_entry(dev, head, unreg_list)
list_add_tail(&dev->close_list, &close_head);
- dev_close_many(&close_head);
+ dev_close_many(&close_head, true);
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
@@ -6295,8 +6354,6 @@ int register_netdevice(struct net_device *dev)
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
- dev->iflink = -1;
-
ret = dev_get_valid_name(net, dev, dev->name);
if (ret < 0)
goto out;
@@ -6326,9 +6383,6 @@ int register_netdevice(struct net_device *dev)
else if (__dev_get_by_index(net, dev->ifindex))
goto err_uninit;
- if (dev->iflink == -1)
- dev->iflink = dev->ifindex;
-
/* Transfer changeable features to wanted_features and enable
* software offloads (GSO and GRO).
*/
@@ -6841,8 +6895,6 @@ void free_netdev(struct net_device *dev)
{
struct napi_struct *p, *n;
- release_net(dev_net(dev));
-
netif_free_tx_queues(dev);
#ifdef CONFIG_SYSFS
kvfree(dev->_rx);
@@ -7043,12 +7095,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
dev_net_set(dev, net);
/* If there is an ifindex conflict assign a new one */
- if (__dev_get_by_index(net, dev->ifindex)) {
- int iflink = (dev->iflink == dev->ifindex);
+ if (__dev_get_by_index(net, dev->ifindex))
dev->ifindex = dev_new_index(net);
- if (iflink)
- dev->iflink = dev->ifindex;
- }
/* Send a netdev-add uevent to the new namespace */
kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 91f74f3eb204..1d00b8922902 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -98,6 +98,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_RXALL_BIT] = "rx-all",
[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
[NETIF_F_BUSY_POLL_BIT] = "busy-poll",
+ [NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload",
};
static const char
@@ -789,7 +790,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
if (ops->get_rxfh_indir_size)
dev_indir_size = ops->get_rxfh_indir_size(dev);
if (ops->get_rxfh_key_size)
- dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
+ dev_key_size = ops->get_rxfh_key_size(dev);
if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
return -EFAULT;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 44706e81b2e0..9a12668f7d62 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,7 +31,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
r->pref = pref;
r->table = table;
r->flags = flags;
- r->fr_net = hold_net(ops->fro_net);
+ r->fr_net = ops->fro_net;
r->suppress_prefixlen = -1;
r->suppress_ifgroup = -1;
@@ -116,7 +116,6 @@ static int __fib_rules_register(struct fib_rules_ops *ops)
if (ops->family == o->family)
goto errout;
- hold_net(net);
list_add_tail_rcu(&ops->list, &net->rules_ops);
err = 0;
errout:
@@ -160,25 +159,16 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
}
}
-static void fib_rules_put_rcu(struct rcu_head *head)
-{
- struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
- struct net *net = ops->fro_net;
-
- release_net(net);
- kfree(ops);
-}
-
void fib_rules_unregister(struct fib_rules_ops *ops)
{
struct net *net = ops->fro_net;
spin_lock(&net->rules_mod_lock);
list_del_rcu(&ops->list);
- fib_rules_cleanup_ops(ops);
spin_unlock(&net->rules_mod_lock);
- call_rcu(&ops->rcu, fib_rules_put_rcu);
+ fib_rules_cleanup_ops(ops);
+ kfree_rcu(ops, rcu);
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
@@ -303,7 +293,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
err = -ENOMEM;
goto errout;
}
- rule->fr_net = hold_net(net);
+ rule->fr_net = net;
if (tb[FRA_PRIORITY])
rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
@@ -423,7 +413,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
return 0;
errout_free:
- release_net(rule->fr_net);
kfree(rule);
errout:
rules_ops_put(ops);
@@ -492,6 +481,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
goto errout;
}
+ if (ops->delete) {
+ err = ops->delete(rule);
+ if (err)
+ goto errout;
+ }
+
list_del_rcu(&rule->list);
if (rule->action == FR_ACT_GOTO) {
@@ -517,8 +512,6 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).portid);
- if (ops->delete)
- ops->delete(rule);
fib_rule_put(rule);
flush_route_cache(ops);
rules_ops_put(ops);
diff --git a/net/core/filter.c b/net/core/filter.c
index f6bdc2b1ba01..bf831a85c315 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -150,10 +150,62 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
return prandom_u32();
}
+static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (skb_field) {
+ case SKF_AD_MARK:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, mark));
+ break;
+
+ case SKF_AD_PKTTYPE:
+ *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET());
+ *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX);
+#ifdef __BIG_ENDIAN_BITFIELD
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5);
+#endif
+ break;
+
+ case SKF_AD_QUEUE:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, queue_mapping));
+ break;
+
+ case SKF_AD_VLAN_TAG:
+ case SKF_AD_VLAN_TAG_PRESENT:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+ BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+ /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, vlan_tci));
+ if (skb_field == SKF_AD_VLAN_TAG) {
+ *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
+ ~VLAN_TAG_PRESENT);
+ } else {
+ /* dst_reg >>= 12 */
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
+ /* dst_reg &= 1 */
+ *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
+ }
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
static bool convert_bpf_extensions(struct sock_filter *fp,
struct bpf_insn **insnp)
{
struct bpf_insn *insn = *insnp;
+ u32 cnt;
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PROTOCOL:
@@ -167,13 +219,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
break;
case SKF_AD_OFF + SKF_AD_PKTTYPE:
- *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
- PKT_TYPE_OFFSET());
- *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX);
-#ifdef __BIG_ENDIAN_BITFIELD
- insn++;
- *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5);
-#endif
+ cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn);
+ insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_IFINDEX:
@@ -197,10 +244,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
break;
case SKF_AD_OFF + SKF_AD_MARK:
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
-
- *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
- offsetof(struct sk_buff, mark));
+ cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn);
+ insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_RXHASH:
@@ -211,29 +256,30 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
break;
case SKF_AD_OFF + SKF_AD_QUEUE:
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
-
- *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
- offsetof(struct sk_buff, queue_mapping));
+ cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn);
+ insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+ cnt = convert_skb_access(SKF_AD_VLAN_TAG,
+ BPF_REG_A, BPF_REG_CTX, insn);
+ insn += cnt - 1;
+ break;
+
case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
- BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+ cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
+ BPF_REG_A, BPF_REG_CTX, insn);
+ insn += cnt - 1;
+ break;
- /* A = *(u16 *) (CTX + offsetof(vlan_tci)) */
+ case SKF_AD_OFF + SKF_AD_VLAN_TPID:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);
+
+ /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */
*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
- offsetof(struct sk_buff, vlan_tci));
- if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
- *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A,
- ~VLAN_TAG_PRESENT);
- } else {
- /* A >>= 12 */
- *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12);
- /* A &= 1 */
- *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1);
- }
+ offsetof(struct sk_buff, vlan_proto));
+ /* A = ntohs(A) [emitting a nop or swap16] */
+ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
break;
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
@@ -814,7 +860,7 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
static void __bpf_prog_release(struct bpf_prog *prog)
{
- if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+ if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) {
bpf_prog_put(prog);
} else {
bpf_release_orig_filter(prog);
@@ -1019,6 +1065,32 @@ void bpf_prog_destroy(struct bpf_prog *fp)
}
EXPORT_SYMBOL_GPL(bpf_prog_destroy);
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+{
+ struct sk_filter *fp, *old_fp;
+
+ fp = kmalloc(sizeof(*fp), GFP_KERNEL);
+ if (!fp)
+ return -ENOMEM;
+
+ fp->prog = prog;
+ atomic_set(&fp->refcnt, 0);
+
+ if (!sk_filter_charge(sk, fp)) {
+ kfree(fp);
+ return -ENOMEM;
+ }
+
+ old_fp = rcu_dereference_protected(sk->sk_filter,
+ sock_owned_by_user(sk));
+ rcu_assign_pointer(sk->sk_filter, fp);
+
+ if (old_fp)
+ sk_filter_uncharge(sk, old_fp);
+
+ return 0;
+}
+
/**
* sk_attach_filter - attach a socket filter
* @fprog: the filter program
@@ -1031,7 +1103,6 @@ EXPORT_SYMBOL_GPL(bpf_prog_destroy);
*/
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
- struct sk_filter *fp, *old_fp;
unsigned int fsize = bpf_classic_proglen(fprog);
unsigned int bpf_fsize = bpf_prog_size(fprog->len);
struct bpf_prog *prog;
@@ -1068,36 +1139,20 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (IS_ERR(prog))
return PTR_ERR(prog);
- fp = kmalloc(sizeof(*fp), GFP_KERNEL);
- if (!fp) {
+ err = __sk_attach_prog(prog, sk);
+ if (err < 0) {
__bpf_prog_release(prog);
- return -ENOMEM;
- }
- fp->prog = prog;
-
- atomic_set(&fp->refcnt, 0);
-
- if (!sk_filter_charge(sk, fp)) {
- __sk_filter_release(fp);
- return -ENOMEM;
+ return err;
}
- old_fp = rcu_dereference_protected(sk->sk_filter,
- sock_owned_by_user(sk));
- rcu_assign_pointer(sk->sk_filter, fp);
-
- if (old_fp)
- sk_filter_uncharge(sk, old_fp);
-
return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
-#ifdef CONFIG_BPF_SYSCALL
int sk_attach_bpf(u32 ufd, struct sock *sk)
{
- struct sk_filter *fp, *old_fp;
struct bpf_prog *prog;
+ int err;
if (sock_flag(sk, SOCK_FILTER_LOCKED))
return -EPERM;
@@ -1106,40 +1161,191 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
if (IS_ERR(prog))
return PTR_ERR(prog);
- if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
- /* valid fd, but invalid program type */
+ if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
bpf_prog_put(prog);
return -EINVAL;
}
- fp = kmalloc(sizeof(*fp), GFP_KERNEL);
- if (!fp) {
+ err = __sk_attach_prog(prog, sk);
+ if (err < 0) {
bpf_prog_put(prog);
- return -ENOMEM;
+ return err;
}
- fp->prog = prog;
- atomic_set(&fp->refcnt, 0);
+ return 0;
+}
- if (!sk_filter_charge(sk, fp)) {
- __sk_filter_release(fp);
- return -ENOMEM;
+/**
+ * bpf_skb_clone_not_writable - is the header of a clone not writable
+ * @skb: buffer to check
+ * @len: length up to which to write, can be negative
+ *
+ * Returns true if modifying the header part of the cloned buffer
+ * does require the data to be copied. I.e. this version works with
+ * negative lengths needed for eBPF case!
