summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf.h12
-rw-r--r--include/linux/filter.h17
-rw-r--r--include/linux/ipv6.h4
-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.h13
-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.h27
-rw-r--r--include/linux/netfilter.h42
-rw-r--r--include/linux/netfilter/x_tables.h8
-rw-r--r--include/linux/netfilter_bridge.h12
-rw-r--r--include/linux/perf_event.h10
-rw-r--r--include/linux/phy.h2
-rw-r--r--include/linux/skbuff.h56
-rw-r--r--include/linux/stmmac.h22
-rw-r--r--include/net/act_api.h15
-rw-r--r--include/net/addrconf.h4
-rw-r--r--include/net/bluetooth/hci_core.h2
-rw-r--r--include/net/bluetooth/l2cap.h2
-rw-r--r--include/net/bond_options.h1
-rw-r--r--include/net/cfg802154.h2
-rw-r--r--include/net/cls_cgroup.h29
-rw-r--r--include/net/dsa.h17
-rw-r--r--include/net/dst.h6
-rw-r--r--include/net/dst_metadata.h56
-rw-r--r--include/net/fib_rules.h1
-rw-r--r--include/net/flow.h8
-rw-r--r--include/net/gre.h92
-rw-r--r--include/net/inet_hashtables.h4
-rw-r--r--include/net/inet_timewait_sock.h8
-rw-r--r--include/net/ip.h16
-rw-r--r--include/net/ip6_fib.h3
-rw-r--r--include/net/ip_fib.h5
-rw-r--r--include/net/ip_tunnels.h119
-rw-r--r--include/net/ipv6.h76
-rw-r--r--include/net/lwtunnel.h147
-rw-r--r--include/net/mac802154.h17
-rw-r--r--include/net/mpls_iptunnel.h29
-rw-r--r--include/net/neighbour.h1
-rw-r--r--include/net/netns/ipv6.h1
-rw-r--r--include/net/netns/netfilter.h1
-rw-r--r--include/net/route.h1
-rw-r--r--include/net/rtnetlink.h1
-rw-r--r--include/net/sch_generic.h31
-rw-r--r--include/net/sock.h18
-rw-r--r--include/net/switchdev.h10
-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.h7
-rw-r--r--include/net/timewait_sock.h3
-rw-r--r--include/net/vxlan.h83
-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.h4
-rw-r--r--include/uapi/linux/if_tunnel.h1
-rw-r--r--include/uapi/linux/ipv6.h2
-rw-r--r--include/uapi/linux/lwtunnel.h16
-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/nfnetlink_cttimeout.h2
-rw-r--r--include/uapi/linux/openvswitch.h2
-rw-r--r--include/uapi/linux/rtnetlink.h17
-rw-r--r--include/uapi/linux/snmp.h2
72 files changed, 956 insertions, 270 deletions
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/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/ipv6.h b/include/linux/ipv6.h
index 82806c60aa42..cb9dcad72372 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,6 +29,7 @@ struct ipv6_devconf {
__s32 max_desync_factor;
__s32 max_addresses;
__s32 accept_ra_defrtr;
+ __s32 accept_ra_min_hop_limit;
__s32 accept_ra_pinfo;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
@@ -57,6 +58,7 @@ struct ipv6_devconf {
bool initialized;
struct in6_addr secret;
} stable_secret;
+ __s32 use_oif_addrs_only;
void *sysctl;
};
@@ -94,7 +96,6 @@ 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 +112,7 @@ 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..2039546b0ec6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -103,6 +103,7 @@ enum {
MLX5_REG_PMTU = 0x5003,
MLX5_REG_PTYS = 0x5004,
MLX5_REG_PAOS = 0x5006,
+ MLX5_REG_PPCNT = 0x5008,
MLX5_REG_PMAOS = 0x5012,
MLX5_REG_PUDE = 0x5009,
MLX5_REG_PMPE = 0x5010,
@@ -380,7 +381,7 @@ 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 +436,8 @@ 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 +466,10 @@ 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 +679,8 @@ 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,
@@ -773,6 +782,8 @@ 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..607b5f41f46f 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);
};
/**
@@ -1448,6 +1463,8 @@ 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 +1519,10 @@ 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.
