summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/average.h61
-rw-r--r--include/linux/bcma/bcma_driver_chipcommon.h1
-rw-r--r--include/linux/bpf.h12
-rw-r--r--include/linux/etherdevice.h2
-rw-r--r--include/linux/filter.h17
-rw-r--r--include/linux/ieee80211.h2
-rw-r--r--include/linux/igmp.h1
-rw-r--r--include/linux/ipv6.h5
-rw-r--r--include/linux/mlx4/cq.h3
-rw-r--r--include/linux/mlx4/device.h5
-rw-r--r--include/linux/mlx4/qp.h3
-rw-r--r--include/linux/mlx5/device.h10
-rw-r--r--include/linux/mlx5/driver.h29
-rw-r--r--include/linux/mlx5/mlx5_ifc.h24
-rw-r--r--include/linux/mpls_iptunnel.h6
-rw-r--r--include/linux/net.h8
-rw-r--r--include/linux/netdevice.h176
-rw-r--r--include/linux/netfilter.h44
-rw-r--r--include/linux/netfilter/nf_conntrack_zones_common.h23
-rw-r--r--include/linux/netfilter/nfnetlink_acct.h3
-rw-r--r--include/linux/netfilter/x_tables.h8
-rw-r--r--include/linux/netfilter_bridge.h12
-rw-r--r--include/linux/netfilter_ipv6.h18
-rw-r--r--include/linux/perf_event.h10
-rw-r--r--include/linux/phy.h14
-rw-r--r--include/linux/phy_fixed.h8
-rw-r--r--include/linux/platform_data/st_nci.h29
-rw-r--r--include/linux/property.h4
-rw-r--r--include/linux/skbuff.h153
-rw-r--r--include/linux/stmmac.h22
-rw-r--r--include/linux/uaccess.h2
-rw-r--r--include/net/6lowpan.h23
-rw-r--r--include/net/act_api.h16
-rw-r--r--include/net/addrconf.h4
-rw-r--r--include/net/bluetooth/hci_core.h31
-rw-r--r--include/net/bluetooth/l2cap.h2
-rw-r--r--include/net/bond_options.h1
-rw-r--r--include/net/cfg80211.h3
-rw-r--r--include/net/cfg802154.h10
-rw-r--r--include/net/checksum.h8
-rw-r--r--include/net/cls_cgroup.h29
-rw-r--r--include/net/dsa.h33
-rw-r--r--include/net/dst.h29
-rw-r--r--include/net/dst_metadata.h108
-rw-r--r--include/net/fib_rules.h1
-rw-r--r--include/net/flow.h29
-rw-r--r--include/net/flow_dissector.h67
-rw-r--r--include/net/geneve.h35
-rw-r--r--include/net/gre.h92
-rw-r--r--include/net/gro_cells.h18
-rw-r--r--include/net/inet_hashtables.h4
-rw-r--r--include/net/inet_timewait_sock.h8
-rw-r--r--include/net/inetpeer.h118
-rw-r--r--include/net/ip.h31
-rw-r--r--include/net/ip6_fib.h2
-rw-r--r--include/net/ip_fib.h5
-rw-r--r--include/net/ip_tunnels.h145
-rw-r--r--include/net/ip_vs.h23
-rw-r--r--include/net/ipv6.h76
-rw-r--r--include/net/lwtunnel.h175
-rw-r--r--include/net/mac80211.h69
-rw-r--r--include/net/mac802154.h17
-rw-r--r--include/net/mpls_iptunnel.h29
-rw-r--r--include/net/ndisc.h3
-rw-r--r--include/net/neighbour.h1
-rw-r--r--include/net/net_namespace.h3
-rw-r--r--include/net/netfilter/ipv4/nf_dup_ipv4.h7
-rw-r--r--include/net/netfilter/ipv6/nf_dup_ipv6.h7
-rw-r--r--include/net/netfilter/nf_conntrack.h10
-rw-r--r--include/net/netfilter/nf_conntrack_core.h3
-rw-r--r--include/net/netfilter/nf_conntrack_expect.h11
-rw-r--r--include/net/netfilter/nf_conntrack_labels.h4
-rw-r--r--include/net/netfilter/nf_conntrack_zones.h86
-rw-r--r--include/net/netfilter/nft_dup.h9
-rw-r--r--include/net/netns/ipv6.h1
-rw-r--r--include/net/netns/netfilter.h1
-rw-r--r--include/net/nfc/nci_core.h3
-rw-r--r--include/net/nfc/nfc.h41
-rw-r--r--include/net/nl802154.h4
-rw-r--r--include/net/pkt_sched.h4
-rw-r--r--include/net/route.h7
-rw-r--r--include/net/rtnetlink.h1
-rw-r--r--include/net/sch_generic.h32
-rw-r--r--include/net/sock.h18
-rw-r--r--include/net/switchdev.h10
-rw-r--r--include/net/tc_act/tc_bpf.h2
-rw-r--r--include/net/tc_act/tc_gact.h7
-rw-r--r--include/net/tc_act/tc_mirred.h2
-rw-r--r--include/net/tcp.h24
-rw-r--r--include/net/timewait_sock.h3
-rw-r--r--include/net/udp_tunnel.h7
-rw-r--r--include/net/vrf.h178
-rw-r--r--include/net/vxlan.h90
-rw-r--r--include/net/xfrm.h7
-rw-r--r--include/trace/events/fib.h113
-rw-r--r--include/uapi/linux/Kbuild1
-rw-r--r--include/uapi/linux/bpf.h29
-rw-r--r--include/uapi/linux/ethtool.h5
-rw-r--r--include/uapi/linux/fib_rules.h2
-rw-r--r--include/uapi/linux/if_bridge.h1
-rw-r--r--include/uapi/linux/if_link.h16
-rw-r--r--include/uapi/linux/if_packet.h3
-rw-r--r--include/uapi/linux/if_tunnel.h1
-rw-r--r--include/uapi/linux/ila.h15
-rw-r--r--include/uapi/linux/ip_vs.h5
-rw-r--r--include/uapi/linux/ipv6.h3
-rw-r--r--include/uapi/linux/lwtunnel.h47
-rw-r--r--include/uapi/linux/mpls.h2
-rw-r--r--include/uapi/linux/mpls_iptunnel.h28
-rw-r--r--include/uapi/linux/neighbour.h1
-rw-r--r--include/uapi/linux/netfilter/nf_conntrack_sctp.h2
-rw-r--r--include/uapi/linux/netfilter/nf_tables.h23
-rw-r--r--include/uapi/linux/netfilter/nfnetlink_conntrack.h1
-rw-r--r--include/uapi/linux/netfilter/nfnetlink_cttimeout.h2
-rw-r--r--include/uapi/linux/netfilter/xt_CT.h8
-rw-r--r--include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h4
-rw-r--r--include/uapi/linux/netlink.h1
-rw-r--r--include/uapi/linux/openvswitch.h60
-rw-r--r--include/uapi/linux/rtnetlink.h13
-rw-r--r--include/uapi/linux/snmp.h2
-rw-r--r--include/xen/interface/io/netif.h8
121 files changed, 2284 insertions, 654 deletions
diff --git a/include/linux/average.h b/include/linux/average.h
index c6028fd742c1..d04aa58280de 100644
--- a/include/linux/average.h
+++ b/include/linux/average.h
@@ -3,28 +3,43 @@
/* Exponentially weighted moving average (EWMA) */
-/* For more documentation see lib/average.c */
-
-struct ewma {
- unsigned long internal;
- unsigned long factor;
- unsigned long weight;
-};
-
-extern void ewma_init(struct ewma *avg, unsigned long factor,
- unsigned long weight);
-
-extern struct ewma *ewma_add(struct ewma *avg, unsigned long val);
-
-/**
- * ewma_read() - Get average value
- * @avg: Average structure
- *
- * Returns the average value held in @avg.
- */
-static inline unsigned long ewma_read(const struct ewma *avg)
-{
- return avg->internal >> avg->factor;
-}
+#define DECLARE_EWMA(name, _factor, _weight) \
+ struct ewma_##name { \
+ unsigned long internal; \
+ }; \
+ static inline void ewma_##name##_init(struct ewma_##name *e) \
+ { \
+ BUILD_BUG_ON(!__builtin_constant_p(_factor)); \
+ BUILD_BUG_ON(!__builtin_constant_p(_weight)); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \
+ e->internal = 0; \
+ } \
+ static inline unsigned long \
+ ewma_##name##_read(struct ewma_##name *e) \
+ { \
+ BUILD_BUG_ON(!__builtin_constant_p(_factor)); \
+ BUILD_BUG_ON(!__builtin_constant_p(_weight)); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \
+ return e->internal >> ilog2(_factor); \
+ } \
+ static inline void ewma_##name##_add(struct ewma_##name *e, \
+ unsigned long val) \
+ { \
+ unsigned long internal = ACCESS_ONCE(e->internal); \
+ unsigned long weight = ilog2(_weight); \
+ unsigned long factor = ilog2(_factor); \
+ \
+ BUILD_BUG_ON(!__builtin_constant_p(_factor)); \
+ BUILD_BUG_ON(!__builtin_constant_p(_weight)); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \
+ BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \
+ \
+ ACCESS_ONCE(e->internal) = internal ? \
+ (((internal << weight) - internal) + \
+ (val << factor)) >> weight : \
+ (val << factor); \
+ }
#endif /* _LINUX_AVERAGE_H */
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 6cceedf65ca2..cf038431a5cc 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -640,7 +640,6 @@ struct bcma_drv_cc {
spinlock_t gpio_lock;
#ifdef CONFIG_BCMA_DRIVER_GPIO
struct gpio_chip gpio;
- struct irq_domain *irq_domain;
#endif
};
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4383476a0d48..f57d7fed9ec3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -10,6 +10,7 @@
#include <uapi/linux/bpf.h>
#include <linux/workqueue.h>
#include <linux/file.h>
+#include <linux/perf_event.h>
struct bpf_map;
@@ -24,6 +25,10 @@ struct bpf_map_ops {
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
int (*map_delete_elem)(struct bpf_map *map, void *key);
+
+ /* funcs called by prog_array and perf_event_array map */
+ void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
+ void (*map_fd_put_ptr) (void *ptr);
};
struct bpf_map {
@@ -142,13 +147,13 @@ struct bpf_array {
bool owner_jited;
union {
char value[0] __aligned(8);
- struct bpf_prog *prog[0] __aligned(8);
+ void *ptrs[0] __aligned(8);
};
};
#define MAX_TAIL_CALL_CNT 32
u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
-void bpf_prog_array_map_clear(struct bpf_map *map);
+void bpf_fd_array_map_clear(struct bpf_map *map);
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
@@ -185,6 +190,7 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
extern const struct bpf_func_proto bpf_map_delete_elem_proto;
+extern const struct bpf_func_proto bpf_perf_event_read_proto;
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
extern const struct bpf_func_proto bpf_tail_call_proto;
@@ -192,5 +198,7 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
+extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
+extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 9012f8775208..eb049c622208 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -76,7 +76,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr)
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return (((*(const u32 *)addr) ^ (*(const u32 *)b)) |
- ((a[2] ^ b[2]) & m)) == 0;
+ (__force int)((a[2] ^ b[2]) & m)) == 0;
#else
return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 17724f6ea983..fa2cab985e57 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -12,6 +12,7 @@
#include <linux/linkage.h>
#include <linux/printk.h>
#include <linux/workqueue.h>
+#include <linux/sched.h>
#include <asm/cacheflush.h>
@@ -354,6 +355,16 @@ static inline unsigned int bpf_prog_size(unsigned int proglen)
offsetof(struct bpf_prog, insns[proglen]));
}
+static inline bool bpf_prog_was_classic(const struct bpf_prog *prog)
+{
+ /* When classic BPF programs have been loaded and the arch
+ * does not have a classic BPF JIT (anymore), they have been
+ * converted via bpf_migrate_filter() to eBPF and thus always
+ * have an unspec program type.
+ */
+ return prog->type == BPF_PROG_TYPE_UNSPEC;
+}
+
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
#ifdef CONFIG_DEBUG_SET_MODULE_RONX
@@ -411,6 +422,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
void bpf_int_jit_compile(struct bpf_prog *fp);
+bool bpf_helper_changes_skb_data(void *func);
#ifdef CONFIG_BPF_JIT
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
@@ -427,8 +439,9 @@ void bpf_jit_free(struct bpf_prog *fp);
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
u32 pass, void *image)
{
- pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
- flen, proglen, pass, image);
+ pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen,
+ proglen, pass, image, current->comm, task_pid_nr(current));
+
if (image)
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index b9c7897dc566..cfa906f28b7a 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2074,8 +2074,8 @@ enum ieee80211_tdls_actioncode {
#define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6)
#define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7)
+#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5)
#define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6)
-#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(7)
/* TDLS specific payload type in the LLC/SNAP header */
#define WLAN_TDLS_SNAP_RFTYPE 0x2
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 193ad488d3e2..908429216d9f 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -37,6 +37,7 @@ static inline struct igmpv3_query *
return (struct igmpv3_query *)skb_transport_header(skb);
}
+extern int sysctl_igmp_llm_reports;
extern int sysctl_igmp_max_memberships;
extern int sysctl_igmp_max_msf;
extern int sysctl_igmp_qrv;
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 82806c60aa42..f1f32af6d9b9 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,7 +29,9 @@ struct ipv6_devconf {
__s32 max_desync_factor;
__s32 max_addresses;
__s32 accept_ra_defrtr;
+ __s32 accept_ra_min_hop_limit;
__s32 accept_ra_pinfo;
+ __s32 ignore_routes_with_linkdown;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
@@ -57,6 +59,7 @@ struct ipv6_devconf {
bool initialized;
struct in6_addr secret;
} stable_secret;
+ __s32 use_oif_addrs_only;
void *sysctl;
};
@@ -94,7 +97,6 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb)
struct inet6_skb_parm {
int iif;
__be16 ra;
- __u16 hop;
__u16 dst0;
__u16 srcrt;
__u16 dst1;
@@ -111,6 +113,7 @@ struct inet6_skb_parm {
#define IP6SKB_REROUTED 4
#define IP6SKB_ROUTERALERT 8
#define IP6SKB_FRAGMENTED 16
+#define IP6SKB_HOPBYHOP 32
};
#define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb))
diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h
index e7ecc12a1163..09cebe528488 100644
--- a/include/linux/mlx4/cq.h
+++ b/include/linux/mlx4/cq.h
@@ -88,7 +88,8 @@ struct mlx4_ts_cqe {
enum {
MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31,
- MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29,
+ MLX4_CQE_CVLAN_PRESENT_MASK = 1 << 29,
+ MLX4_CQE_SVLAN_PRESENT_MASK = 1 << 30,
MLX4_CQE_L2_TUNNEL = 1 << 27,
MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26,
MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index fd13c1ce3b4a..bcbf8c72a77b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -211,6 +211,8 @@ enum {
MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26,
MLX4_DEV_CAP_FLAG2_PORT_BEACON = 1LL << 27,
MLX4_DEV_CAP_FLAG2_IGNORE_FCS = 1LL << 28,
+ MLX4_DEV_CAP_FLAG2_PHV_EN = 1LL << 29,
+ MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN = 1LL << 30,
};
enum {
@@ -581,6 +583,7 @@ struct mlx4_caps {
u64 phys_port_id[MLX4_MAX_PORTS + 1];
int tunnel_offload_mode;
u8 rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
+ u8 phv_bit[MLX4_MAX_PORTS + 1];
u8 alloc_res_qp_mask;
u32 dmfs_high_rate_qpn_base;
u32 dmfs_high_rate_qpn_range;
@@ -1332,6 +1335,8 @@ int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time);
int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port,
u8 ignore_fcs_value);
int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable);
+int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val);
+int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv);
int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 6fed539e5456..de45a51b3f04 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -272,7 +272,8 @@ enum {
MLX4_WQE_CTRL_SOLICITED = 1 << 1,
MLX4_WQE_CTRL_IP_CSUM = 1 << 4,
MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5,
- MLX4_WQE_CTRL_INS_VLAN = 1 << 6,
+ MLX4_WQE_CTRL_INS_CVLAN = 1 << 6,
+ MLX4_WQE_CTRL_INS_SVLAN = 1 << 7,
MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7,
MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0,
};
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index b943cd9e2097..250b1ff8b48d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1182,6 +1182,16 @@ enum {
MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40,
};
+enum {
+ MLX5_IEEE_802_3_COUNTERS_GROUP = 0x0,
+ MLX5_RFC_2863_COUNTERS_GROUP = 0x1,
+ MLX5_RFC_2819_COUNTERS_GROUP = 0x2,
+ MLX5_RFC_3635_COUNTERS_GROUP = 0x3,
+ MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP = 0x5,
+ MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10,
+ MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11
+};
+
static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
{
if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5722d88c2429..8b6d6f2154a4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -103,6 +103,8 @@ enum {
MLX5_REG_PMTU = 0x5003,
MLX5_REG_PTYS = 0x5004,
MLX5_REG_PAOS = 0x5006,
+ MLX5_REG_PFCC = 0x5007,
+ MLX5_REG_PPCNT = 0x5008,
MLX5_REG_PMAOS = 0x5012,
MLX5_REG_PUDE = 0x5009,
MLX5_REG_PMPE = 0x5010,
@@ -151,8 +153,8 @@ enum mlx5_dev_event {
};
enum mlx5_port_status {
- MLX5_PORT_UP = 1 << 1,
- MLX5_PORT_DOWN = 1 << 2,
+ MLX5_PORT_UP = 1,
+ MLX5_PORT_DOWN = 2,
};
struct mlx5_uuar_info {
@@ -380,7 +382,7 @@ struct mlx5_uar {
u32 index;
struct list_head bf_list;
unsigned free_bf_bmap;
- void __iomem *wc_map;
+ void __iomem *bf_map;
void __iomem *map;
};
@@ -435,6 +437,8 @@ struct mlx5_priv {
struct mlx5_uuar_info uuari;
MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock);
+ struct io_mapping *bf_mapping;
+
/* pages stuff */
struct workqueue_struct *pg_wq;
struct rb_root page_root;
@@ -463,6 +467,10 @@ struct mlx5_priv {
/* end: mr staff */
/* start: alloc staff */
+ /* protect buffer alocation according to numa node */
+ struct mutex alloc_mutex;
+ int numa_node;
+
struct mutex pgdir_mutex;
struct list_head pgdir_list;
/* end: alloc staff */
@@ -672,6 +680,8 @@ void mlx5_health_cleanup(void);
void __init mlx5_health_init(void);
void mlx5_start_health_poll(struct mlx5_core_dev *dev);
void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
+ struct mlx5_buf *buf, int node);
int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf);
struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev,
@@ -752,9 +762,10 @@ int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
u8 local_port);
int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
int proto_mask);
-int mlx5_set_port_status(struct mlx5_core_dev *dev,
- enum mlx5_port_status status);
-int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status);
+int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
+ enum mlx5_port_status status);
+int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
+ enum mlx5_port_status *status);
int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
@@ -764,6 +775,10 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
u8 *vl_hw_cap, u8 local_port);
+int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
+int mlx5_query_port_pause(struct mlx5_core_dev *dev,
+ u32 *rx_pause, u32 *tx_pause);
+
int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
@@ -773,6 +788,8 @@ void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db);
+int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db,
+ int node);
void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
const char *mlx5_command_str(int command);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6d2f6fee041c..dd2097455a2e 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1936,9 +1936,9 @@ enum {
};
enum {
- MLX5_TIRC_RX_HASH_FN_HASH_NONE = 0x0,
- MLX5_TIRC_RX_HASH_FN_HASH_INVERTED_XOR8 = 0x1,
- MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ = 0x2,
+ MLX5_RX_HASH_FN_NONE = 0x0,
+ MLX5_RX_HASH_FN_INVERTED_XOR8 = 0x1,
+ MLX5_RX_HASH_FN_TOEPLITZ = 0x2,
};
enum {
@@ -4050,6 +4050,13 @@ struct mlx5_ifc_modify_tis_in_bits {
struct mlx5_ifc_tisc_bits ctx;
};
+struct mlx5_ifc_modify_tir_bitmask_bits {
+ u8 reserved[0x20];
+
+ u8 reserved1[0x1f];
+ u8 lro[0x1];
+};
+
struct mlx5_ifc_modify_tir_out_bits {
u8 status[0x8];
u8 reserved_0[0x18];
@@ -4071,7 +4078,7 @@ struct mlx5_ifc_modify_tir_in_bits {
u8 reserved_3[0x20];
- u8 modify_bitmask[0x40];
+ struct mlx5_ifc_modify_tir_bitmask_bits bitmask;
u8 reserved_4[0x40];
@@ -4116,6 +4123,13 @@ struct mlx5_ifc_modify_rqt_out_bits {
u8 reserved_1[0x40];
};
+struct mlx5_ifc_rqt_bitmask_bits {
+ u8 reserved[0x20];
+
+ u8 reserved1[0x1f];
+ u8 rqn_list[0x1];
+};
+
struct mlx5_ifc_modify_rqt_in_bits {
u8 opcode[0x10];
u8 reserved_0[0x10];
@@ -4128,7 +4142,7 @@ struct mlx5_ifc_modify_rqt_in_bits {
u8 reserved_3[0x20];
- u8 modify_bitmask[0x40];
+ struct mlx5_ifc_rqt_bitmask_bits bitmask;
u8 reserved_4[0x40];
diff --git a/include/linux/mpls_iptunnel.h b/include/linux/mpls_iptunnel.h
new file mode 100644
index 000000000000..ef29eb2d6dfd
--- /dev/null
+++ b/include/linux/mpls_iptunnel.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_MPLS_IPTUNNEL_H
+#define _LINUX_MPLS_IPTUNNEL_H
+
+#include <uapi/linux/mpls_iptunnel.h>
+
+#endif /* _LINUX_MPLS_IPTUNNEL_H */
diff --git a/include/linux/net.h b/include/linux/net.h
index 04aa06852771..049d4b03c4c4 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -239,8 +239,16 @@ do { \
net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
#define net_info_ratelimited(fmt, ...) \
net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
+#if defined(DEBUG)
#define net_dbg_ratelimited(fmt, ...) \
net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
+#else
+#define net_dbg_ratelimited(fmt, ...) \
+ do { \
+ if (0) \
+ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \
+ } while (0)
+#endif
bool __net_get_random_once(void *buf, int nbytes, bool *done,
struct static_key *done_key);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e20979dfd6a9..88a00694eda5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -766,6 +766,13 @@ struct netdev_phys_item_id {
unsigned char id_len;
};
+static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
+ struct netdev_phys_item_id *b)
+{
+ return a->id_len == b->id_len &&
+ memcmp(a->id, b->id, a->id_len) == 0;
+}
+
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb);
@@ -1041,6 +1048,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* TX queue.