+ */
+static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len)
+{
+ return skb_header_cloned(skb) ||
+ (int) skb_headroom(skb) + len > skb->hdr_len;
+}
+
+#define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1)
+
+static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ int offset = (int) r2;
+ void *from = (void *) (long) r3;
+ unsigned int len = (unsigned int) r4;
+ char buf[16];
+ void *ptr;
+
+ /* bpf verifier guarantees that:
+ * 'from' pointer points to bpf program stack
+ * 'len' bytes of it were initialized
+ * 'len' > 0
+ * 'skb' is a valid pointer to 'struct sk_buff'
+ *
+ * so check for invalid 'offset' and too large 'len'
+ */
+ if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
+ return -EFAULT;
+
+ offset -= skb->data - skb_mac_header(skb);
+ if (unlikely(skb_cloned(skb) &&
+ bpf_skb_clone_unwritable(skb, offset + len)))
+ return -EFAULT;
+
+ ptr = skb_header_pointer(skb, offset, len, buf);
+ if (unlikely(!ptr))
+ return -EFAULT;
+
+ if (BPF_RECOMPUTE_CSUM(flags))
+ skb_postpull_rcsum(skb, ptr, len);
+
+ memcpy(ptr, from, len);
+
+ if (ptr == buf)
+ /* skb_store_bits cannot return -EFAULT here */
+ skb_store_bits(skb, offset, ptr, len);
+
+ if (BPF_RECOMPUTE_CSUM(flags) && skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0));
+ return 0;
+}
+
+const struct bpf_func_proto bpf_skb_store_bytes_proto = {
+ .func = bpf_skb_store_bytes,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_STACK,
+ .arg4_type = ARG_CONST_STACK_SIZE,
+ .arg5_type = ARG_ANYTHING,
+};
+
+#define BPF_HEADER_FIELD_SIZE(flags) ((flags) & 0x0f)
+#define BPF_IS_PSEUDO_HEADER(flags) ((flags) & 0x10)
+
+static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ int offset = (int) r2;
+ __sum16 sum, *ptr;
+
+ if (unlikely((u32) offset > 0xffff))
+ return -EFAULT;
+
+ offset -= skb->data - skb_mac_header(skb);
+ if (unlikely(skb_cloned(skb) &&
+ bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+ return -EFAULT;
+
+ ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
+ if (unlikely(!ptr))
+ return -EFAULT;
+
+ switch (BPF_HEADER_FIELD_SIZE(flags)) {
+ case 2:
+ csum_replace2(ptr, from, to);
+ break;
+ case 4:
+ csum_replace4(ptr, from, to);
+ break;
+ default:
+ return -EINVAL;
}
- old_fp = rcu_dereference_protected(sk->sk_filter,
- sock_owned_by_user(sk));
- rcu_assign_pointer(sk->sk_filter, fp);
+ if (ptr == &sum)
+ /* skb_store_bits guaranteed to not return -EFAULT here */
+ skb_store_bits(skb, offset, ptr, sizeof(sum));
- if (old_fp)
- sk_filter_uncharge(sk, old_fp);
+ return 0;
+}
+
+const struct bpf_func_proto bpf_l3_csum_replace_proto = {
+ .func = bpf_l3_csum_replace,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags);
+ int offset = (int) r2;
+ __sum16 sum, *ptr;
+
+ if (unlikely((u32) offset > 0xffff))
+ return -EFAULT;
+
+ offset -= skb->data - skb_mac_header(skb);
+ if (unlikely(skb_cloned(skb) &&
+ bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+ return -EFAULT;
+
+ ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
+ if (unlikely(!ptr))
+ return -EFAULT;
+
+ switch (BPF_HEADER_FIELD_SIZE(flags)) {
+ case 2:
+ inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
+ break;
+ case 4:
+ inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (ptr == &sum)
+ /* skb_store_bits guaranteed to not return -EFAULT here */
+ skb_store_bits(skb, offset, ptr, sizeof(sum));
return 0;
}
-/* allow socket filters to call
- * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
- */
-static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id)
+const struct bpf_func_proto bpf_l4_csum_replace_proto = {
+ .func = bpf_l4_csum_replace,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+sk_filter_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -1148,39 +1354,144 @@ static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func
return &bpf_map_update_elem_proto;
case BPF_FUNC_map_delete_elem:
return &bpf_map_delete_elem_proto;
+ case BPF_FUNC_get_prandom_u32:
+ return &bpf_get_prandom_u32_proto;
+ case BPF_FUNC_get_smp_processor_id:
+ return &bpf_get_smp_processor_id_proto;
default:
return NULL;
}
}
-static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+static const struct bpf_func_proto *
+tc_cls_act_func_proto(enum bpf_func_id func_id)
{
- /* skb fields cannot be accessed yet */
- return false;
+ switch (func_id) {
+ case BPF_FUNC_skb_store_bytes:
+ return &bpf_skb_store_bytes_proto;
+ case BPF_FUNC_l3_csum_replace:
+ return &bpf_l3_csum_replace_proto;
+ case BPF_FUNC_l4_csum_replace:
+ return &bpf_l4_csum_replace_proto;
+ default:
+ return sk_filter_func_proto(func_id);
+ }
}
-static struct bpf_verifier_ops sock_filter_ops = {
- .get_func_proto = sock_filter_func_proto,
- .is_valid_access = sock_filter_is_valid_access,
+static bool sk_filter_is_valid_access(int off, int size,
+ enum bpf_access_type type)
+{
+ /* only read is allowed */
+ if (type != BPF_READ)
+ return false;
+
+ /* check bounds */
+ if (off < 0 || off >= sizeof(struct __sk_buff))
+ return false;
+
+ /* disallow misaligned access */
+ if (off % size != 0)
+ return false;
+
+ /* all __sk_buff fields are __u32 */
+ if (size != 4)
+ return false;
+
+ return true;
+}
+
+static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (ctx_off) {
+ case offsetof(struct __sk_buff, len):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, len));
+ break;
+
+ case offsetof(struct __sk_buff, protocol):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, protocol));
+ break;
+
+ case offsetof(struct __sk_buff, vlan_proto):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sk_buff, vlan_proto));
+ break;
+
+ case offsetof(struct __sk_buff, priority):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
+ break;
+
+ case offsetof(struct __sk_buff, mark):
+ return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn);
+
+ case offsetof(struct __sk_buff, pkt_type):
+ return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn);
+
+ case offsetof(struct __sk_buff, queue_mapping):
+ return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn);
+
+ case offsetof(struct __sk_buff, vlan_present):
