summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/avf/virtchnl.h20
-rw-r--r--include/linux/bpf-cgroup.h69
-rw-r--r--include/linux/bpf.h174
-rw-r--r--include/linux/bpf_types.h32
-rw-r--r--include/linux/bpf_verifier.h47
-rw-r--r--include/linux/brcmphy.h1
-rw-r--r--include/linux/byteorder/generic.h16
-rw-r--r--include/linux/connector.h4
-rw-r--r--include/linux/device_cgroup.h67
-rw-r--r--include/linux/dsa/lan9303.h38
-rw-r--r--include/linux/dynamic_queue_limits.h2
-rw-r--r--include/linux/etherdevice.h1
-rw-r--r--include/linux/ethtool.h10
-rw-r--r--include/linux/filter.h32
-rw-r--r--include/linux/ieee80211.h1
-rw-r--r--include/linux/if_arp.h2
-rw-r--r--include/linux/if_bridge.h6
-rw-r--r--include/linux/if_frad.h1
-rw-r--r--include/linux/if_macvlan.h18
-rw-r--r--include/linux/if_phonet.h2
-rw-r--r--include/linux/if_tap.h4
-rw-r--r--include/linux/inetdevice.h2
-rw-r--r--include/linux/ipv6.h1
-rw-r--r--include/linux/lsm_hooks.h54
-rw-r--r--include/linux/mlx4/device.h8
-rw-r--r--include/linux/mlx5/cq.h4
-rw-r--r--include/linux/mlx5/device.h31
-rw-r--r--include/linux/mlx5/driver.h33
-rw-r--r--include/linux/mlx5/mlx5_ifc.h60
-rw-r--r--include/linux/mlx5/port.h5
-rw-r--r--include/linux/mlx5/qp.h1
-rw-r--r--include/linux/mod_devicetable.h26
-rw-r--r--include/linux/mroute.h46
-rw-r--r--include/linux/netdevice.h120
-rw-r--r--include/linux/netlink.h3
-rw-r--r--include/linux/of.h62
-rw-r--r--include/linux/once.h6
-rw-r--r--include/linux/phy.h2
-rw-r--r--include/linux/qed/qed_ll2_if.h8
-rw-r--r--include/linux/rtnetlink.h4
-rw-r--r--include/linux/security.h48
-rw-r--r--include/linux/skbuff.h134
-rw-r--r--include/linux/tcp.h24
-rw-r--r--include/linux/thunderbolt.h598
-rw-r--r--include/linux/trace_events.h43
-rw-r--r--include/net/act_api.h37
-rw-r--r--include/net/addrconf.h10
-rw-r--r--include/net/af_rxrpc.h7
-rw-r--r--include/net/af_vsock.h20
-rw-r--r--include/net/bluetooth/bluetooth.h3
-rw-r--r--include/net/bluetooth/hci.h2
-rw-r--r--include/net/bonding.h7
-rw-r--r--include/net/cfg80211.h40
-rw-r--r--include/net/dn.h7
-rw-r--r--include/net/dn_nsp.h1
-rw-r--r--include/net/dsa.h132
-rw-r--r--include/net/dst.h17
-rw-r--r--include/net/dst_metadata.h6
-rw-r--r--include/net/fib_notifier.h3
-rw-r--r--include/net/flow_dissector.h12
-rw-r--r--include/net/fq.h7
-rw-r--r--include/net/fq_impl.h72
-rw-r--r--include/net/inet_connection_sock.h6
-rw-r--r--include/net/inet_ecn.h5
-rw-r--r--include/net/inet_frag.h2
-rw-r--r--include/net/inet_sock.h3
-rw-r--r--include/net/ip6_fib.h79
-rw-r--r--include/net/ip6_route.h5
-rw-r--r--include/net/ip_fib.h3
-rw-r--r--include/net/ip_tunnels.h3
-rw-r--r--include/net/ipv6.h45
-rw-r--r--include/net/llc_c_ac.h8
-rw-r--r--include/net/mac80211.h8
-rw-r--r--include/net/neighbour.h4
-rw-r--r--include/net/netevent.h1
-rw-r--r--include/net/netfilter/ipv4/nf_conntrack_ipv4.h2
-rw-r--r--include/net/netfilter/ipv6/nf_conntrack_ipv6.h2
-rw-r--r--include/net/netfilter/nf_conntrack_l4proto.h25
-rw-r--r--include/net/netfilter/nf_tables.h5
-rw-r--r--include/net/netns/ipv4.h41
-rw-r--r--include/net/netns/ipv6.h9
-rw-r--r--include/net/nsh.h3
-rw-r--r--include/net/phonet/phonet.h6
-rw-r--r--include/net/pkt_cls.h233
-rw-r--r--include/net/pkt_sched.h21
-rw-r--r--include/net/request_sock.h2
-rw-r--r--include/net/rtnetlink.h5
-rw-r--r--include/net/sch_generic.h51
-rw-r--r--include/net/sctp/sm.h10
-rw-r--r--include/net/sctp/stream_sched.h72
-rw-r--r--include/net/sctp/structs.h63
-rw-r--r--include/net/sock.h35
-rw-r--r--include/net/switchdev.h2
-rw-r--r--include/net/tc_act/tc_gact.h5
-rw-r--r--include/net/tc_act/tc_ife.h12
-rw-r--r--include/net/tc_act/tc_mirred.h1
-rw-r--r--include/net/tc_act/tc_vlan.h46
-rw-r--r--include/net/tcp.h224
-rw-r--r--include/net/tipc.h62
-rw-r--r--include/net/tls.h23
-rw-r--r--include/net/xfrm.h8
-rw-r--r--include/trace/events/bpf.h5
-rw-r--r--include/trace/events/fib6.h6
