aboutsummaryrefslogtreecommitdiffstats
path: root/include/net
diff options
context:
space:
mode:
Diffstat (limited to 'include/net')
-rw-r--r--include/net/caif/caif_shm.h26
-rw-r--r--include/net/cfg80211.h126
-rw-r--r--include/net/dn_fib.h28
-rw-r--r--include/net/firewire.h25
-rw-r--r--include/net/gre.h51
-rw-r--r--include/net/inet_connection_sock.h5
-rw-r--r--include/net/inet_frag.h22
-rw-r--r--include/net/ip6_tunnel.h21
-rw-r--r--include/net/ip_tunnels.h177
-rw-r--r--include/net/ip_vs.h132
-rw-r--r--include/net/ipip.h87
-rw-r--r--include/net/ipv6.h22
-rw-r--r--include/net/mac80211.h29
-rw-r--r--include/net/net_namespace.h2
-rw-r--r--include/net/netfilter/nf_conntrack_core.h1
-rw-r--r--include/net/netfilter/nf_log.h14
-rw-r--r--include/net/netns/ipv6.h1
-rw-r--r--include/net/netns/netfilter.h18
-rw-r--r--include/net/request_sock.h8
-rw-r--r--include/net/rtnetlink.h2
-rw-r--r--include/net/sock.h1
-rw-r--r--include/net/tcp.h145
22 files changed, 581 insertions, 362 deletions
diff --git a/include/net/caif/caif_shm.h b/include/net/caif/caif_shm.h
deleted file mode 100644
index 5bcce55..0000000
--- a/include/net/caif/caif_shm.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Contact: Sjur Brendeland / sjur.brandeland@stericsson.com
- * Author: Amarnath Revanna / amarnath.bangalore.revanna@stericsson.com
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#ifndef CAIF_SHM_H_
-#define CAIF_SHM_H_
-
-struct shmdev_layer {
- u32 shm_base_addr;
- u32 shm_total_sz;
- u32 shm_id;
- u32 shm_loopback;
- void *hmbx;
- int (*pshmdev_mbxsend) (u32 shm_id, u32 mbx_msg);
- int (*pshmdev_mbxsetup) (void *pshmdrv_cb,
- struct shmdev_layer *pshm_dev, void *pshm_drv);
- struct net_device *pshm_netdev;
-};
-
-extern int caif_shmcore_probe(struct shmdev_layer *pshm_dev);
-extern void caif_shmcore_remove(struct net_device *pshm_netdev);
-
-#endif
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d581c6d..bdba9b6 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -611,22 +611,10 @@ struct cfg80211_ap_settings {
};
/**
- * enum plink_action - actions to perform in mesh peers
- *
- * @PLINK_ACTION_INVALID: action 0 is reserved
- * @PLINK_ACTION_OPEN: start mesh peer link establishment
- * @PLINK_ACTION_BLOCK: block traffic from this mesh peer
- */
-enum plink_actions {
- PLINK_ACTION_INVALID,
- PLINK_ACTION_OPEN,
- PLINK_ACTION_BLOCK,
-};
-
-/**
* enum station_parameters_apply_mask - station parameter values to apply
* @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp)
* @STATION_PARAM_APPLY_CAPABILITY: apply new capability
+ * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state
*
* Not all station parameters have in-band "no change" signalling,
* for those that don't these flags will are used.
@@ -634,6 +622,7 @@ enum plink_actions {
enum station_parameters_apply_mask {
STATION_PARAM_APPLY_UAPSD = BIT(0),
STATION_PARAM_APPLY_CAPABILITY = BIT(1),
+ STATION_PARAM_APPLY_PLINK_STATE = BIT(2),
};
/**
@@ -669,7 +658,7 @@ enum station_parameters_apply_mask {
* @ext_capab_len: number of extended capabilities
*/
struct station_parameters {
- u8 *supported_rates;
+ const u8 *supported_rates;
struct net_device *vlan;
u32 sta_flags_mask, sta_flags_set;
u32 sta_modify_mask;
@@ -678,17 +667,60 @@ struct station_parameters {
u8 supported_rates_len;
u8 plink_action;
u8 plink_state;
- struct ieee80211_ht_cap *ht_capa;
- struct ieee80211_vht_cap *vht_capa;
+ const struct ieee80211_ht_cap *ht_capa;
+ const struct ieee80211_vht_cap *vht_capa;
u8 uapsd_queues;
u8 max_sp;
enum nl80211_mesh_power_mode local_pm;
u16 capability;
- u8 *ext_capab;
+ const u8 *ext_capab;
u8 ext_capab_len;
};
/**
+ * enum cfg80211_station_type - the type of station being modified
+ * @CFG80211_STA_AP_CLIENT: client of an AP interface
+ * @CFG80211_STA_AP_MLME_CLIENT: client of an AP interface that has
+ * the AP MLME in the device
+ * @CFG80211_STA_AP_STA: AP station on managed interface
+ * @CFG80211_STA_IBSS: IBSS station
+ * @CFG80211_STA_TDLS_PEER_SETUP: TDLS peer on managed interface (dummy entry
+ * while TDLS setup is in progress, it moves out of this state when
+ * being marked authorized; use this only if TDLS with external setup is
+ * supported/used)
+ * @CFG80211_STA_TDLS_PEER_ACTIVE: TDLS peer on managed interface (active
+ * entry that is operating, has been marked authorized by userspace)
+ * @CFG80211_STA_MESH_PEER_KERNEL: peer on mesh interface (kernel managed)
+ * @CFG80211_STA_MESH_PEER_USER: peer on mesh interface (user managed)
+ */
+enum cfg80211_station_type {
+ CFG80211_STA_AP_CLIENT,
+ CFG80211_STA_AP_MLME_CLIENT,
+ CFG80211_STA_AP_STA,
+ CFG80211_STA_IBSS,
+ CFG80211_STA_TDLS_PEER_SETUP,
+ CFG80211_STA_TDLS_PEER_ACTIVE,
+ CFG80211_STA_MESH_PEER_KERNEL,
+ CFG80211_STA_MESH_PEER_USER,
+};
+
+/**
+ * cfg80211_check_station_change - validate parameter changes
+ * @wiphy: the wiphy this operates on
+ * @params: the new parameters for a station
+ * @statype: the type of station being modified
+ *
+ * Utility function for the @change_station driver method. Call this function
+ * with the appropriate station type looking up the station (and checking that
+ * it exists). It will verify whether the station change is acceptable, and if
+ * not will return an error code. Note that it may modify the parameters for
+ * backward compatibility reasons, so don't use them before calling this.