+ return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
+ dst_reg, src_reg, insn);
+
+ case offsetof(struct __sk_buff, vlan_tci):
+ return convert_skb_access(SKF_AD_VLAN_TAG,
+ dst_reg, src_reg, insn);
+ }
+
+ return insn - insn_buf;
+}
+
+static const struct bpf_verifier_ops sk_filter_ops = {
+ .get_func_proto = sk_filter_func_proto,
+ .is_valid_access = sk_filter_is_valid_access,
+ .convert_ctx_access = sk_filter_convert_ctx_access,
+};
+
+static const struct bpf_verifier_ops tc_cls_act_ops = {
+ .get_func_proto = tc_cls_act_func_proto,
+ .is_valid_access = sk_filter_is_valid_access,
+ .convert_ctx_access = sk_filter_convert_ctx_access,
};
-static struct bpf_prog_type_list tl = {
- .ops = &sock_filter_ops,
+static struct bpf_prog_type_list sk_filter_type __read_mostly = {
+ .ops = &sk_filter_ops,
.type = BPF_PROG_TYPE_SOCKET_FILTER,
};
-static int __init register_sock_filter_ops(void)
+static struct bpf_prog_type_list sched_cls_type __read_mostly = {
+ .ops = &tc_cls_act_ops,
+ .type = BPF_PROG_TYPE_SCHED_CLS,
+};
+
+static struct bpf_prog_type_list sched_act_type __read_mostly = {
+ .ops = &tc_cls_act_ops,
+ .type = BPF_PROG_TYPE_SCHED_ACT,
+};
+
+static int __init register_sk_filter_ops(void)
{
- bpf_register_prog_type(&tl);
+ bpf_register_prog_type(&sk_filter_type);
+ bpf_register_prog_type(&sched_cls_type);
+ bpf_register_prog_type(&sched_act_type);
+
return 0;
}
-late_initcall(register_sock_filter_ops);
-#else
-int sk_attach_bpf(u32 ufd, struct sock *sk)
-{
- return -EOPNOTSUPP;
-}
-#endif
+late_initcall(register_sk_filter_ops);
+
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 0c08062d1796..1e2f46a69d50 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
return 0;
nla_put_failure:
+ kfree(d->xstats);
+ d->xstats = NULL;
+ d->xstats_len = 0;
spin_unlock_bh(d->lock);
return -1;
}
@@ -305,7 +308,9 @@ int
gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
{
if (d->compat_xstats) {
- d->xstats = st;
+ d->xstats = kmemdup(st, len, GFP_ATOMIC);
+ if (!d->xstats)
+ goto err_out;
d->xstats_len = len;
}
@@ -313,6 +318,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
return gnet_stats_copy(d, TCA_STATS_APP, st, len);
return 0;
+
+err_out:
+ d->xstats_len = 0;
+ spin_unlock_bh(d->lock);
+ return -1;
}
EXPORT_SYMBOL(gnet_stats_copy_app);
@@ -345,6 +355,9 @@ gnet_stats_finish_copy(struct gnet_dump *d)
return -1;
}
+ kfree(d->xstats);
+ d->xstats = NULL;
+ d->xstats_len = 0;
spin_unlock_bh(d->lock);
return 0;
}
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 49a9e3e06c08..982861607f88 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -40,7 +40,7 @@ static DEFINE_SPINLOCK(lweventlist_lock);
static unsigned char default_operstate(const struct net_device *dev)
{
if (!netif_carrier_ok(dev))
- return (dev->ifindex != dev->iflink ?
+ return (dev->ifindex != dev_get_iflink(dev) ?
IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN);
if (netif_dormant(dev))
@@ -89,7 +89,7 @@ static bool linkwatch_urgent_event(struct net_device *dev)
if (!netif_running(dev))
return false;
- if (dev->ifindex != dev->iflink)
+ if (dev->ifindex != dev_get_iflink(dev))
return true;
if (dev->priv_flags & IFF_TEAM_PORT)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 70fe9e10ac86..3de654256028 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -397,25 +397,15 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
struct net_device *dev)
{
struct neighbour *n;
- int key_len = tbl->key_len;
- u32 hash_val;
- struct neigh_hash_table *nht;
NEIGH_CACHE_STAT_INC(tbl, lookups);
rcu_read_lock_bh();
- nht = rcu_dereference_bh(tbl->nht);
- hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
-
- for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
- n != NULL;
- n = rcu_dereference_bh(n->next)) {
- if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
- if (!atomic_inc_not_zero(&n->refcnt))
- n = NULL;
- NEIGH_CACHE_STAT_INC(tbl, hits);
- break;
- }
+ n = __neigh_lookup_noref(tbl, pkey, dev);
+ if (n) {
+ if (!atomic_inc_not_zero(&n->refcnt))
+ n = NULL;
+ NEIGH_CACHE_STAT_INC(tbl, hits);
}
rcu_read_unlock_bh();
@@ -601,7 +591,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
if (!n)
goto out;
- write_pnet(&n->net, hold_net(net));
+ write_pnet(&n->net, net);
memcpy(n->key, pkey, key_len);
n->dev = dev;
if (dev)
@@ -610,7 +600,6 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
if (tbl->pconstructor && tbl->pconstructor(n)) {
if (dev)
dev_put(dev);
- release_net(net);
kfree(n);
n = NULL;
goto out;
@@ -644,7 +633,6 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
tbl->pdestructor(n);
if (n->dev)
dev_put(n->dev);
- release_net(pneigh_net(n));
kfree(n);
return 0;
}
@@ -667,7 +655,6 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
tbl->pdestructor(n);
if (n->dev)
dev_put(n->dev);
- release_net(pneigh_net(n));
kfree(n);
continue;
}
@@ -830,10 +817,9 @@ out:
static __inline__ int neigh_max_probes(struct neighbour *n)
{
struct neigh_parms *p = n->parms;
- int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
- if (!(n->nud_state & NUD_PROBE))
- max_probes += NEIGH_VAR(p, MCAST_PROBES);
- return max_probes;
+ return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
+ (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) :
+ NEIGH_VAR(p, MCAST_PROBES));
}
static void neigh_invalidate(struct neighbour *neigh)
@@ -1263,10 +1249,10 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
EXPORT_SYMBOL(neigh_event_ns);
/* called with read_lock_bh(&n->lock); */
-static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
+static void neigh_hh_init(struct neighbour *n)
{
- struct net_device *dev = dst->dev;
- __be16 prot = dst->ops->protocol;
+ struct net_device *dev = n->dev;
+ __be16 prot = n->tbl->protocol;
struct hh_cache *hh = &n->hh;
write_lock_bh(&n->lock);
@@ -1280,43 +1266,19 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
write_unlock_bh(&n->lock);
}
-/* This function can be used in contexts, where only old dev_queue_xmit
- * worked, f.e. if you want to override normal output path (eql, shaper),
- * but resolution is not made yet.