-rw-r--r--include/trace/events/sock.h2
-rw-r--r--include/trace/events/tcp.h299
-rw-r--r--include/trace/events/xdp.h80
-rw-r--r--include/trace/perf.h6
-rw-r--r--include/uapi/linux/batman_adv.h369
-rw-r--r--include/uapi/linux/bpf.h158
-rw-r--r--include/uapi/linux/dcbnl.h1
-rw-r--r--include/uapi/linux/if_link.h8
-rw-r--r--include/uapi/linux/if_tun.h2
-rw-r--r--include/uapi/linux/if_tunnel.h1
-rw-r--r--include/uapi/linux/ila.h21
-rw-r--r--include/uapi/linux/in6.h1
-rw-r--r--include/uapi/linux/ip6_tunnel.h2
-rw-r--r--include/uapi/linux/ipv6.h1
-rw-r--r--include/uapi/linux/ipv6_route.h2
-rw-r--r--include/uapi/linux/nfc.h2
-rw-r--r--include/uapi/linux/nl80211.h82
-rw-r--r--include/uapi/linux/openvswitch.h88
-rw-r--r--include/uapi/linux/pkt_sched.h63
-rw-r--r--include/uapi/linux/qrtr.h35
-rw-r--r--include/uapi/linux/rtnetlink.h2
-rw-r--r--include/uapi/linux/rxrpc.h10
-rw-r--r--include/uapi/linux/sctp.h16
-rw-r--r--include/uapi/linux/snmp.h1
-rw-r--r--include/uapi/linux/tc_act/tc_mirred.h6
-rw-r--r--include/uapi/linux/tcp.h2
-rw-r--r--include/uapi/linux/tipc.h15
-rw-r--r--include/uapi/linux/tls.h4
-rw-r--r--include/uapi/linux/vm_sockets_diag.h33
132 files changed, 4042 insertions, 674 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 2b038442c352..3ce61342fa31 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -135,6 +135,7 @@ enum virtchnl_ops {
VIRTCHNL_OP_SET_RSS_HENA = 26,
VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27,
VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28,
+ VIRTCHNL_OP_REQUEST_QUEUES = 29,
};
/* This macro is used to generate a compilation error if a structure
@@ -235,6 +236,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
#define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008
#define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010
#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020
+#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040
#define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000
#define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000
#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000
@@ -325,6 +327,21 @@ struct virtchnl_vsi_queue_config_info {
struct virtchnl_queue_pair_info qpair[1];
};
+/* VIRTCHNL_OP_REQUEST_QUEUES
+ * VF sends this message to request the PF to allocate additional queues to
+ * this VF. Each VF gets a guaranteed number of queues on init but asking for
+ * additional queues must be negotiated. This is a best effort request as it
+ * is possible the PF does not have enough queues left to support the request.
+ * If the PF cannot support the number requested it will respond with the
+ * maximum number it is able to support. If the request is successful, PF will
+ * then reset the VF to institute required changes.
+ */
+
+/* VF resource request */
+struct virtchnl_vf_res_request {
+ u16 num_queue_pairs;
+};
+
VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
/* VIRTCHNL_OP_CONFIG_IRQ_MAP
@@ -691,6 +708,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
break;
+ case VIRTCHNL_OP_REQUEST_QUEUES:
+ valid_len = sizeof(struct virtchnl_vf_res_request);
+ break;
/* These are always errors coming from the VF. */
case VIRTCHNL_OP_EVENT:
case VIRTCHNL_OP_UNKNOWN:
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 44dfae288fcf..a7f16e0f8d68 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -15,27 +15,46 @@ struct bpf_sock_ops_kern;
extern struct static_key_false cgroup_bpf_enabled_key;
#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
+struct bpf_prog_list {
+ struct list_head node;
+ struct bpf_prog *prog;
+};
+
+struct bpf_prog_array;
+
struct cgroup_bpf {
- /*
- * Store two sets of bpf_prog pointers, one for programs that are
- * pinned directly to this cgroup, and one for those that are effective
- * when this cgroup is accessed.