+ */
+int cfg80211_check_station_change(struct wiphy *wiphy,
+ struct station_parameters *params,
+ enum cfg80211_station_type statype);
+
+/**
* enum station_info_flags - station information flags
*
* Used by the driver to indicate which info in &struct station_info
@@ -1119,6 +1151,7 @@ struct mesh_config {
* @ie_len: length of vendor information elements
* @is_authenticated: this mesh requires authentication
* @is_secure: this mesh uses security
+ * @user_mpm: userspace handles all MPM functions
* @dtim_period: DTIM period to use
* @beacon_interval: beacon interval to use
* @mcast_rate: multicat rate for Mesh Node [6Mbps is the default for 802.11a]
@@ -1136,6 +1169,7 @@ struct mesh_setup {
u8 ie_len;
bool is_authenticated;
bool is_secure;
+ bool user_mpm;
u8 dtim_period;
u16 beacon_interval;
int mcast_rate[IEEE80211_NUM_BANDS];
@@ -1398,9 +1432,11 @@ struct cfg80211_auth_request {
* enum cfg80211_assoc_req_flags - Over-ride default behaviour in association.
*
* @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n)
+ * @ASSOC_REQ_DISABLE_VHT: Disable VHT
*/
enum cfg80211_assoc_req_flags {
ASSOC_REQ_DISABLE_HT = BIT(0),
+ ASSOC_REQ_DISABLE_VHT = BIT(1),
};
/**
@@ -1422,6 +1458,8 @@ enum cfg80211_assoc_req_flags {
* @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask
* will be used in ht_capa. Un-supported values will be ignored.
* @ht_capa_mask: The bits of ht_capa which are to be used.
+ * @vht_capa: VHT capability override
+ * @vht_capa_mask: VHT capability mask indicating which fields to use
*/
struct cfg80211_assoc_request {
struct cfg80211_bss *bss;
@@ -1432,6 +1470,7 @@ struct cfg80211_assoc_request {
u32 flags;
struct ieee80211_ht_cap ht_capa;
struct ieee80211_ht_cap ht_capa_mask;
+ struct ieee80211_vht_cap vht_capa, vht_capa_mask;
};
/**
@@ -1542,6 +1581,8 @@ struct cfg80211_ibss_params {
* @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask
* will be used in ht_capa. Un-supported values will be ignored.
* @ht_capa_mask: The bits of ht_capa which are to be used.
+ * @vht_capa: VHT Capability overrides
+ * @vht_capa_mask: The bits of vht_capa which are to be used.
*/
struct cfg80211_connect_params {
struct ieee80211_channel *channel;
@@ -1560,6 +1601,8 @@ struct cfg80211_connect_params {
int bg_scan_period;
struct ieee80211_ht_cap ht_capa;
struct ieee80211_ht_cap ht_capa_mask;
+ struct ieee80211_vht_cap vht_capa;
+ struct ieee80211_vht_cap vht_capa_mask;
};
/**
@@ -1722,6 +1765,21 @@ struct cfg80211_gtk_rekey_data {
};
/**
+ * struct cfg80211_update_ft_ies_params - FT IE Information
+ *
+ * This structure provides information needed to update the fast transition IE
+ *
+ * @md: The Mobility Domain ID, 2 Octet value
+ * @ie: Fast Transition IEs
+ * @ie_len: Length of ft_ie in octets
+ */
+struct cfg80211_update_ft_ies_params {
+ u16 md;
+ const u8 *ie;
+ size_t ie_len;
+};
+
+/**
* struct cfg80211_ops - backend description for wireless configuration
*
* This struct is registered by fullmac card drivers and/or wireless stacks
@@ -1781,9 +1839,8 @@ struct cfg80211_gtk_rekey_data {
* @change_station: Modify a given station. Note that flags changes are not much
* validated in cfg80211, in particular the auth/assoc/authorized flags
* might come to the driver in invalid combinations -- make sure to check
- * them, also against the existing state! Also, supported_rates changes are
- * not checked in station mode -- drivers need to reject (or ignore) them
- * for anything but TDLS peers.
+ * them, also against the existing state! Drivers must call
+ * cfg80211_check_station_change() to validate the information.
* @get_station: get station information for the station identified by @mac
* @dump_station: dump station callback -- resume dump at index @idx
*
@@ -2168,6 +2225,8 @@ struct cfg80211_ops {
int (*start_radar_detection)(struct wiphy *wiphy,
struct net_device *dev,
struct cfg80211_chan_def *chandef);
+ int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_update_ft_ies_params *ftie);
};
/*
@@ -2485,6 +2544,8 @@ struct wiphy_wowlan_support {
* @ap_sme_capa: AP SME capabilities, flags from &enum nl80211_ap_sme_features.
* @ht_capa_mod_mask: Specify what ht_cap values can be over-ridden.
* If null, then none can be over-ridden.
+ * @vht_capa_mod_mask: Specify what VHT capabilities can be over-ridden.
+ * If null, then none can be over-ridden.
*
* @max_acl_mac_addrs: Maximum number of MAC addresses that the device
* supports for ACL.
@@ -2593,6 +2654,7 @@ struct wiphy {
struct dentry *debugfsdir;
const struct ieee80211_ht_cap *ht_capa_mod_mask;
+ const struct ieee80211_vht_cap *vht_capa_mod_mask;
#ifdef CONFIG_NET_NS
/* the network namespace this phy lives in currently */
@@ -4002,6 +4064,30 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate);
void cfg80211_unregister_wdev(struct wireless_dev *wdev);
/**
+ * struct cfg80211_ft_event - FT Information Elements
+ * @ies: FT IEs
+ * @ies_len: length of the FT IE in bytes
+ * @target_ap: target AP's MAC address
+ * @ric_ies: RIC IE
+ * @ric_ies_len: length of the RIC IE in bytes
+ */
+struct cfg80211_ft_event_params {
+ const u8 *ies;
+ size_t ies_len;
+ const u8 *target_ap;
+ const u8 *ric_ies;
+ size_t ric_ies_len;
+};
+
+/**
+ * cfg80211_ft_event - notify userspace about FT IE and RIC IE
+ * @netdev: network device
+ * @ft_event: IE information
+ */
+void cfg80211_ft_event(struct net_device *netdev,
+ struct cfg80211_ft_event_params *ft_event);
+
+/**
* cfg80211_get_p2p_attr - find and copy a P2P attribute from IE buffer
* @ies: the input IE buffer
* @len: the input length
diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h
index 1ee9d4b..74004af 100644
--- a/include/net/dn_fib.h
+++ b/include/net/dn_fib.h
@@ -1,24 +1,9 @@
#ifndef _NET_DN_FIB_H
#define _NET_DN_FIB_H
-/* WARNING: The ordering of these elements must match ordering
- * of RTA_* rtnetlink attribute numbers.