- */
-
-int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
-{
- struct net_device *dev = skb->dev;
-
- __skb_pull(skb, skb_network_offset(skb));
-
- if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
- skb->len) < 0 &&
- dev_rebuild_header(skb))
- return 0;
-
- return dev_queue_xmit(skb);
-}
-EXPORT_SYMBOL(neigh_compat_output);
-
/* Slow and careful. */
int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
int rc = 0;
- if (!dst)
- goto discard;
-
if (!neigh_event_send(neigh, skb)) {
int err;
struct net_device *dev = neigh->dev;
unsigned int seq;
if (dev->header_ops->cache && !neigh->hh.hh_len)
- neigh_hh_init(neigh, dst);
+ neigh_hh_init(neigh);
do {
__skb_pull(skb, skb_network_offset(skb));
@@ -1332,8 +1294,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
}
out:
return rc;
-discard:
- neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh);
out_kfree_skb:
rc = -EINVAL;
kfree_skb(skb);
@@ -1464,11 +1424,10 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
dev_hold(dev);
p->dev = dev;
- write_pnet(&p->net, hold_net(net));
+ write_pnet(&p->net, net);
p->sysctl_table = NULL;
if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
- release_net(net);
dev_put(dev);
kfree(p);
return NULL;
@@ -1508,7 +1467,6 @@ EXPORT_SYMBOL(neigh_parms_release);
static void neigh_parms_destroy(struct neigh_parms *parms)
{
- release_net(neigh_parms_net(parms));
kfree(parms);
}
@@ -1783,6 +1741,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
NEIGH_VAR(parms, UCAST_PROBES)) ||
nla_put_u32(skb, NDTPA_MCAST_PROBES,
NEIGH_VAR(parms, MCAST_PROBES)) ||
+ nla_put_u32(skb, NDTPA_MCAST_REPROBES,
+ NEIGH_VAR(parms, MCAST_REPROBES)) ||
nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) ||
nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME,
NEIGH_VAR(parms, BASE_REACHABLE_TIME)) ||
@@ -1942,6 +1902,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
[NDTPA_APP_PROBES] = { .type = NLA_U32 },
[NDTPA_UCAST_PROBES] = { .type = NLA_U32 },
[NDTPA_MCAST_PROBES] = { .type = NLA_U32 },
+ [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 },
[NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 },
[NDTPA_GC_STALETIME] = { .type = NLA_U64 },
[NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 },
@@ -2042,6 +2003,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
NEIGH_VAR_SET(p, MCAST_PROBES,
nla_get_u32(tbp[i]));
break;
+ case NDTPA_MCAST_REPROBES:
+ NEIGH_VAR_SET(p, MCAST_REPROBES,
+ nla_get_u32(tbp[i]));
+ break;
case NDTPA_BASE_REACHABLE_TIME:
NEIGH_VAR_SET(p, BASE_REACHABLE_TIME,
nla_get_msecs(tbp[i]));
@@ -2427,6 +2392,40 @@ void __neigh_for_each_release(struct neigh_table *tbl,
}
EXPORT_SYMBOL(__neigh_for_each_release);
+int neigh_xmit(int index, struct net_device *dev,
+ const void *addr, struct sk_buff *skb)
+{
+ int err = -EAFNOSUPPORT;
+ if (likely(index < NEIGH_NR_TABLES)) {
+ struct neigh_table *tbl;
+ struct neighbour *neigh;
+
+ tbl = neigh_tables[index];
+ if (!tbl)
+ goto out;
+ neigh = __neigh_lookup_noref(tbl, addr, dev);
+ if (!neigh)
+ neigh = __neigh_create(tbl, addr, dev, false);
+ err = PTR_ERR(neigh);
+ if (IS_ERR(neigh))
+ goto out_kfree_skb;
+ err = neigh->output(neigh, skb);
+ }
+ else if (index == NEIGH_LINK_TABLE) {
+ err = dev_hard_header(skb, dev, ntohs(skb->protocol),
+ addr, NULL, skb->len);
+ if (err < 0)
+ goto out_kfree_skb;
+ err = dev_queue_xmit(skb);
+ }
+out:
+ return err;
+out_kfree_skb:
+ kfree_skb(skb);
+ goto out;
+}
+EXPORT_SYMBOL(neigh_xmit);
+
#ifdef CONFIG_PROC_FS
static struct neighbour *neigh_get_first(struct seq_file *seq)
@@ -2994,6 +2993,7 @@ static struct neigh_sysctl_table {
NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"),
NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"),
NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"),
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"),
NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"),
NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"),
NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"),
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f2aa73bfb0e4..4238d6da5c60 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -23,6 +23,7 @@
#include <linux/export.h>
#include <linux/jiffies.h>
#include <linux/pm_runtime.h>
+#include <linux/of.h>
#include "net-sysfs.h"
@@ -108,11 +109,19 @@ NETDEVICE_SHOW_RO(dev_id, fmt_hex);
NETDEVICE_SHOW_RO(dev_port, fmt_dec);
NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
NETDEVICE_SHOW_RO(addr_len, fmt_dec);
-NETDEVICE_SHOW_RO(iflink, fmt_dec);
NETDEVICE_SHOW_RO(ifindex, fmt_dec);
NETDEVICE_SHOW_RO(type, fmt_dec);
NETDEVICE_SHOW_RO(link_mode, fmt_dec);
+static ssize_t iflink_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct net_device *ndev = to_net_dev(dev);
+
+ return sprintf(buf, fmt_dec, dev_get_iflink(ndev));
+}
+static DEVICE_ATTR_RO(iflink);
+
static ssize_t format_name_assign_type(const struct net_device *dev, char *buf)
{
return sprintf(buf, fmt_dec, dev->name_assign_type);
@@ -417,6 +426,28 @@ static ssize_t phys_port_id_show(struct device *dev,
}
static DEVICE_ATTR_RO(phys_port_id);
+static ssize_t phys_port_name_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ ssize_t ret = -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (dev_isalive(netdev)) {
+ char name[IFNAMSIZ];
+
+ ret = dev_get_phys_port_name(netdev, name, sizeof(name));
+ if (!ret)
+ ret = sprintf(buf, "%s\n", name);
+ }
+ rtnl_unlock();
+
+ return ret;
+}
+static DEVICE_ATTR_RO(phys_port_name);
+
static ssize_t phys_switch_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -464,6 +495,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_tx_queue_len.attr,
&dev_attr_gro_flush_timeout.attr,
&dev_attr_phys_port_id.attr,
+ &dev_attr_phys_port_name.attr,
&dev_attr_phys_switch_id.attr,
NULL,
};
@@ -950,6 +982,60 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
return sprintf(buf, "%lu", trans_timeout);
}
+#ifdef CONFIG_XPS
+static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+{
+ struct net_device *dev = queue->dev;
+ int i;
+
+ for (i = 0; i < dev->num_tx_queues; i++)
+ if (queue == &dev->_tx[i])
+ break;
+
+ BUG_ON(i >= dev->num_tx_queues);
+
+ return i;
+}
+
+static ssize_t show_tx_maxrate(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ char *buf)
+{
+ return sprintf(buf, "%lu\n", queue->tx_maxrate);
+}
+
+static ssize_t set_tx_maxrate(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ const char *buf, size_t len)
+{
+ struct net_device *dev = queue->dev;
+ int err, index = get_netdev_queue_index(queue);
+ u32 rate = 0;
+
+ err = kstrtou32(buf, 10, &rate);
+ if (err < 0)
+ return err;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ err = -EOPNOTSUPP;
+ if (dev->netdev_ops->ndo_set_tx_maxrate)
+ err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
+
+ rtnl_unlock();
+ if (!err) {
+ queue->tx_maxrate = rate;
+ return len;
+ }
+ return err;
+}
+
+static struct netdev_queue_attribute queue_tx_maxrate =
+ __ATTR(tx_maxrate, S_IRUGO | S_IWUSR,
+ show_tx_maxrate, set_tx_maxrate);
+#endif
+
static struct netdev_queue_attribute queue_trans_timeout =
__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
@@ -1064,18 +1150,6 @@ static struct attribute_group dql_group = {
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
-static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-{
- struct net_device *dev = queue->dev;
- unsigned int i;
-
- i = queue - dev->_tx;
- BUG_ON(i >= dev->num_tx_queues);
-
- return i;
-}
-
-
static ssize_t show_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute, char *buf)
{
@@ -1152,6 +1226,7 @@ static struct attribute *netdev_queue_default_attrs[] = {
&queue_trans_timeout.attr,
#ifdef CONFIG_XPS
&xps_cpus_attribute.attr,
+ &queue_tx_maxrate.attr,
#endif
NULL
};
@@ -1374,6 +1449,30 @@ static struct class net_class = {
.namespace = net_namespace,
};
+#ifdef CONFIG_OF_NET
+static int of_dev_node_match(struct device *dev, const void *data)
+{
+ int ret = 0;
+
+ if (dev->parent)
+ ret = dev->parent->of_node == data;
+
+ return ret == 0 ? dev->of_node == data : ret;
+}
+
+struct net_device *of_find_net_device_by_node(struct device_node *np)
+{
+ struct device *dev;
+
+ dev = class_find_device(&net_class, NULL, np, of_dev_node_match);
+ if (!dev)
+ return NULL;
+
+ return to_net_dev(dev);
+}
+EXPORT_SYMBOL(of_find_net_device_by_node);
+#endif
+
/* Delete sysfs entries but hold kobject reference until after all
* netdev references are gone.
