summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
Diffstat (limited to 'include/net')
-rw-r--r--include/net/addrconf.h1
-rw-r--r--include/net/af_vsock.h2
-rw-r--r--include/net/bond_options.h3
-rw-r--r--include/net/bonding.h3
-rw-r--r--include/net/cfg80211.h4
-rw-r--r--include/net/checksum.h4
-rw-r--r--include/net/codel.h12
-rw-r--r--include/net/dst.h18
-rw-r--r--include/net/flow_dissector.h167
-rw-r--r--include/net/flow_keys.h45
-rw-r--r--include/net/geneve.h5
-rw-r--r--include/net/inet_common.h2
-rw-r--r--include/net/inet_hashtables.h2
-rw-r--r--include/net/ip.h25
-rw-r--r--include/net/ip6_fib.h41
-rw-r--r--include/net/ipv6.h19
-rw-r--r--include/net/llc_conn.h2
-rw-r--r--include/net/mac80211.h161
-rw-r--r--include/net/net_namespace.h3
-rw-r--r--include/net/netns/ipv4.h2
-rw-r--r--include/net/netns/ipv6.h1
-rw-r--r--include/net/request_sock.h4
-rw-r--r--include/net/sch_generic.h23
-rw-r--r--include/net/sock.h30
-rw-r--r--include/net/switchdev.h257
-rw-r--r--include/net/tcp.h79
26 files changed, 581 insertions, 334 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 80456f72d70a..def59d3a34d5 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -142,6 +142,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev);
void ipv6_mc_remap(struct inet6_dev *idev);
void ipv6_mc_init_dev(struct inet6_dev *idev);
void ipv6_mc_destroy_dev(struct inet6_dev *idev);
+int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed);
void addrconf_dad_failure(struct inet6_ifaddr *ifp);
bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 172632dd9930..db639a4c5ab8 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -74,7 +74,7 @@ void vsock_pending_work(struct work_struct *work);
struct sock *__vsock_create(struct net *net,
struct socket *sock,
struct sock *parent,
- gfp_t priority, unsigned short type);
+ gfp_t priority, unsigned short type, int kern);
/**** TRANSPORT ****/
diff --git a/include/net/bond_options.h b/include/net/bond_options.h
index ea6546d2c946..c28aca25320e 100644
--- a/include/net/bond_options.h
+++ b/include/net/bond_options.h
@@ -63,6 +63,9 @@ enum {
BOND_OPT_LP_INTERVAL,
BOND_OPT_SLAVES,
BOND_OPT_TLB_DYNAMIC_LB,
+ BOND_OPT_AD_ACTOR_SYS_PRIO,
+ BOND_OPT_AD_ACTOR_SYSTEM,
+ BOND_OPT_AD_USER_PORT_KEY,
BOND_OPT_LAST
};
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 78ed135e9dea..20defc0353d1 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -136,6 +136,9 @@ struct bond_params {
int packets_per_slave;
int tlb_dynamic_lb;
struct reciprocal_value reciprocal_packets_per_slave;
+ u16 ad_actor_sys_prio;
+ u16 ad_user_port_key;
+ u8 ad_actor_system[ETH_ALEN];
};
struct bond_parm_tbl {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f8d6813cd5b2..d63ecec73090 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -111,7 +111,7 @@ enum ieee80211_band {
* This may be due to the driver or due to regulatory bandwidth
* restrictions.
* @IEEE80211_CHAN_INDOOR_ONLY: see %NL80211_FREQUENCY_ATTR_INDOOR_ONLY
- * @IEEE80211_CHAN_GO_CONCURRENT: see %NL80211_FREQUENCY_ATTR_GO_CONCURRENT
+ * @IEEE80211_CHAN_IR_CONCURRENT: see %NL80211_FREQUENCY_ATTR_IR_CONCURRENT
* @IEEE80211_CHAN_NO_20MHZ: 20 MHz bandwidth is not permitted
* on this channel.
* @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted
@@ -129,7 +129,7 @@ enum ieee80211_channel_flags {
IEEE80211_CHAN_NO_80MHZ = 1<<7,
IEEE80211_CHAN_NO_160MHZ = 1<<8,
IEEE80211_CHAN_INDOOR_ONLY = 1<<9,
- IEEE80211_CHAN_GO_CONCURRENT = 1<<10,
+ IEEE80211_CHAN_IR_CONCURRENT = 1<<10,
IEEE80211_CHAN_NO_20MHZ = 1<<11,
IEEE80211_CHAN_NO_10MHZ = 1<<12,
};
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 0a55ac715077..2d1d73cb773e 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -122,7 +122,9 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
{
- *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to));
+ __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
+
+ *sum = csum_fold(csum_add(tmp, (__force __wsum)to));
}
/* Implements RFC 1624 (Incremental Internet Checksum)
diff --git a/include/net/codel.h b/include/net/codel.h
index 1e18005f7f65..267e70210061 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -7,7 +7,7 @@
* Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com>
* Copyright (C) 2011-2012 Van Jacobson <van@pollere.net>
* Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net>
- * Copyright (C) 2012 Eric Dumazet <edumazet@google.com>
+ * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
@@ -119,12 +119,14 @@ static inline u32 codel_time_to_us(codel_time_t val)
/**
* struct codel_params - contains codel parameters
* @target: target queue size (in time units)
+ * @ce_threshold: threshold for marking packets with ECN CE
* @interval: width of moving time window
* @mtu: device mtu, or minimal queue backlog in bytes.