* int (*ndo_get_iflink)(const struct net_device *dev);
* Called to get the iflink value of this device.
+ * void (*ndo_change_proto_down)(struct net_device *dev,
+ * bool proto_down);
+ * This function is used to pass protocol port error state information
+ * to the switch driver. The switch driver can react to the proto_down
+ * by doing a phys down on the associated switch port.
+ *
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1211,6 +1224,8 @@ struct net_device_ops {
int queue_index,
u32 maxrate);
int (*ndo_get_iflink)(const struct net_device *dev);
+ int (*ndo_change_proto_down)(struct net_device *dev,
+ bool proto_down);
};
/**
@@ -1225,13 +1240,8 @@ struct net_device_ops {
*
* @IFF_802_1Q_VLAN: 802.1Q VLAN device
* @IFF_EBRIDGE: Ethernet bridging device
- * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
- * @IFF_MASTER_8023AD: bonding master, 802.3ad
- * @IFF_MASTER_ALB: bonding master, balance-alb
* @IFF_BONDING: bonding master or slave
- * @IFF_SLAVE_NEEDARP: need ARPs for validation
* @IFF_ISATAP: ISATAP interface (RFC4214)
- * @IFF_MASTER_ARPMON: bonding master, ARP mon in use
* @IFF_WAN_HDLC: WAN HDLC device
* @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
* release skb->dst
@@ -1247,44 +1257,40 @@ struct net_device_ops {
* @IFF_LIVE_ADDR_CHANGE: device supports hardware address
* change when it's running
* @IFF_MACVLAN: Macvlan device
+ * @IFF_VRF_MASTER: device is a VRF master
+ * @IFF_NO_QUEUE: device can run without qdisc attached
+ * @IFF_OPENVSWITCH: device is a Open vSwitch master
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_EBRIDGE = 1<<1,
- IFF_SLAVE_INACTIVE = 1<<2,
- IFF_MASTER_8023AD = 1<<3,
- IFF_MASTER_ALB = 1<<4,
- IFF_BONDING = 1<<5,
- IFF_SLAVE_NEEDARP = 1<<6,
- IFF_ISATAP = 1<<7,
- IFF_MASTER_ARPMON = 1<<8,
- IFF_WAN_HDLC = 1<<9,
- IFF_XMIT_DST_RELEASE = 1<<10,
- IFF_DONT_BRIDGE = 1<<11,
- IFF_DISABLE_NETPOLL = 1<<12,
- IFF_MACVLAN_PORT = 1<<13,
- IFF_BRIDGE_PORT = 1<<14,
- IFF_OVS_DATAPATH = 1<<15,
- IFF_TX_SKB_SHARING = 1<<16,
- IFF_UNICAST_FLT = 1<<17,
- IFF_TEAM_PORT = 1<<18,
- IFF_SUPP_NOFCS = 1<<19,
- IFF_LIVE_ADDR_CHANGE = 1<<20,
- IFF_MACVLAN = 1<<21,
- IFF_XMIT_DST_RELEASE_PERM = 1<<22,
- IFF_IPVLAN_MASTER = 1<<23,
- IFF_IPVLAN_SLAVE = 1<<24,
+ IFF_BONDING = 1<<2,
+ IFF_ISATAP = 1<<3,
+ IFF_WAN_HDLC = 1<<4,
+ IFF_XMIT_DST_RELEASE = 1<<5,
+ IFF_DONT_BRIDGE = 1<<6,
+ IFF_DISABLE_NETPOLL = 1<<7,
+ IFF_MACVLAN_PORT = 1<<8,
+ IFF_BRIDGE_PORT = 1<<9,
+ IFF_OVS_DATAPATH = 1<<10,
+ IFF_TX_SKB_SHARING = 1<<11,
+ IFF_UNICAST_FLT = 1<<12,
+ IFF_TEAM_PORT = 1<<13,
+ IFF_SUPP_NOFCS = 1<<14,
+ IFF_LIVE_ADDR_CHANGE = 1<<15,
+ IFF_MACVLAN = 1<<16,
+ IFF_XMIT_DST_RELEASE_PERM = 1<<17,
+ IFF_IPVLAN_MASTER = 1<<18,
+ IFF_IPVLAN_SLAVE = 1<<19,
+ IFF_VRF_MASTER = 1<<20,
+ IFF_NO_QUEUE = 1<<21,
+ IFF_OPENVSWITCH = 1<<22,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
#define IFF_EBRIDGE IFF_EBRIDGE
-#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE
-#define IFF_MASTER_8023AD IFF_MASTER_8023AD
-#define IFF_MASTER_ALB IFF_MASTER_ALB
#define IFF_BONDING IFF_BONDING
-#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP
#define IFF_ISATAP IFF_ISATAP
-#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON
#define IFF_WAN_HDLC IFF_WAN_HDLC
#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE
#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE
@@ -1301,6 +1307,9 @@ enum netdev_priv_flags {
#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM
#define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER
#define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE
+#define IFF_VRF_MASTER IFF_VRF_MASTER
+#define IFF_NO_QUEUE IFF_NO_QUEUE
+#define IFF_OPENVSWITCH IFF_OPENVSWITCH
/**
* struct net_device - The DEVICE structure.
@@ -1417,6 +1426,7 @@ enum netdev_priv_flags {
* @dn_ptr: DECnet specific data
* @ip6_ptr: IPv6 specific data
* @ax25_ptr: AX.25 specific data
+ * @vrf_ptr: VRF specific data
* @ieee80211_ptr: IEEE 802.11 specific data, assign before registering
*
* @last_rx: Time of last Rx
@@ -1448,6 +1458,8 @@ enum netdev_priv_flags {
*
* @xps_maps: XXX: need comments on this one
*
+ * @offload_fwd_mark: Offload device fwding mark
+ *
* @trans_start: Time (in jiffies) of last Tx
* @watchdog_timeo: Represents the timeout that is used by
* the watchdog ( see dev_watchdog() )
@@ -1502,6 +1514,10 @@ enum netdev_priv_flags {
*
* @qdisc_tx_busylock: XXX: need comments on this one
*
+ * @proto_down: protocol port state information can be sent to the
+ * switch driver and used to set the phys state of the
+ * switch port.
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
@@ -1629,6 +1645,7 @@ struct net_device {
struct dn_dev __rcu *dn_ptr;
struct inet6_dev __rcu *ip6_ptr;
void *ax25_ptr;
+ struct net_vrf_dev __rcu *vrf_ptr;
struct wireless_dev *ieee80211_ptr;
struct wpan_dev *ieee802154_ptr;
#if IS_ENABLED(CONFIG_MPLS_ROUTING)
@@ -1685,6 +1702,10 @@ struct net_device {
struct xps_dev_maps __rcu *xps_maps;
#endif
+#ifdef CONFIG_NET_SWITCHDEV
+ u32 offload_fwd_mark;
+#endif
+
/* These may be needed for future network-power-down code. */
/*
@@ -1762,6 +1783,7 @@ struct net_device {
#endif
struct phy_device *phydev;
struct lock_class_key *qdisc_tx_busylock;
+ bool proto_down;
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -2093,6 +2115,13 @@ struct netdev_notifier_change_info {
unsigned int flags_changed;
};
+struct netdev_notifier_changeupper_info {
+ struct netdev_notifier_info info; /* must be first */
+ struct net_device *upper_dev; /* new upper dev */
+ bool master; /* is upper dev master */
+ bool linking; /* is the nofication for link or unlink */
+};
+
static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
struct net_device *dev)
{
@@ -2277,8 +2306,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
{
- return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) ==
- skb_gro_offset(skb));
+ return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb));
}
static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
@@ -2374,37 +2402,58 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
grc->delta = 0;
}
-static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
- int start, int offset,
- struct gro_remcsum *grc,
- bool nopartial)
+static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
+ unsigned int off, size_t hdrlen,
+ int start, int offset,
+ struct gro_remcsum *grc,
+ bool nopartial)
{
__wsum delta;
+ size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
if (!nopartial) {
- NAPI_GRO_CB(skb)->gro_remcsum_start =
- ((unsigned char *)ptr + start) - skb->head;
- return;
+ NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start;
+ return ptr;
+ }
+
+ ptr = skb_gro_header_fast(skb, off);
+ if (skb_gro_header_hard(skb, off + plen)) {
+ ptr = skb_gro_header_slow(skb, off + plen, off);
+ if (!ptr)
+ return NULL;
}
- delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);
+ delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum,
+ start, offset);
/* Adjust skb->csum since we changed the packet */
NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
- grc->offset = (ptr + offset) - (void *)skb->head;
+ grc->offset = off + hdrlen + offset;
grc->delta = delta;
+
+ return ptr;
}
static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
struct gro_remcsum *grc)
{
+ void *ptr;
+ size_t plen = grc->offset + sizeof(u16);
+
if (!grc->delta)
return;
- remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta);
+ ptr = skb_gro_header_fast(skb, grc->offset);
+ if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) {
+ ptr = skb_gro_header_slow(skb, plen, grc->offset);
+ if (!ptr)
+ return;
+ }
+
+ remcsum_unadjust((__sum16 *)ptr, grc->delta);
}
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
@@ -2982,6 +3031,7 @@ int dev_get_phys_port_id(struct net_device *dev,
struct netdev_phys_item_id *ppid);
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len);
+int dev_change_proto_down(struct net_device *dev, bool proto_down);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
@@ -3781,6 +3831,42 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
return dev->priv_flags & IFF_SUPP_NOFCS;
}
+static inline bool netif_is_vrf(const struct net_device *dev)
+{
+ return dev->priv_flags & IFF_VRF_MASTER;
+}
+
+static inline bool netif_is_bridge_master(const struct net_device *dev)
+{
+ return dev->priv_flags & IFF_EBRIDGE;
+}
+
+static inline bool netif_is_ovs_master(const struct net_device *dev)
+{
+ return dev->priv_flags & IFF_OPENVSWITCH;
+}
+
+static inline bool netif_index_is_vrf(struct net *net, int ifindex)
+{
+ bool rc = false;
+
+#if IS_ENABLED(CONFIG_NET_VRF)
+ struct net_device *dev;
+
+ if (ifindex == 0)
+ return false;
+
+ rcu_read_lock();
+
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (dev)
+ rc = netif_is_vrf(dev);
+
+ rcu_read_unlock();
+#endif
+ return rc;
+}
+
/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
static inline void netif_keep_dst(struct net_device *dev)
{
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 00050dfd9f23..36a652531791 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -11,6 +11,8 @@
#include <linux/list.h>
#include <linux/static_key.h>
#include <linux/netfilter_defs.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
#ifdef CONFIG_NETFILTER
static inline int NF_DROP_GETERR(int verdict)
@@ -118,6 +120,13 @@ struct nf_sockopt_ops {
};
/* Function to register/unregister hook points. */
+int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops);
+void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops);
+int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
+ unsigned int n);
+void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
+ unsigned int n);
+
int nf_register_hook(struct nf_hook_ops *reg);
void nf_unregister_hook(struct nf_hook_ops *reg);
int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n);
@@ -128,33 +137,26 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n);
int nf_register_sockopt(struct nf_sockopt_ops *reg);
void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
-extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
#ifdef HAVE_JUMP_LABEL
extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-static inline bool nf_hook_list_active(struct list_head *nf_hook_list,
+static inline bool nf_hook_list_active(struct list_head *hook_list,
u_int8_t pf, unsigned int hook)
{
if (__builtin_constant_p(pf) &&
__builtin_constant_p(hook))
return static_key_false(&nf_hooks_needed[pf][hook]);
- return !list_empty(nf_hook_list);
+ return !list_empty(hook_list);
}
#else
-static inline bool nf_hook_list_active(struct list_head *nf_hook_list,
+static inline bool nf_hook_list_active(struct list_head *hook_list,
u_int8_t pf, unsigned int hook)
{
- return !list_empty(nf_hook_list);
+ return !list_empty(hook_list);
}
#endif
-static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
-{
- return nf_hook_list_active(&nf_hooks[pf][hook], pf, hook);
-}
-
int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
/**
@@ -172,10 +174,13 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
int (*okfn)(struct sock *, struct sk_buff *),
int thresh)
{
- if (nf_hooks_active(pf, hook)) {
+ struct net *net = dev_net(indev ? indev : outdev);
+ struct list_head *hook_list = &net->nf.hooks[pf][hook];
+
+ if (nf_hook_list_active(hook_list, pf, hook)) {
struct nf_hook_state state;
- nf_hook_state_init(&state, &nf_hooks[pf][hook], hook, thresh,
+ nf_hook_state_init(&state, hook_list, hook, thresh,
pf, indev, outdev, sk, okfn);
return nf_hook_slow(skb, &state);
}
@@ -363,6 +368,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
#endif /*CONFIG_NETFILTER*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#include <linux/netfilter/nf_conntrack_zones_common.h>
+
extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu;
void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
@@ -385,4 +392,15 @@ extern struct nfq_ct_hook __rcu *nfq_ct_hook;
static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
#endif
+/**
+ * nf_skb_duplicated - TEE target has sent a packet
+ *
+ * When a xtables target sends a packet, the OUTPUT and POSTROUTING
+ * hooks are traversed again, i.e. nft and xtables are invoked recursively.
+ *
+ * This is used by xtables TEE target to prevent the duplicated skb from
+ * being duplicated again.
+ */
+DECLARE_PER_CPU(bool, nf_skb_duplicated);
+
#endif /*__LINUX_NETFILTER_H*/
diff --git a/include/linux/netfilter/nf_conntrack_zones_common.h b/include/linux/netfilter/nf_conntrack_zones_common.h
new file mode 100644
index 000000000000..5d7cf36d4766
--- /dev/null
+++ b/include/linux/netfilter/nf_conntrack_zones_common.h
@@ -0,0 +1,23 @@
+#ifndef _NF_CONNTRACK_ZONES_COMMON_H
+#define _NF_CONNTRACK_ZONES_COMMON_H
+
+#include <uapi/linux/netfilter/nf_conntrack_tuple_common.h>
+
+#define NF_CT_DEFAULT_ZONE_ID 0
+
+#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL)
+#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY)
+
+#define NF_CT_DEFAULT_ZONE_DIR (NF_CT_ZONE_DIR_ORIG | NF_CT_ZONE_DIR_REPL)
+
+#define NF_CT_FLAG_MARK 1
+
+struct nf_conntrack_zone {
+ u16 id;
+ u8 flags;
+ u8 dir;
+};
+
+extern const struct nf_conntrack_zone nf_ct_zone_dflt;
+
+#endif /* _NF_CONNTRACK_ZONES_COMMON_H */
diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h
index 6ec975748742..80ca889b164e 100644
--- a/include/linux/netfilter/nfnetlink_acct.h
+++ b/include/linux/netfilter/nfnetlink_acct.h
@@ -2,6 +2,7 @@
#define _NFNL_ACCT_H_
#include <uapi/linux/netfilter/nfnetlink_acct.h>
+#include <net/net_namespace.h>
enum {
NFACCT_NO_QUOTA = -1,
@@ -11,7 +12,7 @@ enum {
struct nf_acct;
-struct nf_acct *nfnl_acct_find_get(const char *filter_name);
+struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name);
void nfnl_acct_put(struct nf_acct *acct);
void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
extern int nfnl_acct_overquota(const struct sk_buff *skb,
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 286098a5667f..b006b719183f 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -3,6 +3,7 @@
#include <linux/netdevice.h>
+#include <linux/static_key.h>
#include <uapi/linux/netfilter/x_tables.h>
/**
@@ -222,7 +223,6 @@ struct xt_table_info {
* @stacksize jumps (number of user chains) can possibly be made.
*/
unsigned int stacksize;
- unsigned int __percpu *stackptr;
void ***jumpstack;
unsigned char entries[0] __aligned(8);
@@ -281,6 +281,12 @@ void xt_free_table_info(struct xt_table_info *info);
*/
DECLARE_PER_CPU(seqcount_t, xt_recseq);
+/* xt_tee_enabled - true if x_tables needs to handle reentrancy
+ *
+ * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
+ */
+extern struct static_key xt_tee_enabled;
+
/**
* xt_write_recseq_begin - start of a write section
*
diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index 6d80fc686323..2437b8a5d7a9 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -17,9 +17,6 @@ enum nf_br_hook_priorities {
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-#define BRNF_BRIDGED_DNAT 0x02
-#define BRNF_NF_BRIDGE_PREROUTING 0x08
-
int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);
static inline void br_drop_fake_rtable(struct sk_buff *skb)
@@ -63,8 +60,17 @@ nf_bridge_get_physoutdev(const struct sk_buff *skb)
{
return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL;
}
+
+static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb)
+{
+ return skb->nf_bridge && skb->nf_bridge->in_prerouting;
+}
#else
#define br_drop_fake_rtable(skb) do { } while (0)
+static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb)
+{
+ return false;
+}
#endif /* CONFIG_BRIDGE_NETFILTER */
#endif
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 8b7d28f3aada..771574677e83 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -9,15 +9,6 @@
#include <uapi/linux/netfilter_ipv6.h>
-
-#ifdef CONFIG_NETFILTER
-int ip6_route_me_harder(struct sk_buff *skb);
-__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
- unsigned int dataoff, u_int8_t protocol);
-
-int ipv6_netfilter_init(void);
-void ipv6_netfilter_fini(void);
-
/*
* Hook functions for ipv6 to allow xt_* modules to be built-in even
* if IPv6 is a module.