+ /* array of effective progs in this cgroup */
+ struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE];
+
+ /* attached progs to this cgroup and attach flags
+ * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
+ * have either zero or one element
+ * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
*/
- struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
- struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
- bool disallow_override[MAX_BPF_ATTACH_TYPE];
+ struct list_head progs[MAX_BPF_ATTACH_TYPE];
+ u32 flags[MAX_BPF_ATTACH_TYPE];
+
+ /* temp storage for effective prog array used by prog_attach/detach */
+ struct bpf_prog_array __rcu *inactive;
};
void cgroup_bpf_put(struct cgroup *cgrp);
-void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
-
-int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
- struct bpf_prog *prog, enum bpf_attach_type type,
- bool overridable);
-
-/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type, bool overridable);
+int cgroup_bpf_inherit(struct cgroup *cgrp);
+
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+
+/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
int __cgroup_bpf_run_filter_skb(struct sock *sk,
struct sk_buff *skb,
@@ -48,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
struct bpf_sock_ops_kern *sock_ops,
enum bpf_attach_type type);
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+ short access, enum bpf_attach_type type);
+
/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
({ \
@@ -93,17 +115,28 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
} \
__ret; \
})
+
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \
+ access, \
+ BPF_CGROUP_DEVICE); \
+ \
+ __ret; \
+})
#else
struct cgroup_bpf {};
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
-static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
- struct cgroup *parent) {}
+static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
#endif /* CONFIG_CGROUP_BPF */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f1af7d63d678..c397934f91dd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -15,6 +15,7 @@
#include <linux/err.h>
#include <linux/rbtree_latch.h>
#include <linux/numa.h>
+#include <linux/wait.h>
struct perf_event;
struct bpf_prog;
@@ -56,6 +57,10 @@ struct bpf_map {
struct work_struct work;
atomic_t usercnt;
struct bpf_map *inner_map_meta;
+ char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+ void *security;
+#endif
};
/* function argument constraints */
@@ -137,6 +142,7 @@ enum bpf_reg_type {
PTR_TO_MAP_VALUE, /* reg points to map element value */
PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
PTR_TO_STACK, /* reg == frame_pointer + offset */
+ PTR_TO_PACKET_META, /* skb->data - meta_len */
PTR_TO_PACKET, /* reg points to skb->data */
PTR_TO_PACKET_END, /* skb->data + headlen */
};
@@ -155,6 +161,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
aux->ctx_field_size = size;
}
+struct bpf_prog_ops {
+ int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
+};
+
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
@@ -170,8 +181,16 @@ struct bpf_verifier_ops {
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog, u32 *target_size);
- int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
- union bpf_attr __user *uattr);
+};
+
+struct bpf_dev_offload {
+ struct bpf_prog *prog;
+ struct net_device *netdev;
+ void *dev_priv;
+ struct list_head offloads;
+ bool dev_state;
+ bool verifier_running;
+ wait_queue_head_t verifier_done;
};
struct bpf_prog_aux {
@@ -182,10 +201,16 @@ struct bpf_prog_aux {
u32 id;
struct latch_tree_node ksym_tnode;
struct list_head ksym_lnode;
- const struct bpf_verifier_ops *ops;
+ const struct bpf_prog_ops *ops;
struct bpf_map **used_maps;
struct bpf_prog *prog;
struct user_struct *user;
+ u64 load_time; /* ns since boottime */
+ char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+ void *security;
+#endif
+ struct bpf_dev_offload *offload;
union {
struct work_struct work;
struct rcu_head rcu;
@@ -218,9 +243,6 @@ struct bpf_event_entry {
struct rcu_head rcu;
};
-u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
-u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
int bpf_prog_calc_tag(struct bpf_prog *fp);
@@ -237,19 +259,84 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
+/* an array of programs to be executed under rcu_lock.
+ *
+ * Typical usage:
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ *
+ * the structure returned by bpf_prog_array_alloc() should be populated
+ * with program pointers and the last pointer must be NULL.
+ * The user has to keep refcnt on the program and make sure the program
+ * is removed from the array before bpf_prog_put().
+ * The 'struct bpf_prog_array *' should only be replaced with xchg()
+ * since other cpus are walking the array of pointers in parallel.
+ */
+struct bpf_prog_array {
+ struct rcu_head rcu;
+ struct bpf_prog *progs[0];
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+ __u32 __user *prog_ids, u32 cnt);
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+ struct bpf_prog *old_prog);
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array);
+
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
+ ({ \
+ struct bpf_prog **_prog, *__prog; \
+ struct bpf_prog_array *_array; \
+ u32 _ret = 1; \
+ rcu_read_lock(); \
+ _array = rcu_dereference(array); \
+ if (unlikely(check_non_null && !_array))\
+ goto _out; \
+ _prog = _array->progs; \
+ while ((__prog = READ_ONCE(*_prog))) { \
+ _ret &= func(__prog, ctx); \
+ _prog++; \
+ } \
+_out: \
+ rcu_read_unlock(); \
+ _ret; \
+ })
+
+#define BPF_PROG_RUN_ARRAY(array, ctx, func) \
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+
+#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
-#define BPF_PROG_TYPE(_id, _ops) \
- extern const struct bpf_verifier_ops _ops;
+extern const struct file_operations bpf_map_fops;
+extern const struct file_operations bpf_prog_fops;
+
+#define BPF_PROG_TYPE(_id, _name) \
+ extern const struct bpf_prog_ops _name ## _prog_ops; \
+ extern const struct bpf_verifier_ops _name ## _verifier_ops;
#define BPF_MAP_TYPE(_id, _ops) \
extern const struct bpf_map_ops _ops;
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
+extern const struct bpf_prog_ops bpf_offload_prog_ops;
+extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
+extern const struct bpf_verifier_ops xdp_analyzer_ops;
+
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
+struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
+ struct net_device *netdev);
struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