- */
-struct dn_kern_rta {
- void *rta_dst;
- void *rta_src;
- int *rta_iif;
- int *rta_oif;
- void *rta_gw;
- u32 *rta_priority;
- void *rta_prefsrc;
- struct rtattr *rta_mx;
- struct rtattr *rta_mp;
- unsigned char *rta_protoinfo;
- u32 *rta_flow;
- struct rta_cacheinfo *rta_ci;
- struct rta_session *rta_sess;
-};
+#include <linux/netlink.h>
+
+extern const struct nla_policy rtm_dn_policy[];
struct dn_fib_res {
struct fib_rule *r;
@@ -93,10 +78,10 @@ struct dn_fib_table {
u32 n;
int (*insert)(struct dn_fib_table *t, struct rtmsg *r,
- struct dn_kern_rta *rta, struct nlmsghdr *n,
+ struct nlattr *attrs[], struct nlmsghdr *n,
struct netlink_skb_parms *req);
int (*delete)(struct dn_fib_table *t, struct rtmsg *r,
- struct dn_kern_rta *rta, struct nlmsghdr *n,
+ struct nlattr *attrs[], struct nlmsghdr *n,
struct netlink_skb_parms *req);
int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld,
struct dn_fib_res *res);
@@ -116,13 +101,12 @@ extern void dn_fib_cleanup(void);
extern int dn_fib_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg);
extern struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r,
- struct dn_kern_rta *rta,
+ struct nlattr *attrs[],
const struct nlmsghdr *nlh, int *errp);
extern int dn_fib_semantic_match(int type, struct dn_fib_info *fi,
const struct flowidn *fld,
struct dn_fib_res *res);
extern void dn_fib_release_info(struct dn_fib_info *fi);
-extern __le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type);
extern void dn_fib_flush(void);
extern void dn_fib_select_multipath(const struct flowidn *fld,
struct dn_fib_res *res);
diff --git a/include/net/firewire.h b/include/net/firewire.h
new file mode 100644
index 0000000..31bcbfe
--- /dev/null
+++ b/include/net/firewire.h
@@ -0,0 +1,25 @@
+#ifndef _NET_FIREWIRE_H
+#define _NET_FIREWIRE_H
+
+/* Pseudo L2 address */
+#define FWNET_ALEN 16
+union fwnet_hwaddr {
+ u8 u[FWNET_ALEN];
+ /* "Hardware address" defined in RFC2734/RF3146 */
+ struct {
+ __be64 uniq_id; /* EUI-64 */
+ u8 max_rec; /* max packet size */
+ u8 sspd; /* max speed */
+ __be16 fifo_hi; /* hi 16bits of FIFO addr */
+ __be32 fifo_lo; /* lo 32bits of FIFO addr */
+ } __packed uc;
+};
+
+/* Pseudo L2 Header */
+#define FWNET_HLEN 18
+struct fwnet_header {
+ u8 h_dest[FWNET_ALEN]; /* destination address */
+ __be16 h_proto; /* packet type ID field */
+} __packed;
+
+#endif
diff --git a/include/net/gre.h b/include/net/gre.h
index 8266547..9f03a39 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -2,6 +2,7 @@
#define __LINUX_GRE_H
#include <linux/skbuff.h>
+#include <net/ip_tunnels.h>
#define GREPROTO_CISCO 0
#define GREPROTO_PPTP 1
@@ -12,7 +13,57 @@ struct gre_protocol {
void (*err_handler)(struct sk_buff *skb, u32 info);
};
+struct gre_base_hdr {
+ __be16 flags;
+ __be16 protocol;
+};
+#define GRE_HEADER_SECTION 4
+
int gre_add_protocol(const struct gre_protocol *proto, u8 version);
int gre_del_protocol(const struct gre_protocol *proto, u8 version);
+static inline __be16 gre_flags_to_tnl_flags(__be16 flags)
+{
+ __be16 tflags = 0;
+
+ if (flags & GRE_CSUM)
+ tflags |= TUNNEL_CSUM;
+ if (flags & GRE_ROUTING)
+ tflags |= TUNNEL_ROUTING;
+ if (flags & GRE_KEY)
+ tflags |= TUNNEL_KEY;
+ if (flags & GRE_SEQ)
+ tflags |= TUNNEL_SEQ;
+ if (flags & GRE_STRICT)
+ tflags |= TUNNEL_STRICT;
+ if (flags & GRE_REC)
+ tflags |= TUNNEL_REC;
+ if (flags & GRE_VERSION)
+ tflags |= TUNNEL_VERSION;
+
+ return tflags;
+}
+
+static inline __be16 tnl_flags_to_gre_flags(__be16 tflags)
+{
+ __be16 flags = 0;
+
+ if (tflags & TUNNEL_CSUM)
+ flags |= GRE_CSUM;
+ if (tflags & TUNNEL_ROUTING)
+ flags |= GRE_ROUTING;
+ if (tflags & TUNNEL_KEY)
+ flags |= GRE_KEY;
+ if (tflags & TUNNEL_SEQ)
+ flags |= GRE_SEQ;
+ if (tflags & TUNNEL_STRICT)
+ flags |= GRE_STRICT;
+ if (tflags & TUNNEL_REC)
+ flags |= GRE_REC;
+ if (tflags & TUNNEL_VERSION)
+ flags |= GRE_VERSION;
+
+ return flags;
+}
+
#endif
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 1832927..de2c785 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -133,6 +133,8 @@ struct inet_connection_sock {
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
+#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */
+#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */
static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
@@ -222,7 +224,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
when = max_when;
}
- if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
+ if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
+ what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE) {
icsk->icsk_pending = what;
icsk->icsk_timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 0a1dcc2..6f41b45 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -50,10 +50,16 @@ struct inet_frag_queue {
*/
#define INETFRAGS_MAXDEPTH 128
+struct inet_frag_bucket {
+ struct hlist_head chain;
+ spinlock_t chain_lock;
+};
+
struct inet_frags {
- struct hlist_head hash[INETFRAGS_HASHSZ];
+ struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
/* This rwlock is a global lock (seperate per IPv4, IPv6 and
* netfilter). Important to keep this on a seperate cacheline.
+ * Its primarily a rebuild protection rwlock.
*/
rwlock_t lock ____cacheline_aligned_in_smp;
int secret_interval;
@@ -143,6 +149,7 @@ static inline void inet_frag_lru_del(struct inet_frag_queue *q)
{
spin_lock(&q->net->lru_lock);
list_del(&q->lru_list);
+ q->net->nqueues--;
spin_unlock(&q->net->lru_lock);
}
@@ -151,6 +158,19 @@ static inline void inet_frag_lru_add(struct netns_frags *nf,
{
spin_lock(&nf->lru_lock);
list_add_tail(&q->lru_list, &nf->lru_list);
+ q->net->nqueues++;
spin_unlock(&nf->lru_lock);
}
+
+/* RFC 3168 support :
+ * We want to check ECN values of all fragments, do detect invalid combinations.
+ * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
+ */
+#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */
+#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */
+#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */
+#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */
+
+extern const u8 ip_frag_ecn_table[16];
+
#endif
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index e03047f..4da5de1 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -3,6 +3,7 @@
#include <linux/ipv6.h>
#include <linux/netdevice.h>
+#include <linux/if_tunnel.h>
#include <linux/ip6_tunnel.h>
#define IP6TUNNEL_ERR_TIMEO (30*HZ)
@@ -68,4 +69,24 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
__u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
const struct in6_addr *raddr);
+static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct net_device_stats *stats = &dev->stats;
+ int pkt_len, err;
+
+ nf_reset(skb);
+ pkt_len = skb->len;
+ err = ip6_local_out(skb);
+
+ if (net_xmit_eval(err) == 0) {
+ struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ stats->tx_errors++;
+ stats->tx_aborted_errors++;
+ }
+}
#endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
new file mode 100644
index 0000000..4b6f0b2
--- /dev/null
+++ b/include/net/ip_tunnels.h
@@ -0,0 +1,177 @@
+#ifndef __NET_IP_TUNNELS_H
+#define __NET_IP_TUNNELS_H 1
+
+#include <linux/if_tunnel.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync.h>
+#include <net/dsfield.h>
+#include <net/gro_cells.h>
+#include <net/inet_ecn.h>
+#include <net/ip.h>
+#include <net/rtnetlink.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#endif
+
+/* Keep error state on tunnel for 30 sec */
+#define IPTUNNEL_ERR_TIMEO (30*HZ)
+
+/* 6rd prefix/relay information */
+#ifdef CONFIG_IPV6_SIT_6RD
+struct ip_tunnel_6rd_parm {
+ struct in6_addr prefix;
+ __be32 relay_prefix;
+ u16 prefixlen;
+ u16 relay_prefixlen;
+};
+#endif
+
+struct ip_tunnel_prl_entry {
+ struct ip_tunnel_prl_entry __rcu *next;
+ __be32 addr;
+ u16 flags;
+ struct rcu_head rcu_head;
+};
+
+struct ip_tunnel {
+ struct ip_tunnel __rcu *next;
+ struct hlist_node hash_node;
+ struct net_device *dev;
+
+ int err_count; /* Number of arrived ICMP errors */
+ unsigned long err_time; /* Time when the last ICMP error
+ * arrived */
+
+ /* These four fields used only by GRE */
+ __u32 i_seqno; /* The last seen seqno */
+ __u32 o_seqno; /* The last output seqno */
+ int hlen; /* Precalculated header length */
+ int mlink;
+
+ struct ip_tunnel_parm parms;
+
+ /* for SIT */
+#ifdef CONFIG_IPV6_SIT_6RD
+ struct ip_tunnel_6rd_parm ip6rd;
+#endif
+ struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
+ unsigned int prl_count; /* # of entries in PRL */
+ int ip_tnl_net_id;
+ struct gro_cells gro_cells;
+};
+
+#define TUNNEL_CSUM __cpu_to_be16(0x01)
+#define TUNNEL_ROUTING __cpu_to_be16(0x02)
+#define TUNNEL_KEY __cpu_to_be16(0x04)
+#define TUNNEL_SEQ __cpu_to_be16(0x08)
+#define TUNNEL_STRICT __cpu_to_be16(0x10)
+#define TUNNEL_REC __cpu_to_be16(0x20)
+#define TUNNEL_VERSION __cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
+
+struct tnl_ptk_info {
+ __be16 flags;
+ __be16 proto;
+ __be32 key;
+ __be32 seq;
+};
+
+#define PACKET_RCVD 0
+#define PACKET_REJECT 1
+
+#define IP_TNL_HASH_BITS 10
+#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS)
+
+struct ip_tunnel_net {
+ struct hlist_head *tunnels;
+ struct net_device *fb_tunnel_dev;
+};
+
+int ip_tunnel_init(struct net_device *dev);
+void ip_tunnel_uninit(struct net_device *dev);
+void ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
+int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+ struct rtnl_link_ops *ops, char *devname);
+
+void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn);
+
+void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params);
+int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
+
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot);
+struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
+ int link, __be16 flags,
+ __be32 remote, __be32 local,
+ __be32 key);
+
+int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi, bool log_ecn_error);
+int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p);
+int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p);
+void ip_tunnel_setup(struct net_device *dev, int net_id);
+
+/* Extract dsfield from inner protocol */
+static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
+ const struct sk_buff *skb)
+{
+ if (skb->protocol == htons(ETH_P_IP))
+ return iph->tos;
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ return ipv6_get_dsfield((const struct ipv6hdr *)iph);
+ else
+ return 0;
+}
+
+/* Propogate ECN bits out */
+static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
+ const struct sk_buff *skb)
+{
+ u8 inner = ip_tunnel_get_dsfield(iph, skb);
+
+ return INET_ECN_encapsulate(tos, inner);
+}
+
+static inline void tunnel_ip_select_ident(struct sk_buff *skb,
+ const struct iphdr *old_iph,
+ struct dst_entry *dst)
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ /* Use inner packet iph-id if possible. */
+ if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
+ iph->id = old_iph->id;
+ else
+ __ip_select_ident(iph, dst,
+ (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+}
+
+static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ int err;
+ int pkt_len = skb->len - skb_transport_offset(skb);
+ struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
+
+ nf_reset(skb);
+
+ err = ip_local_out(skb);
+ if (likely(net_xmit_eval(err) == 0)) {
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ dev->stats.tx_errors++;
+ dev->stats.tx_aborted_errors++;
+ }
+}
+#endif /* __NET_IP_TUNNELS_H */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index fce8e6b..f9f5b05 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -233,6 +233,21 @@ static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
dst->ip = src->ip;
}
+static inline void ip_vs_addr_set(int af, union nf_inet_addr *dst,
+ const union nf_inet_addr *src)
+{
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6) {
+ dst->in6 = src->in6;
+ return;
+ }
+#endif
+ dst->ip = src->ip;
+ dst->all[1] = 0;
+ dst->all[2] = 0;
+ dst->all[3] = 0;
+}
+
static inline int ip_vs_addr_equal(int af, const union nf_inet_addr *a,
const union nf_inet_addr *b)
{
@@ -344,8 +359,6 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
#define LeaveFunction(level) do {} while (0)
#endif
-#define IP_VS_WAIT_WHILE(expr) while (expr) { cpu_relax(); }
-
/*
* The port number of FTP service (in network order).