@@ -30,6 +21,14 @@ struct nf_ipv6_ops {
int (*output)(struct sock *, struct sk_buff *));
};
+#ifdef CONFIG_NETFILTER
+int ip6_route_me_harder(struct sk_buff *skb);
+__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
+ unsigned int dataoff, u_int8_t protocol);
+
+int ipv6_netfilter_init(void);
+void ipv6_netfilter_fini(void);
+
extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops;
static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void)
{
@@ -39,6 +38,7 @@ static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void)
#else /* CONFIG_NETFILTER */
static inline int ipv6_netfilter_init(void) { return 0; }
static inline void ipv6_netfilter_fini(void) { return; }
+static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { return NULL; }
#endif /* CONFIG_NETFILTER */
#endif /*__LINUX_IP6_NETFILTER_H*/
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2027809433b3..092a0e8a479a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -641,6 +641,8 @@ extern int perf_event_init_task(struct task_struct *child);
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
+extern struct perf_event *perf_event_get(unsigned int fd);
+extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
@@ -659,6 +661,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
void *context);
extern void perf_pmu_migrate_context(struct pmu *pmu,
int src_cpu, int dst_cpu);
+extern u64 perf_event_read_local(struct perf_event *event);
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
@@ -979,6 +982,12 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; }
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
+static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
+static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; }
static inline void perf_event_print_debug(void) { }
static inline int perf_event_task_disable(void) { return -EINVAL; }
static inline int perf_event_task_enable(void) { return -EINVAL; }
@@ -1011,6 +1020,7 @@ static inline void perf_event_enable(struct perf_event *event) { }
static inline void perf_event_disable(struct perf_event *event) { }
static inline int __perf_event_disable(void *info) { return -1; }
static inline void perf_event_task_tick(void) { }
+static inline int perf_event_release_kernel(struct perf_event *event) { return 0; }
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a26c3f84b8dd..962387a192f1 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -330,6 +330,7 @@ struct phy_c45_device_ids {
* c45_ids: 802.3-c45 Device Identifers if is_c45.
* is_c45: Set to true if this phy uses clause 45 addressing.
* is_internal: Set to true if this phy is internal to a MAC.
+ * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
* has_fixups: Set to true if this phy has fixups/quirks.
* suspended: Set to true if this phy has been suspended successfully.
* state: state of the PHY for management purposes
@@ -368,6 +369,7 @@ struct phy_device {
struct phy_c45_device_ids c45_ids;
bool is_c45;
bool is_internal;
+ bool is_pseudo_fixed_link;
bool has_fixups;
bool suspended;
@@ -424,6 +426,8 @@ struct phy_device {
struct net_device *attached_dev;
+ u8 mdix;
+
void (*adjust_link)(struct net_device *dev);
};
#define to_phy_device(d) container_of(d, struct phy_device, dev)
@@ -686,6 +690,16 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev)
{
return phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID;
+};
+
+/*
+ * phy_is_pseudo_fixed_link - Convenience function for testing if this
+ * PHY is the CPU port facing side of an Ethernet switch, or similar.
+ * @phydev: the phy_device struct
+ */
+static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev)
+{
+ return phydev->is_pseudo_fixed_link;
}
/**
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index fe5732d53eda..2400d2ea4f34 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -13,9 +13,11 @@ struct device_node;
#if IS_ENABLED(CONFIG_FIXED_PHY)
extern int fixed_phy_add(unsigned int irq, int phy_id,
- struct fixed_phy_status *status);
+ struct fixed_phy_status *status,
+ int link_gpio);
extern struct phy_device *fixed_phy_register(unsigned int irq,
struct fixed_phy_status *status,
+ int link_gpio,
struct device_node *np);
extern void fixed_phy_del(int phy_addr);
extern int fixed_phy_set_link_update(struct phy_device *phydev,
@@ -26,12 +28,14 @@ extern int fixed_phy_update_state(struct phy_device *phydev,
const struct fixed_phy_status *changed);
#else
static inline int fixed_phy_add(unsigned int irq, int phy_id,
- struct fixed_phy_status *status)
+ struct fixed_phy_status *status,
+ int link_gpio)
{
return -ENODEV;
}
static inline struct phy_device *fixed_phy_register(unsigned int irq,
struct fixed_phy_status *status,
+ int gpio_link,
struct device_node *np)
{
return ERR_PTR(-ENODEV);
diff --git a/include/linux/platform_data/st_nci.h b/include/linux/platform_data/st_nci.h
deleted file mode 100644
index d9d400a297bd..000000000000
--- a/include/linux/platform_data/st_nci.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Driver include for ST NCI NFC chip family.
- *
- * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _ST_NCI_H_
-#define _ST_NCI_H_
-
-#define ST_NCI_DRIVER_NAME "st_nci"
-
-struct st_nci_nfc_platform_data {
- unsigned int gpio_reset;
- unsigned int irq_polarity;
-};
-
-#endif /* _ST_NCI_H_ */
diff --git a/include/linux/property.h b/include/linux/property.h
index 76ebde9c11d4..a59c6ee566c2 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -166,4 +166,8 @@ void device_add_property_set(struct device *dev, struct property_set *pset);
bool device_dma_is_coherent(struct device *dev);
+int device_get_phy_mode(struct device *dev);
+
+void *device_get_mac_address(struct device *dev, char *addr, int alen);
+
#endif /* _LINUX_PROPERTY_H_ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9b88536487e6..2738d355cdf9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -37,6 +37,7 @@
#include <net/flow_dissector.h>
#include <linux/splice.h>
#include <linux/in6.h>
+#include <net/flow.h>
/* A. Checksumming of received packets by device.
*
@@ -173,17 +174,24 @@ struct nf_bridge_info {
BRNF_PROTO_8021Q,
BRNF_PROTO_PPPOE
} orig_proto:8;
- bool pkt_otherhost;
+ u8 pkt_otherhost:1;
+ u8 in_prerouting:1;
+ u8 bridged_dnat:1;
__u16 frag_max_size;
- unsigned int mask;
struct net_device *physindev;
union {
- struct net_device *physoutdev;
- char neigh_header[8];
- };
- union {
+ /* prerouting: detect dnat in orig/reply direction */
__be32 ipv4_daddr;
struct in6_addr ipv6_daddr;
+
+ /* after prerouting + nat detected: store original source
+ * mac since neigh resolution overwrites it, only used while
+ * skb is out in neigh layer.
+ */
+ char neigh_header[8];
+
+ /* always valid & non-NULL from FORWARD on, for physdev match */
+ struct net_device *physoutdev;
};
};
#endif
@@ -506,6 +514,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
* @napi_id: id of the NAPI struct this skb came from
* @secmark: security marking
+ * @offload_fwd_mark: fwding offload mark
* @mark: Generic packet mark
* @vlan_proto: vlan encapsulation protocol
* @vlan_tci: vlan tag control information
@@ -650,9 +659,15 @@ struct sk_buff {
unsigned int sender_cpu;
};
#endif
+ union {
#ifdef CONFIG_NETWORK_SECMARK
- __u32 secmark;
+ __u32 secmark;
+#endif
+#ifdef CONFIG_NET_SWITCHDEV
+ __u32 offload_fwd_mark;
#endif
+ };
+
union {
__u32 mark;
__u32 reserved_tailroom;
@@ -922,14 +937,90 @@ enum pkt_hash_types {
PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */
};
-static inline void
-skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
+static inline void skb_clear_hash(struct sk_buff *skb)
{
- skb->l4_hash = (type == PKT_HASH_TYPE_L4);
+ skb->hash = 0;
skb->sw_hash = 0;
+ skb->l4_hash = 0;
+}
+
+static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
+{
+ if (!skb->l4_hash)
+ skb_clear_hash(skb);
+}
+
+static inline void
+__skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4)
+{
+ skb->l4_hash = is_l4;
+ skb->sw_hash = is_sw;
skb->hash = hash;
}
+static inline void
+skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
+{
+ /* Used by drivers to set hash from HW */
+ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4);
+}
+
+static inline void
+__skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
+{
+ __skb_set_hash(skb, hash, true, is_l4);
+}
+
+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);
+__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);
+}
+
+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,
+ unsigned int flags);
+
+static inline bool skb_flow_dissect(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, unsigned int flags)
+{
+ return __skb_flow_dissect(skb, flow_dissector, target_container,
+ NULL, 0, 0, 0, flags);
+}
+
+static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+ struct flow_keys *flow,
+ unsigned int flags)
+{
+ memset(flow, 0, sizeof(*flow));
+ return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
+ NULL, 0, 0, 0, flags);
+}
+
+static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
+ void *data, __be16 proto,
+ int nhoff, int hlen,
+ unsigned int flags)
+{
+ memset(flow, 0, sizeof(*flow));
+ return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
+ data, proto, nhoff, hlen, flags);
+}
+
static inline __u32 skb_get_hash(struct sk_buff *skb)
{
if (!skb->l4_hash && !skb->sw_hash)
@@ -938,24 +1029,39 @@ static inline __u32 skb_get_hash(struct sk_buff *skb)
return skb->hash;
}
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6);
-static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
+static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6)
{
+ if (!skb->l4_hash && !skb->sw_hash) {
+ struct flow_keys keys;
+ __u32 hash = __get_hash_from_flowi6(fl6, &keys);
+
+ __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
+ }
+
return skb->hash;
}
-static inline void skb_clear_hash(struct sk_buff *skb)
+__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl);
+
+static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4)
{
- skb->hash = 0;
- skb->sw_hash = 0;
- skb->l4_hash = 0;
+ if (!skb->l4_hash && !skb->sw_hash) {
+ struct flow_keys keys;
+ __u32 hash = __get_hash_from_flowi4(fl4, &keys);
+
+ __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
+ }
+
+ return skb->hash;
}
-static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+
+static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
{
- if (!skb->l4_hash)
- skb_clear_hash(skb);
+ return skb->hash;
}
static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
@@ -1943,7 +2049,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
if (skb_transport_header_was_set(skb))
return;
- else if (skb_flow_dissect_flow_keys(skb, &keys))
+ else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
skb_set_transport_header(skb, keys.control.thoff);
else
skb_set_transport_header(skb, offset_hint);
@@ -2667,12 +2773,6 @@ static inline void skb_frag_list_init(struct sk_buff *skb)
skb_shinfo(skb)->frag_list = NULL;
}
-static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag)
-{
- frag->next = skb_shinfo(skb)->frag_list;
- skb_shinfo(skb)->frag_list = frag;
-}
-
#define skb_walk_frags(skb, iter) \
for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
@@ -3464,5 +3564,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
skb_network_header(skb);
return hdr_len + skb_gso_transport_seglen(skb);
}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index c735f5c91eea..eead8ab93c0a 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -119,30 +119,8 @@ struct plat_stmmacenet_data {
int rx_fifo_size;
void (*fix_mac_speed)(void *priv, unsigned int speed);
void (*bus_setup)(void __iomem *ioaddr);
- void *(*setup)(struct platform_device *pdev);
- void (*free)(struct platform_device *pdev, void *priv);
int (*init)(struct platform_device *pdev, void *priv);
void (*exit)(struct platform_device *pdev, void *priv);
- void *custom_cfg;
- void *custom_data;
void *bsp_priv;
};
-
-/* of_data for SoC glue layer device tree bindings */
-
-struct stmmac_of_data {
- int has_gmac;
- int enh_desc;
- int tx_coe;
- int rx_coe;
- int bugged_jumbo;
- int pmt;
- int riwt_off;
- void (*fix_mac_speed)(void *priv, unsigned int speed);
- void (*bus_setup)(void __iomem *ioaddr);
- void *(*setup)(struct platform_device *pdev);
- void (*free)(struct platform_device *pdev, void *priv);
- int (*init)(struct platform_device *pdev, void *priv);
- void (*exit)(struct platform_device *pdev, void *priv);
-};
#endif
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ae572c138607..d6f2c2c5b043 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -129,4 +129,6 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size);
extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
+extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+
#endif /* __LINUX_UACCESS_H__ */
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index dc03d77ad23b..a2f59ec98d24 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -197,6 +197,27 @@
#define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */
#define LOWPAN_NHC_UDP_CS_C 0x04 /* checksum elided */
+#define LOWPAN_PRIV_SIZE(llpriv_size) \
+ (sizeof(struct lowpan_priv) + llpriv_size)
+
+enum lowpan_lltypes {
+ LOWPAN_LLTYPE_BTLE,
+ LOWPAN_LLTYPE_IEEE802154,
+};
+
+struct lowpan_priv {
+ enum lowpan_lltypes lltype;
+
+ /* must be last */
+ u8 priv[0] __aligned(sizeof(void *));
+};
+
+static inline
+struct lowpan_priv *lowpan_priv(const struct net_device *dev)
+{
+ return netdev_priv(dev);
+}
+
#ifdef DEBUG
/* print data in line */
static inline void raw_dump_inline(const char *caller, char *msg,
@@ -372,6 +393,8 @@ lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset)
return skb->len + uncomp_header - ret;
}
+void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype);
+
int
lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev,
const u8 *saddr, const u8 saddr_type,
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 931738bc5bba..9d446f136607 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -21,6 +21,8 @@ struct tcf_common {
struct gnet_stats_rate_est64 tcfc_rate_est;
spinlock_t tcfc_lock;
struct rcu_head tcfc_rcu;
+ struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+ struct gnet_stats_queue __percpu *cpu_qstats;
};
#define tcf_head common.tcfc_head
#define tcf_index common.tcfc_index
@@ -68,6 +70,17 @@ static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf)
kfree(hf->htab);
}
+/* Update lastuse only if needed, to avoid dirtying a cache line.
+ * We use a temp variable to avoid fetching jiffies twice.
+ */
+static inline void tcf_lastuse_update(struct tcf_t *tm)
+{
+ unsigned long now = jiffies;
+
+ if (tm->lastuse != now)
+ tm->lastuse = now;
+}
+
#ifdef CONFIG_NET_CLS_ACT
#define ACT_P_CREATED 1
@@ -98,11 +111,10 @@ struct tc_action_ops {
};
int tcf_hash_search(struct tc_action *a, u32 index);
-void tcf_hash_destroy(struct tc_action *a);
u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
int tcf_hash_check(u32 index, struct tc_action *a, int bind);
int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
- int size, int bind);
+ int size, int bind, bool cpustats);
void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
void tcf_hash_insert(struct tc_action *a);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index def59d3a34d5..0c3ac5acb85f 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -158,8 +158,8 @@ struct ipv6_stub {
const struct in6_addr *addr);
int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
const struct in6_addr *addr);
- int (*ipv6_dst_lookup)(struct sock *sk, struct dst_entry **dst,
- struct flowi6 *fl6);
+ int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
+ struct dst_entry **dst, struct flowi6 *fl6);
void (*udpv6_encap_enable)(void);
void (*ndisc_send_na)(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *daddr,
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3bd618d3e55d..9e1a59e01fa2 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -512,9 +512,11 @@ struct hci_conn_params {
HCI_AUTO_CONN_DIRECT,
HCI_AUTO_CONN_ALWAYS,
HCI_AUTO_CONN_LINK_LOSS,
+ HCI_AUTO_CONN_EXPLICIT,
} auto_connect;
struct hci_conn *conn;
+ bool explicit_connect;
};
extern struct list_head hci_dev_list;
@@ -639,6 +641,7 @@ enum {
HCI_CONN_DROP,
HCI_CONN_PARAM_REMOVAL_PEND,
HCI_CONN_NEW_LINK_KEY,
+ HCI_CONN_SCANNING,
};
static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
@@ -808,6 +811,26 @@ static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
return NULL;
}
+static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev)
+{
+ struct hci_conn_hash *h = &hdev->conn_hash;
+ struct hci_conn *c;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(c, &h->list, list) {
+ if (c->type == LE_LINK && c->state == BT_CONNECT &&
+ !test_bit(HCI_CONN_SCANNING, &c->flags)) {
+ rcu_read_unlock();
+ return c;
+ }
+ }
+
+ rcu_read_unlock();
+
+ return NULL;
+}
+
int hci_disconnect(struct hci_conn *conn, __u8 reason);
bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
void hci_sco_setup(struct hci_conn *conn, __u8 status);
@@ -823,6 +846,9 @@ void hci_chan_del(struct hci_chan *chan);
void hci_chan_list_flush(struct hci_conn *conn);
struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle);
+struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst,
+ u8 dst_type, u8 sec_level,
+ u16 conn_timeout, u8 role);
struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
u8 dst_type, u8 sec_level, u16 conn_timeout,
u8 role);
@@ -988,6 +1014,9 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev);
struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
bdaddr_t *addr,
u8 addr_type);
+struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev,
+ bdaddr_t *addr,
+ u8 addr_type);
void hci_uuids_clear(struct hci_dev *hdev);
@@ -1297,7 +1326,7 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency,
if (max >= to_multiplier * 8)
return -EINVAL;
- max_latency = (to_multiplier * 8 / max) - 1;
+ max_latency = (to_multiplier * 4 / max) - 1;
if (latency > 499 || latency > max_latency)
return -EINVAL;
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 2239a3753092..c98afc08cc26 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -55,6 +55,8 @@
#define L2CAP_INFO_TIMEOUT msecs_to_jiffies(4000)
#define L2CAP_MOVE_TIMEOUT msecs_to_jiffies(4000)
#define L2CAP_MOVE_ERTX_TIMEOUT msecs_to_jiffies(60000)
+#define L2CAP_WAIT_ACK_POLL_PERIOD msecs_to_jiffies(200)
+#define L2CAP_WAIT_ACK_TIMEOUT msecs_to_jiffies(10000)
#define L2CAP_A2MP_DEFAULT_MTU 670
diff --git a/include/net/bond_options.h b/include/net/bond_options.h
index c28aca25320e..1797235cd590 100644
--- a/include/net/bond_options.h
+++ b/include/net/bond_options.h
@@ -66,6 +66,7 @@ enum {
BOND_OPT_AD_ACTOR_SYS_PRIO,
BOND_OPT_AD_ACTOR_SYSTEM,
BOND_OPT_AD_USER_PORT_KEY,
+ BOND_OPT_NUM_PEER_NOTIF_ALIAS,
BOND_OPT_LAST
};
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 883fe1e7c5a1..f0889a247643 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2369,8 +2369,7 @@ struct cfg80211_qos_map {
* method returns 0.)
*
* @mgmt_frame_register: Notify driver that a management frame type was
- * registered. Note that this callback may not sleep, and cannot run
- * concurrently with itself.
+ * registered. The callback is allowed to sleep.
*
* @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device.
* Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 290a9a69af07..76b1ffaea863 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -34,6 +34,8 @@ struct cfg802154_ops {
int type);
void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
struct net_device *dev);
+ int (*suspend)(struct wpan_phy *wpan_phy);
+ int (*resume)(struct wpan_phy *wpan_phy);
int (*add_virtual_intf)(struct wpan_phy *wpan_phy,
const char *name,
unsigned char name_assign_type,
@@ -61,6 +63,8 @@ struct cfg802154_ops {
s8 max_frame_retries);
int (*set_lbt_mode)(struct wpan_phy *wpan_phy,
struct wpan_dev *wpan_dev, bool mode);
+ int (*set_ackreq_default)(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev, bool ackreq);
};
static inline bool
@@ -171,6 +175,9 @@ struct wpan_dev {
struct list_head list;
struct net_device *netdev;
+ /* lowpan interface, set when the wpan_dev belongs to one lowpan_dev */
+ struct net_device *lowpan_dev;
+
u32 identifier;
/* MAC PIB */
@@ -191,6 +198,9 @@ struct wpan_dev {
bool lbt;
bool promiscuous_mode;
+
+ /* fallback for acknowledgment bit setting */
+ bool ackreq;
};
#define to_phy(_dev) container_of(_dev, struct wpan_phy, dev)
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 2d1d73cb773e..9fcaedf994ee 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -140,14 +140,16 @@ static inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
struct sk_buff;
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
- __be32 from, __be32 to, int pseudohdr);
+ __be32 from, __be32 to, bool pseudohdr);
void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
const __be32 *from, const __be32 *to,
- int pseudohdr);
+ bool pseudohdr);
+void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
+ __wsum diff, bool pseudohdr);
static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
__be16 from, __be16 to,
- int pseudohdr)
+ bool pseudohdr)
{
inet_proto_csum_replace4(sum, skb, (__force __be32)from,
(__force __be32)to, pseudohdr);
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index c15d39456e14..ccd6d8bffa4d 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -49,9 +49,38 @@ static inline void sock_update_classid(struct sock *sk)
if (classid != sk->sk_classid)
sk->sk_classid = classid;
}
+
+static inline u32 task_get_classid(const struct sk_buff *skb)
+{
+ u32 classid = task_cls_state(current)->classid;
+
+ /* Due to the nature of the classifier it is required to ignore all
+ * packets originating from softirq context as accessing `current'
+ * would lead to false results.