void bpf_prog_sub(struct bpf_prog *prog, int i);
struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog);
@@ -269,11 +356,11 @@ void bpf_map_area_free(void *base);
extern int sysctl_unprivileged_bpf_disabled;
-int bpf_map_new_fd(struct bpf_map *map);
+int bpf_map_new_fd(struct bpf_map *map, int flags);
int bpf_prog_new_fd(struct bpf_prog *prog);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname);
+int bpf_obj_get_user(const char __user *pathname, int flags);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
@@ -292,6 +379,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
+int bpf_get_file_flag(int flags);
+
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
* Best-effort only. No barriers here, since it _will_ race with concurrent
@@ -316,6 +405,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
+void __cpu_map_flush(struct bpf_map *map);
+struct xdp_buff;
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx);
+
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
@@ -323,7 +419,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
attr->numa_node : NUMA_NO_NODE;
}
-#else
+#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
@@ -334,6 +430,14 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
{
return ERR_PTR(-EOPNOTSUPP);
}
+
+static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
+ enum bpf_prog_type type,
+ struct net_device *netdev)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog,
int i)
{
@@ -368,7 +472,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
{
}
-static inline int bpf_obj_get_user(const char __user *pathname)
+static inline int bpf_obj_get_user(const char __user *pathname, int flags)
{
return -EOPNOTSUPP;
}
@@ -386,8 +490,54 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
static inline void __dev_map_flush(struct bpf_map *map)
{
}
+
+static inline
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ return NULL;
+}
+
+static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
+{
+}
+
+static inline void __cpu_map_flush(struct bpf_map *map)
+{
+}
+
+struct xdp_buff;
+static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return 0;
+}
#endif /* CONFIG_BPF_SYSCALL */
+int bpf_prog_offload_compile(struct bpf_prog *prog);
+void bpf_prog_offload_destroy(struct bpf_prog *prog);
+u32 bpf_prog_offload_ifindex(struct bpf_prog *prog);
+
+#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+ return aux->offload;
+}
+#else
+static inline int bpf_prog_offload_init(struct bpf_prog *prog,
+ union bpf_attr *attr)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+ return false;
+}
+#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
+
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index e1149327a0c0..978c1d9c9383 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -2,22 +2,25 @@
/* internal file - do not include directly */
#ifdef CONFIG_NET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
+BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
#endif
#ifdef CONFIG_BPF_EVENTS
-BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops)
+BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
+BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
+#endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
@@ -42,4 +45,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
#ifdef CONFIG_STREAM_PARSER
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b8d200f60a40..07b96aaca256 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -88,14 +88,19 @@ enum bpf_stack_slot_type {
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
+struct bpf_stack_state {
+ struct bpf_reg_state spilled_ptr;
+ u8 slot_type[BPF_REG_SIZE];
+};
+
/* state of the program:
* type of all registers and stack info
*/
struct bpf_verifier_state {
struct bpf_reg_state regs[MAX_BPF_REG];
- u8 stack_slot_type[MAX_BPF_STACK];
- struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE];
struct bpf_verifier_state *parent;
+ int allocated_stack;
+ struct bpf_stack_state *stack;
};
/* linked list of verifier states used to prune search */
@@ -115,6 +120,21 @@ struct bpf_insn_aux_data {
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
+#define BPF_VERIFIER_TMP_LOG_SIZE 1024
+
+struct bpf_verifer_log {
+ u32 level;
+ char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
+ char __user *ubuf;
+ u32 len_used;
+ u32 len_total;
+};
+
+static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log)
+{
+ return log->len_used >= log->len_total - 1;
+}
+
struct bpf_verifier_env;
struct bpf_ext_analyzer_ops {
int (*insn_hook)(struct bpf_verifier_env *env,
@@ -126,22 +146,35 @@ struct bpf_ext_analyzer_ops {
*/
struct bpf_verifier_env {
struct bpf_prog *prog; /* eBPF program being verified */
+ const struct bpf_verifier_ops *ops;
struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
int stack_size; /* number of states to be processed */
bool strict_alignment; /* perform strict pointer alignment checks */
- struct bpf_verifier_state cur_state; /* current verifier state */
+ struct bpf_verifier_state *cur_state; /* current verifier state */
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
- const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */
- void *analyzer_priv; /* pointer to external analyzer's private data */
+ const struct bpf_ext_analyzer_ops *dev_ops; /* device analyzer ops */
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
u32 id_gen; /* used to generate unique reg IDs */
bool allow_ptr_leaks;
bool seen_direct_write;
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
+
+ struct bpf_verifer_log log;
};
-int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
- void *priv);
+static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
+{
+ return env->cur_state->regs;
+}
+
+#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
+#else
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+{
+ return -EOPNOTSUPP;
+}
+#endif
#endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 4f087f86a741..8ff86b4c1b8a 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -64,6 +64,7 @@
#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000
#define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000
#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000
+#define PHY_BRCM_EN_MASTER_MODE 0x00010000
/* Broadcom BCM7xxx specific workarounds */
#define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff)
diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h
index 133b76d0d2c0..451aaa0786ae 100644
--- a/include/linux/byteorder/generic.h
+++ b/include/linux/byteorder/generic.h
@@ -171,4 +171,20 @@ static inline void be64_add_cpu(__be64 *var, u64 val)