* @ecn: is Explicit Congestion Notification enabled
*/
struct codel_params {
codel_time_t target;
+ codel_time_t ce_threshold;
codel_time_t interval;
u32 mtu;
bool ecn;
@@ -161,19 +163,24 @@ struct codel_vars {
* @maxpacket: largest packet we've seen so far
* @drop_count: temp count of dropped packets in dequeue()
* ecn_mark: number of packets we ECN marked instead of dropping
+ * ce_mark: number of packets CE marked because sojourn time was above ce_threshold
*/
struct codel_stats {
u32 maxpacket;
u32 drop_count;
u32 ecn_mark;
+ u32 ce_mark;
};
+#define CODEL_DISABLED_THRESHOLD INT_MAX
+
static void codel_params_init(struct codel_params *params,
const struct Qdisc *sch)
{
params->interval = MS2TIME(100);
params->target = MS2TIME(5);
params->mtu = psched_mtu(qdisc_dev(sch));
+ params->ce_threshold = CODEL_DISABLED_THRESHOLD;
params->ecn = false;
}
@@ -354,6 +361,9 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
vars->rec_inv_sqrt);
}
end:
+ if (skb && codel_time_after(vars->ldelay, params->ce_threshold) &&
+ INET_ECN_set_ce(skb))
+ stats->ce_mark++;
return skb;
}
#endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 0fb99a26e973..2bc73f8a00a9 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -109,7 +109,6 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
extern const u32 dst_default_metrics[];
#define DST_METRICS_READ_ONLY 0x1UL
-#define DST_METRICS_FORCE_OVERWRITE 0x2UL
#define DST_METRICS_FLAGS 0x3UL
#define __DST_METRICS_PTR(Y) \
((u32 *)((Y) & ~DST_METRICS_FLAGS))
@@ -120,11 +119,6 @@ static inline bool dst_metrics_read_only(const struct dst_entry *dst)
return dst->_metrics & DST_METRICS_READ_ONLY;
}
-static inline void dst_metrics_set_force_overwrite(struct dst_entry *dst)
-{
- dst->_metrics |= DST_METRICS_FORCE_OVERWRITE;
-}
-
void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
@@ -355,18 +349,6 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
__skb_tunnel_rx(skb, dev, net);
}
-/* Children define the path of the packet through the
- * Linux networking. Thus, destinations are stackable.
- */
-
-static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
-{
- struct dst_entry *child = dst_clone(skb_dst(skb)->child);
-
- skb_dst_drop(skb);
- return child;
-}
-
int dst_discard_sk(struct sock *sk, struct sk_buff *skb);
static inline int dst_discard(struct sk_buff *skb)
{
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
new file mode 100644
index 000000000000..bac9c1421f58
--- /dev/null
+++ b/include/net/flow_dissector.h
@@ -0,0 +1,167 @@
+#ifndef _NET_FLOW_DISSECTOR_H
+#define _NET_FLOW_DISSECTOR_H
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/in6.h>
+#include <uapi/linux/if_ether.h>
+
+/**
+ * struct flow_dissector_key_basic:
+ * @thoff: Transport header offset
+ * @n_proto: Network header protocol (eg. IPv4/IPv6)
+ * @ip_proto: Transport header protocol (eg. TCP/UDP)
+ */
+struct flow_dissector_key_basic {
+ u16 thoff;
+ __be16 n_proto;
+ u8 ip_proto;
+};
+
+/**
+ * struct flow_dissector_key_addrs:
+ * @src: source ip address in case of IPv4
+ * For IPv6 it contains 32bit hash of src address
+ * @dst: destination ip address in case of IPv4
+ * For IPv6 it contains 32bit hash of dst address
+ */
+struct flow_dissector_key_addrs {
+ /* (src,dst) must be grouped, in the same way than in IP header */
+ __be32 src;
+ __be32 dst;
+};
+
+/**
+ * flow_dissector_key_tp_ports:
+ * @ports: port numbers of Transport header
+ * src: source port number
+ * dst: destination port number
+ */
+struct flow_dissector_key_ports {
+ union {
+ __be32 ports;
+ struct {
+ __be16 src;
+ __be16 dst;
+ };
+ };
+};
+
+/**
+ * struct flow_dissector_key_ipv6_addrs:
+ * @src: source ip address
+ * @dst: destination ip address
+ */
+struct flow_dissector_key_ipv6_addrs {
+ /* (src,dst) must be grouped, in the same way than in IP header */
+ struct in6_addr src;
+ struct in6_addr dst;
+};
+
+/**
+ * struct flow_dissector_key_eth_addrs:
+ * @src: source Ethernet address
+ * @dst: destination Ethernet address
+ */
+struct flow_dissector_key_eth_addrs {
+ /* (dst,src) must be grouped, in the same way than in ETH header */
+ unsigned char dst[ETH_ALEN];
+ unsigned char src[ETH_ALEN];
+};
+
+enum flow_dissector_key_id {
+ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_addrs */
+ FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS, /* struct flow_dissector_key_addrs */
+ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
+ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
+
+ FLOW_DISSECTOR_KEY_MAX,
+};
+
+struct flow_dissector_key {
+ enum flow_dissector_key_id key_id;
+ size_t offset; /* offset of struct flow_dissector_key_*
+ in target the struct */
+};
+
+struct flow_dissector {
+ unsigned int used_keys; /* each bit repesents presence of one key id */
+ unsigned short int offset[FLOW_DISSECTOR_KEY_MAX];
+};
+
+void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
+ const struct flow_dissector_key *key,
+ unsigned int key_count);
+
+bool __skb_flow_dissect(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ void *data, __be16 proto, int nhoff, int hlen);
+
+static inline bool skb_flow_dissect(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
+{
+ return __skb_flow_dissect(skb, flow_dissector, target_container,
+ NULL, 0, 0, 0);
+}
+
+struct flow_keys {
+ struct flow_dissector_key_addrs addrs;
+ struct flow_dissector_key_ports ports;
+ struct flow_dissector_key_basic basic;
+};
+
+extern struct flow_dissector flow_keys_dissector;
+extern struct flow_dissector flow_keys_buf_dissector;
+
+static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+ struct flow_keys *flow)
+{
+ memset(flow, 0, sizeof(*flow));
+ return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
+ NULL, 0, 0, 0);
+}
+
+static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
+ void *data, __be16 proto,
+ int nhoff, int hlen)
+{
+ memset(flow, 0, sizeof(*flow));
+ return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
+ data, proto, nhoff, hlen);
+}
+
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+ void *data, int hlen_proto);
+
+static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
+ int thoff, u8 ip_proto)
+{
+ return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
+}
+
+u32 flow_hash_from_keys(struct flow_keys *keys);
+void __skb_get_hash(struct sk_buff *skb);
+u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+ const struct flow_keys *keys, int hlen);
+
+/* struct flow_keys_digest:
+ *
+ * This structure is used to hold a digest of the full flow keys. This is a
+ * larger "hash" of a flow to allow definitively matching specific flows where
+ * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
+ * that it can by used in CB of skb (see sch_choke for an example).