+ *
+ * This test assumes that all callers of dev_queue_xmit() explicitly
+ * disable bh. Knowing this, it is possible to detect softirq based
+ * calls by looking at the number of nested bh disable calls because
+ * softirqs always disables bh.
+ */
+ if (in_serving_softirq()) {
+ /* If there is an sk_classid we'll use that. */
+ if (!skb->sk)
+ return 0;
+
+ classid = skb->sk->sk_classid;
+ }
+
+ return classid;
+}
#else /* !CONFIG_CGROUP_NET_CLASSID */
static inline void sock_update_classid(struct sock *sk)
{
}
+
+static inline u32 task_get_classid(const struct sk_buff *skb)
+{
+ return 0;
+}
#endif /* CONFIG_CGROUP_NET_CLASSID */
#endif /* _NET_CLS_CGROUP_H */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index fbca63ba8f73..b34d812bc5d0 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -171,6 +171,11 @@ static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
}
+static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
+{
+ return !!((ds->dsa_port_mask) & (1 << p));
+}
+
static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
{
return ds->phys_port_mask & (1 << p) && ds->ports[p];
@@ -296,12 +301,28 @@ struct dsa_switch_driver {
u32 br_port_mask);
int (*port_stp_update)(struct dsa_switch *ds, int port,
u8 state);
- int (*fdb_add)(struct dsa_switch *ds, int port,
- const unsigned char *addr, u16 vid);
- int (*fdb_del)(struct dsa_switch *ds, int port,
- const unsigned char *addr, u16 vid);
- int (*fdb_getnext)(struct dsa_switch *ds, int port,
- unsigned char *addr, bool *is_static);
+
+ /*
+ * VLAN support
+ */
+ int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid);
+ int (*port_pvid_set)(struct dsa_switch *ds, int port, u16 pvid);
+ int (*port_vlan_add)(struct dsa_switch *ds, int port, u16 vid,
+ bool untagged);
+ int (*port_vlan_del)(struct dsa_switch *ds, int port, u16 vid);
+ int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid,
+ unsigned long *ports, unsigned long *untagged);
+
+ /*
+ * Forwarding database
+ */
+ int (*port_fdb_add)(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid);
+ int (*port_fdb_del)(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid);
+ int (*port_fdb_getnext)(struct dsa_switch *ds, int port,
+ unsigned char *addr, u16 *vid,
+ bool *is_static);
};
void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/include/net/dst.h b/include/net/dst.h
index 2bc73f8a00a9..9261d928303d 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -57,6 +57,7 @@ struct dst_entry {
#define DST_FAKE_RTABLE 0x0040
#define DST_XFRM_TUNNEL 0x0080
#define DST_XFRM_QUEUE 0x0100
+#define DST_METADATA 0x0200
unsigned short pending_confirm;
@@ -83,12 +84,13 @@ struct dst_entry {
__u32 __pad2;
#endif
+#ifdef CONFIG_64BIT
+ struct lwtunnel_state *lwtstate;
/*
* Align __refcnt to a 64 bytes alignment
* (L1_CACHE_SIZE would be too much)
*/
-#ifdef CONFIG_64BIT
- long __pad_to_align_refcnt[2];
+ long __pad_to_align_refcnt[1];
#endif
/*
* __refcnt wants to be on a different cache line from
@@ -97,6 +99,9 @@ struct dst_entry {
atomic_t __refcnt; /* client references */
int __use;
unsigned long lastuse;
+#ifndef CONFIG_64BIT
+ struct lwtunnel_state *lwtstate;
+#endif
union {
struct dst_entry *next;
struct rtable __rcu *rt_next;
@@ -202,6 +207,12 @@ static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
p[metric-1] = val;
}
+/* Kernel-internal feature bits that are unallocated in user space. */
+#define DST_FEATURE_ECN_CA (1 << 31)
+
+#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA)
+#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN)
+
static inline u32
dst_feature(const struct dst_entry *dst, u32 feature)
{
@@ -284,13 +295,18 @@ static inline void skb_dst_drop(struct sk_buff *skb)
}
}
-static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb)
+static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst)
{
- nskb->_skb_refdst = oskb->_skb_refdst;
+ nskb->_skb_refdst = refdst;
if (!(nskb->_skb_refdst & SKB_DST_NOREF))
dst_clone(skb_dst(nskb));
}
+static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb)
+{
+ __skb_dst_copy(nskb, oskb->_skb_refdst);
+}
+
/**
* skb_dst_force - makes sure skb dst is refcounted
* @skb: buffer
@@ -356,6 +372,9 @@ static inline int dst_discard(struct sk_buff *skb)
}
void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
int initial_obsolete, unsigned short flags);
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags);
void __dst_free(struct dst_entry *dst);
struct dst_entry *dst_destroy(struct dst_entry *dst);
@@ -457,7 +476,7 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
return dst;
}
-void dst_init(void);
+void dst_subsys_init(void);
/* Flags for xfrm_lookup flags argument. */
enum {
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
new file mode 100644
index 000000000000..af9d5382f6cb
--- /dev/null
+++ b/include/net/dst_metadata.h
@@ -0,0 +1,108 @@
+#ifndef __NET_DST_METADATA_H
+#define __NET_DST_METADATA_H 1
+
+#include <linux/skbuff.h>
+#include <net/ip_tunnels.h>
+#include <net/dst.h>
+
+struct metadata_dst {
+ struct dst_entry dst;
+ union {
+ struct ip_tunnel_info tun_info;
+ } u;
+};
+
+static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+{
+ struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
+
+ if (md_dst && md_dst->dst.flags & DST_METADATA)
+ return md_dst;
+
+ return NULL;
+}
+
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+{
+ struct metadata_dst *md_dst = skb_metadata_dst(skb);
+ struct dst_entry *dst;
+
+ if (md_dst)
+ return &md_dst->u.tun_info;
+
+ dst = skb_dst(skb);
+ if (dst && dst->lwtstate)
+ return lwt_tun_info(dst->lwtstate);
+
+ return NULL;
+}
+
+static inline bool skb_valid_dst(const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ return dst && !(dst->flags & DST_METADATA);
+}
+
+struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
+struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
+
+static inline struct metadata_dst *tun_rx_dst(int md_size)
+{
+ struct metadata_dst *tun_dst;
+
+ tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC);
+ if (!tun_dst)
+ return NULL;
+
+ tun_dst->u.tun_info.options_len = 0;
+ tun_dst->u.tun_info.mode = 0;
+ return tun_dst;
+}
+
+static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
+ __be16 flags,
+ __be64 tunnel_id,
+ int md_size)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct metadata_dst *tun_dst;
+
+ tun_dst = tun_rx_dst(md_size);
+ if (!tun_dst)
+ return NULL;
+
+ ip_tunnel_key_init(&tun_dst->u.tun_info.key,
+ iph->saddr, iph->daddr, iph->tos, iph->ttl,
+ 0, 0, tunnel_id, flags);
+ return tun_dst;
+}
+
+static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
+ __be16 flags,
+ __be64 tunnel_id,
+ int md_size)
+{
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct metadata_dst *tun_dst;
+ struct ip_tunnel_info *info;
+
+ tun_dst = tun_rx_dst(md_size);
+ if (!tun_dst)
+ return NULL;
+
+ info = &tun_dst->u.tun_info;
+ info->mode = IP_TUNNEL_INFO_IPV6;
+ info->key.tun_flags = flags;
+ info->key.tun_id = tunnel_id;
+ info->key.tp_src = 0;
+ info->key.tp_dst = 0;
+
+ info->key.u.ipv6.src = ip6h->saddr;
+ info->key.u.ipv6.dst = ip6h->daddr;
+ info->key.tos = ipv6_get_dsfield(ip6h);
+ info->key.ttl = ip6h->hop_limit;
+ return tun_dst;
+}
+
+#endif /* __NET_DST_METADATA_H */
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 903a55efbffe..4e8f804f4589 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -19,6 +19,7 @@ struct fib_rule {
u8 action;
/* 3 bytes hole, try to use */
u32 target;
+ __be64 tun_id;
struct fib_rule __rcu *ctarget;
struct net *fr_net;
diff --git a/include/net/flow.h b/include/net/flow.h
index 8109a159d1b3..acd6a096250e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -10,6 +10,7 @@
#include <linux/socket.h>
#include <linux/in6.h>
#include <linux/atomic.h>
+#include <net/flow_dissector.h>
/*
* ifindex generation is per-net namespace, and loopback is
@@ -19,6 +20,10 @@
#define LOOPBACK_IFINDEX 1
+struct flowi_tunnel {
+ __be64 tun_id;
+};
+
struct flowi_common {
int flowic_oif;
int flowic_iif;
@@ -29,7 +34,9 @@ struct flowi_common {
__u8 flowic_flags;
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_KNOWN_NH 0x02
+#define FLOWI_FLAG_VRFSRC 0x04
__u32 flowic_secid;
+ struct flowi_tunnel flowic_tun_key;
};
union flowi_uli {
@@ -66,6 +73,7 @@ struct flowi4 {
#define flowi4_proto __fl_common.flowic_proto
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
+#define flowi4_tun_key __fl_common.flowic_tun_key
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -95,6 +103,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
fl4->flowi4_proto = proto;
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
+ fl4->flowi4_tun_key.tun_id = 0;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
@@ -122,6 +131,7 @@ struct flowi6 {
#define flowi6_proto __fl_common.flowic_proto
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
+#define flowi6_tun_key __fl_common.flowic_tun_key
struct in6_addr daddr;
struct in6_addr saddr;
__be32 flowlabel;
@@ -165,6 +175,7 @@ struct flowi {
#define flowi_proto u.__fl_common.flowic_proto
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
+#define flowi_tun_key u.__fl_common.flowic_tun_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
@@ -233,4 +244,22 @@ void flow_cache_flush(struct net *net);
void flow_cache_flush_deferred(struct net *net);
extern atomic_t flow_cache_genid;
+__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
+
+static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6)
+{
+ struct flow_keys keys;
+
+ return __get_hash_from_flowi6(fl6, &keys);
+}
+
+__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys);
+
+static inline __u32 get_hash_from_flowi4(const struct flowi4 *fl4)
+{
+ struct flow_keys keys;
+
+ return __get_hash_from_flowi4(fl4, &keys);
+}
+
#endif
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 1a8c22419936..8c8548cf5888 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -2,7 +2,6 @@
#define _NET_FLOW_DISSECTOR_H
#include <linux/types.h>
-#include <linux/skbuff.h>
#include <linux/in6.h>
#include <uapi/linux/if_ether.h>
@@ -13,8 +12,13 @@
struct flow_dissector_key_control {
u16 thoff;
u16 addr_type;
+ u32 flags;
};
+#define FLOW_DIS_IS_FRAGMENT BIT(0)
+#define FLOW_DIS_FIRST_FRAG BIT(1)
+#define FLOW_DIS_ENCAPSULATION BIT(2)
+
/**
* struct flow_dissector_key_basic:
* @thoff: Transport header offset
@@ -123,6 +127,11 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_MAX,
};
+#define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0)
+#define FLOW_DISSECTOR_F_STOP_AT_L3 BIT(1)
+#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(2)
+#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(3)
+
struct flow_dissector_key {
enum flow_dissector_key_id key_id;
size_t offset; /* offset of struct flow_dissector_key_*
@@ -134,23 +143,6 @@ struct flow_dissector {
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_control control;
#define FLOW_KEYS_HASH_START_FIELD basic
@@ -170,38 +162,6 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow);
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
@@ -217,4 +177,11 @@ struct flow_keys_digest {
void make_flow_keys_digest(struct flow_keys_digest *digest,
const struct flow_keys *flow);
+static inline bool flow_keys_have_l4(struct flow_keys *keys)
+{
+ return (keys->ports.ports || keys->tags.flow_label);
+}
+
+u32 flow_hash_from_keys(struct flow_keys *keys);
+
#endif
diff --git a/include/net/geneve.h b/include/net/geneve.h
index 2a0543a1899d..3106ed6eae0d 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -62,40 +62,9 @@ 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;
-
-typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
-
-struct geneve_sock {
- struct list_head list;
- geneve_rcv_t *rcv;
- void *rcv_data;
- struct socket *sock;
- struct rcu_head rcu;
- int refcnt;
- struct udp_offload udp_offloads;
-};
-
-#define GENEVE_VER 0
-#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
-
-struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
- geneve_rcv_t *rcv, void *data,
- bool no_share, bool ipv6);
-
-void geneve_sock_release(struct geneve_sock *vs);
-
-int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
- struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
- __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
- __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
- bool csum, bool xnet);
+struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
+ u8 name_assign_type, u16 dst_port);
#endif /*ifdef CONFIG_INET */
#endif /*ifdef__NET_GENEVE_H */
diff --git a/include/net/gre.h b/include/net/gre.h
index b53182018743..97eafdc47eea 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -4,6 +4,12 @@
#include <linux/skbuff.h>
#include <net/ip_tunnels.h>
+struct gre_base_hdr {
+ __be16 flags;
+ __be16 protocol;
+};
+#define GRE_HEADER_SECTION 4
+
#define GREPROTO_CISCO 0
#define GREPROTO_PPTP 1
#define GREPROTO_MAX 2
@@ -14,91 +20,9 @@ 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);
-struct gre_cisco_protocol {
- int (*handler)(struct sk_buff *skb, const struct tnl_ptk_info *tpi);
- int (*err_handler)(struct sk_buff *skb, u32 info,
- const struct tnl_ptk_info *tpi);
- u8 priority;
-};
-
-int gre_cisco_register(struct gre_cisco_protocol *proto);
-int gre_cisco_unregister(struct gre_cisco_protocol *proto);
-
-void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
- int hdr_len);
-
-static inline struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
- bool csum)
-{
- return iptunnel_handle_offloads(skb, csum,
- csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
-}
-
-
-static inline int ip_gre_calc_hlen(__be16 o_flags)
-{
- int addend = 4;
-
- if (o_flags&TUNNEL_CSUM)
- addend += 4;
- if (o_flags&TUNNEL_KEY)
- addend += 4;
- if (o_flags&TUNNEL_SEQ)
- addend += 4;
- return addend;
-}
-
-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;
-}
-
+struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
+ u8 name_assign_type);
#endif
diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index 0f712c0bc0bf..cf6c74550baa 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -32,37 +32,28 @@ static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *s
return;
}
- /* We run in BH context */
- spin_lock(&cell->napi_skbs.lock);
-
__skb_queue_tail(&cell->napi_skbs, skb);
if (skb_queue_len(&cell->napi_skbs) == 1)
napi_schedule(&cell->napi);
-
- spin_unlock(&cell->napi_skbs.lock);
}
-/* called unser BH context */
+/* called under BH context */
static inline int gro_cell_poll(struct napi_struct *napi, int budget)
{
struct gro_cell *cell = container_of(napi, struct gro_cell, napi);
struct sk_buff *skb;
int work_done = 0;
- spin_lock(&cell->napi_skbs.lock);
while (work_done < budget) {
skb = __skb_dequeue(&cell->napi_skbs);
if (!skb)
break;
- spin_unlock(&cell->napi_skbs.lock);
napi_gro_receive(napi, skb);
work_done++;
- spin_lock(&cell->napi_skbs.lock);
}
if (work_done < budget)
- napi_complete(napi);
- spin_unlock(&cell->napi_skbs.lock);
+ napi_complete_done(napi, work_done);
return work_done;
}
@@ -77,7 +68,7 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
for_each_possible_cpu(i) {
struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
- skb_queue_head_init(&cell->napi_skbs);
+ __skb_queue_head_init(&cell->napi_skbs);
netif_napi_add(dev, &cell->napi, gro_cell_poll, 64);
napi_enable(&cell->napi);
}
@@ -92,8 +83,9 @@ static inline void gro_cells_destroy(struct gro_cells *gcells)
return;
for_each_possible_cpu(i) {
struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
+
netif_napi_del(&cell->napi);
- skb_queue_purge(&cell->napi_skbs);
+ __skb_queue_purge(&cell->napi_skbs);
}
free_percpu(gcells->cells);
gcells->cells = NULL;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index b73c88a19dd4..b07d126694a7 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -205,8 +205,8 @@ void inet_put_port(struct sock *sk);
void inet_hashinfo_init(struct inet_hashinfo *h);
-int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw);
-int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw);
+void __inet_hash_nolisten(struct sock *sk, struct sock *osk);
+void __inet_hash(struct sock *sk, struct sock *osk);
void inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 360c4802288d..879d6e5a973b 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -100,10 +100,8 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
void inet_twsk_free(struct inet_timewait_sock *tw);
void inet_twsk_put(struct inet_timewait_sock *tw);
-int inet_twsk_unhash(struct inet_timewait_sock *tw);
-
-int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
- struct inet_hashinfo *hashinfo);
+void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
+ struct inet_hashinfo *hashinfo);
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
struct inet_timewait_death_row *dr,
@@ -113,7 +111,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
struct inet_hashinfo *hashinfo);
void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo);
-void inet_twsk_deschedule(struct inet_timewait_sock *tw);
+void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
void inet_twsk_purge(struct inet_hashinfo *hashinfo,
struct inet_timewait_death_row *twdr, int family);
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index d5332ddcea3f..4a6009d4486b 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -15,16 +15,20 @@
#include <net/ipv6.h>
#include <linux/atomic.h>
-struct inetpeer_addr_base {
- union {
- __be32 a4;
- __be32 a6[4];
- struct in6_addr in6;
- };
+/* IPv4 address key for cache lookups */
+struct ipv4_addr_key {
+ __be32 addr;
+ int vif;
};
+#define INETPEER_MAXKEYSZ (sizeof(struct in6_addr) / sizeof(u32))
+
struct inetpeer_addr {
- struct inetpeer_addr_base addr;
+ union {
+ struct ipv4_addr_key a4;
+ struct in6_addr a6;
+ u32 key[INETPEER_MAXKEYSZ];
+ };
__u16 family;
};
@@ -65,69 +69,33 @@ struct inet_peer_base {
int total;
};
-#define INETPEER_BASE_BIT 0x1UL
-
-static inline struct inet_peer *inetpeer_ptr(unsigned long val)
-{
- BUG_ON(val & INETPEER_BASE_BIT);
- return (struct inet_peer *) val;
-}
+void inet_peer_base_init(struct inet_peer_base *);
-static inline struct inet_peer_base *inetpeer_base_ptr(unsigned long val)
-{
- if (!(val & INETPEER_BASE_BIT))
- return NULL;
- val &= ~INETPEER_BASE_BIT;
- return (struct inet_peer_base *) val;
-}
+void inet_initpeers(void) __init;
-static inline bool inetpeer_ptr_is_peer(unsigned long val)
-{
- return !(val & INETPEER_BASE_BIT);
-}
+#define INETPEER_METRICS_NEW (~(u32) 0)
-static inline void __inetpeer_ptr_set_peer(unsigned long *val, struct inet_peer *peer)
+static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
{
- /* This implicitly clears INETPEER_BASE_BIT */
- *val = (unsigned long) peer;
+ iaddr->a4.addr = ip;
+ iaddr->family = AF_INET;
}
-static inline bool inetpeer_ptr_set_peer(unsigned long *ptr, struct inet_peer *peer)
+static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
{
- unsigned long val = (unsigned long) peer;
- unsigned long orig = *ptr;
-
- if (!(orig & INETPEER_BASE_BIT) ||
- cmpxchg(ptr, orig, val) != orig)
- return false;
- return true;
+ return iaddr->a4.addr;
}
-static inline void inetpeer_init_ptr(unsigned long *ptr, struct inet_peer_base *base)
+static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
+ struct in6_addr *in6)
{
- *ptr = (unsigned long) base | INETPEER_BASE_BIT;
+ iaddr->a6 = *in6;
+ iaddr->family = AF_INET6;
}
-static inline void inetpeer_transfer_peer(unsigned long *to, unsigned long *from)
+static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
{
- unsigned long val = *from;
-
- *to = val;
- if (inetpeer_ptr_is_peer(val)) {
- struct inet_peer *peer = inetpeer_ptr(val);
- atomic_inc(&peer->refcnt);
- }
-}
-
-void inet_peer_base_init(struct inet_peer_base *);
-
-void inet_initpeers(void) __init;
-
-#define INETPEER_METRICS_NEW (~(u32) 0)
-
-static inline bool inet_metrics_new(const struct inet_peer *p)
-{
- return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW;
+ return &iaddr->a6;
}
/* can be called with or without local BH being disabled */
@@ -137,11 +105,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
__be32 v4daddr,
- int create)
+ int vif, int create)
{
struct inetpeer_addr daddr;
- daddr.addr.a4 = v4daddr;
+ daddr.a4.addr = v4daddr;
+ daddr.a4.vif = vif;
daddr.family = AF_INET;
return inet_getpeer(base, &daddr, create);
}
@@ -152,23 +121,36 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
{
struct inetpeer_addr daddr;
- daddr.addr.in6 = *v6daddr;
+ daddr.a6 = *v6daddr;
daddr.family = AF_INET6;
return inet_getpeer(base, &daddr, create);
}