*var = cpu_to_be64(be64_to_cpu(*var) + val);
}
+static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len)
+{
+ int i;
+
+ for (i = 0; i < len; i++)
+ dst[i] = cpu_to_be32(src[i]);
+}
+
+static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len)
+{
+ int i;
+
+ for (i = 0; i < len; i++)
+ dst[i] = be32_to_cpu(src[i]);
+}
+
#endif /* _LINUX_BYTEORDER_GENERIC_H */
diff --git a/include/linux/connector.h b/include/linux/connector.h
index f8fe8637d771..032102b19645 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -22,7 +22,7 @@
#define __CONNECTOR_H
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/list.h>
#include <linux/workqueue.h>
@@ -49,7 +49,7 @@ struct cn_callback_id {
struct cn_callback_entry {
struct list_head callback_entry;
- atomic_t refcnt;
+ refcount_t refcnt;
struct cn_queue_dev *pdev;
struct cn_callback_id id;
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index cdbc344a92e4..8557efe096dc 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -1,17 +1,76 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/fs.h>
+#include <linux/bpf-cgroup.h>
+
+#define DEVCG_ACC_MKNOD 1
+#define DEVCG_ACC_READ 2
+#define DEVCG_ACC_WRITE 4
+#define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE)
+
+#define DEVCG_DEV_BLOCK 1
+#define DEVCG_DEV_CHAR 2
+#define DEVCG_DEV_ALL 4 /* this represents all devices */
#ifdef CONFIG_CGROUP_DEVICE
-extern int __devcgroup_inode_permission(struct inode *inode, int mask);
-extern int devcgroup_inode_mknod(int mode, dev_t dev);
+extern int __devcgroup_check_permission(short type, u32 major, u32 minor,
+ short access);
+#else
+static inline int __devcgroup_check_permission(short type, u32 major, u32 minor,
+ short access)
+{ return 0; }
+#endif
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
+ short access)
+{
+ int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
+
+ if (rc)
+ return -EPERM;
+
+ return __devcgroup_check_permission(type, major, minor, access);
+}
+
static inline int devcgroup_inode_permission(struct inode *inode, int mask)
{
+ short type, access = 0;
+
if (likely(!inode->i_rdev))
return 0;
- if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
+
+ if (S_ISBLK(inode->i_mode))
+ type = DEVCG_DEV_BLOCK;
+ else if (S_ISCHR(inode->i_mode))
+ type = DEVCG_DEV_CHAR;
+ else
+ return 0;
+
+ if (mask & MAY_WRITE)
+ access |= DEVCG_ACC_WRITE;
+ if (mask & MAY_READ)
+ access |= DEVCG_ACC_READ;
+
+ return devcgroup_check_permission(type, imajor(inode), iminor(inode),
+ access);
+}
+
+static inline int devcgroup_inode_mknod(int mode, dev_t dev)
+{
+ short type;
+
+ if (!S_ISBLK(mode) && !S_ISCHR(mode))
return 0;
- return __devcgroup_inode_permission(inode, mask);
+
+ if (S_ISBLK(mode))
+ type = DEVCG_DEV_BLOCK;
+ else
+ type = DEVCG_DEV_CHAR;
+
+ return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
+ DEVCG_ACC_MKNOD);
}
+
#else
static inline int devcgroup_inode_permission(struct inode *inode, int mask)
{ return 0; }
diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h
new file mode 100644
index 000000000000..f48a85c377de
--- /dev/null
+++ b/include/linux/dsa/lan9303.h
@@ -0,0 +1,38 @@
+/* Included by drivers/net/dsa/lan9303.h and net/dsa/tag_lan9303.c */
+#include <linux/if_ether.h>
+
+struct lan9303;
+
+struct lan9303_phy_ops {
+ /* PHY 1 and 2 access*/
+ int (*phy_read)(struct lan9303 *chip, int port, int regnum);
+ int (*phy_write)(struct lan9303 *chip, int port,
+ int regnum, u16 val);
+};
+
+#define LAN9303_NUM_ALR_RECORDS 512
+struct lan9303_alr_cache_entry {
+ u8 mac_addr[ETH_ALEN];
+ u8 port_map; /* Bitmap of ports. Zero if unused entry */
+ u8 stp_override; /* non zero if set LAN9303_ALR_DAT1_AGE_OVERRID */
+};
+
+struct lan9303 {
+ struct device *dev;
+ struct regmap *regmap;
+ struct regmap_irq_chip_data *irq_data;
+ struct gpio_desc *reset_gpio;
+ u32 reset_duration; /* in [ms] */
+ bool phy_addr_sel_strap;
+ struct dsa_switch *ds;
+ struct mutex indirect_mutex; /* protect indexed register access */
+ const struct lan9303_phy_ops *ops;
+ bool is_bridged; /* true if port 1 and 2 are bridged */
+
+ /* remember LAN9303_SWE_PORT_STATE while not bridged */
+ u32 swe_port_state;
+ /* LAN9303 do not offer reading specific ALR entry. Cache all
+ * static entries in a flat table
+ **/
+ struct lan9303_alr_cache_entry alr_cache[LAN9303_NUM_ALR_RECORDS];
+};
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 023eae69398c..99fc06f0afc1 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -99,7 +99,7 @@ void dql_completed(struct dql *dql, unsigned int count);
void dql_reset(struct dql *dql);
/* Initialize dql state */
-int dql_init(struct dql *dql, unsigned hold_time);
+void dql_init(struct dql *dql, unsigned int hold_time);
#endif /* _KERNEL_ */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2d9f80848d4b..263dbcad22fc 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -66,6 +66,7 @@ int eth_gro_complete(struct sk_buff *skb, int nhoff);
/* Reserved Ethernet Addresses per IEEE 802.1Q */
static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+#define eth_stp_addr eth_reserved_addr_base
/**
* is_link_local_ether_addr - Determine if given Ethernet address is link-local
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 0c0146e7e274..2ec41a7eb54f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -164,6 +164,16 @@ extern int
__ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *link_ksettings);
+/**
+ * ethtool_intersect_link_masks - Given two link masks, AND them together
+ * @dst: first mask and where result is stored
+ * @src: second mask to intersect with
+ *
+ * Given two link mode masks, AND them together and save the result in dst.
+ */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+ struct ethtool_link_ksettings *src);
+
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 48ec57e70f9f..0cd02ff4ae30 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -482,30 +482,36 @@ struct sk_filter {
struct bpf_prog *prog;
};
-#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi)
+#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi)
#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
struct bpf_skb_data_end {
struct qdisc_skb_cb qdisc_cb;
+ void *data_meta;
void *data_end;
};
struct xdp_buff {
void *data;
void *data_end;
+ void *data_meta;
void *data_hard_start;
};
-/* compute the linear packet data range [data, data_end) which
- * will be accessed by cls_bpf, act_bpf and lwt programs
+/* Compute the linear packet data range [data, data_end) which
+ * will be accessed by various program types (cls_bpf, act_bpf,
+ * lwt, ...). Subsystems allowing direct data access must (!)