*/
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cb5290b8c428..78fc04ad36fc 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -16,7 +16,6 @@
#include <linux/export.h>
#include <linux/user_namespace.h>
#include <linux/net_namespace.h>
-#include <linux/rtnetlink.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/net_namespace.h>
@@ -148,9 +147,11 @@ static void ops_free_list(const struct pernet_operations *ops,
}
}
+static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
+ int id);
static int alloc_netid(struct net *net, struct net *peer, int reqid)
{
- int min = 0, max = 0;
+ int min = 0, max = 0, id;
ASSERT_RTNL();
@@ -159,7 +160,11 @@ static int alloc_netid(struct net *net, struct net *peer, int reqid)
max = reqid + 1;
}
- return idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL);
+ id = idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL);
+ if (id >= 0)
+ rtnl_net_notifyid(net, peer, RTM_NEWNSID, id);
+
+ return id;
}
/* This function is used by idr_for_each(). If net is equal to peer, the
@@ -198,8 +203,10 @@ static int __peernet2id(struct net *net, struct net *peer, bool alloc)
*/
int peernet2id(struct net *net, struct net *peer)
{
- int id = __peernet2id(net, peer, true);
+ bool alloc = atomic_read(&peer->count) == 0 ? false : true;
+ int id;
+ id = __peernet2id(net, peer, alloc);
return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
}
EXPORT_SYMBOL(peernet2id);
@@ -236,10 +243,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
net->user_ns = user_ns;
idr_init(&net->netns_ids);
-#ifdef NETNS_REFCNT_DEBUG
- atomic_set(&net->use_count, 0);
-#endif
-
list_for_each_entry(ops, &pernet_list, list) {
error = ops_init(ops, net);
if (error < 0)
@@ -294,13 +297,6 @@ out_free:
static void net_free(struct net *net)
{
-#ifdef NETNS_REFCNT_DEBUG
- if (unlikely(atomic_read(&net->use_count) != 0)) {
- pr_emerg("network namespace not free! Usage: %d\n",
- atomic_read(&net->use_count));
- return;
- }
-#endif
kfree(rcu_access_pointer(net->gen));
kmem_cache_free(net_cachep, net);
}
@@ -368,8 +364,10 @@ static void cleanup_net(struct work_struct *work)
for_each_net(tmp) {
int id = __peernet2id(tmp, net, false);
- if (id >= 0)
+ if (id >= 0) {
+ rtnl_net_notifyid(tmp, net, RTM_DELNSID, id);
idr_remove(&tmp->netns_ids, id);
+ }
}
idr_destroy(&net->netns_ids);
@@ -540,7 +538,8 @@ static int rtnl_net_get_size(void)
}
static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
- int cmd, struct net *net, struct net *peer)
+ int cmd, struct net *net, struct net *peer,
+ int nsid)
{
struct nlmsghdr *nlh;
struct rtgenmsg *rth;
@@ -555,9 +554,13 @@ static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
rth = nlmsg_data(nlh);
rth->rtgen_family = AF_UNSPEC;
- id = __peernet2id(net, peer, false);
- if (id < 0)
- id = NETNSA_NSID_NOT_ASSIGNED;
+ if (nsid >= 0) {
+ id = nsid;
+ } else {
+ id = __peernet2id(net, peer, false);
+ if (id < 0)
+ id = NETNSA_NSID_NOT_ASSIGNED;
+ }
if (nla_put_s32(skb, NETNSA_NSID, id))
goto nla_put_failure;
@@ -574,8 +577,8 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
struct nlattr *tb[NETNSA_MAX + 1];
struct sk_buff *msg;
- int err = -ENOBUFS;
struct net *peer;
+ int err;
err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
rtnl_net_policy);
@@ -598,7 +601,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
}
err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
- RTM_GETNSID, net, peer);
+ RTM_GETNSID, net, peer, -1);
if (err < 0)
goto err_out;
@@ -612,6 +615,75 @@ out:
return err;
}
+struct rtnl_net_dump_cb {
+ struct net *net;
+ struct sk_buff *skb;
+ struct netlink_callback *cb;
+ int idx;
+ int s_idx;
+};
+
+static int rtnl_net_dumpid_one(int id, void *peer, void *data)
+{
+ struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data;
+ int ret;
+
+ if (net_cb->idx < net_cb->s_idx)
+ goto cont;
+
+ ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
+ net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWNSID, net_cb->net, peer, id);
+ if (ret < 0)
+ return ret;
+
+cont:
+ net_cb->idx++;
+ return 0;
+}
+
+static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct rtnl_net_dump_cb net_cb = {
+ .net = net,
+ .skb = skb,
+ .cb = cb,
+ .idx = 0,
+ .s_idx = cb->args[0],
+ };
+
+ ASSERT_RTNL();
+
+ idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+
+ cb->args[0] = net_cb.idx;
+ return skb->len;
+}
+
+static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
+ int id)
+{
+ struct sk_buff *msg;
+ int err = -ENOMEM;
+
+ msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+ if (!msg)
+ goto out;
+
+ err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, peer, id);
+ if (err < 0)
+ goto err_out;
+
+ rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
+ return;
+
+err_out:
+ nlmsg_free(msg);
+out:
+ rtnl_set_sk_err(net, RTNLGRP_NSID, err);
+}
+
static int __init net_ns_init(void)
{
struct net_generic *ng;
@@ -646,7 +718,8 @@ static int __init net_ns_init(void)
register_pernet_subsys(&net_ns_ops);
rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
+ NULL);
return 0;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b4899f5b7388..508155b283dd 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1134,6 +1134,9 @@ static ssize_t pktgen_if_write(struct file *file,
return len;
i += len;
+ if ((value > 1) &&
+ (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+ return -ENOTSUPP;
pkt_dev->burst = value < 1 ? 1 : value;
sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
return count;
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 04db318e6218..87b22c0bc08c 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -58,14 +58,14 @@ int reqsk_queue_alloc(struct request_sock_queue *queue,
return -ENOMEM;
get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
- rwlock_init(&queue->syn_wait_lock);
+ spin_lock_init(&queue->syn_wait_lock);
queue->rskq_accept_head = NULL;
lopt->nr_table_entries = nr_table_entries;
lopt->max_qlen_log = ilog2(nr_table_entries);
- write_lock_bh(&queue->syn_wait_lock);
+ spin_lock_bh(&queue->syn_wait_lock);
queue->listen_opt = lopt;
- write_unlock_bh(&queue->syn_wait_lock);
+ spin_unlock_bh(&queue->syn_wait_lock);
return 0;
}
@@ -81,10 +81,10 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk(
{
struct listen_sock *lopt;
- write_lock_bh(&queue->syn_wait_lock);
+ spin_lock_bh(&queue->syn_wait_lock);
lopt = queue->listen_opt;
queue->listen_opt = NULL;
- write_unlock_bh(&queue->syn_wait_lock);
+ spin_unlock_bh(&queue->syn_wait_lock);
return lopt;
}
@@ -94,21 +94,26 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
/* make all the listen_opt local to us */
struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
- if (lopt->qlen != 0) {
+ if (listen_sock_qlen(lopt) != 0) {
unsigned int i;
for (i = 0; i < lopt->nr_table_entries; i++) {
struct request_sock *req;
+ spin_lock_bh(&queue->syn_wait_lock);
while ((req = lopt->syn_table[i]) != NULL) {
lopt->syn_table[i] = req->dl_next;
- lopt->qlen--;
- reqsk_free(req);
+ atomic_inc(&lopt->qlen_dec);
+ if (del_timer(&req->rsk_timer))
+ reqsk_put(req);
+ reqsk_put(req);
}
+ spin_unlock_bh(&queue->syn_wait_lock);
}
}
- WARN_ON(lopt->qlen != 0);
+ if (WARN_ON(listen_sock_qlen(lopt) != 0))
+ pr_err("qlen %u\n", listen_sock_qlen(lopt));
kvfree(lopt);
}
@@ -153,24 +158,22 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
* case might also exist in tcp_v4_hnd_req() that will trigger this locking
* order.