@@ -459,7 +472,7 @@ struct ip_vs_estimator {
struct ip_vs_stats {
struct ip_vs_stats_user ustats; /* statistics */
struct ip_vs_estimator est; /* estimator */
- struct ip_vs_cpu_stats *cpustats; /* per cpu counters */
+ struct ip_vs_cpu_stats __percpu *cpustats; /* per cpu counters */
spinlock_t lock; /* spin lock */
struct ip_vs_stats_user ustats0; /* reset values */
};
@@ -566,20 +579,19 @@ struct ip_vs_conn_param {
*/
struct ip_vs_conn {
struct hlist_node c_list; /* hashed list heads */
-#ifdef CONFIG_NET_NS
- struct net *net; /* Name space */
-#endif
/* Protocol, addresses and port numbers */
- u16 af; /* address family */
__be16 cport;
- __be16 vport;
__be16 dport;
- __u32 fwmark; /* Fire wall mark from skb */
+ __be16 vport;
+ u16 af; /* address family */
union nf_inet_addr caddr; /* client address */
union nf_inet_addr vaddr; /* virtual address */
union nf_inet_addr daddr; /* destination address */
volatile __u32 flags; /* status flags */
__u16 protocol; /* Which protocol (TCP/UDP) */
+#ifdef CONFIG_NET_NS
+ struct net *net; /* Name space */
+#endif
/* counter and timer */
atomic_t refcnt; /* reference count */
@@ -593,6 +605,7 @@ struct ip_vs_conn {
* state transition triggerd
* synchronization
*/
+ __u32 fwmark; /* Fire wall mark from skb */
unsigned long sync_endtime; /* jiffies + sent_retries */
/* Control members */
@@ -620,6 +633,8 @@ struct ip_vs_conn {
const struct ip_vs_pe *pe;
char *pe_data;
__u8 pe_data_len;
+
+ struct rcu_head rcu_head;
};
/*
@@ -695,10 +710,9 @@ struct ip_vs_dest_user_kern {
* and the forwarding entries
*/
struct ip_vs_service {
- struct list_head s_list; /* for normal service table */
- struct list_head f_list; /* for fwmark-based service table */
+ struct hlist_node s_list; /* for normal service table */
+ struct hlist_node f_list; /* for fwmark-based service table */
atomic_t refcnt; /* reference counter */
- atomic_t usecnt; /* use counter */
u16 af; /* address family */
__u16 protocol; /* which protocol (TCP/UDP) */
@@ -713,25 +727,35 @@ struct ip_vs_service {
struct list_head destinations; /* real server d-linked list */
__u32 num_dests; /* number of servers */
struct ip_vs_stats stats; /* statistics for the service */
- struct ip_vs_app *inc; /* bind conns to this app inc */
/* for scheduling */
- struct ip_vs_scheduler *scheduler; /* bound scheduler object */
- rwlock_t sched_lock; /* lock sched_data */
+ struct ip_vs_scheduler __rcu *scheduler; /* bound scheduler object */
+ spinlock_t sched_lock; /* lock sched_data */
void *sched_data; /* scheduler application data */
/* alternate persistence engine */
- struct ip_vs_pe *pe;
+ struct ip_vs_pe __rcu *pe;
+
+ struct rcu_head rcu_head;
};
+/* Information for cached dst */
+struct ip_vs_dest_dst {
+ struct dst_entry *dst_cache; /* destination cache entry */
+ u32 dst_cookie;
+ union nf_inet_addr dst_saddr;
+ struct rcu_head rcu_head;
+};
+/* In grace period after removing */
+#define IP_VS_DEST_STATE_REMOVING 0x01
/*
* The real server destination forwarding entry
* with ip address, port number, and so on.
*/
struct ip_vs_dest {
struct list_head n_list; /* for the dests in the service */
- struct list_head d_list; /* for table with all the dests */
+ struct hlist_node d_list; /* for table with all the dests */
u16 af; /* address family */
__be16 port; /* port number of the server */
@@ -742,6 +766,7 @@ struct ip_vs_dest {
atomic_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
+ unsigned long state; /* state flags */
/* connection counters and thresholds */
atomic_t activeconns; /* active connections */
@@ -752,10 +777,7 @@ struct ip_vs_dest {
/* for destination cache */
spinlock_t dst_lock; /* lock of dst_cache */
- struct dst_entry *dst_cache; /* destination cache entry */
- u32 dst_rtos; /* RT_TOS(tos) for dst */
- u32 dst_cookie;
- union nf_inet_addr dst_saddr;
+ struct ip_vs_dest_dst __rcu *dest_dst; /* cached dst info */
/* for virtual service */
struct ip_vs_service *svc; /* service it belongs to */
@@ -763,6 +785,10 @@ struct ip_vs_dest {
__be16 vport; /* virtual port number */
union nf_inet_addr vaddr; /* virtual IP address */
__u32 vfwmark; /* firewall mark of service */
+
+ struct list_head t_list; /* in dest_trash */
+ struct rcu_head rcu_head;
+ unsigned int in_rs_table:1; /* we are in rs_table */
};
@@ -778,9 +804,13 @@ struct ip_vs_scheduler {
/* scheduler initializing service */
int (*init_service)(struct ip_vs_service *svc);
/* scheduling service finish */
- int (*done_service)(struct ip_vs_service *svc);
- /* scheduler updating service */
- int (*update_service)(struct ip_vs_service *svc);
+ void (*done_service)(struct ip_vs_service *svc);
+ /* dest is linked */
+ int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
+ /* dest is unlinked */
+ int (*del_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
+ /* dest is updated */
+ int (*upd_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
/* selecting a server from the given service */
struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc,
@@ -819,6 +849,7 @@ struct ip_vs_app {
struct ip_vs_app *app; /* its real application */
__be16 port; /* port number in net order */
atomic_t usecnt; /* usage counter */
+ struct rcu_head rcu_head;
/*
* output hook: Process packet in inout direction, diff set for TCP.
@@ -881,6 +912,9 @@ struct ipvs_master_sync_state {
struct netns_ipvs *ipvs;
};
+/* How much time to keep dests in trash */
+#define IP_VS_DEST_TRASH_PERIOD (120 * HZ)
+
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
@@ -892,7 +926,7 @@ struct netns_ipvs {
#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
- struct list_head rs_table[IP_VS_RTAB_SIZE];
+ struct hlist_head rs_table[IP_VS_RTAB_SIZE];
/* ip_vs_app */
struct list_head app_list;
/* ip_vs_proto */
@@ -904,7 +938,6 @@ struct netns_ipvs {
#define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS)
#define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1)
struct list_head tcp_apps[TCP_APP_TAB_SIZE];
- spinlock_t tcp_app_lock;
#endif
/* ip_vs_proto_udp */
#ifdef CONFIG_IP_VS_PROTO_UDP
@@ -912,7 +945,6 @@ struct netns_ipvs {
#define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS)
#define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1)
struct list_head udp_apps[UDP_APP_TAB_SIZE];
- spinlock_t udp_app_lock;
#endif
/* ip_vs_proto_sctp */
#ifdef CONFIG_IP_VS_PROTO_SCTP
@@ -921,7 +953,6 @@ struct netns_ipvs {
#define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1)
/* Hash table for SCTP application incarnations */
struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
- spinlock_t sctp_app_lock;
#endif
/* ip_vs_conn */
atomic_t conn_count; /* connection counter */
@@ -931,9 +962,10 @@ struct netns_ipvs {
int num_services; /* no of virtual services */
- rwlock_t rs_lock; /* real services table */
/* Trash for destinations */
struct list_head dest_trash;
+ spinlock_t dest_trash_lock;
+ struct timer_list dest_trash_timer; /* expiration timer */
/* Service counters */
atomic_t ftpsvc_counter;
atomic_t nullsvc_counter;
@@ -1181,9 +1213,19 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
const struct ip_vs_iphdr *iph,
int inverse);
+/* Get reference to gain full access to conn.