+ * ensure that cb[] area can be written to when BPF program is
+ * invoked (otherwise cb[] save/restore is necessary).
*/
-static inline void bpf_compute_data_end(struct sk_buff *skb)
+static inline void bpf_compute_data_pointers(struct sk_buff *skb)
{
struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
- cb->data_end = skb->data + skb_headlen(skb);
+ cb->data_meta = skb->data - skb_metadata_len(skb);
+ cb->data_end = skb->data + skb_headlen(skb);
}
static inline u8 *bpf_skb_cb(struct sk_buff *skb)
@@ -726,8 +732,22 @@ int xdp_do_redirect(struct net_device *dev,
struct bpf_prog *prog);
void xdp_do_flush_map(void);
+/* Drivers not supporting XDP metadata can use this helper, which
+ * rejects any room expansion for metadata as a result.
+ */
+static __always_inline void
+xdp_set_data_meta_invalid(struct xdp_buff *xdp)
+{
+ xdp->data_meta = xdp->data + 1;
+}
+
+static __always_inline bool
+xdp_data_meta_unsupported(const struct xdp_buff *xdp)
+{
+ return unlikely(xdp->data_meta > xdp->data);
+}
+
void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_redirect(u32 ifindex);
struct sock *do_sk_redirect_map(struct sk_buff *skb);
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 55a604ad459f..ee6657a0ed69 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action {
#define WLAN_OUI_TYPE_MICROSOFT_WPA 1
#define WLAN_OUI_TYPE_MICROSOFT_WMM 2
#define WLAN_OUI_TYPE_MICROSOFT_WPS 4
+#define WLAN_OUI_TYPE_MICROSOFT_TPC 8
/*
* WMM/802.11e Tspec Element
diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index 3355efc89781..6756fea18b69 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -31,7 +31,7 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb)
return (struct arphdr *)skb_network_header(skb);
}
-static inline int arp_hdr_len(struct net_device *dev)
+static inline unsigned int arp_hdr_len(const struct net_device *dev)
{
switch (dev->type) {
#if IS_ENABLED(CONFIG_FIREWIRE_NET)
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3cd18ac0697f..02639ebea2f0 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -49,6 +49,7 @@ struct br_ip_list {
#define BR_MULTICAST_TO_UNICAST BIT(12)
#define BR_VLAN_TUNNEL BIT(13)
#define BR_BCAST_FLOOD BIT(14)
+#define BR_NEIGH_SUPPRESS BIT(15)
#define BR_DEFAULT_AGEING_TIME (300 * HZ)
@@ -63,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto);
bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto);
bool br_multicast_enabled(const struct net_device *dev);
+bool br_multicast_router(const struct net_device *dev);
#else
static inline int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list)
@@ -83,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev)
{
return false;
}
+static inline bool br_multicast_router(const struct net_device *dev)
+{
+ return false;
+}
#endif
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h
index 46df7e565d6f..82a1b4e93570 100644
--- a/include/linux/if_frad.h
+++ b/include/linux/if_frad.h
@@ -83,6 +83,7 @@ struct frad_local
/* fields that are used by the Sangoma SDLA cards */
struct timer_list timer;
+ struct net_device *dev;
int type; /* adapter type */
int state; /* state of the S502/8 control latch */
int buffer; /* current buffer for S508 firmware */
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 0e2c60efad2d..bedf54b6f943 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -11,13 +11,6 @@
#include <linux/u64_stats_sync.h>
struct macvlan_port;
-struct macvtap_queue;
-
-/*
- * Maximum times a macvtap device can be opened. This can be used to
- * configure the number of receive queue, e.g. for multiqueue virtio.
- */
-#define MAX_TAP_QUEUES 256
#define MACVLAN_MC_FILTER_BITS 8
#define MACVLAN_MC_FILTER_SZ (1 << MACVLAN_MC_FILTER_BITS)
@@ -36,14 +29,6 @@ struct macvlan_dev {
netdev_features_t set_features;
enum macvlan_mode mode;
u16 flags;
- /* This array tracks active taps. */
- struct tap_queue __rcu *taps[MAX_TAP_QUEUES];
- /* This list tracks all taps (both enabled and disabled) */
- struct list_head queue_list;
- int numvtaps;
- int numqueues;
- netdev_features_t tap_features;
- int minor;
int nest_level;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
@@ -73,7 +58,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
extern void macvlan_common_setup(struct net_device *dev);
extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[]);
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack);
extern void macvlan_count_rx(const struct macvlan_dev *vlan,
unsigned int len, bool success,
diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h
index 3b5c60da2e2a..2d8486168ec5 100644
--- a/include/linux/if_phonet.h
+++ b/include/linux/if_phonet.h
@@ -11,5 +11,5 @@
#include <uapi/linux/if_phonet.h>
-extern struct header_ops phonet_header_ops;
+extern const struct header_ops phonet_header_ops;
#endif
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 13edf19ce9fb..3ecef57c31e3 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -23,6 +23,10 @@ static inline struct skb_array *tap_get_skb_array(struct file *f)
#include <net/sock.h>
#include <linux/skb_array.h>
+/*
+ * Maximum times a tap device can be opened. This can be used to
+ * configure the number of receive queue, e.g. for multiqueue virtio.