+ */
+#define FLOW_KEYS_DIGEST_LEN 16
+struct flow_keys_digest {
+ u8 data[FLOW_KEYS_DIGEST_LEN];
+};
+
+void make_flow_keys_digest(struct flow_keys_digest *digest,
+ const struct flow_keys *flow);
+
+#endif
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
deleted file mode 100644
index dc8fd81412bf..000000000000
--- a/include/net/flow_keys.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef _NET_FLOW_KEYS_H
-#define _NET_FLOW_KEYS_H
-
-/* struct flow_keys:
- * @src: source ip address in case of IPv4
- * For IPv6 it contains 32bit hash of src address
- * @dst: destination ip address in case of IPv4
- * For IPv6 it contains 32bit hash of dst address
- * @ports: port numbers of Transport header
- * port16[0]: src port number
- * port16[1]: dst port number
- * @thoff: Transport header offset
- * @n_proto: Network header protocol (eg. IPv4/IPv6)
- * @ip_proto: Transport header protocol (eg. TCP/UDP)
- * All the members, except thoff, are in network byte order.
- */
-struct flow_keys {
- /* (src,dst) must be grouped, in the same way than in IP header */
- __be32 src;
- __be32 dst;
- union {
- __be32 ports;
- __be16 port16[2];
- };
- u16 thoff;
- __be16 n_proto;
- u8 ip_proto;
-};
-
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
- void *data, __be16 proto, int nhoff, int hlen);
-static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
-{
- return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0);
-}
-__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
- void *data, int hlen_proto);
-static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
-{
- return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
-}
-u32 flow_hash_from_keys(struct flow_keys *keys);
-unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len,
- __be16 protocol);
-#endif
diff --git a/include/net/geneve.h b/include/net/geneve.h
index 14fb8d3390b4..2a0543a1899d 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -62,6 +62,11 @@ struct genevehdr {
struct geneve_opt options[];
};
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+ return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
#ifdef CONFIG_INET
struct geneve_sock;
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 4a92423eefa5..279f83591971 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,7 +41,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
static inline void inet_ctl_sock_destroy(struct sock *sk)
{
- sk_release_kernel(sk);
+ sock_release(sk->sk_socket);
}
#endif
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 73fe0f9525d9..774d24151d4a 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -148,8 +148,6 @@ struct inet_hashinfo {
*/
struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE]
____cacheline_aligned_in_smp;
-
- atomic_t bsockets;
};
static inline struct inet_ehash_bucket *inet_ehash_bucket(
diff --git a/include/net/ip.h b/include/net/ip.h
index d14af7edd197..7921a36b805c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -31,7 +31,7 @@
#include <net/route.h>
#include <net/snmp.h>
#include <net/flow.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
struct sock;
@@ -108,9 +108,8 @@ int ip_local_deliver(struct sk_buff *skb);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *));
-int ip_do_nat(struct sk_buff *skb);
+int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct sock *, struct sk_buff *));
void ip_send_check(struct iphdr *ip);
int __ip_local_out(struct sk_buff *skb);
int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
@@ -360,10 +359,10 @@ static inline void inet_set_txhash(struct sock *sk)
struct inet_sock *inet = inet_sk(sk);
struct flow_keys keys;
- keys.src = inet->inet_saddr;
- keys.dst = inet->inet_daddr;
- keys.port16[0] = inet->inet_sport;
- keys.port16[1] = inet->inet_dport;
+ keys.addrs.src = inet->inet_saddr;
+ keys.addrs.dst = inet->inet_daddr;
+ keys.ports.src = inet->inet_sport;
+ keys.ports.dst = inet->inet_dport;
sk->sk_txhash = flow_hash_from_keys(&keys);
}
@@ -478,6 +477,16 @@ enum ip_defrag_users {
IP_DEFRAG_MACVLAN,
};
+/* Return true if the value of 'user' is between 'lower_bond'
+ * and 'upper_bond' inclusively.
+ */
+static inline bool ip_defrag_user_in_between(u32 user,
+ enum ip_defrag_users lower_bond,
+ enum ip_defrag_users upper_bond)
+{
+ return user >= lower_bond && user <= upper_bond;
+}
+
int ip_defrag(struct sk_buff *skb, u32 user);
#ifdef CONFIG_INET
struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 20e80fa7bbdd..e00018011028 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -121,44 +121,14 @@ struct rt6_info {
struct rt6key rt6i_prefsrc;
struct inet6_dev *rt6i_idev;
- unsigned long _rt6i_peer;
u32 rt6i_metric;
+ u32 rt6i_pmtu;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
};
-static inline struct inet_peer *rt6_peer_ptr(struct rt6_info *rt)
-{
- return inetpeer_ptr(rt->_rt6i_peer);
-}
-
-static inline bool rt6_has_peer(struct rt6_info *rt)
-{
- return inetpeer_ptr_is_peer(rt->_rt6i_peer);
-}
-
-static inline void __rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
-{
- __inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
-}
-
-static inline bool rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
-{
- return inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
-}
-
-static inline void rt6_init_peer(struct rt6_info *rt, struct inet_peer_base *base)
-{
- inetpeer_init_ptr(&rt->_rt6i_peer, base);
-}
-
-static inline void rt6_transfer_peer(struct rt6_info *rt, struct rt6_info *ort)
-{
- inetpeer_transfer_peer(&rt->_rt6i_peer, &ort->_rt6i_peer);
-}
-
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
{
return ((struct rt6_info *)dst)->rt6i_idev;
@@ -189,15 +159,6 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
rt0->rt6i_flags |= RTF_EXPIRES;
}
-static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
-{
- struct dst_entry *new = (struct dst_entry *) from;
-
- rt->rt6i_flags &= ~RTF_EXPIRES;
- dst_hold(new);
- rt->dst.from = new;
-}
-
static inline void ip6_rt_put(struct rt6_info *rt)
{
/* dst_release() accepts a NULL parameter.