+ * By default, RCU read-side critical sections have access only to
+ * conn fields and its PE data, see ip_vs_conn_rcu_free() for reference.
+ */
+static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
+{
+ return atomic_inc_not_zero(&cp->refcnt);
+}
+
/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
+ smp_mb__before_atomic_dec();
atomic_dec(&cp->refcnt);
}
extern void ip_vs_conn_put(struct ip_vs_conn *cp);
@@ -1298,8 +1340,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
-void ip_vs_unbind_pe(struct ip_vs_service *svc);
int register_ip_vs_pe(struct ip_vs_pe *pe);
int unregister_ip_vs_pe(struct ip_vs_pe *pe);
struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
@@ -1346,7 +1386,8 @@ extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
struct ip_vs_scheduler *scheduler);
-extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc);
+extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
+ struct ip_vs_scheduler *sched);
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
@@ -1366,17 +1407,12 @@ extern struct ip_vs_stats ip_vs_stats;
extern int sysctl_ip_vs_sync_ver;
extern struct ip_vs_service *
-ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
const union nf_inet_addr *vaddr, __be16 vport);
-static inline void ip_vs_service_put(struct ip_vs_service *svc)
-{
- atomic_dec(&svc->usecnt);
-}
-
-extern struct ip_vs_dest *
-ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
- const union nf_inet_addr *daddr, __be16 dport);
+extern bool
+ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
+ const union nf_inet_addr *daddr, __be16 dport);
extern int ip_vs_use_count_inc(void);
extern void ip_vs_use_count_dec(void);
@@ -1388,8 +1424,18 @@ extern struct ip_vs_dest *
ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
__u16 protocol, __u32 fwmark, __u32 flags);
-extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
+extern void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
+static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
+{
+ atomic_inc(&dest->refcnt);
+}
+
+static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
+{
+ smp_mb__before_atomic_dec();
+ atomic_dec(&dest->refcnt);
+}
/*
* IPVS sync daemon data and function prototypes
@@ -1428,7 +1474,7 @@ extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset,
unsigned int hooknum, struct ip_vs_iphdr *iph);
-extern void ip_vs_dst_reset(struct ip_vs_dest *dest);
+extern void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
#ifdef CONFIG_IP_VS_IPV6
extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
diff --git a/include/net/ipip.h b/include/net/ipip.h
deleted file mode 100644
index 982141c..0000000
--- a/include/net/ipip.h
+++ /dev/null
@@ -1,87 +0,0 @@
-#ifndef __NET_IPIP_H
-#define __NET_IPIP_H 1
-
-#include <linux/if_tunnel.h>
-#include <net/gro_cells.h>
-#include <net/ip.h>
-
-/* Keep error state on tunnel for 30 sec */
-#define IPTUNNEL_ERR_TIMEO (30*HZ)
-
-/* 6rd prefix/relay information */
-struct ip_tunnel_6rd_parm {
- struct in6_addr prefix;
- __be32 relay_prefix;
- u16 prefixlen;
- u16 relay_prefixlen;
-};
-
-struct ip_tunnel {
- struct ip_tunnel __rcu *next;
- struct net_device *dev;
-
- int err_count; /* Number of arrived ICMP errors */
- unsigned long err_time; /* Time when the last ICMP error arrived */
-
- /* These four fields used only by GRE */
- __u32 i_seqno; /* The last seen seqno */
- __u32 o_seqno; /* The last output seqno */
- int hlen; /* Precalculated GRE header length */
- int mlink;
-
- struct ip_tunnel_parm parms;
-
- /* for SIT */
-#ifdef CONFIG_IPV6_SIT_6RD
- struct ip_tunnel_6rd_parm ip6rd;
-#endif
- struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
- unsigned int prl_count; /* # of entries in PRL */
-
- struct gro_cells gro_cells;
-};
-
-struct ip_tunnel_prl_entry {
- struct ip_tunnel_prl_entry __rcu *next;
- __be32 addr;
- u16 flags;
- struct rcu_head rcu_head;
-};
-
-static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- int err;
- struct iphdr *iph = ip_hdr(skb);
- int pkt_len = skb->len - skb_transport_offset(skb);
- struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
-
- nf_reset(skb);
- skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(iph, skb_dst(skb), NULL);
-
- err = ip_local_out(skb);
- if (likely(net_xmit_eval(err) == 0)) {
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
- } else {
- dev->stats.tx_errors++;
- dev->stats.tx_aborted_errors++;
- }
-}
-
-static inline void tunnel_ip_select_ident(struct sk_buff *skb,
- const struct iphdr *old_iph,
- struct dst_entry *dst)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- /* Use inner packet iph-id if possible. */
- if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
- iph->id = old_iph->id;
- else
- __ip_select_ident(iph, dst,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
-}
-#endif
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 64d12e7..0810aa5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -217,7 +217,7 @@ struct ipv6_txoptions {
};
struct ip6_flowlabel {
- struct ip6_flowlabel *next;
+ struct ip6_flowlabel __rcu *next;
__be32 label;
atomic_t users;
struct in6_addr dst;
@@ -238,9 +238,9 @@ struct ip6_flowlabel {
#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF)
struct ipv6_fl_socklist {
- struct ipv6_fl_socklist *next;
- struct ip6_flowlabel *fl;
- struct rcu_head rcu;
+ struct ipv6_fl_socklist __rcu *next;
+ struct ip6_flowlabel *fl;
+ struct rcu_head rcu;
};
extern struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
@@ -320,6 +320,18 @@ static inline int ipv6_addr_src_scope(const struct in6_addr *addr)
return __ipv6_addr_src_scope(__ipv6_addr_type(addr));
}
+static inline bool __ipv6_addr_needs_scope_id(int type)
+{
+ return type & IPV6_ADDR_LINKLOCAL ||
+ (type & IPV6_ADDR_MULTICAST &&
+ (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)));
+}
+
+static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface)
+{
+ return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0;
+}
+
static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2)
{
return memcmp(a1, a2, sizeof(struct in6_addr));
@@ -466,6 +478,7 @@ struct ip6_create_arg {
u32 user;
const struct in6_addr *src;
const struct in6_addr *dst;
+ u8 ecn;
};
void ip6_frag_init(struct inet_frag_queue *q, void *a);
@@ -485,6 +498,7 @@ struct frag_queue {
int iif;
unsigned int csum;
__u16 nhoffset;
+ u8 ecn;
};
void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index f7eba13..cdd7cea 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1101,8 +1101,6 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif)
* These flags are used for communication about keys between the driver
* and mac80211, with the @flags parameter of &struct ieee80211_key_conf.