+ */
#define MAX_TAP_QUEUES 256
struct tap_queue;
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 5058f061cb2b..1ac5bf95bfdd 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -155,6 +155,7 @@ struct in_ifaddr {
struct in_validator_info {
__be32 ivi_addr;
struct in_device *ivi_dev;
+ struct netlink_ext_ack *extack;
};
int register_inetaddr_notifier(struct notifier_block *nb);
@@ -180,6 +181,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst,
__be32 local, int scope);
struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
__be32 mask);
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr);
static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa)
{
return !((addr^ifa->ifa_address)&ifa->ifa_mask);
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ea04ca024f0d..cb18c6290ca8 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -73,6 +73,7 @@ struct ipv6_devconf {
__u32 enhanced_dad;
__u32 addr_gen_mode;
__s32 disable_policy;
+ __s32 ndisc_tclass;
struct ctl_table_header *sysctl_header;
};
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index c9258124e417..7161d8e7ee79 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1351,6 +1351,40 @@
* @inode we wish to get the security context of.
* @ctx is a pointer in which to place the allocated security context.
* @ctxlen points to the place to put the length of @ctx.
+ *
+ * Security hooks for using the eBPF maps and programs functionalities through
+ * eBPF syscalls.
+ *
+ * @bpf:
+ * Do a initial check for all bpf syscalls after the attribute is copied
+ * into the kernel. The actual security module can implement their own
+ * rules to check the specific cmd they need.
+ *
+ * @bpf_map:
+ * Do a check when the kernel generate and return a file descriptor for
+ * eBPF maps.
+ *
+ * @map: bpf map that we want to access
+ * @mask: the access flags
+ *
+ * @bpf_prog:
+ * Do a check when the kernel generate and return a file descriptor for
+ * eBPF programs.
+ *
+ * @prog: bpf prog that userspace want to use.
+ *
+ * @bpf_map_alloc_security:
+ * Initialize the security field inside bpf map.
+ *
+ * @bpf_map_free_security:
+ * Clean up the security information stored inside bpf map.
+ *
+ * @bpf_prog_alloc_security:
+ * Initialize the security field inside bpf program.
+ *
+ * @bpf_prog_free_security:
+ * Clean up the security information stored inside bpf prog.
+ *
*/
union security_list_options {
int (*binder_set_context_mgr)(struct task_struct *mgr);
@@ -1682,6 +1716,17 @@ union security_list_options {
struct audit_context *actx);
void (*audit_rule_free)(void *lsmrule);
#endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+ int (*bpf)(int cmd, union bpf_attr *attr,
+ unsigned int size);
+ int (*bpf_map)(struct bpf_map *map, fmode_t fmode);
+ int (*bpf_prog)(struct bpf_prog *prog);
+ int (*bpf_map_alloc_security)(struct bpf_map *map);
+ void (*bpf_map_free_security)(struct bpf_map *map);
+ int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux);
+ void (*bpf_prog_free_security)(struct bpf_prog_aux *aux);
+#endif /* CONFIG_BPF_SYSCALL */
};
struct security_hook_heads {
@@ -1901,6 +1946,15 @@ struct security_hook_heads {
struct list_head audit_rule_match;
struct list_head audit_rule_free;
#endif /* CONFIG_AUDIT */
+#ifdef CONFIG_BPF_SYSCALL
+ struct list_head bpf;
+ struct list_head bpf_map;
+ struct list_head bpf_prog;
+ struct list_head bpf_map_alloc_security;
+ struct list_head bpf_map_free_security;
+ struct list_head bpf_prog_alloc_security;
+ struct list_head bpf_prog_free_security;
+#endif /* CONFIG_BPF_SYSCALL */
} __randomize_layout;
/*
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b0a57e043fa3..a9b5fed8f7c6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -40,7 +40,7 @@
#include <linux/cpu_rmap.h>
#include <linux/crash_dump.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/timecounter.h>
@@ -751,7 +751,7 @@ struct mlx4_cq {
int cqn;
unsigned vector;
- atomic_t refcount;
+ refcount_t refcount;
struct completion free;
struct {
struct list_head list;
@@ -768,7 +768,7 @@ struct mlx4_qp {
int qpn;
- atomic_t refcount;
+ refcount_t refcount;
struct completion free;
u8 usage;
};
@@ -781,7 +781,7 @@ struct mlx4_srq {
int max_gs;
int wqe_shift;
- atomic_t refcount;
+ refcount_t refcount;
struct completion free;
};
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 95898847c7d4..6a57ec2f1ef7 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -35,7 +35,7 @@
#include <rdma/ib_verbs.h>
#include <linux/mlx5/driver.h>
-
+#include <linux/refcount.h>
struct mlx5_core_cq {
u32 cqn;
@@ -43,7 +43,7 @@ struct mlx5_core_cq {
__be32 *set_ci_db;
__be32 *arm_db;
struct mlx5_uars_page *uar;
- atomic_t refcount;
+ refcount_t refcount;
struct completion free;
unsigned vector;