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index eec8ad3c9843..aab8190d16e8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -19,7 +19,7 @@
#include <net/if_inet6.h>
#include <net/ndisc.h>
#include <net/flow.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
#include <net/snmp.h>
#define SIN6_LEN_RFC2133 24
@@ -239,8 +239,10 @@ struct ip6_flowlabel {
struct net *fl_net;
};
-#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
-#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF)
+#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
+#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF)
+#define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000)
+
#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
#define IPV6_TCLASS_SHIFT 20
@@ -696,10 +698,10 @@ static inline void ip6_set_txhash(struct sock *sk)
struct ipv6_pinfo *np = inet6_sk(sk);
struct flow_keys keys;
- keys.src = (__force __be32)ipv6_addr_hash(&np->saddr);
- keys.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
- keys.port16[0] = inet->inet_sport;
- keys.port16[1] = inet->inet_dport;
+ keys.addrs.src = (__force __be32)ipv6_addr_hash(&np->saddr);
+ keys.addrs.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
+ keys.ports.src = inet->inet_sport;
+ keys.ports.dst = inet->inet_dport;
sk->sk_txhash = flow_hash_from_keys(&keys);
}
@@ -719,6 +721,9 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
hash ^= hash >> 12;
flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
+
+ if (net->ipv6.sysctl.flowlabel_state_ranges)
+ flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG;
}
return flowlabel;
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 0134681acc4c..fe994d2e5286 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -96,7 +96,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
}
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
- struct proto *prot);
+ struct proto *prot, int kern);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8e3668b44c29..2f8b7decace0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -337,10 +337,16 @@ enum ieee80211_bss_change {
* enum ieee80211_event_type - event to be notified to the low level driver
* @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver.
* @MLME_EVENT: event related to MLME
+ * @BAR_RX_EVENT: a BAR was received
+ * @BA_FRAME_TIMEOUT: Frames were released from the reordering buffer because
+ * they timed out. This won't be called for each frame released, but only
+ * once each time the timeout triggers.
*/
enum ieee80211_event_type {
RSSI_EVENT,
MLME_EVENT,
+ BAR_RX_EVENT,
+ BA_FRAME_TIMEOUT,
};
/**
@@ -354,7 +360,7 @@ enum ieee80211_rssi_event_data {
};
/**
- * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT
+ * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT
* @data: See &enum ieee80211_rssi_event_data
*/
struct ieee80211_rssi_event {
@@ -388,7 +394,7 @@ enum ieee80211_mlme_event_status {
};
/**
- * enum ieee80211_mlme_event - data attached to an %MLME_EVENT
+ * struct ieee80211_mlme_event - data attached to an %MLME_EVENT
* @data: See &enum ieee80211_mlme_event_data
* @status: See &enum ieee80211_mlme_event_status
* @reason: the reason code if applicable
@@ -400,16 +406,31 @@ struct ieee80211_mlme_event {
};
/**
+ * struct ieee80211_ba_event - data attached for BlockAck related events
+ * @sta: pointer to the &ieee80211_sta to which this event relates
+ * @tid: the tid
+ * @ssn: the starting sequence number (for %BAR_RX_EVENT)
+ */
+struct ieee80211_ba_event {
+ struct ieee80211_sta *sta;
+ u16 tid;
+ u16 ssn;
+};
+
+/**
* struct ieee80211_event - event to be sent to the driver
- * @type The event itself. See &enum ieee80211_event_type.
+ * @type: The event itself. See &enum ieee80211_event_type.
* @rssi: relevant if &type is %RSSI_EVENT
* @mlme: relevant if &type is %AUTH_EVENT
+ * @ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT
+ * @u:union holding the fields above
*/
struct ieee80211_event {
enum ieee80211_event_type type;
union {
struct ieee80211_rssi_event rssi;
struct ieee80211_mlme_event mlme;
+ struct ieee80211_ba_event ba;
} u;
};
@@ -1480,6 +1501,47 @@ struct ieee80211_key_conf {
u8 key[0];
};
+#define IEEE80211_MAX_PN_LEN 16
+
+/**
+ * struct ieee80211_key_seq - key sequence counter
+ *
+ * @tkip: TKIP data, containing IV32 and IV16 in host byte order
+ * @ccmp: PN data, most significant byte first (big endian,
+ * reverse order than in packet)
+ * @aes_cmac: PN data, most significant byte first (big endian,
+ * reverse order than in packet)
+ * @aes_gmac: PN data, most significant byte first (big endian,
+ * reverse order than in packet)
+ * @gcmp: PN data, most significant byte first (big endian,
+ * reverse order than in packet)
+ * @hw: data for HW-only (e.g. cipher scheme) keys
+ */
+struct ieee80211_key_seq {
+ union {
+ struct {
+ u32 iv32;
+ u16 iv16;
+ } tkip;
+ struct {
+ u8 pn[6];
+ } ccmp;
+ struct {
+ u8 pn[6];
+ } aes_cmac;
+ struct {
+ u8 pn[6];
+ } aes_gmac;
+ struct {
+ u8 pn[6];
+ } gcmp;
+ struct {
+ u8 seq[IEEE80211_MAX_PN_LEN];
+ u8 seq_len;
+ } hw;
+ };
+};
+
/**
* struct ieee80211_cipher_scheme - cipher scheme
*
@@ -1797,6 +1859,10 @@ struct ieee80211_txq {
* the driver returns 1. This also forces the driver to advertise its
* supported cipher suites.
*
+ * @IEEE80211_HW_SUPPORT_FAST_XMIT: The driver/hardware supports fast-xmit,
+ * this currently requires only the ability to calculate the duration
+ * for frames.
+ *
* @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface
* queue mapping in order to use different queues (not just one per AC)
* for different virtual interfaces. See the doc section on HW queue
@@ -1845,7 +1911,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_WANT_MONITOR_VIF = 1<<14,
IEEE80211_HW_NO_AUTO_VIF = 1<<15,
IEEE80211_HW_SW_CRYPTO_CONTROL = 1<<16,
- /* free slots */
+ IEEE80211_HW_SUPPORT_FAST_XMIT = 1<<17,
IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18,
IEEE80211_HW_CONNECTION_MONITOR = 1<<19,
IEEE80211_HW_QUEUE_CONTROL = 1<<20,
@@ -1939,8 +2005,8 @@ enum ieee80211_hw_flags {
* Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values.
*
* @netdev_features: netdev features to be set in each netdev created
- * from this HW. Note only HW checksum features are currently
- * compatible with mac80211. Other feature bits will be rejected.
+ * from this HW. Note that not all features are usable with mac80211,
+ * other features will be rejected during HW registration.
*
* @uapsd_queues: This bitmap is included in (re)association frame to indicate
* for each access category if it is uAPSD trigger-enabled and delivery-
@@ -2504,10 +2570,6 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
* stack. It is always safe to pass more frames than requested,
* but this has negative impact on power consumption.
*
- * @FIF_PROMISC_IN_BSS: promiscuous mode within your BSS,
- * think of the BSS as your network segment and then this corresponds
- * to the regular ethernet device promiscuous mode.
- *
* @FIF_ALLMULTI: pass all multicast frames, this is used if requested
* by the user or if the hardware is not capable of filtering by
* multicast address.