*
- * @IEEE80211_KEY_FLAG_WMM_STA: Set by mac80211, this flag indicates
- * that the STA this key will be used with could be using QoS.
* @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the
* driver to indicate that it requires IV generation for this
* particular key.
@@ -1127,7 +1125,6 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif)
* %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW.
*/
enum ieee80211_key_flags {
- IEEE80211_KEY_FLAG_WMM_STA = 1<<0,
IEEE80211_KEY_FLAG_GENERATE_IV = 1<<1,
IEEE80211_KEY_FLAG_GENERATE_MMIC= 1<<2,
IEEE80211_KEY_FLAG_PAIRWISE = 1<<3,
@@ -1231,9 +1228,8 @@ enum ieee80211_sta_rx_bandwidth {
* @addr: MAC address
* @aid: AID we assigned to the station if we're an AP
* @supp_rates: Bitmap of supported rates (per band)
- * @ht_cap: HT capabilities of this STA; restricted to our own TX capabilities
- * @vht_cap: VHT capabilities of this STA; Not restricting any capabilities
- * of remote STA. Taking as is.
+ * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
+ * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
* @wme: indicates whether the STA supports WME. Only valid during AP-mode.
* @drv_priv: data area for driver use, will always be aligned to
* sizeof(void *), size is determined in hw information.
@@ -2135,6 +2131,24 @@ enum ieee80211_rate_control_changed {
};
/**
+ * enum ieee80211_roc_type - remain on channel type
+ *
+ * With the support for multi channel contexts and multi channel operations,
+ * remain on channel operations might be limited/deferred/aborted by other
+ * flows/operations which have higher priority (and vise versa).
+ * Specifying the ROC type can be used by devices to prioritize the ROC
+ * operations compared to other operations/flows.
+ *
+ * @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC.
+ * @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required
+ * for sending managment frames offchannel.
+ */
+enum ieee80211_roc_type {
+ IEEE80211_ROC_TYPE_NORMAL = 0,
+ IEEE80211_ROC_TYPE_MGMT_TX,
+};
+
+/**
* struct ieee80211_ops - callbacks from mac80211 to the driver
*
* This structure contains various callbacks that the driver may
@@ -2687,7 +2701,8 @@ struct ieee80211_ops {
int (*remain_on_channel)(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ieee80211_channel *chan,
- int duration);
+ int duration,
+ enum ieee80211_roc_type type);
int (*cancel_remain_on_channel)(struct ieee80211_hw *hw);
int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx);
void (*get_ringparam)(struct ieee80211_hw *hw,
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index de644bc..b176978 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -17,6 +17,7 @@
#include <net/netns/ipv6.h>
#include <net/netns/sctp.h>
#include <net/netns/dccp.h>
+#include <net/netns/netfilter.h>
#include <net/netns/x_tables.h>
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netns/conntrack.h>
@@ -94,6 +95,7 @@ struct net {
struct netns_dccp dccp;
#endif
#ifdef CONFIG_NETFILTER
+ struct netns_nf nf;
struct netns_xt xt;
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct netns_ct ct;
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 930275fa..fb2b623 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -27,6 +27,7 @@ extern unsigned int nf_conntrack_in(struct net *net,
extern int nf_conntrack_init_net(struct net *net);
extern void nf_conntrack_cleanup_net(struct net *net);
+extern void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
extern int nf_conntrack_proto_pernet_init(struct net *net);
extern void nf_conntrack_proto_pernet_fini(struct net *net);
diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index e991bd0..31f1fb9 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -49,12 +49,18 @@ struct nf_logger {
int nf_log_register(u_int8_t pf, struct nf_logger *logger);
void nf_log_unregister(struct nf_logger *logger);
-int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger);
-void nf_log_unbind_pf(u_int8_t pf);
+void nf_log_set(struct net *net, u_int8_t pf,
+ const struct nf_logger *logger);
+void nf_log_unset(struct net *net, const struct nf_logger *logger);
+
+int nf_log_bind_pf(struct net *net, u_int8_t pf,
+ const struct nf_logger *logger);
+void nf_log_unbind_pf(struct net *net, u_int8_t pf);
/* Calls the registered backend logging function */
-__printf(7, 8)
-void nf_log_packet(u_int8_t pf,
+__printf(8, 9)
+void nf_log_packet(struct net *net,
+ u_int8_t pf,
unsigned int hooknum,
const struct sk_buff *skb,
const struct net_device *in,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 1242f37..005e2c2 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -71,6 +71,7 @@ struct netns_ipv6 {
struct fib_rules_ops *mr6_rules_ops;
#endif
#endif
+ atomic_t dev_addr_genid;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
new file mode 100644
index 0000000..8874002
--- /dev/null
+++ b/include/net/netns/netfilter.h
@@ -0,0 +1,18 @@
+#ifndef __NETNS_NETFILTER_H
+#define __NETNS_NETFILTER_H
+
+#include <linux/proc_fs.h>
+#include <linux/netfilter.h>
+
+struct nf_logger;
+
+struct netns_nf {
+#if defined CONFIG_PROC_FS
+ struct proc_dir_entry *proc_netfilter;
+#endif
+ const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO];
+#ifdef CONFIG_SYSCTL
+ struct ctl_table_header *nf_log_dir_header;
+#endif
+};
+#endif
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index a51dbd1..9069e65 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -27,19 +27,13 @@ struct sk_buff;
struct dst_entry;
struct proto;
-/* empty to "strongly type" an otherwise void parameter.
- */
-struct request_values {
-};
-
struct request_sock_ops {
int family;
int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(struct sock *sk,
- struct request_sock *req,
- struct request_values *rvp);
+ struct request_sock *req);
void (*send_ack)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(struct sock *sk,
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 5a15fab..7026648 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -4,7 +4,7 @@
#include <linux/rtnetlink.h>
#include <net/netlink.h>
-typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *);
+typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *);
typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *);
diff --git a/include/net/sock.h b/include/net/sock.h
index 14f6e9d..08f05f9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -667,6 +667,7 @@ enum sock_flags {
* user-space instead.