*
- * When a TFO req is created, it needs to sock_hold its listener to prevent
- * the latter data structure from going away.
- *
- * This function also sets "treq->listener" to NULL and unreference listener
- * socket. treq->listener is used by the listener so it is protected by the
+ * This function also sets "treq->tfo_listener" to false.
+ * treq->tfo_listener is used by the listener so it is protected by the
* fastopenq->lock in this function.
*/
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset)
{
- struct sock *lsk = tcp_rsk(req)->listener;
- struct fastopen_queue *fastopenq =
- inet_csk(lsk)->icsk_accept_queue.fastopenq;
+ struct sock *lsk = req->rsk_listener;
+ struct fastopen_queue *fastopenq;
+
+ fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq;
tcp_sk(sk)->fastopen_rsk = NULL;
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
- tcp_rsk(req)->listener = NULL;
+ tcp_rsk(req)->tfo_listener = false;
if (req->sk) /* the child socket hasn't been accepted yet */
goto out;
@@ -179,8 +182,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
* special RST handling below.
*/
spin_unlock_bh(&fastopenq->lock);
- sock_put(lsk);
- reqsk_free(req);
+ reqsk_put(req);
return;
}
/* Wait for 60secs before removing a req that has triggered RST.
@@ -190,7 +192,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
*
* For more details see CoNext'11 "TCP Fast Open" paper.
*/
- req->expires = jiffies + 60*HZ;
+ req->rsk_timer.expires = jiffies + 60*HZ;
if (fastopenq->rskq_rst_head == NULL)
fastopenq->rskq_rst_head = req;
else
@@ -201,5 +203,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
fastopenq->qlen++;
out:
spin_unlock_bh(&fastopenq->lock);
- sock_put(lsk);
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ab293a3066b3..358d52a38533 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -818,7 +818,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
nla_total_size(sizeof(struct ifla_vf_vlan)) +
nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
nla_total_size(sizeof(struct ifla_vf_rate)) +
- nla_total_size(sizeof(struct ifla_vf_link_state)));
+ nla_total_size(sizeof(struct ifla_vf_link_state)) +
+ nla_total_size(sizeof(struct ifla_vf_rss_query_en)));
return size;
} else
return 0;
@@ -982,6 +983,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
return 0;
}
+static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
+{
+ char name[IFNAMSIZ];
+ int err;
+
+ err = dev_get_phys_port_name(dev, name, sizeof(name));
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
@@ -1037,8 +1056,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
- (dev->ifindex != dev->iflink &&
- nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
+ (dev->ifindex != dev_get_iflink(dev) &&
+ nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
(upper_dev &&
nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
@@ -1072,6 +1091,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (rtnl_phys_port_id_fill(skb, dev))
goto nla_put_failure;
+ if (rtnl_phys_port_name_fill(skb, dev))
+ goto nla_put_failure;
+
if (rtnl_phys_switch_id_fill(skb, dev))
goto nla_put_failure;
@@ -1111,14 +1133,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_tx_rate vf_tx_rate;
struct ifla_vf_spoofchk vf_spoofchk;
struct ifla_vf_link_state vf_linkstate;
+ struct ifla_vf_rss_query_en vf_rss_query_en;
/*
* Not all SR-IOV capable drivers support the
- * spoofcheck query. Preset to -1 so the user
- * space tool can detect that the driver didn't
- * report anything.
+ * spoofcheck and "RSS query enable" query. Preset to
+ * -1 so the user space tool can detect that the driver
+ * didn't report anything.
*/
ivi.spoofchk = -1;
+ ivi.rss_query_en = -1;
memset(ivi.mac, 0, sizeof(ivi.mac));
/* The default value for VF link state is "auto"
* IFLA_VF_LINK_STATE_AUTO which equals zero
@@ -1131,7 +1155,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
vf_rate.vf =
vf_tx_rate.vf =
vf_spoofchk.vf =
- vf_linkstate.vf = ivi.vf;
+ vf_linkstate.vf =
+ vf_rss_query_en.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
@@ -1141,6 +1166,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
vf_rate.max_tx_rate = ivi.max_tx_rate;
vf_spoofchk.setting = ivi.spoofchk;
vf_linkstate.link_state = ivi.linkstate;
+ vf_rss_query_en.setting = ivi.rss_query_en;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
@@ -1155,7 +1181,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
&vf_spoofchk) ||
nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
- &vf_linkstate))
+ &vf_linkstate) ||
+ nla_put(skb, IFLA_VF_RSS_QUERY_EN,
+ sizeof(vf_rss_query_en),
+ &vf_rss_query_en))
goto nla_put_failure;
nla_nest_end(skb, vf);
}
@@ -1269,6 +1298,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
[IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) },
[IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) },
[IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) },
+ [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) },
};
static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1300,7 +1330,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
s_h = cb->args[0];
s_idx = cb->args[1];
- rcu_read_lock();
cb->seq = net->dev_base_seq;
/* A hack to preserve kernel<->userspace interface.
@@ -1322,7 +1351,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
- hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ hlist_for_each_entry(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -1344,7 +1373,6 @@ cont:
}
}
out:
- rcu_read_unlock();
cb->args[1] = idx;
cb->args[0] = h;
@@ -1481,6 +1509,17 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
ivl->link_state);
break;
}
+ case IFLA_VF_RSS_QUERY_EN: {
+ struct ifla_vf_rss_query_en *ivrssq_en;
+
+ ivrssq_en = nla_data(vf);
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_rss_query_en)
+ err = ops->ndo_set_vf_rss_query_en(dev,
+ ivrssq_en->vf,
+ ivrssq_en->setting);
+ break;
+ }
default:
err = -EINVAL;
break;
@@ -1817,6 +1856,42 @@ errout:
return err;
}
+static int rtnl_group_dellink(const struct net *net, int group)
+{
+ struct net_device *dev, *aux;
+ LIST_HEAD(list_kill);
+ bool found = false;
+
+ if (!group)
+ return -EPERM;
+
+ for_each_netdev(net, dev) {
+ if (dev->group == group) {
+ const struct rtnl_link_ops *ops;
+
+ found = true;
+ ops = dev->rtnl_link_ops;
+ if (!ops || !ops->dellink)
+ return -EOPNOTSUPP;
+ }
+ }
+
+ if (!found)
+ return -ENODEV;
+
+ for_each_netdev_safe(net, dev, aux) {
+ if (dev->group == group) {
+ const struct rtnl_link_ops *ops;
+
+ ops = dev->rtnl_link_ops;
+ ops->dellink(dev, &list_kill);
+ }
+ }
+ unregister_netdevice_many(&list_kill);
+
+ return 0;
+}
+
static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
@@ -1840,6 +1915,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
dev = __dev_get_by_name(net, ifname);
+ else if (tb[IFLA_GROUP])
+ return rtnl_group_dellink(net, nla_get_u32(tb[IFLA_GROUP]));
else
return -EINVAL;
@@ -1875,7 +1952,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
EXPORT_SYMBOL(rtnl_configure_link);
struct net_device *rtnl_create_link(struct net *net,
- char *ifname, unsigned char name_assign_type,
+ const char *ifname, unsigned char name_assign_type,
const struct rtnl_link_ops *ops, struct nlattr *tb[])
{
int err;
@@ -1934,10 +2011,10 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
struct ifinfomsg *ifm,
struct nlattr **tb)
{
- struct net_device *dev;
+ struct net_device *dev, *aux;
int err;
- for_each_netdev(net, dev) {
+ for_each_netdev_safe(net, dev, aux) {
if (dev->group == group) {
err = do_setlink(skb, dev, ifm, tb, NULL, 0);
if (err < 0)
@@ -2012,8 +2089,8 @@ replay:
}
if (1) {
- struct nlattr *attr[ops ? ops->maxtype + 1 : 0];
- struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0];
+ struct nlattr *attr[ops ? ops->maxtype + 1 : 1];
+ struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 1];
struct nlattr **data = NULL;
struct nlattr **slave_data = NULL;
struct net *dest_net, *link_net = NULL;
@@ -2122,6 +2199,10 @@ replay:
if (IS_ERR(dest_net))
return PTR_ERR(dest_net);
+ err = -EPERM;
+ if (!netlink_ns_capable(skb, dest_net->user_ns, CAP_NET_ADMIN))
+ goto out;
+
if (tb[IFLA_LINK_NETNSID]) {
int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
@@ -2130,6 +2211,9 @@ replay:
err = -EINVAL;
goto out;
}
+ err = -EPERM;
+ if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
+ goto out;
}
dev = rtnl_create_link(link_net ? : dest_net, ifname,
@@ -2161,28 +2245,28 @@ replay:
}
}
err = rtnl_configure_link(dev, ifm);
- if (err < 0) {
- if (ops->newlink) {
- LIST_HEAD(list_kill);
-
- ops->dellink(dev, &list_kill);
- unregister_netdevice_many(&list_kill);
- } else {
- unregister_netdevice(dev);
- }