@@ -2524,8 +2586,8 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
* mac80211 needs to do and the amount of CPU wakeups, so you should
* honour this flag if possible.
*
- * @FIF_CONTROL: pass control frames (except for PS Poll), if PROMISC_IN_BSS
- * is not set then only those addressed to this station.
+ * @FIF_CONTROL: pass control frames (except for PS Poll) addressed to this
+ * station
*
* @FIF_OTHER_BSS: pass frames destined to other BSSes
*
@@ -2535,7 +2597,6 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
* @FIF_PROBE_REQ: pass probe request frames
*/
enum ieee80211_filter_flags {
- FIF_PROMISC_IN_BSS = 1<<0,
FIF_ALLMULTI = 1<<1,
FIF_FCSFAIL = 1<<2,
FIF_PLCPFAIL = 1<<3,
@@ -2818,9 +2879,9 @@ enum ieee80211_reconfig_type {
* Returns zero if statistics are available.
* The callback can sleep.
*
- * @get_tkip_seq: If your device implements TKIP encryption in hardware this
- * callback should be provided to read the TKIP transmit IVs (both IV32
- * and IV16) for the given key from hardware.
+ * @get_key_seq: If your device implements encryption in hardware and does
+ * IV/PN assignment then this callback should be provided to read the
+ * IV/PN for the given key from hardware.
* The callback must be atomic.
*
* @set_frag_threshold: Configuration of fragmentation threshold. Assign this
@@ -3003,7 +3064,7 @@ enum ieee80211_reconfig_type {
* The callback can sleep.
* @event_callback: Notify driver about any event in mac80211. See
* &enum ieee80211_event_type for the different types.
- * The callback can sleep.
+ * The callback must be atomic.
*
* @release_buffered_frames: Release buffered frames according to the given
* parameters. In the case where the driver buffers some frames for
@@ -3219,8 +3280,9 @@ struct ieee80211_ops {
struct ieee80211_vif *vif);
int (*get_stats)(struct ieee80211_hw *hw,
struct ieee80211_low_level_stats *stats);
- void (*get_tkip_seq)(struct ieee80211_hw *hw, u8 hw_key_idx,
- u32 *iv32, u16 *iv16);
+ void (*get_key_seq)(struct ieee80211_hw *hw,
+ struct ieee80211_key_conf *key,
+ struct ieee80211_key_seq *seq);
int (*set_frag_threshold)(struct ieee80211_hw *hw, u32 value);
int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value);
int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
@@ -3468,14 +3530,15 @@ enum ieee80211_tpt_led_trigger_flags {
};
#ifdef CONFIG_MAC80211_LEDS
-char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw);
-char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw);
-char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw);
-char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw);
-char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
- unsigned int flags,
- const struct ieee80211_tpt_blink *blink_table,
- unsigned int blink_table_len);
+const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw);
+const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw);
+const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw);
+const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw);
+const char *
+__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
+ unsigned int flags,
+ const struct ieee80211_tpt_blink *blink_table,
+ unsigned int blink_table_len);
#endif
/**
* ieee80211_get_tx_led_name - get name of TX LED
@@ -3489,7 +3552,7 @@ char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw,
*
* Return: The name of the LED trigger. %NULL if not configured for LEDs.
*/
-static inline char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw)
+static inline const char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw)
{
#ifdef CONFIG_MAC80211_LEDS
return __ieee80211_get_tx_led_name(hw);
@@ -3510,7 +3573,7 @@ static inline char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw)
*
* Return: The name of the LED trigger. %NULL if not configured for LEDs.
*/
-static inline char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw)
+static inline const char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw)
{
#ifdef CONFIG_MAC80211_LEDS
return __ieee80211_get_rx_led_name(hw);
@@ -3531,7 +3594,7 @@ static inline char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw)
*
* Return: The name of the LED trigger. %NULL if not configured for LEDs.
*/
-static inline char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw)
+static inline const char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw)
{
#ifdef CONFIG_MAC80211_LEDS
return __ieee80211_get_assoc_led_name(hw);
@@ -3552,7 +3615,7 @@ static inline char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw)
*
* Return: The name of the LED trigger. %NULL if not configured for LEDs.
*/
-static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw)
+static inline const char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw)
{
#ifdef CONFIG_MAC80211_LEDS
return __ieee80211_get_radio_led_name(hw);
@@ -3573,7 +3636,7 @@ static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw)
*
* Note: This function must be called before ieee80211_register_hw().
*/
-static inline char *
+static inline const char *
ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags,
const struct ieee80211_tpt_blink *blink_table,
unsigned int blink_table_len)
@@ -4254,40 +4317,6 @@ void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
u8 *k1, u8 *k2);
/**
- * struct ieee80211_key_seq - key sequence counter
- *
- * @tkip: TKIP data, containing IV32 and IV16 in host byte order
- * @ccmp: PN data, most significant byte first (big endian,
- * reverse order than in packet)
- * @aes_cmac: PN data, most significant byte first (big endian,
- * reverse order than in packet)
- * @aes_gmac: PN data, most significant byte first (big endian,
- * reverse order than in packet)
- * @gcmp: PN data, most significant byte first (big endian,
- * reverse order than in packet)
- */
-struct ieee80211_key_seq {
- union {
- struct {
- u32 iv32;
- u16 iv16;
- } tkip;
- struct {
- u8 pn[6];
- } ccmp;
- struct {
- u8 pn[6];
- } aes_cmac;
- struct {
- u8 pn[6];
- } aes_gmac;
- struct {
- u8 pn[6];
- } gcmp;
- };
-};
-
-/**
* ieee80211_get_key_tx_seq - get key TX sequence counter
*
* @keyconf: the parameter passed with the set key
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index f733656404de..72eb23723294 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -58,6 +58,7 @@ struct net {
struct list_head exit_list; /* Use only net_mutex */
struct user_namespace *user_ns; /* Owning user namespace */
+ spinlock_t nsid_lock;
struct idr netns_ids;
struct ns_common ns;
@@ -271,7 +272,9 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
#define __net_initconst __initconst
#endif
+int peernet2id_alloc(struct net *net, struct net *peer);
int peernet2id(struct net *net, struct net *peer);
+bool peernet_has_id(struct net *net, struct net *peer);
struct net *get_net_ns_by_id(struct net *net, int id);
struct pernet_operations {
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 614a49be68a9..6848b8bb2e63 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -77,6 +77,8 @@ struct netns_ipv4 {