*/
SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
+ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
};
static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index cf0694d..4475aaf 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -179,7 +179,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
-#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
* experimental options. See draft-ietf-tcpm-experimental-options-00.txt
@@ -273,7 +272,6 @@ extern int sysctl_tcp_app_win;
extern int sysctl_tcp_adv_win_scale;
extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
-extern int sysctl_tcp_frto_response;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_dma_copybreak;
extern int sysctl_tcp_nometrics_save;
@@ -284,7 +282,6 @@ extern int sysctl_tcp_base_mss;
extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
extern int sysctl_tcp_max_ssthresh;
-extern int sysctl_tcp_cookie_size;
extern int sysctl_tcp_thin_linear_timeouts;
extern int sysctl_tcp_thin_dupack;
extern int sysctl_tcp_early_retrans;
@@ -425,8 +422,6 @@ extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
bool fastopen);
extern int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb);
-extern bool tcp_use_frto(struct sock *sk);
-extern void tcp_enter_frto(struct sock *sk);
extern void tcp_enter_loss(struct sock *sk, int how);
extern void tcp_clear_retrans(struct tcp_sock *tp);
extern void tcp_update_metrics(struct sock *sk);
@@ -454,7 +449,7 @@ extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len);
extern void tcp_parse_options(const struct sk_buff *skb,
- struct tcp_options_received *opt_rx, const u8 **hvpp,
+ struct tcp_options_received *opt_rx,
int estab, struct tcp_fastopen_cookie *foc);
extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
@@ -476,7 +471,6 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
extern int tcp_connect(struct sock *sk);
extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
struct tcp_fastopen_cookie *foc);
extern int tcp_disconnect(struct sock *sk, int flags);
@@ -543,6 +537,8 @@ extern bool tcp_syn_flood_action(struct sock *sk,
extern void tcp_push_one(struct sock *, unsigned int mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);
+extern void tcp_send_loss_probe(struct sock *sk);
+extern bool tcp_schedule_loss_probe(struct sock *sk);
/* tcp_input.c */
extern void tcp_cwnd_application_limited(struct sock *sk);
@@ -756,7 +752,6 @@ enum tcp_ca_event {
CA_EVENT_TX_START, /* first transmit when no packets in flight */
CA_EVENT_CWND_RESTART, /* congestion window restart */
CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
- CA_EVENT_FRTO, /* fast recovery timeout */
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_FAST_ACK, /* in sequence ack */
CA_EVENT_SLOW_ACK, /* other ack */
@@ -873,8 +868,8 @@ static inline void tcp_enable_fack(struct tcp_sock *tp)
static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
{
tp->do_early_retrans = sysctl_tcp_early_retrans &&
- !sysctl_tcp_thin_dupack && sysctl_tcp_reordering == 3;
- tp->early_retrans_delayed = 0;
+ sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
+ sysctl_tcp_reordering == 3;
}
static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
@@ -1030,50 +1025,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
#endif
}
-/* Packet is added to VJ-style prequeue for processing in process
- * context, if a reader task is waiting. Apparently, this exciting
- * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
- * failed somewhere. Latency? Burstiness? Well, at least now we will
- * see, why it failed. 8)8) --ANK
- *
- * NOTE: is this not too big to inline?
- */
-static inline bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- if (sysctl_tcp_low_latency || !tp->ucopy.task)
- return false;
-
- if (skb->len <= tcp_hdrlen(skb) &&
- skb_queue_len(&tp->ucopy.prequeue) == 0)
- return false;
-
- __skb_queue_tail(&tp->ucopy.prequeue, skb);
- tp->ucopy.memory += skb->truesize;
- if (tp->ucopy.memory > sk->sk_rcvbuf) {
- struct sk_buff *skb1;
-
- BUG_ON(sock_owned_by_user(sk));
-
- while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
- sk_backlog_rcv(sk, skb1);
- NET_INC_STATS_BH(sock_net(sk),
- LINUX_MIB_TCPPREQUEUEDROPPED);
- }
-
- tp->ucopy.memory = 0;
- } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
- wake_up_interruptible_sync_poll(sk_sleep(sk),
- POLLIN | POLLRDNORM | POLLRDBAND);
- if (!inet_csk_ack_scheduled(sk))
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
- (3 * tcp_rto_min(sk)) / 4,
- TCP_RTO_MAX);
- }
- return true;
-}
-
+extern bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
#undef STATE_TRACE
@@ -1630,91 +1582,6 @@ struct tcp_request_sock_ops {
#endif
};
-/* Using SHA1 for now, define some constants.
- */
-#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS)
-#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4)
-#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS)
-
-extern int tcp_cookie_generator(u32 *bakery);
-
-/**
- * struct tcp_cookie_values - each socket needs extra space for the
- * cookies, together with (optional) space for any SYN data.
- *
- * A tcp_sock contains a pointer to the current value, and this is
- * cloned to the tcp_timewait_sock.
- *
- * @cookie_pair: variable data from the option exchange.
- *
- * @cookie_desired: user specified tcpct_cookie_desired. Zero
- * indicates default (sysctl_tcp_cookie_size).
- * After cookie sent, remembers size of cookie.
- * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
- *
- * @s_data_desired: user specified tcpct_s_data_desired. When the
- * constant payload is specified (@s_data_constant),
- * holds its length instead.
- * Range 0 to TCP_MSS_DESIRED.
- *
- * @s_data_payload: constant data that is to be included in the
- * payload of SYN or SYNACK segments when the
- * cookie option is present.
- */
-struct tcp_cookie_values {
- struct kref kref;
- u8 cookie_pair[TCP_COOKIE_PAIR_SIZE];
- u8 cookie_pair_size;
- u8 cookie_desired;
- u16 s_data_desired:11,
- s_data_constant:1,
- s_data_in:1,
- s_data_out:1,
- s_data_unused:2;
- u8 s_data_payload[0];
-};
-
-static inline void tcp_cookie_values_release(struct kref *kref)
-{
- kfree(container_of(kref, struct tcp_cookie_values, kref));
-}
-
-/* The length of constant payload data. Note that s_data_desired is
- * overloaded, depending on s_data_constant: either the length of constant
- * data (returned here) or the limit on variable data.
- */
-static inline int tcp_s_data_size(const struct tcp_sock *tp)
-{
- return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
- ? tp->cookie_values->s_data_desired
- : 0;
-}
-
-/**
- * struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace.
- *
- * As tcp_request_sock has already been extended in other places, the
- * only remaining method is to pass stack values along as function
- * parameters. These parameters are not needed after sending SYNACK.
- *
- * @cookie_bakery: cryptographic secret and message workspace.
- *
- * @cookie_plus: bytes in authenticator/cookie option, copied from
- * struct tcp_options_received (above).
- */
-struct tcp_extend_values {
- struct request_values rv;
- u32 cookie_bakery[COOKIE_WORKSPACE_WORDS];
- u8 cookie_plus:6,
- cookie_out_never:1,
- cookie_in_always:1;
-};
-
-static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
-{
- return (struct tcp_extend_values *)rvp;
-}
-
extern void tcp_v4_init(void);
extern void tcp_init(void);
generated by cgit v1.1 at 2025-08-22 00:17:04 +0000