+static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
+ const struct inetpeer_addr *b)
+{
+ int i, n;
+
+ if (a->family == AF_INET)
+ n = sizeof(a->a4) / sizeof(u32);
+ else
+ n = sizeof(a->a6) / sizeof(u32);
+
+ for (i = 0; i < n; i++) {
+ if (a->key[i] == b->key[i])
+ continue;
+ if (a->key[i] < b->key[i])
+ return -1;
+ return 1;
+ }
+
+ return 0;
+}
+
/* can be called from BH context or outside */
void inet_putpeer(struct inet_peer *p);
bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
void inetpeer_invalidate_tree(struct inet_peer_base *);
-/*
- * temporary check to make sure we dont access rid, tcp_ts,
- * tcp_ts_stamp if no refcount is taken on inet_peer
- */
-static inline void inet_peer_refcheck(const struct inet_peer *p)
-{
- WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
-}
#endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index d5fe9f2ab699..9b9ca2839399 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -202,10 +202,20 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
#define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd)
#define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)
+u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offct);
unsigned long snmp_fold_field(void __percpu *mib, int offt);
#if BITS_PER_LONG==32
+u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
+ size_t syncp_offset);
u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off);
#else
+static inline u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
+ size_t syncp_offset)
+{
+ return snmp_get_cpu_field(mib, cpu, offct);
+
+}
+
static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off)
{
return snmp_fold_field(mib, offt);
@@ -370,22 +380,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
-static inline void inet_set_txhash(struct sock *sk)
-{
- struct inet_sock *inet = inet_sk(sk);
- struct flow_keys keys;
-
- memset(&keys, 0, sizeof(keys));
-
- keys.addrs.v4addrs.src = inet->inet_saddr;
- keys.addrs.v4addrs.dst = inet->inet_daddr;
- keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
- keys.ports.src = inet->inet_sport;
- keys.ports.dst = inet->inet_dport;
-
- sk->sk_txhash = flow_hash_from_keys(&keys);
-}
-
static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto)
{
const struct iphdr *iph = skb_gro_network_header(skb);
@@ -474,6 +468,11 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
#endif
+static inline unsigned int ipv4_addr_hash(__be32 ip)
+{
+ return (__force unsigned int) ip;
+}
+
bool ip_call_ra_chain(struct sk_buff *skb);
/*
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3b76849c190f..063d30474cf6 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -51,6 +51,8 @@ struct fib6_config {
struct nlattr *fc_mp;
struct nl_info fc_nlinfo;
+ struct nlattr *fc_encap;
+ u16 fc_encap_type;
};
struct fib6_node {
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5fa643b4e891..a37d0432bebd 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -44,7 +44,9 @@ struct fib_config {
u32 fc_flow;
u32 fc_nlflags;
struct nl_info fc_nlinfo;
- };
+ struct nlattr *fc_encap;
+ u16 fc_encap_type;
+};
struct fib_info;
struct rtable;
@@ -89,6 +91,7 @@ struct fib_nh {
struct rtable __rcu * __percpu *nh_pcpu_rth_output;
struct rtable __rcu *nh_rth_input;
struct fnhe_hash_bucket __rcu *nh_exceptions;
+ struct lwtunnel_state *nh_lwtstate;
};
/*
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8214cb88bbc..9a6a3ba888e8 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -4,14 +4,15 @@
#include <linux/if_tunnel.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <linux/socket.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/netns/generic.h>
#include <net/rtnetlink.h>
+#include <net/lwtunnel.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
@@ -22,6 +23,44 @@
/* Keep error state on tunnel for 30 sec */
#define IPTUNNEL_ERR_TIMEO (30*HZ)
+/* Used to memset ip_tunnel padding. */
+#define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst)
+
+/* Used to memset ipv4 address padding. */
+#define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst)
+#define IP_TUNNEL_KEY_IPV4_PAD_LEN \
+ (FIELD_SIZEOF(struct ip_tunnel_key, u) - \
+ FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))
+
+struct ip_tunnel_key {
+ __be64 tun_id;
+ union {
+ struct {
+ __be32 src;
+ __be32 dst;
+ } ipv4;
+ struct {
+ struct in6_addr src;
+ struct in6_addr dst;
+ } ipv6;
+ } u;
+ __be16 tun_flags;
+ u8 tos; /* TOS for IPv4, TC for IPv6 */
+ u8 ttl; /* TTL for IPv4, HL for IPv6 */
+ __be16 tp_src;
+ __be16 tp_dst;
+};
+
+/* Flags for ip_tunnel_info mode. */
+#define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */
+#define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */
+
+struct ip_tunnel_info {
+ struct ip_tunnel_key key;
+ u8 options_len;
+ u8 mode;
+};
+
/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
@@ -33,8 +72,8 @@ struct ip_tunnel_6rd_parm {
#endif
struct ip_tunnel_encap {
- __u16 type;
- __u16 flags;
+ u16 type;
+ u16 flags;
__be16 sport;
__be16 dport;
};
@@ -51,6 +90,8 @@ struct ip_tunnel_dst {
__be32 saddr;
};
+struct metadata_dst;
+
struct ip_tunnel {
struct ip_tunnel __rcu *next;
struct hlist_node hash_node;
@@ -62,8 +103,8 @@ struct ip_tunnel {
* arrived */
/* These four fields used only by GRE */
- __u32 i_seqno; /* The last seen seqno */
- __u32 o_seqno; /* The last output seqno */
+ u32 i_seqno; /* The last seen seqno */
+ u32 o_seqno; /* The last output seqno */
int tun_hlen; /* Precalculated header length */
int mlink;
@@ -84,6 +125,7 @@ struct ip_tunnel {
unsigned int prl_count; /* # of entries in PRL */
int ip_tnl_net_id;
struct gro_cells gro_cells;
+ bool collect_md;
};
#define TUNNEL_CSUM __cpu_to_be16(0x01)
@@ -118,6 +160,7 @@ struct tnl_ptk_info {
struct ip_tunnel_net {
struct net_device *fb_tunnel_dev;
struct hlist_head tunnels[IP_TNL_HASH_SIZE];
+ struct ip_tunnel __rcu *collect_md_tun;
};
struct ip_tunnel_encap_ops {
@@ -136,6 +179,40 @@ int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
unsigned int num);
+static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
+ __be32 saddr, __be32 daddr,
+ u8 tos, u8 ttl,
+ __be16 tp_src, __be16 tp_dst,
+ __be64 tun_id, __be16 tun_flags)
+{
+ key->tun_id = tun_id;
+ key->u.ipv4.src = saddr;
+ key->u.ipv4.dst = daddr;
+ memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD,
+ 0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
+ key->tos = tos;
+ key->ttl = ttl;
+ key->tun_flags = tun_flags;
+
+ /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+ * the upper tunnel are used.
+ * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+ */
+ key->tp_src = tp_src;
+ key->tp_dst = tp_dst;
+
+ /* Clear struct padding. */
+ if (sizeof(*key) != IP_TUNNEL_KEY_SIZE)
+ memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE,
+ 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
+}
+
+static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
+ *tun_info)
+{
+ return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET;
+}
+
#ifdef CONFIG_INET
int ip_tunnel_init(struct net_device *dev);
@@ -163,7 +240,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
__be32 key);
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
- const struct tnl_ptk_info *tpi, bool log_ecn_error);
+ const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
+ 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[],
@@ -196,8 +274,8 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
- __be32 src, __be32 dst, __u8 proto,
- __u8 tos, __u8 ttl, __be16 df, bool xnet);
+ __be32 src, __be32 dst, u8 proto,
+ u8 tos, u8 ttl, __be16 df, bool xnet);
struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
int gso_type_mask);
@@ -221,6 +299,57 @@ static inline void iptunnel_xmit_stats(int err,
}
}
+static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info)
+{
+ return info + 1;
+}
+
+static inline void ip_tunnel_info_opts_get(void *to,
+ const struct ip_tunnel_info *info)
+{
+ memcpy(to, info + 1, info->options_len);
+}
+
+static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
+ const void *from, int len)
+{
+ memcpy(ip_tunnel_info_opts(info), from, len);
+ info->options_len = len;
+}
+
+static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
+{
+ return (struct ip_tunnel_info *)lwtstate->data;
+}
+
+extern struct static_key ip_tunnel_metadata_cnt;
+
+/* Returns > 0 if metadata should be collected */
+static inline int ip_tunnel_collect_metadata(void)
+{
+ return static_key_false(&ip_tunnel_metadata_cnt);
+}
+
+void __init ip_tunnel_core_init(void);
+
+void ip_tunnel_need_metadata(void);
+void ip_tunnel_unneed_metadata(void);
+
+#else /* CONFIG_INET */
+
+static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
+{
+ return NULL;
+}
+
+static inline void ip_tunnel_need_metadata(void)
+{
+}
+
+static inline void ip_tunnel_unneed_metadata(void)
+{
+}
+
#endif /* CONFIG_INET */
#endif /* __NET_IP_TUNNELS_H */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4e3731ee4eac..9b9ca87a4210 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -846,6 +846,17 @@ struct ipvs_master_sync_state {
/* How much time to keep dests in trash */
#define IP_VS_DEST_TRASH_PERIOD (120 * HZ)
+struct ipvs_sync_daemon_cfg {
+ union nf_inet_addr mcast_group;
+ int syncid;
+ u16 sync_maxlen;
+ u16 mcast_port;
+ u8 mcast_af;
+ u8 mcast_ttl;
+ /* multicast interface name */
+ char mcast_ifn[IP_VS_IFNAME_MAXLEN];
+};
+
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
@@ -961,15 +972,10 @@ struct netns_ipvs {
spinlock_t sync_buff_lock;
struct task_struct **backup_threads;
int threads_mask;
- int send_mesg_maxlen;
- int recv_mesg_maxlen;
volatile int sync_state;
- volatile int master_syncid;
- volatile int backup_syncid;
struct mutex sync_mutex;
- /* multicast interface name */
- char master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
- char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+ struct ipvs_sync_daemon_cfg mcfg; /* Master Configuration */
+ struct ipvs_sync_daemon_cfg bcfg; /* Backup Configuration */
/* net name space ptr */
struct net *net; /* Needed by timer routines */
/* Number of heterogeneous destinations, needed becaus heterogeneous
@@ -1408,7 +1414,8 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
/* IPVS sync daemon data and function prototypes
* (from ip_vs_sync.c)
*/
-int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid);
+int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *cfg,
+ int state);
int stop_sync_thread(struct net *net, int state);
void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 82dbdb092a5d..711cca428cc8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -707,54 +707,69 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
}
#if IS_ENABLED(CONFIG_IPV6)
-static inline void ip6_set_txhash(struct sock *sk)
-{
- struct inet_sock *inet = inet_sk(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct flow_keys keys;
- memset(&keys, 0, sizeof(keys));
+/* Sysctl settings for net ipv6.auto_flowlabels */
+#define IP6_AUTO_FLOW_LABEL_OFF 0
+#define IP6_AUTO_FLOW_LABEL_OPTOUT 1
+#define IP6_AUTO_FLOW_LABEL_OPTIN 2
+#define IP6_AUTO_FLOW_LABEL_FORCED 3
- memcpy(&keys.addrs.v6addrs.src, &np->saddr,
- sizeof(keys.addrs.v6addrs.src));
- memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr,
- sizeof(keys.addrs.v6addrs.dst));
- keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
- keys.ports.src = inet->inet_sport;
- keys.ports.dst = inet->inet_dport;
+#define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED
- sk->sk_txhash = flow_hash_from_keys(&keys);
-}
+#define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT
static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
- __be32 flowlabel, bool autolabel)
+ __be32 flowlabel, bool autolabel,
+ struct flowi6 *fl6)
{
- if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
- u32 hash;
+ u32 hash;
+
+ if (flowlabel ||
+ net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
+ (!autolabel &&
+ net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED))
+ return flowlabel;
- hash = skb_get_hash(skb);
+ hash = skb_get_hash_flowi6(skb, fl6);
- /* Since this is being sent on the wire obfuscate hash a bit
- * to minimize possbility that any useful information to an
- * attacker is leaked. Only lower 20 bits are relevant.
- */
- hash ^= hash >> 12;
+ /* Since this is being sent on the wire obfuscate hash a bit
+ * to minimize possbility that any useful information to an
+ * attacker is leaked. Only lower 20 bits are relevant.
+ */
+ rol32(hash, 16);
- flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
+ flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
- if (net->ipv6.sysctl.flowlabel_state_ranges)
- flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG;
- }
+ if (net->ipv6.sysctl.flowlabel_state_ranges)
+ flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG;
return flowlabel;
}
+
+static inline int ip6_default_np_autolabel(struct net *net)
+{
+ switch (net->ipv6.sysctl.auto_flowlabels) {
+ case IP6_AUTO_FLOW_LABEL_OFF:
+ case IP6_AUTO_FLOW_LABEL_OPTIN:
+ default:
+ return 0;
+ case IP6_AUTO_FLOW_LABEL_OPTOUT:
+ case IP6_AUTO_FLOW_LABEL_FORCED:
+ return 1;
+ }
+}
#else
static inline void ip6_set_txhash(struct sock *sk) { }
static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
- __be32 flowlabel, bool autolabel)
+ __be32 flowlabel, bool autolabel,
+ struct flowi6 *fl6)
{
return flowlabel;
}
+static inline int ip6_default_np_autolabel(struct net *net)
+{
+ return 0;
+}
#endif
@@ -832,7 +847,8 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
&inet6_sk(sk)->cork);
}
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6);
+int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
+ struct flowi6 *fl6);
struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst);
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
new file mode 100644
index 000000000000..fce0e35e74d0
--- /dev/null
+++ b/include/net/lwtunnel.h
@@ -0,0 +1,175 @@
+#ifndef __NET_LWTUNNEL_H
+#define __NET_LWTUNNEL_H 1
+
+#include <linux/lwtunnel.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/route.h>
+
+#define LWTUNNEL_HASH_BITS 7
+#define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS)
+
+/* lw tunnel state flags */
+#define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0)
+#define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1)
+
+struct lwtunnel_state {
+ __u16 type;
+ __u16 flags;
+ atomic_t refcnt;
+ int (*orig_output)(struct sock *sk, struct sk_buff *skb);
+ int (*orig_input)(struct sk_buff *);
+ int len;
+ __u8 data[0];
+};
+
+struct lwtunnel_encap_ops {
+ int (*build_state)(struct net_device *dev, struct nlattr *encap,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **ts);
+ int (*output)(struct sock *sk, struct sk_buff *skb);
+ int (*input)(struct sk_buff *skb);
+ int (*fill_encap)(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate);
+ int (*get_encap_size)(struct lwtunnel_state *lwtstate);
+ int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
+};
+
+#ifdef CONFIG_LWTUNNEL
+static inline void lwtstate_free(struct lwtunnel_state *lws)
+{
+ kfree(lws);
+}
+
+static inline struct lwtunnel_state *
+lwtstate_get(struct lwtunnel_state *lws)
+{
+ if (lws)
+ atomic_inc(&lws->refcnt);
+
+ return lws;
+}
+
+static inline void lwtstate_put(struct lwtunnel_state *lws)
+{
+ if (!lws)
+ return;
+
+ if (atomic_dec_and_test(&lws->refcnt))
+ lwtstate_free(lws);
+}
+
+static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
+{
+ if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT))
+ return true;
+
+ return false;
+}
+
+static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate)
+{
+ if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT))
+ return true;
+
+ return false;
+}
+int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
+ unsigned int num);
+int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
+ unsigned int num);
+int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
+ struct nlattr *encap,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **lws);
+int lwtunnel_fill_encap(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate);
+int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
+struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
+int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
+int lwtunnel_output(struct sock *sk, struct sk_buff *skb);
+int lwtunnel_input(struct sk_buff *skb);
+
+#else
+
+static inline void lwtstate_free(struct lwtunnel_state *lws)
+{
+}
+
+static inline struct lwtunnel_state *
+lwtstate_get(struct lwtunnel_state *lws)
+{
+ return lws;
+}
+
+static inline void lwtstate_put(struct lwtunnel_state *lws)
+{
+}
+
+static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
+{
+ return false;
+}
+
+static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate)
+{
+ return false;
+}
+
+static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
+ unsigned int num)
+{
+ return -EOPNOTSUPP;
+
+}
+
+static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
+ unsigned int num)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
+ struct nlattr *encap,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **lws)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_fill_encap(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate)
+{
+ return 0;
+}
+
+static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate)
+{
+ return 0;
+}
+
+static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len)
+{
+ return NULL;
+}
+
+static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a,
+ struct lwtunnel_state *b)
+{
+ return 0;
+}
+
+static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_input(struct sk_buff *skb)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* __NET_LWTUNNEL_H */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 6b1077c2a63f..e3314e516681 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -973,6 +973,10 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
* @RX_FLAG_IV_STRIPPED: The IV/ICV are stripped from this frame.
* If this flag is set, the stack cannot do any replay detection
* hence the driver or hardware will have to do that.
+ * @RX_FLAG_PN_VALIDATED: Currently only valid for CCMP/GCMP frames, this
+ * flag indicates that the PN was verified for replay protection.
+ * Note that this flag is also currently only supported when a frame
+ * is also decrypted (ie. @RX_FLAG_DECRYPTED must be set)
* @RX_FLAG_FAILED_FCS_CRC: Set this flag if the FCS check failed on
* the frame.
* @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
@@ -997,9 +1001,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
* @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference
* number (@ampdu_reference) must be populated and be a distinct number for
* each A-MPDU
- * @RX_FLAG_AMPDU_REPORT_ZEROLEN: driver reports 0-length subframes
- * @RX_FLAG_AMPDU_IS_ZEROLEN: This is a zero-length subframe, for
- * monitoring purposes only
* @RX_FLAG_AMPDU_LAST_KNOWN: last subframe is known, should be set on all
* subframes of a single A-MPDU
* @RX_FLAG_AMPDU_IS_LAST: this subframe is the last subframe of the A-MPDU
@@ -1039,8 +1040,8 @@ enum mac80211_rx_flags {
RX_FLAG_NO_SIGNAL_VAL = BIT(12),
RX_FLAG_HT_GF = BIT(13),
RX_FLAG_AMPDU_DETAILS = BIT(14),
- RX_FLAG_AMPDU_REPORT_ZEROLEN = BIT(15),
- RX_FLAG_AMPDU_IS_ZEROLEN = BIT(16),
+ RX_FLAG_PN_VALIDATED = BIT(15),
+ /* bit 16 free */
RX_FLAG_AMPDU_LAST_KNOWN = BIT(17),
RX_FLAG_AMPDU_IS_LAST = BIT(18),
RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(19),
@@ -1491,8 +1492,10 @@ enum ieee80211_key_flags {
* - Temporal Authenticator Rx MIC Key (64 bits)
* @icv_len: The ICV length for this key type
* @iv_len: The IV length for this key type
+ * @drv_priv: pointer for driver use
*/
struct ieee80211_key_conf {
+ void *drv_priv;
atomic64_t tx_pn;
u32 cipher;
u8 icv_len;
@@ -1675,7 +1678,6 @@ struct ieee80211_sta_rates {
* @tdls: indicates whether the STA is a TDLS peer
* @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only
* valid if the STA is a TDLS peer in the first place.
- * @mfp: indicates whether the STA uses management frame protection or not.
* @txq: per-TID data TX queues (if driver uses the TXQ abstraction)
*/
struct ieee80211_sta {
@@ -1693,7 +1695,6 @@ struct ieee80211_sta {
struct ieee80211_sta_rates __rcu *rates;
bool tdls;
bool tdls_initiator;
- bool mfp;
struct ieee80211_txq *txq[IEEE80211_NUM_TIDS];
@@ -1888,6 +1889,9 @@ struct ieee80211_txq {
* @IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands
* in one command, mac80211 doesn't have to run separate scans per band.