struct local_ports ip_local_ports;
int sysctl_tcp_ecn;
+ int sysctl_tcp_ecn_fallback;
+
int sysctl_ip_no_pmtu_disc;
int sysctl_ip_fwd_use_pmtu;
int sysctl_ip_nonlocal_bind;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index d2527bf81142..8d93544a2d2b 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -34,6 +34,7 @@ struct netns_sysctl_ipv6 {
int fwmark_reflect;
int idgen_retries;
int idgen_delay;
+ int flowlabel_state_ranges;
};
struct netns_ipv6 {
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 9f4265ce8892..87935cad2f7b 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -64,6 +64,7 @@ struct request_sock {
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
+ u32 *saved_syn;
u32 secid;
u32 peer_secid;
};
@@ -77,7 +78,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener)
req->rsk_ops = ops;
sock_hold(sk_listener);
req->rsk_listener = sk_listener;
-
+ req->saved_syn = NULL;
/* Following is temporary. It is coupled with debugging
* helpers in reqsk_put() & reqsk_free()
*/
@@ -104,6 +105,7 @@ static inline void reqsk_free(struct request_sock *req)
req->rsk_ops->destructor(req);
if (req->rsk_listener)
sock_put(req->rsk_listener);
+ kfree(req->saved_syn);
kmem_cache_free(req->rsk_ops->slab, req);
}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6d778efcfdfd..2738f6f87908 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -501,12 +501,6 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return sch->enqueue(skb, sch);
}
-static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch)
-{
- qdisc_skb_cb(skb)->pkt_len = skb->len;
- return qdisc_enqueue(skb, sch) & NET_XMIT_MASK;
-}
-
static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
{
return q->flags & TCQ_F_CPUSTATS;
@@ -745,23 +739,6 @@ static inline u32 qdisc_l2t(struct qdisc_rate_table* rtab, unsigned int pktlen)
return rtab->data[slot];
}
-#ifdef CONFIG_NET_CLS_ACT
-static inline struct sk_buff *skb_act_clone(struct sk_buff *skb, gfp_t gfp_mask,
- int action)
-{
- struct sk_buff *n;
-
- n = skb_clone(skb, gfp_mask);
-
- if (n) {
- n->tc_verd = SET_TC_VERD(n->tc_verd, 0);
- n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
- n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
- }
- return n;
-}
-#endif
-
struct psched_ratecfg {
u64 rate_bytes_ps; /* bytes per second */
u32 mult;
diff --git a/include/net/sock.h b/include/net/sock.h
index 3a4898ec8c67..26c1c3171e00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -184,6 +184,7 @@ struct sock_common {
unsigned char skc_reuse:4;
unsigned char skc_reuseport:1;
unsigned char skc_ipv6only:1;
+ unsigned char skc_net_refcnt:1;
int skc_bound_dev_if;
union {
struct hlist_node skc_bind_node;
@@ -323,6 +324,7 @@ struct sock {
#define sk_reuse __sk_common.skc_reuse
#define sk_reuseport __sk_common.skc_reuseport
#define sk_ipv6only __sk_common.skc_ipv6only
+#define sk_net_refcnt __sk_common.skc_net_refcnt
#define sk_bound_dev_if __sk_common.skc_bound_dev_if
#define sk_bind_node __sk_common.skc_bind_node
#define sk_prot __sk_common.skc_prot
@@ -1366,7 +1368,7 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
* Functions for memory accounting
*/
int __sk_mem_schedule(struct sock *sk, int size, int kind);
-void __sk_mem_reclaim(struct sock *sk);
+void __sk_mem_reclaim(struct sock *sk, int amount);
#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
@@ -1407,7 +1409,7 @@ static inline void sk_mem_reclaim(struct sock *sk)
if (!sk_has_account(sk))
return;
if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
- __sk_mem_reclaim(sk);
+ __sk_mem_reclaim(sk, sk->sk_forward_alloc);
}
static inline void sk_mem_reclaim_partial(struct sock *sk)
@@ -1415,7 +1417,7 @@ static inline void sk_mem_reclaim_partial(struct sock *sk)
if (!sk_has_account(sk))
return;
if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
- __sk_mem_reclaim(sk);
+ __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1);
}
static inline void sk_mem_charge(struct sock *sk, int size)
@@ -1514,9 +1516,8 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
- struct proto *prot);
+ struct proto *prot, int kern);
void sk_free(struct sock *sk);
-void sk_release_kernel(struct sock *sk);
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
@@ -2024,7 +2025,8 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
}
}
-struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);
+struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
+ bool force_schedule);
/**
* sk_page_frag - return an appropriate page_frag
@@ -2192,22 +2194,6 @@ void sock_net_set(struct sock *sk, struct net *net)
write_pnet(&sk->sk_net, net);
}
-/*
- * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
- * They should not hold a reference to a namespace in order to allow
- * to stop it.
- * Sockets after sk_change_net should be released using sk_release_kernel
- */
-static inline void sk_change_net(struct sock *sk, struct net *net)
-{
- struct net *current_net = sock_net(sk);
-
- if (!net_eq(current_net, net)) {
- put_net(current_net);
- sock_net_set(sk, net);
- }
-}
-
static inline struct sock *skb_steal_sock(struct sk_buff *skb)
{
if (skb->sk) {
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d2e69ee3019a..437f8fe75705 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -14,154 +14,261 @@
#include <linux/netdevice.h>
#include <linux/notifier.h>
+#define SWITCHDEV_F_NO_RECURSE BIT(0)
+
+enum switchdev_trans {
+ SWITCHDEV_TRANS_NONE,
+ SWITCHDEV_TRANS_PREPARE,
+ SWITCHDEV_TRANS_ABORT,
+ SWITCHDEV_TRANS_COMMIT,
+};
+
+enum switchdev_attr_id {
+ SWITCHDEV_ATTR_UNDEFINED,
+ SWITCHDEV_ATTR_PORT_PARENT_ID,
+ SWITCHDEV_ATTR_PORT_STP_STATE,
+ SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS,
+};
+
+struct switchdev_attr {
+ enum switchdev_attr_id id;
+ enum switchdev_trans trans;
+ u32 flags;
+ union {
+ struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */
+ u8 stp_state; /* PORT_STP_STATE */
+ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */
+ } u;
+};
+
struct fib_info;
+enum switchdev_obj_id {
+ SWITCHDEV_OBJ_UNDEFINED,
+ SWITCHDEV_OBJ_PORT_VLAN,
+ SWITCHDEV_OBJ_IPV4_FIB,
+ SWITCHDEV_OBJ_PORT_FDB,
+};
+
+struct switchdev_obj {
+ enum switchdev_obj_id id;
+ enum switchdev_trans trans;
+ int (*cb)(struct net_device *dev, struct switchdev_obj *obj);
+ union {
+ struct switchdev_obj_vlan { /* PORT_VLAN */
+ u16 flags;
+ u16 vid_start;
+ u16 vid_end;
+ } vlan;
+ struct switchdev_obj_ipv4_fib { /* IPV4_FIB */
+ u32 dst;
+ int dst_len;
+ struct fib_info *fi;
+ u8 tos;
+ u8 type;
+ u32 nlflags;
+ u32 tb_id;
+ } ipv4_fib;
+ struct switchdev_obj_fdb { /* PORT_FDB */
+ const unsigned char *addr;
+ u16 vid;
+ } fdb;
+ } u;
+};
+
/**
* struct switchdev_ops - switchdev operations
*
- * @swdev_parent_id_get: Called to get an ID of the switch chip this port
- * is part of. If driver implements this, it indicates that it
- * represents a port of a switch chip.
+ * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr).
+ *
+ * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr).
*
- * @swdev_port_stp_update: Called to notify switch device port of bridge
- * port STP state change.
+ * @switchdev_port_obj_add: Add an object to port (see switchdev_obj).
*
- * @swdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device.
+ * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj).
*
- * @swdev_fib_ipv4_del: Called to delete IPv4 route from switch device.
+ * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj).
*/
-struct swdev_ops {
- int (*swdev_parent_id_get)(struct net_device *dev,
- struct netdev_phys_item_id *psid);
- int (*swdev_port_stp_update)(struct net_device *dev, u8 state);
- int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst,
- int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 nlflags,
- u32 tb_id);
- int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst,
- int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 tb_id);
+struct switchdev_ops {
+ int (*switchdev_port_attr_get)(struct net_device *dev,
+ struct switchdev_attr *attr);
+ int (*switchdev_port_attr_set)(struct net_device *dev,
+ struct switchdev_attr *attr);
+ int (*switchdev_port_obj_add)(struct net_device *dev,
+ struct switchdev_obj *obj);
+ int (*switchdev_port_obj_del)(struct net_device *dev,
+ struct switchdev_obj *obj);
+ int (*switchdev_port_obj_dump)(struct net_device *dev,
+ struct switchdev_obj *obj);
};
-enum netdev_switch_notifier_type {
- NETDEV_SWITCH_FDB_ADD = 1,
- NETDEV_SWITCH_FDB_DEL,
+enum switchdev_notifier_type {
+ SWITCHDEV_FDB_ADD = 1,
+ SWITCHDEV_FDB_DEL,
};
-struct netdev_switch_notifier_info {
+struct switchdev_notifier_info {
struct net_device *dev;
};
-struct netdev_switch_notifier_fdb_info {
- struct netdev_switch_notifier_info info; /* must be first */
+struct switchdev_notifier_fdb_info {
+ struct switchdev_notifier_info info; /* must be first */
const unsigned char *addr;
u16 vid;
};
static inline struct net_device *
-netdev_switch_notifier_info_to_dev(const struct netdev_switch_notifier_info *info)
+switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
{
return info->dev;
}
#ifdef CONFIG_NET_SWITCHDEV
-int netdev_switch_parent_id_get(struct net_device *dev,
- struct netdev_phys_item_id *psid);
-int netdev_switch_port_stp_update(struct net_device *dev, u8 state);
-int register_netdev_switch_notifier(struct notifier_block *nb);
-int unregister_netdev_switch_notifier(struct notifier_block *nb);
-int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
- struct netdev_switch_notifier_info *info);
-int netdev_switch_port_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags);
-int netdev_switch_port_bridge_dellink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags);
-int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags);
-int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh, u16 flags);
-int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 nlflags, u32 tb_id);
-int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
- u8 tos, u8 type, u32 tb_id);
-void netdev_switch_fib_ipv4_abort(struct fib_info *fi);
+int switchdev_port_attr_get(struct net_device *dev,
+ struct switchdev_attr *attr);
+int switchdev_port_attr_set(struct net_device *dev,
+ struct switchdev_attr *attr);
+int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj);
+int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj);
+int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj);
+int register_switchdev_notifier(struct notifier_block *nb);
+int unregister_switchdev_notifier(struct notifier_block *nb);
+int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
+ struct switchdev_notifier_info *info);
+int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+ struct net_device *dev, u32 filter_mask,
+ int nlflags);
+int switchdev_port_bridge_setlink(struct net_device *dev,
+ struct nlmsghdr *nlh, u16 flags);
+int switchdev_port_bridge_dellink(struct net_device *dev,
+ struct nlmsghdr *nlh, u16 flags);
+int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+ u8 tos, u8 type, u32 nlflags, u32 tb_id);
+int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+ u8 tos, u8 type, u32 tb_id);
+void switchdev_fib_ipv4_abort(struct fib_info *fi);
+int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ u16 vid, u16 nlm_flags);
+int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ u16 vid);
+int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct net_device *dev,
+ struct net_device *filter_dev, int idx);
#else
-static inline int netdev_switch_parent_id_get(struct net_device *dev,
- struct netdev_phys_item_id *psid)
+static inline int switchdev_port_attr_get(struct net_device *dev,
+ struct switchdev_attr *attr)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_attr_set(struct net_device *dev,
+ struct switchdev_attr *attr)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_obj_add(struct net_device *dev,
+ struct switchdev_obj *obj)
{
return -EOPNOTSUPP;
}
-static inline int netdev_switch_port_stp_update(struct net_device *dev,
- u8 state)
+static inline int switchdev_port_obj_del(struct net_device *dev,
+ struct switchdev_obj *obj)
{
return -EOPNOTSUPP;
}
-static inline int register_netdev_switch_notifier(struct notifier_block *nb)
+static inline int switchdev_port_obj_dump(struct net_device *dev,
+ struct switchdev_obj *obj)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int register_switchdev_notifier(struct notifier_block *nb)
{
return 0;
}
-static inline int unregister_netdev_switch_notifier(struct notifier_block *nb)
+static inline int unregister_switchdev_notifier(struct notifier_block *nb)
{
return 0;
}
-static inline int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
- struct netdev_switch_notifier_info *info)
+static inline int call_switchdev_notifiers(unsigned long val,
+ struct net_device *dev,
+ struct switchdev_notifier_info *info)
{
return NOTIFY_DONE;
}
-static inline int netdev_switch_port_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh,
- u16 flags)
+static inline int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid,
+ u32 seq, struct net_device *dev,
+ u32 filter_mask, int nlflags)
{
return -EOPNOTSUPP;