*/
@@ -1685,6 +1706,10 @@ 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 +1787,7 @@ 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)
@@ -2982,6 +3008,7 @@ 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);
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 00050dfd9f23..d788ce62d826 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);
}
@@ -385,4 +390,15 @@ 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/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/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..e5fb1d415961 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -424,6 +424,8 @@ 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)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 22b6d9ca1654..065e10b81a77 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;
@@ -938,6 +953,26 @@ static inline __u32 skb_get_hash(struct sk_buff *skb)
return skb->hash;
}
+__u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6);
+
+static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6)
+{
+ if (!skb->l4_hash && !skb->sw_hash)
+ __skb_get_hash_flowi6(skb, fl6);
+
+ return skb->hash;
+}
+
+__u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl);
+
+static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4)
+{
+ if (!skb->l4_hash && !skb->sw_hash)
+ __skb_get_hash_flowi4(skb, fl4);
+
+ return skb->hash;
+}
+
__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
@@ -2671,12 +2706,6 @@ 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)
@@ -3468,5 +3497,6 @@ 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/net/act_api.h b/include/net/act_api.h
index 931738bc5bba..4519c81304bd 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
@@ -102,7 +115,7 @@ 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..2a6b0919e23f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1297,7 +1297,7 @@ 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/cfg802154.h b/include/net/cfg802154.h
index 290a9a69af07..382f94b59f2f 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,
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..6356f437e911 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -296,12 +296,17 @@ 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);
+
+ /*
+ * 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..2578811cef51 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;
@@ -356,6 +357,9 @@ 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 +461,7 @@ 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..075f523ff23f
--- /dev/null
+++ b/include/net/dst_metadata.h
@@ -0,0 +1,56 @@
+#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;
+ size_t opts_len;
+ 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,
+ int family)
+{
+ struct metadata_dst *md_dst = skb_metadata_dst(skb);
+ struct rtable *rt;
+
+ if (md_dst)
+ return &md_dst->u.tun_info;
+
+ switch (family) {
+ case AF_INET:
+ rt = (struct rtable *)skb_dst(skb);
+ if (rt && rt->rt_lwtstate)
+ return lwt_tun_info(rt->rt_lwtstate);
+ break;
+ }
+
+ 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);
+
+#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..3098ae33a178 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -19,6 +19,10 @@
#define LOOPBACK_IFINDEX 1
+struct flowi_tunnel {
+ __be64 tun_id;
+};
+
struct flowi_common {
int flowic_oif;
int flowic_iif;
@@ -30,6 +34,7 @@ struct flowi_common {
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_KNOWN_NH 0x02
__u32 flowic_secid;
+ struct flowi_tunnel flowic_tun_key;
};
union flowi_uli {
@@ -66,6 +71,7 @@ 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 +101,7 @@ 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;
@@ -165,6 +172,7 @@ 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)
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/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/ip.h b/include/net/ip.h
index d5fe9f2ab699..bee5f3582e38 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -370,22 +370,6 @@ 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);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3b76849c190f..276328e3daa6 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 {
@@ -131,6 +133,7 @@ struct rt6_info {
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
+ struct lwtunnel_state *rt6i_lwtstate;
};
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
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..984dbfa15e13 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -9,9 +9,9 @@
#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 +22,37 @@
/* 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 \
+ (offsetof(struct ip_tunnel_key, tp_dst) + \
+ FIELD_SIZEOF(struct ip_tunnel_key, tp_dst))
+
+struct ip_tunnel_key {
+ __be64 tun_id;
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ __be16 tun_flags;
+ __u8 ipv4_tos;
+ __u8 ipv4_ttl;
+ __be16 tp_src;
+ __be16 tp_dst;
+} __packed __aligned(4); /* Minimize padding. */
+
+/* Indicates whether the tunnel info structure represents receive
+ * or transmit tunnel parameters.
+ */
+enum {
+ IP_TUNNEL_INFO_RX,
+ IP_TUNNEL_INFO_TX,
+};
+
+struct ip_tunnel_info {
+ struct ip_tunnel_key key;
+ const void *options;
+ u8 options_len;
+ u8 mode;
+};
+
/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
@@ -51,6 +82,8 @@ struct ip_tunnel_dst {
__be32 saddr;
};
+struct metadata_dst;
+
struct ip_tunnel {
struct ip_tunnel __rcu *next;
struct hlist_node hash_node;
@@ -84,6 +117,7 @@ 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 +152,7 @@ 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 +171,47 @@ 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_info_init(struct ip_tunnel_info *tun_info,
+ __be32 saddr, __be32 daddr,
+ u8 tos, u8 ttl,
+ __be16 tp_src, __be16 tp_dst,
+ __be64 tun_id, __be16 tun_flags,
+ const void *opts, u8 opts_len)
+{
+ tun_info->key.tun_id = tun_id;
+ tun_info->key.ipv4_src = saddr;
+ tun_info->key.ipv4_dst = daddr;
+ tun_info->key.ipv4_tos = tos;
+ tun_info->key.ipv4_ttl = ttl;
+ tun_info->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.