*
+ * @IEEE80211_HW_TDLS_WIDER_BW: The device/driver supports wider bandwidth
+ * than then BSS bandwidth for a TDLS link on the base channel.
+ *
* @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
*/
enum ieee80211_hw_flags {
@@ -1920,6 +1924,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_CHANCTX_STA_CSA,
IEEE80211_HW_SUPPORTS_CLONED_SKBS,
IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS,
+ IEEE80211_HW_TDLS_WIDER_BW,
/* keep last, obviously */
NUM_IEEE80211_HW_FLAGS
@@ -3696,20 +3701,28 @@ void ieee80211_free_hw(struct ieee80211_hw *hw);
void ieee80211_restart_hw(struct ieee80211_hw *hw);
/**
- * ieee80211_napi_add - initialize mac80211 NAPI context
- * @hw: the hardware to initialize the NAPI context on
- * @napi: the NAPI context to initialize
- * @napi_dev: dummy NAPI netdevice, here to not waste the space if the
- * driver doesn't use NAPI
- * @poll: poll function
- * @weight: default weight
+ * ieee80211_rx_napi - receive frame from NAPI context
+ *
+ * Use this function to hand received frames to mac80211. The receive
+ * buffer in @skb must start with an IEEE 802.11 header. In case of a
+ * paged @skb is used, the driver is recommended to put the ieee80211
+ * header of the frame on the linear part of the @skb to avoid memory
+ * allocation and/or memcpy by the stack.
+ *
+ * This function may not be called in IRQ context. Calls to this function
+ * for a single hardware must be synchronized against each other. Calls to
+ * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be
+ * mixed for a single hardware. Must not run concurrently with
+ * ieee80211_tx_status() or ieee80211_tx_status_ni().
+ *
+ * This function must be called with BHs disabled.
*
- * See also netif_napi_add().
+ * @hw: the hardware this frame came in on
+ * @skb: the buffer to receive, owned by mac80211 after this call
+ * @napi: the NAPI context
*/
-void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi,
- struct net_device *napi_dev,
- int (*poll)(struct napi_struct *, int),
- int weight);
+void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb,
+ struct napi_struct *napi);
/**
* ieee80211_rx - receive frame
@@ -3731,7 +3744,10 @@ void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi,
* @hw: the hardware this frame came in on
* @skb: the buffer to receive, owned by mac80211 after this call
*/
-void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb);
+static inline void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
+ ieee80211_rx_napi(hw, skb, NULL);
+}
/**
* ieee80211_rx_irqsafe - receive frame
@@ -4315,19 +4331,6 @@ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf,
struct sk_buff *skb, u8 *p2k);
/**
- * ieee80211_aes_cmac_calculate_k1_k2 - calculate the AES-CMAC sub keys
- *
- * This function computes the two AES-CMAC sub-keys, based on the
- * previously installed master key.
- *
- * @keyconf: the parameter passed with the set key
- * @k1: a buffer to be filled with the 1st sub-key
- * @k2: a buffer to be filled with the 2nd sub-key
- */
-void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
- u8 *k1, u8 *k2);
-
-/**
* ieee80211_get_key_tx_seq - get key TX sequence counter
*
* @keyconf: the parameter passed with the set key
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index f534a46911dc..b7f99615224b 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -321,23 +321,6 @@ int ieee802154_register_hw(struct ieee802154_hw *hw);
void ieee802154_unregister_hw(struct ieee802154_hw *hw);
/**
- * ieee802154_rx - receive frame
- *
- * Use this function to hand received frames to mac802154. The receive
- * buffer in @skb must start with an IEEE 802.15.4 header. In case of a
- * paged @skb is used, the driver is recommended to put the ieee802154
- * header of the frame on the linear part of the @skb to avoid memory
- * allocation and/or memcpy by the stack.
- *
- * This function may not be called in IRQ context. Calls to this function
- * for a single hardware must be synchronized against each other.
- *
- * @hw: the hardware this frame came in on
- * @skb: the buffer to receive, owned by mac802154 after this call
- */
-void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb);
-
-/**
* ieee802154_rx_irqsafe - receive frame
*
* Like ieee802154_rx() but can be called in IRQ context
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
new file mode 100644
index 000000000000..4757997f76ed
--- /dev/null
+++ b/include/net/mpls_iptunnel.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2015 Cumulus Networks, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _NET_MPLS_IPTUNNEL_H
+#define _NET_MPLS_IPTUNNEL_H 1
+
+#define MAX_NEW_LABELS 2
+
+struct mpls_iptunnel_encap {
+ u32 label[MAX_NEW_LABELS];
+ u32 labels;
+};
+
+static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
+{
+ return (struct mpls_iptunnel_encap *)lwtstate->data;
+}
+
+#endif
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index b3a7751251b4..aba5695fadb0 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -182,7 +182,8 @@ int ndisc_rcv(struct sk_buff *skb);
void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr);
+ const struct in6_addr *daddr, const struct in6_addr *saddr,
+ struct sk_buff *oskb);
void ndisc_send_rs(struct net_device *dev,
const struct in6_addr *saddr, const struct in6_addr *daddr);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index bd33e66f49aa..8b683841e574 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -125,6 +125,7 @@ struct neigh_statistics {
unsigned long forced_gc_runs; /* number of forced GC runs */
unsigned long unres_discards; /* number of unresolved drops */
+ unsigned long table_fulls; /* times even gc couldn't help */
};
#define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index e951453e0a23..2dcea635ecce 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -118,6 +118,9 @@ struct net {
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
+#if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT)
+ struct list_head nfnl_acct_list;
+#endif
#endif
#ifdef CONFIG_WEXT_CORE
struct sk_buff_head wext_nlevents;
diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h
new file mode 100644
index 000000000000..42008f10dfc4
--- /dev/null
+++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h
@@ -0,0 +1,7 @@
+#ifndef _NF_DUP_IPV4_H_
+#define _NF_DUP_IPV4_H_
+
+void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum,
+ const struct in_addr *gw, int oif);
+
+#endif /* _NF_DUP_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h
new file mode 100644
index 000000000000..ed6bd66fa5a0
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h
@@ -0,0 +1,7 @@
+#ifndef _NF_DUP_IPV6_H_
+#define _NF_DUP_IPV6_H_
+
+void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum,
+ const struct in6_addr *gw, int oif);
+
+#endif /* _NF_DUP_IPV6_H_ */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37cd3911d5c5..f5e23c6dee8b 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -250,8 +250,12 @@ void nf_ct_untracked_status_or(unsigned long bits);
void nf_ct_iterate_cleanup(struct net *net,
int (*iter)(struct nf_conn *i, void *data),
void *data, u32 portid, int report);
+
+struct nf_conntrack_zone;
+
void nf_conntrack_free(struct nf_conn *ct);
-struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
+struct nf_conn *nf_conntrack_alloc(struct net *net,
+ const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *orig,
const struct nf_conntrack_tuple *repl,
gfp_t gfp);
@@ -291,7 +295,9 @@ extern unsigned int nf_conntrack_max;
extern unsigned int nf_conntrack_hash_rnd;
void init_nf_conntrack_hash_rnd(void);
-struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
+ const struct nf_conntrack_zone *zone,
+ gfp_t flags);
#define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count)
#define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index f2f0fa3bb150..c03f9c42b3cd 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -52,7 +52,8 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
/* Find a connection corresponding to a tuple. */
struct nf_conntrack_tuple_hash *
-nf_conntrack_find_get(struct net *net, u16 zone,
+nf_conntrack_find_get(struct net *net,
+ const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple);
int __nf_conntrack_confirm(struct sk_buff *skb);
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 3f3aecbc8632..dce56f09ac9a 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -4,7 +4,9 @@
#ifndef _NF_CONNTRACK_EXPECT_H
#define _NF_CONNTRACK_EXPECT_H
+
#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_zones.h>
extern unsigned int nf_ct_expect_hsize;
extern unsigned int nf_ct_expect_max;
@@ -76,15 +78,18 @@ int nf_conntrack_expect_init(void);
void nf_conntrack_expect_fini(void);
struct nf_conntrack_expect *
-__nf_ct_expect_find(struct net *net, u16 zone,
+__nf_ct_expect_find(struct net *net,
+ const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
-nf_ct_expect_find_get(struct net *net, u16 zone,
+nf_ct_expect_find_get(struct net *net,
+ const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
-nf_ct_find_expectation(struct net *net, u16 zone,
+nf_ct_find_expectation(struct net *net,
+ const struct nf_conntrack_zone *zone,
const struct nf_conntrack_tuple *tuple);
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index dec6336bf850..7e2b1d025f50 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -54,7 +54,11 @@ int nf_connlabels_replace(struct nf_conn *ct,
#ifdef CONFIG_NF_CONNTRACK_LABELS
int nf_conntrack_labels_init(void);
void nf_conntrack_labels_fini(void);
+int nf_connlabels_get(struct net *net, unsigned int n_bits);
+void nf_connlabels_put(struct net *net);
#else
static inline int nf_conntrack_labels_init(void) { return 0; }
static inline void nf_conntrack_labels_fini(void) {}
+static inline int nf_connlabels_get(struct net *net, unsigned int n_bits) { return 0; }
+static inline void nf_connlabels_put(struct net *net) {}
#endif
diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h
index 034efe8d45a5..4e32512cef32 100644
--- a/include/net/netfilter/nf_conntrack_zones.h
+++ b/include/net/netfilter/nf_conntrack_zones.h
@@ -1,25 +1,89 @@
#ifndef _NF_CONNTRACK_ZONES_H
#define _NF_CONNTRACK_ZONES_H
-#define NF_CT_DEFAULT_ZONE 0
+#include <linux/netfilter/nf_conntrack_zones_common.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack_extend.h>
-struct nf_conntrack_zone {
- u16 id;
-};
+static inline const struct nf_conntrack_zone *
+nf_ct_zone(const struct nf_conn *ct)
+{
+ const struct nf_conntrack_zone *nf_ct_zone = NULL;
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE);
+#endif
+ return nf_ct_zone ? nf_ct_zone : &nf_ct_zone_dflt;
+}
+
+static inline const struct nf_conntrack_zone *
+nf_ct_zone_init(struct nf_conntrack_zone *zone, u16 id, u8 dir, u8 flags)
+{
+ zone->id = id;
+ zone->flags = flags;
+ zone->dir = dir;
+
+ return zone;
+}
+
+static inline const struct nf_conntrack_zone *
+nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb,
+ struct nf_conntrack_zone *tmp)
+{
+ const struct nf_conntrack_zone *zone;
+
+ if (!tmpl)
+ return &nf_ct_zone_dflt;
+
+ zone = nf_ct_zone(tmpl);
+ if (zone->flags & NF_CT_FLAG_MARK)
+ zone = nf_ct_zone_init(tmp, skb->mark, zone->dir, 0);
+
+ return zone;
+}
-static inline u16 nf_ct_zone(const struct nf_conn *ct)
+static inline int nf_ct_zone_add(struct nf_conn *ct, gfp_t flags,
+ const struct nf_conntrack_zone *info)
{
#ifdef CONFIG_NF_CONNTRACK_ZONES
struct nf_conntrack_zone *nf_ct_zone;
- nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE);
- if (nf_ct_zone)
- return nf_ct_zone->id;
+
+ nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, flags);
+ if (!nf_ct_zone)
+ return -ENOMEM;
+
+ nf_ct_zone_init(nf_ct_zone, info->id, info->dir,
+ info->flags);
#endif
- return NF_CT_DEFAULT_ZONE;
+ return 0;
}
-#endif /* CONFIG_NF_CONNTRACK || CONFIG_NF_CONNTRACK_MODULE */
+static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone,
+ enum ip_conntrack_dir dir)
+{
+ return zone->dir & (1 << dir);
+}
+
+static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone,
+ enum ip_conntrack_dir dir)
+{
+ return nf_ct_zone_matches_dir(zone, dir) ?
+ zone->id : NF_CT_DEFAULT_ZONE_ID;
+}
+
+static inline bool nf_ct_zone_equal(const struct nf_conn *a,
+ const struct nf_conntrack_zone *b,
+ enum ip_conntrack_dir dir)
+{
+ return nf_ct_zone_id(nf_ct_zone(a), dir) ==
+ nf_ct_zone_id(b, dir);
+}
+
+static inline bool nf_ct_zone_equal_any(const struct nf_conn *a,
+ const struct nf_conntrack_zone *b)
+{
+ return nf_ct_zone(a)->id == b->id;
+}
+#endif /* IS_ENABLED(CONFIG_NF_CONNTRACK) */
#endif /* _NF_CONNTRACK_ZONES_H */
diff --git a/include/net/netfilter/nft_dup.h b/include/net/netfilter/nft_dup.h
new file mode 100644
index 000000000000..6b84cf6491a2
--- /dev/null
+++ b/include/net/netfilter/nft_dup.h
@@ -0,0 +1,9 @@
+#ifndef _NFT_DUP_H_
+#define _NFT_DUP_H_
+
+struct nft_dup_inet {
+ enum nft_registers sreg_addr:8;
+ enum nft_registers sreg_dev:8;
+};
+
+#endif /* _NFT_DUP_H_ */
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 8d93544a2d2b..c0368db6df54 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -31,6 +31,7 @@ struct netns_sysctl_ipv6 {
int auto_flowlabels;
int icmpv6_time;
int anycast_src_echo_reply;
+ int ip_nonlocal_bind;
int fwmark_reflect;
int idgen_retries;
int idgen_delay;
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
index 532e4ba64f49..38aa4983e2a9 100644
--- a/include/net/netns/netfilter.h
+++ b/include/net/netns/netfilter.h
@@ -14,5 +14,6 @@ struct netns_nf {
#ifdef CONFIG_SYSCTL
struct ctl_table_header *nf_log_dir_header;
#endif
+ struct list_head hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
};
#endif
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 01fc8c531115..d0d0f1e53bb9 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -79,6 +79,7 @@ struct nci_ops {
int (*close)(struct nci_dev *ndev);
int (*send)(struct nci_dev *ndev, struct sk_buff *skb);
int (*setup)(struct nci_dev *ndev);
+ int (*post_setup)(struct nci_dev *ndev);
int (*fw_download)(struct nci_dev *ndev, const char *firmware_name);
__u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol);
int (*discover_se)(struct nci_dev *ndev);
@@ -277,6 +278,8 @@ int nci_request(struct nci_dev *ndev,
unsigned long opt),
unsigned long opt, __u32 timeout);
int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload);
+int nci_core_reset(struct nci_dev *ndev);
+int nci_core_init(struct nci_dev *ndev);
int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb);
int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index f9e58ae45f9c..30afc9a6718c 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -203,6 +203,7 @@ struct nfc_dev {
int n_vendor_cmds;
struct nfc_ops *ops;
+ struct genl_info *cur_cmd_info;
};
#define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev)
@@ -318,4 +319,44 @@ static inline int nfc_set_vendor_cmds(struct nfc_dev *dev,
return 0;
}
+struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev,
+ enum nfc_attrs attr,
+ u32 oui, u32 subcmd,
+ int approxlen);
+int nfc_vendor_cmd_reply(struct sk_buff *skb);
+
+/**
+ * nfc_vendor_cmd_alloc_reply_skb - allocate vendor command reply
+ * @dev: nfc device
+ * @oui: vendor oui
+ * @approxlen: an upper bound of the length of the data that will
+ * be put into the skb
+ *
+ * This function allocates and pre-fills an skb for a reply to
+ * a vendor command. Since it is intended for a reply, calling
+ * it outside of a vendor command's doit() operation is invalid.
+ *
+ * The returned skb is pre-filled with some identifying data in
+ * a way that any data that is put into the skb (with skb_put(),
+ * nla_put() or similar) will end up being within the
+ * %NFC_ATTR_VENDOR_DATA attribute, so all that needs to be done
+ * with the skb is adding data for the corresponding userspace tool
+ * which can then read that data out of the vendor data attribute.
+ * You must not modify the skb in any other way.
+ *
+ * When done, call nfc_vendor_cmd_reply() with the skb and return
+ * its error code as the result of the doit() operation.
+ *
+ * Return: An allocated and pre-filled skb. %NULL if any errors happen.