}
-static inline int netdev_switch_port_bridge_dellink(struct net_device *dev,
- struct nlmsghdr *nlh,
- u16 flags)
+static inline int switchdev_port_bridge_setlink(struct net_device *dev,
+ struct nlmsghdr *nlh,
+ u16 flags)
{
return -EOPNOTSUPP;
}
-static inline int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
- struct nlmsghdr *nlh,
- u16 flags)
+static inline int switchdev_port_bridge_dellink(struct net_device *dev,
+ struct nlmsghdr *nlh,
+ u16 flags)
{
- return 0;
+ return -EOPNOTSUPP;
}
-static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
- struct nlmsghdr *nlh,
- u16 flags)
+static inline int switchdev_fib_ipv4_add(u32 dst, int dst_len,
+ struct fib_info *fi,
+ u8 tos, u8 type,
+ u32 nlflags, u32 tb_id)
{
return 0;
}
-static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len,
- struct fib_info *fi,
- u8 tos, u8 type,
- u32 nlflags, u32 tb_id)
+static inline int switchdev_fib_ipv4_del(u32 dst, int dst_len,
+ struct fib_info *fi,
+ u8 tos, u8 type, u32 tb_id)
{
return 0;
}
-static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len,
- struct fib_info *fi,
- u8 tos, u8 type, u32 tb_id)
+static inline void switchdev_fib_ipv4_abort(struct fib_info *fi)
{
- return 0;
}
-static inline void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr,
+ u16 vid, u16 nlm_flags)
{
+ return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct net_device *dev,
+ struct net_device *filter_dev,
+ int idx)
+{
+ return -EOPNOTSUPP;
}
#endif
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6d204f3f9df8..2bb2bad21d5c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -286,6 +286,14 @@ extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
extern int tcp_memory_pressure;
+/* optimized version of sk_under_memory_pressure() for TCP sockets */
+static inline bool tcp_under_memory_pressure(const struct sock *sk)
+{
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+ return !!sk->sk_cgrp->memory_pressure;
+
+ return tcp_memory_pressure;
+}
/*
* The next routines deal with comparing 32 bit unsigned ints
* and worry about wraparound (automatic with unsigned arithmetic).
@@ -311,6 +319,8 @@ static inline bool tcp_out_of_memory(struct sock *sk)
return false;
}
+void sk_forced_mem_schedule(struct sock *sk, int size);
+
static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
{
struct percpu_counter *ocp = sk->sk_prot->orphan_count;
@@ -326,18 +336,6 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
bool tcp_check_oom(struct sock *sk, int shift);
-/* syncookies: remember time of last synqueue overflow */
-static inline void tcp_synq_overflow(struct sock *sk)
-{
- tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
-}
-
-/* syncookies: no recent synqueue overflow on this listening socket? */
-static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
-{
- unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
- return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK);
-}
extern struct proto tcp_prot;
@@ -483,13 +481,35 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
* i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
* the counter advances immediately after a cookie is generated).
*/
-#define MAX_SYNCOOKIE_AGE 2
+#define MAX_SYNCOOKIE_AGE 2
+#define TCP_SYNCOOKIE_PERIOD (60 * HZ)
+#define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD)
+
+/* syncookies: remember time of last synqueue overflow
+ * But do not dirty this field too often (once per second is enough)
+ */
+static inline void tcp_synq_overflow(struct sock *sk)
+{
+ unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+ unsigned long now = jiffies;
+
+ if (time_after(now, last_overflow + HZ))
+ tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+}
+
+/* syncookies: no recent synqueue overflow on this listening socket? */
+static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
+{
+ unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+
+ return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+}
static inline u32 tcp_cookie_time(void)
{
u64 val = get_jiffies_64();
- do_div(val, 60 * HZ);
+ do_div(val, TCP_SYNCOOKIE_PERIOD);
return val;
}
@@ -527,7 +547,7 @@ int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
void tcp_send_probe0(struct sock *);
void tcp_send_partial(struct sock *);
-int tcp_write_wakeup(struct sock *);
+int tcp_write_wakeup(struct sock *, int mib);
void tcp_send_fin(struct sock *sk);
void tcp_send_active_reset(struct sock *sk, gfp_t priority);
int tcp_send_synack(struct sock *);
@@ -692,6 +712,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
#define TCPHDR_ECE 0x40
#define TCPHDR_CWR 0x80
+#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
+
/* This is what the send packet queuing engine uses to pass
* TCP per-packet control information to the transmission code.
* We also store the host-order sequence numbers in here too.
@@ -1043,14 +1065,31 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
return tp->is_cwnd_limited;
}
-static inline void tcp_check_probe_timer(struct sock *sk)
+/* Something is really bad, we could not queue an additional packet,
+ * because qdisc is full or receiver sent a 0 window.
+ * We do not want to add fuel to the fire, or abort too early,
+ * so make sure the timer we arm now is at least 200ms in the future,
+ * regardless of current icsk_rto value (as it could be ~2ms)
+ */
+static inline unsigned long tcp_probe0_base(const struct sock *sk)
{
- const struct tcp_sock *tp = tcp_sk(sk);
- const struct inet_connection_sock *icsk = inet_csk(sk);
+ return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN);
+}
+
+/* Variant of inet_csk_rto_backoff() used for zero window probes */
+static inline unsigned long tcp_probe0_when(const struct sock *sk,
+ unsigned long max_when)
+{
+ u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff;
- if (!tp->packets_out && !icsk->icsk_pending)
+ return (unsigned long)min_t(u64, when, max_when);
+}
+
+static inline void tcp_check_probe_timer(struct sock *sk)
+{
+ if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
- icsk->icsk_rto, TCP_RTO_MAX);
+ tcp_probe0_base(sk), TCP_RTO_MAX);
}
static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
generated by cgit (git 2.34.1) at 2025-03-23 08:12:20 +0000