+ */
+ tun_info->key.tp_src = tp_src;
+ tun_info->key.tp_dst = tp_dst;
+
+ /* Clear struct padding. */
+ if (sizeof(tun_info->key) != IP_TUNNEL_KEY_SIZE)
+ memset((unsigned char *)&tun_info->key + IP_TUNNEL_KEY_SIZE,
+ 0, sizeof(tun_info->key) - IP_TUNNEL_KEY_SIZE);
+
+ tun_info->options = opts;
+ tun_info->options_len = opts_len;
+}
+
+static inline void ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
+ const struct iphdr *iph,
+ __be16 tp_src, __be16 tp_dst,
+ __be64 tun_id, __be16 tun_flags,
+ const void *opts, u8 opts_len)
+{
+ __ip_tunnel_info_init(tun_info, iph->saddr, iph->daddr,
+ iph->tos, iph->ttl, tp_src, tp_dst,
+ tun_id, tun_flags, opts, opts_len);
+}
+
#ifdef CONFIG_INET
int ip_tunnel_init(struct net_device *dev);
@@ -163,7 +239,8 @@ 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[],
@@ -221,6 +298,44 @@ static inline void iptunnel_xmit_stats(int err,
}
}
+static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info, size_t n)
+{
+ return info + 1;
+}
+
+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/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..33bd30963a95
--- /dev/null
+++ b/include/net/lwtunnel.h
@@ -0,0 +1,147 @@
+#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 0x1
+
+struct lwtunnel_state {
+ __u16 type;
+ __u16 flags;
+ atomic_t refcnt;
+ int len;
+ __u8 data[0];
+};
+
+struct lwtunnel_encap_ops {
+ int (*build_state)(struct net_device *dev, struct nlattr *encap,
+ struct lwtunnel_state **ts);
+ int (*output)(struct sock *sk, 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 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))
+ kfree(lws);
+}
+
+static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
+{
+ if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_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,
+ 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_output6(struct sock *sk, struct sk_buff *skb);
+
+#else
+
+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 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,
+ 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_output6(struct sock *sk, struct sk_buff *skb)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* __NET_LWTUNNEL_H */
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/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/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/route.h b/include/net/route.h
index fe22d03afb6a..2d45f419477f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -66,6 +66,7 @@ struct rtable {
struct list_head rt_uncached;
struct uncached_list *rt_uncached_list;
+ struct lwtunnel_state *rt_lwtstate;
};
static inline bool rt_is_input_route(const struct rtable *rt)
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..2eab08c38e32 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -513,17 +513,20 @@ 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 +550,24 @@ 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_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..364426a2be5a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -989,6 +989,11 @@ 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 +1070,7 @@ 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;
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/vxlan.h b/include/net/vxlan.h
index 0082b5d33d7d..e4534f1b2d8c 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 +116,57 @@ 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 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 +180,7 @@ 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 +188,16 @@ 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)
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..d450be36add2 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 +230,7 @@ enum {
IFLA_BR_AGEING_TIME,
IFLA_BR_STP_STATE,
IFLA_BR_PRIORITY,
+ IFLA_BR_VLAN_FILTERING,
__IFLA_BR_MAX,
};
@@ -381,6 +383,7 @@ 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)
@@ -431,6 +434,7 @@ 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_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/ipv6.h b/include/uapi/linux/ipv6.h
index 5efa54ae567c..80f3b74446a1 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -171,6 +171,8 @@ enum {
DEVCONF_USE_OPTIMISTIC,
DEVCONF_ACCEPT_RA_MTU,
DEVCONF_STABLE_SECRET,
+ DEVCONF_USE_OIF_ADDRS_ONLY,
+ DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
new file mode 100644
index 000000000000..31377bbea3f8
--- /dev/null
+++ b/include/uapi/linux/lwtunnel.h
@@ -0,0 +1,16 @@
+#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_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_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/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/openvswitch.h b/include/uapi/linux/openvswitch.h
index 1dab77601c21..d6b885460187 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -321,7 +321,7 @@ enum ovs_key_attr {
* the accepted length of the array. */
#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
};
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index fdd8f07f1d34..47d24cb3fbc1 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -286,6 +286,21 @@ enum rt_class_t {
/* Routing message attributes */
+enum ip_tunnel_t {
+ IP_TUN_UNSPEC,
+ IP_TUN_ID,
+ IP_TUN_DST,
+ IP_TUN_SRC,
+ IP_TUN_TTL,
+ IP_TUN_TOS,
+ IP_TUN_SPORT,
+ IP_TUN_DPORT,
+ IP_TUN_FLAGS,
+ __IP_TUN_MAX,
+};
+
+#define IP_TUN_MAX (__IP_TUN_MAX - 1)
+
enum rtattr_type_t {
RTA_UNSPEC,
RTA_DST,
@@ -308,6 +323,8 @@ enum rtattr_type_t {
RTA_VIA,
RTA_NEWDST,
RTA_PREF,
+ RTA_ENCAP_TYPE,
+ RTA_ENCAP,
__RTA_MAX
};
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
};