+ */
+static inline struct sk_buff *
+nfc_vendor_cmd_alloc_reply_skb(struct nfc_dev *dev,
+ u32 oui, u32 subcmd, int approxlen)
+{
+ return __nfc_alloc_vendor_cmd_reply_skb(dev,
+ NFC_ATTR_VENDOR_DATA,
+ oui,
+ subcmd, approxlen);
+}
+
#endif /* __NET_NFC_H */
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index b0ab530d28cd..cf2713d8b975 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -52,6 +52,8 @@ enum nl802154_commands {
NL802154_CMD_SET_LBT_MODE,
+ NL802154_CMD_SET_ACKREQ_DEFAULT,
+
/* add new commands above here */
/* used to define NL802154_CMD_MAX below */
@@ -104,6 +106,8 @@ enum nl802154_attrs {
NL802154_ATTR_SUPPORTED_COMMANDS,
+ NL802154_ATTR_ACKREQ_DEFAULT,
+
/* add attributes here, update the policy in nl802154.c */
__NL802154_ATTR_AFTER_LAST,
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 2342bf12cb78..401038d2f9b8 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -110,10 +110,8 @@ static inline void qdisc_run(struct Qdisc *q)
__qdisc_run(q);
}
-int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res);
int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res);
+ struct tcf_result *res, bool compat_mode);
static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
{
diff --git a/include/net/route.h b/include/net/route.h
index fe22d03afb6a..cc61cb95f059 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -188,8 +188,12 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
void ip_rt_send_redirect(struct sk_buff *skb);
unsigned int inet_addr_type(struct net *net, __be32 addr);
+unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr);
+unsigned int inet_addr_type_dev_table(struct net *net,
+ const struct net_device *dev,
+ __be32 addr);
void ip_rt_multicast_event(struct in_device *);
int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
@@ -250,6 +254,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
if (inet_sk(sk)->transparent)
flow_flags |= FLOWI_FLAG_ANYSRC;
+ if (netif_index_is_vrf(sock_net(sk), oif))
+ flow_flags |= FLOWI_FLAG_VRFSRC;
+
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
protocol, flow_flags, dst, src, dport, sport);
}
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 343d922d15c2..18fdb98185ab 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -141,6 +141,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
unsigned char name_assign_type,
const struct rtnl_link_ops *ops,
struct nlattr *tb[]);
+int rtnl_delete_link(struct net_device *dev);
int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 2738f6f87908..444faa89a55f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -340,6 +340,7 @@ extern struct Qdisc noop_qdisc;
extern struct Qdisc_ops noop_qdisc_ops;
extern struct Qdisc_ops pfifo_fast_ops;
extern struct Qdisc_ops mq_qdisc_ops;
+extern struct Qdisc_ops noqueue_qdisc_ops;
extern const struct Qdisc_ops *default_qdisc_ops;
struct Qdisc_class_common {
@@ -513,17 +514,20 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
}
-static inline void qdisc_bstats_update_cpu(struct Qdisc *sch,
- const struct sk_buff *skb)
+static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats,
+ const struct sk_buff *skb)
{
- struct gnet_stats_basic_cpu *bstats =
- this_cpu_ptr(sch->cpu_bstats);
-
u64_stats_update_begin(&bstats->syncp);
bstats_update(&bstats->bstats, skb);
u64_stats_update_end(&bstats->syncp);
}
+static inline void qdisc_bstats_cpu_update(struct Qdisc *sch,
+ const struct sk_buff *skb)
+{
+ bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb);
+}
+
static inline void qdisc_bstats_update(struct Qdisc *sch,
const struct sk_buff *skb)
{
@@ -547,16 +551,24 @@ static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count)
sch->qstats.drops += count;
}
-static inline void qdisc_qstats_drop(struct Qdisc *sch)
+static inline void qstats_drop_inc(struct gnet_stats_queue *qstats)
{
- sch->qstats.drops++;
+ qstats->drops++;
}
-static inline void qdisc_qstats_drop_cpu(struct Qdisc *sch)
+static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats)
{
- struct gnet_stats_queue *qstats = this_cpu_ptr(sch->cpu_qstats);
+ qstats->overlimits++;
+}
- qstats->drops++;
+static inline void qdisc_qstats_drop(struct Qdisc *sch)
+{
+ qstats_drop_inc(&sch->qstats);
+}
+
+static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch)
+{
+ qstats_drop_inc(this_cpu_ptr(sch->cpu_qstats));
}
static inline void qdisc_qstats_overlimit(struct Qdisc *sch)
diff --git a/include/net/sock.h b/include/net/sock.h
index f21f0708ec59..43c6abcf06ab 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -429,7 +429,9 @@ struct sock {
void *sk_security;
#endif
__u32 sk_mark;
+#ifdef CONFIG_CGROUP_NET_CLASSID
u32 sk_classid;
+#endif
struct cg_proto *sk_cgrp;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk);
@@ -1685,6 +1687,20 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
+static inline void sk_set_txhash(struct sock *sk)
+{
+ sk->sk_txhash = prandom_u32();
+
+ if (unlikely(!sk->sk_txhash))
+ sk->sk_txhash = 1;
+}
+
+static inline void sk_rethink_txhash(struct sock *sk)
+{
+ if (sk->sk_txhash)
+ sk_set_txhash(sk);
+}
+
static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
@@ -1709,6 +1725,8 @@ static inline void dst_negative_advice(struct sock *sk)
{
struct dst_entry *ndst, *dst = __sk_dst_get(sk);
+ sk_rethink_txhash(sk);
+
if (dst && dst->ops->negative_advice) {
ndst = dst->ops->negative_advice(dst);
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d5671f118bfc..319baab3b48e 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -72,6 +72,7 @@ struct switchdev_obj {
struct switchdev_obj_fdb { /* PORT_FDB */
const unsigned char *addr;
u16 vid;
+ u16 ndm_state;
} fdb;
} u;
};
@@ -157,6 +158,9 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev, int idx);
+void switchdev_port_fwd_mark_set(struct net_device *dev,
+ struct net_device *group_dev,
+ bool joining);
#else
@@ -271,6 +275,12 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
return -EOPNOTSUPP;
}
+static inline void switchdev_port_fwd_mark_set(struct net_device *dev,
+ struct net_device *group_dev,
+ bool joining)
+{
+}
+
#endif
#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h
index a152e9858b2c..958d69cfb19c 100644
--- a/include/net/tc_act/tc_bpf.h
+++ b/include/net/tc_act/tc_bpf.h
@@ -15,7 +15,7 @@
struct tcf_bpf {
struct tcf_common common;
- struct bpf_prog *filter;
+ struct bpf_prog __rcu *filter;
union {
u32 bpf_fd;
u16 bpf_num_ops;
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index 9fc9b578908a..592a6bc02b0b 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -6,9 +6,10 @@
struct tcf_gact {
struct tcf_common common;
#ifdef CONFIG_GACT_PROB
- u16 tcfg_ptype;
- u16 tcfg_pval;
- int tcfg_paction;
+ u16 tcfg_ptype;
+ u16 tcfg_pval;
+ int tcfg_paction;
+ atomic_t packets;
#endif
};
#define to_gact(a) \
diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index 4dd77a1c106b..dae96bae1c19 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -8,7 +8,7 @@ struct tcf_mirred {
int tcfm_eaction;
int tcfm_ifindex;
int tcfm_ok_push;
- struct net_device *tcfm_dev;
+ struct net_device __rcu *tcfm_dev;
struct list_head tcfm_list;
};
#define to_mirred(a) \
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 950cfecaad3c..0cab28cd43a9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -281,6 +281,8 @@ extern unsigned int sysctl_tcp_notsent_lowat;
extern int sysctl_tcp_min_tso_segs;
extern int sysctl_tcp_autocorking;
extern int sysctl_tcp_invalid_ratelimit;
+extern int sysctl_tcp_pacing_ss_ratio;
+extern int sysctl_tcp_pacing_ca_ratio;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -886,7 +888,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
-u32 tcp_ca_get_key_by_name(const char *name);
+u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
char *tcp_ca_get_name_by_key(u32 key, char *buffer);
#else
@@ -989,6 +991,11 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
#define TCP_INFINITE_SSTHRESH 0x7fffffff
+static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
{
return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
@@ -1065,7 +1072,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
const struct tcp_sock *tp = tcp_sk(sk);
/* If in slow start, ensure cwnd grows to twice what was ACKed. */
- if (tp->snd_cwnd <= tp->snd_ssthresh)
+ if (tcp_in_slow_start(tp))
return tp->snd_cwnd < 2 * tp->max_packets_out;
return tp->is_cwnd_limited;
@@ -1160,6 +1167,19 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
}
u32 tcp_default_init_rwnd(u32 mss);
+void tcp_cwnd_restart(struct sock *sk, s32 delta);
+
+static inline void tcp_slow_start_after_idle_check(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ s32 delta;
+
+ if (!sysctl_tcp_slow_start_after_idle || tp->packets_out)
+ return;
+ delta = tcp_time_stamp - tp->lsndtime;
+ if (delta > inet_csk(sk)->icsk_rto)
+ tcp_cwnd_restart(sk, delta);
+}
/* Determine a window scaling and initial window to offer. */
void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h
index 68f0ecad6c6e..1a47946f95ba 100644
--- a/include/net/timewait_sock.h
+++ b/include/net/timewait_sock.h
@@ -33,9 +33,6 @@ static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
static inline void twsk_destructor(struct sock *sk)
{
- BUG_ON(sk == NULL);
- BUG_ON(sk->sk_prot == NULL);
- BUG_ON(sk->sk_prot->twsk_prot == NULL);
if (sk->sk_prot->twsk_prot->twsk_destructor != NULL)
sk->sk_prot->twsk_prot->twsk_destructor(sk);
}
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index c491c1221606..cb2f89f20f5c 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -31,7 +31,8 @@ struct udp_port_cfg {
__be16 peer_udp_port;
unsigned int use_udp_checksums:1,
use_udp6_tx_checksums:1,
- use_udp6_rx_checksums:1;
+ use_udp6_rx_checksums:1,
+ ipv6_v6only:1;
};
int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
@@ -93,6 +94,10 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
void udp_tunnel_sock_release(struct socket *sock);
+struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
+ __be16 flags, __be64 tunnel_id,
+ int md_size);
+
static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
bool udp_csum)
{
diff --git a/include/net/vrf.h b/include/net/vrf.h
new file mode 100644
index 000000000000..593e6094ddd4
--- /dev/null
+++ b/include/net/vrf.h
@@ -0,0 +1,178 @@
+/*
+ * include/net/net_vrf.h - adds vrf dev structure definitions
+ * Copyright (c) 2015 Cumulus Networks
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_NET_VRF_H
+#define __LINUX_NET_VRF_H
+
+struct net_vrf_dev {
+ struct rcu_head rcu;
+ int ifindex; /* ifindex of master dev */
+ u32 tb_id; /* table id for VRF */
+};
+
+struct slave {
+ struct list_head list;
+ struct net_device *dev;
+};
+
+struct slave_queue {
+ struct list_head all_slaves;
+};
+
+struct net_vrf {
+ struct slave_queue queue;
+ struct rtable *rth;
+ u32 tb_id;
+};
+
+
+#if IS_ENABLED(CONFIG_NET_VRF)
+/* called with rcu_read_lock() */
+static inline int vrf_master_ifindex_rcu(const struct net_device *dev)
+{
+ struct net_vrf_dev *vrf_ptr;
+ int ifindex = 0;
+
+ if (!dev)
+ return 0;
+
+ if (netif_is_vrf(dev)) {
+ ifindex = dev->ifindex;
+ } else {
+ vrf_ptr = rcu_dereference(dev->vrf_ptr);
+ if (vrf_ptr)
+ ifindex = vrf_ptr->ifindex;
+ }
+
+ return ifindex;
+}
+
+static inline int vrf_master_ifindex(const struct net_device *dev)
+{
+ int ifindex;
+
+ rcu_read_lock();
+ ifindex = vrf_master_ifindex_rcu(dev);
+ rcu_read_unlock();
+
+ return ifindex;
+}
+
+/* called with rcu_read_lock */
+static inline u32 vrf_dev_table_rcu(const struct net_device *dev)
+{
+ u32 tb_id = 0;
+
+ if (dev) {
+ struct net_vrf_dev *vrf_ptr;
+
+ vrf_ptr = rcu_dereference(dev->vrf_ptr);
+ if (vrf_ptr)
+ tb_id = vrf_ptr->tb_id;
+ }
+ return tb_id;
+}
+
+static inline u32 vrf_dev_table(const struct net_device *dev)
+{
+ u32 tb_id;
+
+ rcu_read_lock();
+ tb_id = vrf_dev_table_rcu(dev);
+ rcu_read_unlock();
+
+ return tb_id;
+}
+
+static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex)
+{
+ struct net_device *dev;
+ u32 tb_id = 0;
+
+ if (!ifindex)
+ return 0;
+
+ rcu_read_lock();
+
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (dev)
+ tb_id = vrf_dev_table_rcu(dev);
+
+ rcu_read_unlock();
+
+ return tb_id;
+}
+
+/* called with rtnl */
+static inline u32 vrf_dev_table_rtnl(const struct net_device *dev)
+{
+ u32 tb_id = 0;
+
+ if (dev) {
+ struct net_vrf_dev *vrf_ptr;
+
+ vrf_ptr = rtnl_dereference(dev->vrf_ptr);
+ if (vrf_ptr)
+ tb_id = vrf_ptr->tb_id;
+ }
+ return tb_id;
+}
+
+/* caller has already checked netif_is_vrf(dev) */
+static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev)
+{
+ struct rtable *rth = ERR_PTR(-ENETUNREACH);
+ struct net_vrf *vrf = netdev_priv(dev);
+
+ if (vrf) {
+ rth = vrf->rth;
+ atomic_inc(&rth->dst.__refcnt);
+ }
+ return rth;
+}
+
+#else
+static inline int vrf_master_ifindex_rcu(const struct net_device *dev)
+{
+ return 0;
+}
+
+static inline int vrf_master_ifindex(const struct net_device *dev)
+{
+ return 0;
+}
+
+static inline u32 vrf_dev_table_rcu(const struct net_device *dev)
+{
+ return 0;
+}
+
+static inline u32 vrf_dev_table(const struct net_device *dev)
+{
+ return 0;
+}
+
+static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex)
+{
+ return 0;
+}
+
+static inline u32 vrf_dev_table_rtnl(const struct net_device *dev)
+{
+ return 0;
+}
+
+static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev)
+{
+ return ERR_PTR(-ENETUNREACH);
+}
+#endif
+
+#endif /* __LINUX_NET_VRF_H */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0082b5d33d7d..480a319b4c92 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -7,6 +7,7 @@
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/udp.h>
+#include <net/dst_metadata.h>
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
@@ -94,20 +95,18 @@ struct vxlanhdr {
#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+#define VNI_HASH_BITS 10
+#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
+#define FDB_HASH_BITS 8
+#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
+
struct vxlan_metadata {
- __be32 vni;
u32 gbp;
};
-struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb,
- struct vxlan_metadata *md);
-
/* per UDP socket information */
struct vxlan_sock {
struct hlist_node hlist;
- vxlan_rcv_t *rcv;
- void *data;
struct work_struct del_work;
struct socket *sock;
struct rcu_head rcu;
@@ -117,6 +116,58 @@ struct vxlan_sock {
u32 flags;
};
+union vxlan_addr {
+ struct sockaddr_in sin;
+ struct sockaddr_in6 sin6;
+ struct sockaddr sa;
+};
+
+struct vxlan_rdst {
+ union vxlan_addr remote_ip;
+ __be16 remote_port;
+ u32 remote_vni;
+ u32 remote_ifindex;
+ struct list_head list;
+ struct rcu_head rcu;
+};
+
+struct vxlan_config {
+ union vxlan_addr remote_ip;
+ union vxlan_addr saddr;
+ u32 vni;
+ int remote_ifindex;
+ int mtu;
+ __be16 dst_port;
+ __u16 port_min;
+ __u16 port_max;
+ __u8 tos;
+ __u8 ttl;
+ u32 flags;
+ unsigned long age_interval;
+ unsigned int addrmax;
+ bool no_share;
+};
+
+/* Pseudo network device */
+struct vxlan_dev {
+ struct hlist_node hlist; /* vni hash table */
+ struct list_head next; /* vxlan's per namespace list */
+ struct vxlan_sock *vn_sock; /* listening socket */
+ struct net_device *dev;
+ struct net *net; /* netns for packet i/o */
+ struct vxlan_rdst default_dst; /* default destination */
+ u32 flags; /* VXLAN_F_* in vxlan.h */
+
+ struct timer_list age_timer;
+ spinlock_t hash_lock;
+ unsigned int addrcnt;
+ struct gro_cells gro_cells;
+
+ struct vxlan_config cfg;
+
+ struct hlist_head fdb_head[FDB_HASH_SIZE];
+};
+
#define VXLAN_F_LEARN 0x01
#define VXLAN_F_PROXY 0x02
#define VXLAN_F_RSC 0x04
@@ -130,6 +181,7 @@ struct vxlan_sock {
#define VXLAN_F_REMCSUM_RX 0x400
#define VXLAN_F_GBP 0x800
#define VXLAN_F_REMCSUM_NOPARTIAL 0x1000
+#define VXLAN_F_COLLECT_METADATA 0x2000
/* Flags that are used in the receive path. These flags must match in
* order for a socket to be shareable
@@ -137,18 +189,16 @@ struct vxlan_sock {
#define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \
VXLAN_F_UDP_ZERO_CSUM6_RX | \
VXLAN_F_REMCSUM_RX | \
- VXLAN_F_REMCSUM_NOPARTIAL)
-
-struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
- bool no_share, u32 flags);
+ VXLAN_F_REMCSUM_NOPARTIAL | \
+ VXLAN_F_COLLECT_METADATA)
-void vxlan_sock_release(struct vxlan_sock *vs);
+struct net_device *vxlan_dev_create(struct net *net, const char *name,
+ u8 name_assign_type, struct vxlan_config *conf);
-int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
- __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
- bool xnet, u32 vxflags);
+static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan)
+{
+ return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport;
+}
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
netdev_features_t features)
@@ -191,4 +241,10 @@ static inline void vxlan_get_rx_port(struct net_device *netdev)
{
}
#endif
+
+static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
+{
+ return vs->sock->sk->sk_family;
+}
+
#endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f0ee97eec24d..312e3fee9ccf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -285,10 +285,13 @@ struct xfrm_policy_afinfo {
unsigned short family;
struct dst_ops *dst_ops;
void (*garbage_collect)(struct net *net);
- struct dst_entry *(*dst_lookup)(struct net *net, int tos,
+ struct dst_entry *(*dst_lookup)(struct net *net,
+ int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr);
- int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr);
+ int (*get_saddr)(struct net *net, int oif,
+ xfrm_address_t *saddr,
+ xfrm_address_t *daddr);
void (*decode_session)(struct sk_buff *skb,
struct flowi *fl,
int reverse);
diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h
new file mode 100644
index 000000000000..833cfcb6750d
--- /dev/null
+++ b/include/trace/events/fib.h
@@ -0,0 +1,113 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM fib
+
+#if !defined(_TRACE_FIB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FIB_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <net/ip_fib.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(fib_table_lookup,
+
+ TP_PROTO(u32 tb_id, const struct flowi4 *flp),
+
+ TP_ARGS(tb_id, flp),
+
+ TP_STRUCT__entry(
+ __field( u32, tb_id )
+ __field( int, oif )
+ __field( int, iif )
+ __field( __u8, tos )
+ __field( __u8, scope )
+ __field( __u8, flags )
+ __array( __u8, src, 4 )
+ __array( __u8, dst, 4 )
+ ),
+
+ TP_fast_assign(
+ __be32 *p32;
+
+ __entry->tb_id = tb_id;
+ __entry->oif = flp->flowi4_oif;
+ __entry->iif = flp->flowi4_iif;
+ __entry->tos = flp->flowi4_tos;
+ __entry->scope = flp->flowi4_scope;
+ __entry->flags = flp->flowi4_flags;
+
+ p32 = (__be32 *) __entry->src;
+ *p32 = flp->saddr;
+
+ p32 = (__be32 *) __entry->dst;
+ *p32 = flp->daddr;
+ ),
+
+ TP_printk("table %u oif %d iif %d src %pI4 dst %pI4 tos %d scope %d flags %x",
+ __entry->tb_id, __entry->oif, __entry->iif,
+ __entry->src, __entry->dst, __entry->tos, __entry->scope,
+ __entry->flags)
+);
+
+TRACE_EVENT(fib_table_lookup_nh,
+
+ TP_PROTO(const struct fib_nh *nh),
+
+ TP_ARGS(nh),
+
+ TP_STRUCT__entry(
+ __string( name, nh->nh_dev->name)
+ __field( int, oif )
+ __array( __u8, src, 4 )
+ ),
+
+ TP_fast_assign(
+ __be32 *p32 = (__be32 *) __entry->src;
+
+ __assign_str(name, nh->nh_dev ? nh->nh_dev->name : "not set");
+ __entry->oif = nh->nh_oif;
+ *p32 = nh->nh_saddr;
+ ),
+
+ TP_printk("nexthop dev %s oif %d src %pI4",
+ __get_str(name), __entry->oif, __entry->src)
+);
+
+TRACE_EVENT(fib_validate_source,
+
+ TP_PROTO(const struct net_device *dev, const struct flowi4 *flp),
+
+ TP_ARGS(dev, flp),
+
+ TP_STRUCT__entry(
+ __string( name, dev->name )
+ __field( int, oif )
+ __field( int, iif )
+ __field( __u8, tos )
+ __array( __u8, src, 4 )
+ __array( __u8, dst, 4 )
+ ),
+
+ TP_fast_assign(
+ __be32 *p32;
+
+ __assign_str(name, dev ? dev->name : "not set");
+ __entry->oif = flp->flowi4_oif;
+ __entry->iif = flp->flowi4_iif;
+ __entry->tos = flp->flowi4_tos;
+
+ p32 = (__be32 *) __entry->src;
+ *p32 = flp->saddr;
+
+ p32 = (__be32 *) __entry->dst;
+ *p32 = flp->daddr;
+ ),
+
+ TP_printk("dev %s oif %d iif %d tos %d src %pI4 dst %pI4",
+ __get_str(name), __entry->oif, __entry->iif, __entry->tos,
+ __entry->src, __entry->dst)
+);
+#endif /* _TRACE_FIB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 1ff9942718fe..aafb9937b162 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -243,6 +243,7 @@ header-y += limits.h
header-y += llc.h
header-y += loop.h
header-y += lp.h
+header-y += lwtunnel.h
header-y += magic.h
header-y += major.h
header-y += map_to_7segment.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 29ef6f99e43d..92a48e2d5461 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -114,6 +114,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH,
BPF_MAP_TYPE_ARRAY,
BPF_MAP_TYPE_PROG_ARRAY,
+ BPF_MAP_TYPE_PERF_EVENT_ARRAY,
};
enum bpf_prog_type {
@@ -249,6 +250,28 @@ enum bpf_func_id {
* Return: 0 on success
*/
BPF_FUNC_get_current_comm,
+
+ /**
+ * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
+ * @skb: pointer to skb
+ * Return: classid if != 0
+ */
+ BPF_FUNC_get_cgroup_classid,
+ BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
+ BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */
+
+ /**
+ * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
+ * retrieve or populate tunnel metadata
+ * @skb: pointer to skb
+ * @key: pointer to 'struct bpf_tunnel_key'
+ * @size: size of 'struct bpf_tunnel_key'
+ * @flags: room for future extensions
+ * Retrun: 0 on success
+ */
+ BPF_FUNC_skb_get_tunnel_key,
+ BPF_FUNC_skb_set_tunnel_key,
+ BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */
__BPF_FUNC_MAX_ID,
};
@@ -269,6 +292,12 @@ struct __sk_buff {
__u32 ifindex;
__u32 tc_index;
__u32 cb[5];
+ __u32 hash;
+};
+
+struct bpf_tunnel_key {
+ __u32 tunnel_id;
+ __u32 remote_ipv4;
};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index cd67aec187d9..cd1629170103 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1093,6 +1093,11 @@ struct ethtool_sfeatures {
* the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
* respectively. For example, if the device supports HWTSTAMP_TX_ON,
* then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set.
+ *
+ * Drivers should only report the filters they actually support without
+ * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for
+ * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the
+ * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op.