- goto out;
- }
-
+ if (err < 0)
+ goto out_unregister;
if (link_net) {
err = dev_change_net_namespace(dev, dest_net, ifname);
if (err < 0)
- unregister_netdevice(dev);
+ goto out_unregister;
}
out:
if (link_net)
put_net(link_net);
put_net(dest_net);
return err;
+out_unregister:
+ if (ops->newlink) {
+ LIST_HEAD(list_kill);
+
+ ops->dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ } else {
+ unregister_netdevice(dev);
+ }
+ goto out;
}
}
@@ -2340,7 +2424,7 @@ EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
- u8 *addr, u32 pid, u32 seq,
+ u8 *addr, u16 vid, u32 pid, u32 seq,
int type, unsigned int flags,
int nlflags)
{
@@ -2362,6 +2446,9 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
goto nla_put_failure;
+ if (vid)
+ if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
@@ -2376,7 +2463,7 @@ static inline size_t rtnl_fdb_nlmsg_size(void)
return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
}
-static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
+static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2386,7 +2473,8 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
if (!skb)
goto errout;
- err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
+ err = nlmsg_populate_fdb_fill(skb, dev, addr, vid,
+ 0, 0, type, NTF_SELF, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -2521,7 +2609,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
nlh->nlmsg_flags);
if (!err) {
- rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
+ rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH);
ndm->ndm_flags &= ~NTF_SELF;
}
}
@@ -2622,7 +2710,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
if (!err) {
- rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
+ rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH);
ndm->ndm_flags &= ~NTF_SELF;
}
}
@@ -2647,7 +2735,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
if (*idx < cb->args[0])
goto skip;
- err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
+ err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
portid, seq,
RTM_NEWNEIGH, NTF_SELF,
NLM_F_MULTI);
@@ -2690,7 +2778,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net_device *dev;
struct nlattr *tb[IFLA_MAX+1];
- struct net_device *bdev = NULL;
struct net_device *br_dev = NULL;
const struct net_device_ops *ops = NULL;
const struct net_device_ops *cops = NULL;
@@ -2714,7 +2801,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
return -ENODEV;
ops = br_dev->netdev_ops;
- bdev = br_dev;
}
for_each_netdev(net, dev) {
@@ -2727,7 +2813,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
cops = br_dev->netdev_ops;
}
- bdev = dev;
} else {
if (dev != br_dev &&
!(dev->priv_flags & IFF_BRIDGE_PORT))
@@ -2737,7 +2822,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
!(dev->priv_flags & IFF_EBRIDGE))
continue;
- bdev = br_dev;
cops = ops;
}
@@ -2799,8 +2883,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) ||
(dev->addr_len &&
nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
- (dev->ifindex != dev->iflink &&
- nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+ (dev->ifindex != dev_get_iflink(dev) &&
+ nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
goto nla_put_failure;
br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 88c613eab142..d1967dab9cc6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2865,7 +2865,6 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
* @from: search offset
* @to: search limit
* @config: textsearch configuration
- * @state: uninitialized textsearch state variable
*
* Finds a pattern in the skb data according to the specified
* textsearch configuration. Use textsearch_next() to retrieve
@@ -2873,17 +2872,17 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
* to the first occurrence or UINT_MAX if no match was found.
*/
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
- unsigned int to, struct ts_config *config,
- struct ts_state *state)
+ unsigned int to, struct ts_config *config)
{
+ struct ts_state state;
unsigned int ret;
config->get_next_block = skb_ts_get_next_block;
config->finish = skb_ts_finish;
- skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));
+ skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state));
- ret = textsearch_find(config, state);
+ ret = textsearch_find(config, &state);
return (ret <= to - from ? ret : UINT_MAX);
}
EXPORT_SYMBOL(skb_find_text);
@@ -3207,10 +3206,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
- struct sk_buff *nskb, *lp, *p = *head;
unsigned int len = skb_gro_len(skb);
+ struct sk_buff *lp, *p = *head;
unsigned int delta_truesize;
- unsigned int headroom;
if (unlikely(p->len + len >= 65536))
return -E2BIG;
@@ -3277,48 +3275,6 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
goto done;
}
- /* switch back to head shinfo */
- pinfo = skb_shinfo(p);
-
- if (pinfo->frag_list)
- goto merge;
- if (skb_gro_len(p) != pinfo->gso_size)
- return -E2BIG;
-
- headroom = skb_headroom(p);
- nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
- if (unlikely(!nskb))
- return -ENOMEM;
-
- __copy_skb_header(nskb, p);
- nskb->mac_len = p->mac_len;
-
- skb_reserve(nskb, headroom);
- __skb_put(nskb, skb_gro_offset(p));
-
- skb_set_mac_header(nskb, skb_mac_header(p) - p->data);
- skb_set_network_header(nskb, skb_network_offset(p));
- skb_set_transport_header(nskb, skb_transport_offset(p));
-
- __skb_pull(p, skb_gro_offset(p));
- memcpy(skb_mac_header(nskb), skb_mac_header(p),
- p->data - skb_mac_header(p));
-
- skb_shinfo(nskb)->frag_list = p;
- skb_shinfo(nskb)->gso_size = pinfo->gso_size;
- pinfo->gso_size = 0;
- __skb_header_release(p);
- NAPI_GRO_CB(nskb)->last = p;
-
- nskb->data_len += p->len;
- nskb->truesize += p->truesize;
- nskb->len += p->len;
-
- *head = nskb;
- nskb->next = p->next;
- p->next = NULL;
-
- p = nskb;
merge:
delta_truesize = skb->truesize;
@@ -3621,13 +3577,14 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
{
struct sk_buff_head *q = &sk->sk_error_queue;
struct sk_buff *skb, *skb_next;
+ unsigned long flags;
int err = 0;
- spin_lock_bh(&q->lock);
+ spin_lock_irqsave(&q->lock, flags);
skb = __skb_dequeue(q);
if (skb && (skb_next = skb_peek(q)))
err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
- spin_unlock_bh(&q->lock);
+ spin_unlock_irqrestore(&q->lock, flags);
sk->sk_err = err;
if (err)
@@ -3732,9 +3689,13 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
struct sock *sk, int tstype)
{
struct sk_buff *skb;
- bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+ bool tsonly;
+
+ if (!sk)
+ return;
- if (!sk || !skb_may_tx_timestamp(sk, tsonly))
+ tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+ if (!skb_may_tx_timestamp(sk, tsonly))
return;
if (tsonly)
@@ -3791,7 +3752,6 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
}
EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
-
/**
* skb_partial_csum_set - set up and verify partial csum values for packet
* @skb: the skb to set
@@ -4164,19 +4124,21 @@ EXPORT_SYMBOL(skb_try_coalesce);
*/
void skb_scrub_packet(struct sk_buff *skb, bool xnet)
{
- if (xnet)
- skb_orphan(skb);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
skb_dst_drop(skb);
- skb->mark = 0;
- skb->sender_cpu = 0;
- skb_init_secmark(skb);
+ skb_sender_cpu_clear(skb);
secpath_reset(skb);
nf_reset(skb);
nf_reset_trace(skb);
+
+ if (!xnet)
+ return;
+
+ skb_orphan(skb);
+ skb->mark = 0;
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
diff --git a/net/core/sock.c b/net/core/sock.c
index 93c8b20c91e4..e891bcf325ca 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -466,7 +466,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
skb_dst_force(skb);
spin_lock_irqsave(&list->lock, flags);
- skb->dropcount = atomic_read(&sk->sk_drops);
+ sock_skb_set_dropcount(sk, skb);
__skb_queue_tail(list, skb);
spin_unlock_irqrestore(&list->lock, flags);
@@ -653,6 +653,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
sock_reset_flag(sk, bit);
}
+bool sk_mc_loop(struct sock *sk)
+{
+ if (dev_recursion_level())
+ return false;
+ if (!sk)
+ return true;
+ switch (sk->sk_family) {
+ case AF_INET:
+ return inet_sk(sk)->mc_loop;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ return inet6_sk(sk)->mc_loop;
+#endif
+ }
+ WARN_ON(1);
+ return true;
+}
+EXPORT_SYMBOL(sk_mc_loop);
+
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
@@ -928,8 +947,6 @@ set_rcvbuf:
sk->sk_mark = val;
break;
- /* We implement the SO_SNDLOWAT etc to
- not be settable (1003.1g 5.3) */
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
break;
@@ -1234,6 +1251,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
default:
+ /* We implement the SO_SNDLOWAT etc to not be settable
+ * (1003.1g 7).
+ */
return -ENOPROTOOPT;
}
@@ -1454,9 +1474,8 @@ void sk_release_kernel(struct sock *sk)
return;
sock_hold(sk);
- sock_release(sk->sk_socket);
- release_net(sock_net(sk));
sock_net_set(sk, get_net(&init_net));
+ sock_release(sk->sk_socket);
sock_put(sk);
}
EXPORT_SYMBOL(sk_release_kernel);
@@ -1538,6 +1557,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_err = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
+ atomic64_set(&newsk->sk_cookie, 0);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -1655,25 +1675,16 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+/*
+ * Buffer destructor for skbs that are not used directly in read or write
+ * path, e.g. for error handler skbs. Automatically called from kfree_skb.
+ */
void sock_efree(struct sk_buff *skb)
{
sock_put(skb->sk);
}
EXPORT_SYMBOL(sock_efree);
-#ifdef CONFIG_INET
-void sock_edemux(struct sk_buff *skb)
-{
- struct sock *sk = skb->sk;
-
- if (sk->sk_state == TCP_TIME_WAIT)
- inet_twsk_put(inet_twsk(sk));
- else
- sock_put(sk);
-}
-EXPORT_SYMBOL(sock_edemux);
-#endif
-
kuid_t sock_i_uid(struct sock *sk)
{
kuid_t uid;
@@ -2163,15 +2174,14 @@ int sock_no_getsockopt(struct socket *sock, int level, int optname,
}
EXPORT_SYMBOL(sock_no_getsockopt);
-int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
- size_t len)
+int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg);
-int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
- size_t len, int flags)
+int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
+ int flags)
{
return -EOPNOTSUPP;
}
@@ -2543,14 +2553,14 @@ int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
EXPORT_SYMBOL(compat_sock_common_getsockopt);
#endif
-int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t size, int flags)
+int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+ int flags)
{
struct sock *sk = sock->sk;
int addr_len = 0;
int err;
- err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+ err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
@@ -2727,6 +2737,42 @@ static inline void release_proto_idx(struct proto *prot)
}
#endif
+static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
+{
+ if (!rsk_prot)
+ return;
+ kfree(rsk_prot->slab_name);
+ rsk_prot->slab_name = NULL;
+ if (rsk_prot->slab) {
+ kmem_cache_destroy(rsk_prot->slab);
+ rsk_prot->slab = NULL;
+ }
+}
+
+static int req_prot_init(const struct proto *prot)
+{
+ struct request_sock_ops *rsk_prot = prot->rsk_prot;
+
+ if (!rsk_prot)
+ return 0;
+
+ rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
+ prot->name);
+ if (!rsk_prot->slab_name)
+ return -ENOMEM;
+
+ rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
+ rsk_prot->obj_size, 0,
+ 0, NULL);
+
+ if (!rsk_prot->slab) {
+ pr_crit("%s: Can't create request sock SLAB cache!\n",
+ prot->name);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
int proto_register(struct proto *prot, int alloc_slab)
{
if (alloc_slab) {
@@ -2740,21 +2786,8 @@ int proto_register(struct proto *prot, int alloc_slab)
goto out;
}
- if (prot->rsk_prot != NULL) {
- prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name);
- if (prot->rsk_prot->slab_name == NULL)
- goto out_free_sock_slab;
-
- prot->rsk_prot->slab = kmem_cache_create(prot->rsk_prot->slab_name,
- prot->rsk_prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN, NULL);
-
- if (prot->rsk_prot->slab == NULL) {
- pr_crit("%s: Can't create request sock SLAB cache!\n",
- prot->name);
- goto out_free_request_sock_slab_name;
- }
- }
+ if (req_prot_init(prot))
+ goto out_free_request_sock_slab;
if (prot->twsk_prot != NULL) {
prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
@@ -2766,8 +2799,7 @@ int proto_register(struct proto *prot, int alloc_slab)
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
- SLAB_HWCACHE_ALIGN |
- prot->slab_flags,
+ prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
goto out_free_timewait_sock_slab_name;
@@ -2783,14 +2815,8 @@ int proto_register(struct proto *prot, int alloc_slab)
out_free_timewait_sock_slab_name:
kfree(prot->twsk_prot->twsk_slab_name);
out_free_request_sock_slab:
- if (prot->rsk_prot && prot->rsk_prot->slab) {
- kmem_cache_destroy(prot->rsk_prot->slab);
- prot->rsk_prot->slab = NULL;
- }
-out_free_request_sock_slab_name:
- if (prot->rsk_prot)
- kfree(prot->rsk_prot->slab_name);
-out_free_sock_slab:
+ req_prot_cleanup(prot->rsk_prot);
+
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
out:
@@ -2810,11 +2836,7 @@ void proto_unregister(struct proto *prot)
prot->slab = NULL;
}
- if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
- kmem_cache_destroy(prot->rsk_prot->slab);
- kfree(prot->rsk_prot->slab_name);
- prot->rsk_prot->slab = NULL;
- }
+ req_prot_cleanup(prot->rsk_prot);
if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
kmem_cache_destroy(prot->twsk_prot->twsk_slab);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index ad704c757bb4..74dddf84adcd 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -13,22 +13,39 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
-int sock_diag_check_cookie(void *sk, __u32 *cookie)
+static u64 sock_gen_cookie(struct sock *sk)
{
- if ((cookie[0] != INET_DIAG_NOCOOKIE ||
- cookie[1] != INET_DIAG_NOCOOKIE) &&
- ((u32)(unsigned long)sk != cookie[0] ||
- (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1]))
- return -ESTALE;
- else
+ while (1) {
+ u64 res = atomic64_read(&sk->sk_cookie);
+
+ if (res)
+ return res;
+ res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+ atomic64_cmpxchg(&sk->sk_cookie, 0, res);
+ }
+}
+
+int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie)
+{
+ u64 res;
+
+ if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE)
return 0;
+
+ res = sock_gen_cookie(sk);
+ if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1])
+ return -ESTALE;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
-void sock_diag_save_cookie(void *sk, __u32 *cookie)
+void sock_diag_save_cookie(struct sock *sk, __u32 *cookie)
{
- cookie[0] = (u32)(unsigned long)sk;
- cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+ u64 res = sock_gen_cookie(sk);
+
+ cookie[0] = (u32)res;
+ cookie[1] = (u32)(res >> 32);
}
EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 433424804284..95b6139d710c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -24,7 +24,8 @@
static int zero = 0;
static int one = 1;
-static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -237,7 +238,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_sndbuf,
},
{
.procname = "rmem_max",
@@ -245,7 +246,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_rcvbuf,
},
{
.procname = "wmem_default",
@@ -253,7 +254,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_sndbuf,
},
{
.procname = "rmem_default",
@@ -261,7 +262,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_rcvbuf,
},
{
.procname = "dev_weight",
@@ -401,7 +402,6 @@ static struct ctl_table netns_core_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.extra1 = &zero,
- .extra2 = &ushort_max,
.proc_handler = proc_dointvec_minmax
},
{ }
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-02 09:22:34 +0300