*/
struct ethtool_ts_info {
__u32 cmd;
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 2b82d7e30974..96161b8202b5 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -43,7 +43,7 @@ enum {
FRA_UNUSED5,
FRA_FWMARK, /* mark */
FRA_FLOW, /* flow/class id */
- FRA_UNUSED6,
+ FRA_TUN_ID,
FRA_SUPPRESS_IFGROUP,
FRA_SUPPRESS_PREFIXLEN,
FRA_TABLE, /* Extended table id */
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index eaaea6208b42..3635b7797508 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -182,6 +182,7 @@ struct br_mdb_entry {
#define MDB_TEMPORARY 0
#define MDB_PERMANENT 1
__u8 state;
+ __u16 vid;
struct {
union {
__be32 ip4;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 2c7e8e3d3981..3a5f263cfc2f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -148,6 +148,7 @@ enum {
IFLA_PHYS_SWITCH_ID,
IFLA_LINK_NETNSID,
IFLA_PHYS_PORT_NAME,
+ IFLA_PROTO_DOWN,
__IFLA_MAX
};
@@ -229,6 +230,8 @@ enum {
IFLA_BR_AGEING_TIME,
IFLA_BR_STP_STATE,
IFLA_BR_PRIORITY,
+ IFLA_BR_VLAN_FILTERING,
+ IFLA_BR_VLAN_PROTOCOL,
__IFLA_BR_MAX,
};
@@ -339,6 +342,15 @@ enum macvlan_macaddr_mode {
#define MACVLAN_FLAG_NOPROMISC 1
+/* VRF section */
+enum {
+ IFLA_VRF_UNSPEC,
+ IFLA_VRF_TABLE,
+ __IFLA_VRF_MAX
+};
+
+#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
@@ -381,6 +393,7 @@ enum {
IFLA_VXLAN_REMCSUM_RX,
IFLA_VXLAN_GBP,
IFLA_VXLAN_REMCSUM_NOPARTIAL,
+ IFLA_VXLAN_COLLECT_METADATA,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
@@ -397,6 +410,8 @@ enum {
IFLA_GENEVE_REMOTE,
IFLA_GENEVE_TTL,
IFLA_GENEVE_TOS,
+ IFLA_GENEVE_PORT, /* destination port */
+ IFLA_GENEVE_COLLECT_METADATA,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
@@ -431,6 +446,7 @@ enum {
IFLA_BOND_AD_ACTOR_SYS_PRIO,
IFLA_BOND_AD_USER_PORT_KEY,
IFLA_BOND_AD_ACTOR_SYSTEM,
+ IFLA_BOND_TLB_DYNAMIC_LB,
__IFLA_BOND_MAX,
};
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index d3d715f8c88f..9e7edfd8141e 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -55,6 +55,7 @@ struct sockaddr_ll {
#define PACKET_TX_HAS_OFF 19
#define PACKET_QDISC_BYPASS 20
#define PACKET_ROLLOVER_STATS 21
+#define PACKET_FANOUT_DATA 22
#define PACKET_FANOUT_HASH 0
#define PACKET_FANOUT_LB 1
@@ -62,6 +63,8 @@ struct sockaddr_ll {
#define PACKET_FANOUT_ROLLOVER 3
#define PACKET_FANOUT_RND 4
#define PACKET_FANOUT_QM 5
+#define PACKET_FANOUT_CBPF 6
+#define PACKET_FANOUT_EBPF 7
#define PACKET_FANOUT_FLAG_ROLLOVER 0x1000
#define PACKET_FANOUT_FLAG_DEFRAG 0x8000
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index bd3cc11a431f..af4de90ba27d 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -112,6 +112,7 @@ enum {
IFLA_GRE_ENCAP_FLAGS,
IFLA_GRE_ENCAP_SPORT,
IFLA_GRE_ENCAP_DPORT,
+ IFLA_GRE_COLLECT_METADATA,
__IFLA_GRE_MAX,
};
diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h
new file mode 100644
index 000000000000..7ed9e670814e
--- /dev/null
+++ b/include/uapi/linux/ila.h
@@ -0,0 +1,15 @@
+/* ila.h - ILA Interface */
+
+#ifndef _UAPI_LINUX_ILA_H
+#define _UAPI_LINUX_ILA_H
+
+enum {
+ ILA_ATTR_UNSPEC,
+ ILA_ATTR_LOCATOR, /* u64 */
+
+ __ILA_ATTR_MAX,
+};
+
+#define ILA_ATTR_MAX (__ILA_ATTR_MAX - 1)
+
+#endif /* _UAPI_LINUX_ILA_H */
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index 3199243f2028..391395c06c7e 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -406,6 +406,11 @@ enum {
IPVS_DAEMON_ATTR_STATE, /* sync daemon state (master/backup) */
IPVS_DAEMON_ATTR_MCAST_IFN, /* multicast interface name */
IPVS_DAEMON_ATTR_SYNC_ID, /* SyncID we belong to */
+ IPVS_DAEMON_ATTR_SYNC_MAXLEN, /* UDP Payload Size */
+ IPVS_DAEMON_ATTR_MCAST_GROUP, /* IPv4 Multicast Address */
+ IPVS_DAEMON_ATTR_MCAST_GROUP6, /* IPv6 Multicast Address */
+ IPVS_DAEMON_ATTR_MCAST_PORT, /* Multicast Port (base) */
+ IPVS_DAEMON_ATTR_MCAST_TTL, /* Multicast TTL */
__IPVS_DAEMON_ATTR_MAX,
};
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 5efa54ae567c..38b4fef20219 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -171,6 +171,9 @@ enum {
DEVCONF_USE_OPTIMISTIC,
DEVCONF_ACCEPT_RA_MTU,
DEVCONF_STABLE_SECRET,
+ DEVCONF_USE_OIF_ADDRS_ONLY,
+ DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
+ DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
new file mode 100644
index 000000000000..34141a5dfe74
--- /dev/null
+++ b/include/uapi/linux/lwtunnel.h
@@ -0,0 +1,47 @@
+#ifndef _UAPI_LWTUNNEL_H_
+#define _UAPI_LWTUNNEL_H_
+
+#include <linux/types.h>
+
+enum lwtunnel_encap_types {
+ LWTUNNEL_ENCAP_NONE,
+ LWTUNNEL_ENCAP_MPLS,
+ LWTUNNEL_ENCAP_IP,
+ LWTUNNEL_ENCAP_ILA,
+ LWTUNNEL_ENCAP_IP6,
+ __LWTUNNEL_ENCAP_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1)
+
+enum lwtunnel_ip_t {
+ LWTUNNEL_IP_UNSPEC,
+ LWTUNNEL_IP_ID,
+ LWTUNNEL_IP_DST,
+ LWTUNNEL_IP_SRC,
+ LWTUNNEL_IP_TTL,
+ LWTUNNEL_IP_TOS,
+ LWTUNNEL_IP_SPORT,
+ LWTUNNEL_IP_DPORT,
+ LWTUNNEL_IP_FLAGS,
+ __LWTUNNEL_IP_MAX,
+};
+
+#define LWTUNNEL_IP_MAX (__LWTUNNEL_IP_MAX - 1)
+
+enum lwtunnel_ip6_t {
+ LWTUNNEL_IP6_UNSPEC,
+ LWTUNNEL_IP6_ID,
+ LWTUNNEL_IP6_DST,
+ LWTUNNEL_IP6_SRC,
+ LWTUNNEL_IP6_HOPLIMIT,
+ LWTUNNEL_IP6_TC,
+ LWTUNNEL_IP6_SPORT,
+ LWTUNNEL_IP6_DPORT,
+ LWTUNNEL_IP6_FLAGS,
+ __LWTUNNEL_IP6_MAX,
+};
+
+#define LWTUNNEL_IP6_MAX (__LWTUNNEL_IP6_MAX - 1)
+
+#endif /* _UAPI_LWTUNNEL_H_ */
diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
index 139d4dd1cab8..24a6cb1aec86 100644
--- a/include/uapi/linux/mpls.h
+++ b/include/uapi/linux/mpls.h
@@ -41,4 +41,6 @@ struct mpls_label {
#define MPLS_LABEL_OAMALERT 14 /* RFC3429 */
#define MPLS_LABEL_EXTENSION 15 /* RFC7274 */
+#define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */
+
#endif /* _UAPI_MPLS_H */
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
new file mode 100644
index 000000000000..d80a0498f77e
--- /dev/null
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -0,0 +1,28 @@
+/*
+ * mpls tunnel api
+ *
+ * Authors:
+ * Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_MPLS_IPTUNNEL_H
+#define _UAPI_LINUX_MPLS_IPTUNNEL_H
+
+/* MPLS tunnel attributes
+ * [RTA_ENCAP] = {
+ * [MPLS_IPTUNNEL_DST]
+ * }
+ */
+enum {
+ MPLS_IPTUNNEL_UNSPEC,
+ MPLS_IPTUNNEL_DST,
+ __MPLS_IPTUNNEL_MAX,
+};
+#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
+
+#endif /* _UAPI_LINUX_MPLS_IPTUNNEL_H */
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 2e35c61bbdd1..788655bfa0f3 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -106,6 +106,7 @@ struct ndt_stats {
__u64 ndts_rcv_probes_ucast;
__u64 ndts_periodic_gc_runs;
__u64 ndts_forced_gc_runs;
+ __u64 ndts_table_fulls;
};
enum {
diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
index ceeefe6681b5..ed4e776e1242 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
@@ -13,6 +13,8 @@ enum sctp_conntrack {
SCTP_CONNTRACK_SHUTDOWN_SENT,
SCTP_CONNTRACK_SHUTDOWN_RECD,
SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
+ SCTP_CONNTRACK_HEARTBEAT_SENT,
+ SCTP_CONNTRACK_HEARTBEAT_ACKED,
SCTP_CONNTRACK_MAX
};
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index a99e6a997140..d8c8a7c9d88a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -756,16 +756,25 @@ enum nft_ct_attributes {
};
#define NFTA_CT_MAX (__NFTA_CT_MAX - 1)
+enum nft_limit_type {
+ NFT_LIMIT_PKTS,
+ NFT_LIMIT_PKT_BYTES
+};
+
/**
* enum nft_limit_attributes - nf_tables limit expression netlink attributes
*
* @NFTA_LIMIT_RATE: refill rate (NLA_U64)
* @NFTA_LIMIT_UNIT: refill unit (NLA_U64)
+ * @NFTA_LIMIT_BURST: burst (NLA_U32)
+ * @NFTA_LIMIT_TYPE: type of limit (NLA_U32: enum nft_limit_type)
*/
enum nft_limit_attributes {
NFTA_LIMIT_UNSPEC,
NFTA_LIMIT_RATE,
NFTA_LIMIT_UNIT,
+ NFTA_LIMIT_BURST,
+ NFTA_LIMIT_TYPE,
__NFTA_LIMIT_MAX
};
#define NFTA_LIMIT_MAX (__NFTA_LIMIT_MAX - 1)
@@ -936,6 +945,20 @@ enum nft_redir_attributes {
#define NFTA_REDIR_MAX (__NFTA_REDIR_MAX - 1)
/**
+ * enum nft_dup_attributes - nf_tables dup expression netlink attributes
+ *
+ * @NFTA_DUP_SREG_ADDR: source register of address (NLA_U32: nft_registers)
+ * @NFTA_DUP_SREG_DEV: source register of output interface (NLA_U32: nft_register)
+ */
+enum nft_dup_attributes {
+ NFTA_DUP_UNSPEC,
+ NFTA_DUP_SREG_ADDR,
+ NFTA_DUP_SREG_DEV,
+ __NFTA_DUP_MAX
+};
+#define NFTA_DUP_MAX (__NFTA_DUP_MAX - 1)
+
+/**
* enum nft_gen_attributes - nf_tables ruleset generation attributes
*
* @NFTA_GEN_ID: Ruleset generation ID (NLA_U32)
diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index acad6c52a652..c1a4e1441a25 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -61,6 +61,7 @@ enum ctattr_tuple {
CTA_TUPLE_UNSPEC,
CTA_TUPLE_IP,
CTA_TUPLE_PROTO,
+ CTA_TUPLE_ZONE,
__CTA_TUPLE_MAX
};
#define CTA_TUPLE_MAX (__CTA_TUPLE_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
index 1ab0b97b3a1e..f2c10dc140d6 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
@@ -92,6 +92,8 @@ enum ctattr_timeout_sctp {
CTA_TIMEOUT_SCTP_SHUTDOWN_SENT,
CTA_TIMEOUT_SCTP_SHUTDOWN_RECD,
CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
+ CTA_TIMEOUT_SCTP_HEARTBEAT_SENT,
+ CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED,
__CTA_TIMEOUT_SCTP_MAX
};
#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)
diff --git a/include/uapi/linux/netfilter/xt_CT.h b/include/uapi/linux/netfilter/xt_CT.h
index 5a688c1ca4d7..9e520418b858 100644
--- a/include/uapi/linux/netfilter/xt_CT.h
+++ b/include/uapi/linux/netfilter/xt_CT.h
@@ -6,7 +6,13 @@
enum {
XT_CT_NOTRACK = 1 << 0,
XT_CT_NOTRACK_ALIAS = 1 << 1,
- XT_CT_MASK = XT_CT_NOTRACK | XT_CT_NOTRACK_ALIAS,
+ XT_CT_ZONE_DIR_ORIG = 1 << 2,
+ XT_CT_ZONE_DIR_REPL = 1 << 3,
+ XT_CT_ZONE_MARK = 1 << 4,
+
+ XT_CT_MASK = XT_CT_NOTRACK | XT_CT_NOTRACK_ALIAS |
+ XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL |
+ XT_CT_ZONE_MARK,
};
struct xt_ct_target_info {
diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h b/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h
index 205ed62e4605..cd2e940c8bf5 100644
--- a/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h
+++ b/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h
@@ -10,7 +10,9 @@ enum ip6t_reject_with {
IP6T_ICMP6_ADDR_UNREACH,
IP6T_ICMP6_PORT_UNREACH,
IP6T_ICMP6_ECHOREPLY,
- IP6T_TCP_RESET
+ IP6T_TCP_RESET,
+ IP6T_ICMP6_POLICY_FAIL,
+ IP6T_ICMP6_REJECT_ROUTE
};
struct ip6t_reject_info {
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index cf6a65cccbdf..6f3fe16cd22a 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -110,6 +110,7 @@ struct nlmsgerr {
#define NETLINK_TX_RING 7
#define NETLINK_LISTEN_ALL_NSID 8
#define NETLINK_LIST_MEMBERSHIPS 9
+#define NETLINK_CAP_ACK 10
struct nl_pktinfo {
__u32 group;
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 1dab77601c21..32e07d8cbaf4 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -164,6 +164,9 @@ enum ovs_packet_cmd {
* %OVS_USERSPACE_ATTR_EGRESS_TUN_PORT attribute, which is sent only if the
* output port is actually a tunnel port. Contains the output tunnel key
* extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
+ * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
+ * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
+ * size.
*
* These attributes follow the &struct ovs_header within the Generic Netlink
* payload for %OVS_PACKET_* commands.
@@ -180,6 +183,7 @@ enum ovs_packet_attr {
OVS_PACKET_ATTR_UNUSED2,
OVS_PACKET_ATTR_PROBE, /* Packet operation is a feature probe,
error logging should be suppressed. */
+ OVS_PACKET_ATTR_MRU, /* Maximum received IP fragment size. */
__OVS_PACKET_ATTR_MAX
};
@@ -319,9 +323,13 @@ enum ovs_key_attr {
OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls.
* The implementation may restrict
* the accepted length of the array. */
+ OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */
+ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */
+ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */
+ OVS_KEY_ATTR_CT_LABEL, /* 16-octet connection tracking label */
#ifdef __KERNEL__
- OVS_KEY_ATTR_TUNNEL_INFO, /* struct ovs_tunnel_info */
+ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */
#endif
__OVS_KEY_ATTR_MAX
};
@@ -431,6 +439,20 @@ struct ovs_key_nd {
__u8 nd_tll[ETH_ALEN];
};
+#define OVS_CT_LABEL_LEN 16
+struct ovs_key_ct_label {
+ __u8 ct_label[OVS_CT_LABEL_LEN];
+};
+
+/* OVS_KEY_ATTR_CT_STATE flags */
+#define OVS_CS_F_NEW 0x01 /* Beginning of a new connection. */
+#define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */
+#define OVS_CS_F_RELATED 0x04 /* Related to an established
+ * connection. */
+#define OVS_CS_F_INVALID 0x20 /* Could not track connection. */
+#define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */
+#define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */
+
/**
* enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
* @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow
@@ -595,6 +617,39 @@ struct ovs_action_hash {
};
/**
+ * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action.
+ * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags.
+ * @OVS_CT_ATTR_ZONE: u16 connection tracking zone.
+ * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the
+ * mask, the corresponding bit in the value is copied to the connection
+ * tracking mark field in the connection.
+ * @OVS_CT_ATTR_LABEL: %OVS_CT_LABEL_LEN value followed by %OVS_CT_LABEL_LEN
+ * mask. For each bit set in the mask, the corresponding bit in the value is
+ * copied to the connection tracking label field in the connection.
+ * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG.
+ */
+enum ovs_ct_attr {
+ OVS_CT_ATTR_UNSPEC,
+ OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */
+ OVS_CT_ATTR_ZONE, /* u16 zone id. */
+ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */
+ OVS_CT_ATTR_LABEL, /* label to associate with this connection. */
+ OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of
+ related connections. */
+ __OVS_CT_ATTR_MAX
+};
+
+#define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1)
+
+/*
+ * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_*
+ * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows
+ * future packets for the same connection to be identified as 'established'
+ * or 'related'.
+ */
+#define OVS_CT_F_COMMIT 0x01
+
+/**
* enum ovs_action_attr - Action types.
*
* @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
@@ -623,6 +678,8 @@ struct ovs_action_hash {
* indicate the new packet contents. This could potentially still be
* %ETH_P_MPLS if the resulting MPLS label stack is not empty. If there
* is no MPLS label stack, as determined by ethertype, no action is taken.
+ * @OVS_ACTION_ATTR_CT: Track the connection. Populate the conntrack-related
+ * entries in the flow key.
*
* Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all
* fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -648,6 +705,7 @@ enum ovs_action_attr {
* data immediately followed by a mask.
* The data must be zero for the unmasked
* bits. */
+ OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index fdd8f07f1d34..702024769c74 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -308,6 +308,8 @@ enum rtattr_type_t {
RTA_VIA,
RTA_NEWDST,
RTA_PREF,
+ RTA_ENCAP_TYPE,
+ RTA_ENCAP,
__RTA_MAX
};
@@ -416,10 +418,13 @@ enum {
#define RTAX_MAX (__RTAX_MAX - 1)
-#define RTAX_FEATURE_ECN 0x00000001
-#define RTAX_FEATURE_SACK 0x00000002
-#define RTAX_FEATURE_TIMESTAMP 0x00000004
-#define RTAX_FEATURE_ALLFRAG 0x00000008
+#define RTAX_FEATURE_ECN (1 << 0)
+#define RTAX_FEATURE_SACK (1 << 1)
+#define RTAX_FEATURE_TIMESTAMP (1 << 2)
+#define RTAX_FEATURE_ALLFRAG (1 << 3)
+
+#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | RTAX_FEATURE_SACK | \
+ RTAX_FEATURE_TIMESTAMP | RTAX_FEATURE_ALLFRAG)
struct rta_session {
__u8 proto;
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index eee8968407f0..25a9ad8bcef1 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -278,6 +278,8 @@ enum
LINUX_MIB_TCPACKSKIPPEDCHALLENGE, /* TCPACKSkippedChallenge */
LINUX_MIB_TCPWINPROBE, /* TCPWinProbe */
LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */
+ LINUX_MIB_TCPMTUPFAIL, /* TCPMTUPFail */
+ LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */
__LINUX_MIB_MAX
};
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index 70054cc0708d..252ffd4801ef 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -156,7 +156,9 @@ struct xen_netif_tx_request {
/* Types of xen_netif_extra_info descriptors. */
#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MAX (2)
+#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MAX (4)
/* xen_netif_extra_info flags. */
#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
@@ -201,6 +203,10 @@ struct xen_netif_extra_info {
uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
} gso;
+ struct {
+ uint8_t addr[6]; /* Address to add/remove. */
+ } mcast;
+
uint16_t pad[3];
} u;
};