unsigned int irqn;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index e32dbc4934db..409ffb14298a 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -49,11 +49,15 @@
#define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0)
#define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld)
#define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld))
+#define __mlx5_16_off(typ, fld) (__mlx5_bit_off(typ, fld) / 16)
#define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32)
#define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64)
+#define __mlx5_16_bit_off(typ, fld) (16 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0xf))
#define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f))
#define __mlx5_mask(typ, fld) ((u32)((1ull << __mlx5_bit_sz(typ, fld)) - 1))
#define __mlx5_dw_mask(typ, fld) (__mlx5_mask(typ, fld) << __mlx5_dw_bit_off(typ, fld))
+#define __mlx5_mask16(typ, fld) ((u16)((1ull << __mlx5_bit_sz(typ, fld)) - 1))
+#define __mlx5_16_mask(typ, fld) (__mlx5_mask16(typ, fld) << __mlx5_16_bit_off(typ, fld))
#define __mlx5_st_sz_bits(typ) sizeof(struct mlx5_ifc_##typ##_bits)
#define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8)
@@ -116,6 +120,19 @@ __mlx5_mask(typ, fld))
___t; \
})
+#define MLX5_GET16(typ, p, fld) ((be16_to_cpu(*((__be16 *)(p) +\
+__mlx5_16_off(typ, fld))) >> __mlx5_16_bit_off(typ, fld)) & \
+__mlx5_mask16(typ, fld))
+
+#define MLX5_SET16(typ, p, fld, v) do { \
+ u16 _v = v; \
+ BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 16); \
+ *((__be16 *)(p) + __mlx5_16_off(typ, fld)) = \
+ cpu_to_be16((be16_to_cpu(*((__be16 *)(p) + __mlx5_16_off(typ, fld))) & \
+ (~__mlx5_16_mask(typ, fld))) | (((_v) & __mlx5_mask16(typ, fld)) \
+ << __mlx5_16_bit_off(typ, fld))); \
+} while (0)
+
/* Big endian getters */
#define MLX5_GET64_BE(typ, p, fld) (*((__be64 *)(p) +\
__mlx5_64_off(typ, fld)))
@@ -1000,6 +1017,14 @@ enum mlx5_mcam_feature_groups {
MLX5_MCAM_FEATURE_ENHANCED_FEATURES = 0x0,
};
+enum mlx5_qcam_reg_groups {
+ MLX5_QCAM_REGS_FIRST_128 = 0x0,
+};
+
+enum mlx5_qcam_feature_groups {
+ MLX5_QCAM_FEATURE_ENHANCED_FEATURES = 0x0,
+};
+
/* GET Dev Caps macros */
#define MLX5_CAP_GEN(mdev, cap) \
MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
@@ -1108,6 +1133,12 @@ enum mlx5_mcam_feature_groups {
#define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
+#define MLX5_CAP_QCAM_REG(mdev, fld) \
+ MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_access_reg_cap_mask.reg_cap.fld)
+
+#define MLX5_CAP_QCAM_FEATURE(mdev, fld) \
+ MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_feature_cap_mask.feature_cap.fld)
+
#define MLX5_CAP_FPGA(mdev, cap) \
MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 401c8972cc3a..a886b51511ab 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -49,6 +49,8 @@
#include <linux/mlx5/device.h>
#include <linux/mlx5/doorbell.h>
#include <linux/mlx5/srq.h>
+#include <linux/timecounter.h>
+#include <linux/ptp_clock_kernel.h>
enum {
MLX5_BOARD_ID_LEN = 64,
@@ -105,8 +107,11 @@ enum {
};
enum {
+ MLX5_REG_QPTS = 0x4002,
MLX5_REG_QETCR = 0x4005,
MLX5_REG_QTCT = 0x400a,
+ MLX5_REG_QPDPM = 0x4013,
+ MLX5_REG_QCAM = 0x4019,
MLX5_REG_DCBX_PARAM = 0x4020,
MLX5_REG_DCBX_APP = 0x4021,
MLX5_REG_FPGA_CAP = 0x4022,
@@ -139,6 +144,11 @@ enum {
MLX5_REG_MCAM = 0x907f,
};
+enum mlx5_qpts_trust_state {
+ MLX5_QPTS_TRUST_PCP = 1,
+ MLX5_QPTS_TRUST_DSCP = 2,
+};
+
enum mlx5_dcbx_oper_mode {
MLX5E_DCBX_PARAM_VER_OPER_HOST = 0x0,
MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3,
@@ -760,6 +770,27 @@ struct mlx5_rsvd_gids {
struct ida ida;
};
+#define MAX_PIN_NUM 8
+struct mlx5_pps {
+ u8 pin_caps[MAX_PIN_NUM];
+ struct work_struct out_work;
+ u64 start[MAX_PIN_NUM];
+ u8 enabled;
+};
+
+struct mlx5_clock {
+ rwlock_t lock;
+ struct cyclecounter cycles;
+ struct timecounter tc;
+ struct hwtstamp_config hwtstamp_config;
+ u32 nominal_c_mult;
+ unsigned long overflow_period;
+ struct delayed_work overflow_work;
+ struct ptp_clock *ptp;
+ struct ptp_clock_info ptp_info;
+ struct mlx5_pps pps_info;
+};
+
struct mlx5_core_dev {
struct pci_dev *pdev;
/* sync pci state */
@@ -775,6 +806,7 @@ struct mlx5_core_dev {
u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
+ u32 qcam[MLX5_ST_SZ_DW(qcam_reg)];
} caps;
phys_addr_t iseg_base;
struct mlx5_init_seg __iomem *iseg;
@@ -800,6 +832,7 @@ struct mlx5_core_dev {
#ifdef CONFIG_RFS_ACCEL
struct cpu_rmap *rmap;
#endif
+ struct mlx5_clock clock;
};
struct mlx5_db {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 69772347f866..3e5363f760dd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -838,7 +838,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 cc_modify_allowed[0x1];
u8 start_pad[0x1];
u8 cache_line_128byte[0x1];
- u8 reserved_at_165[0xb];
+ u8 reserved_at_165[0xa];
+ u8 qcam_reg[0x1];
u8 gid_table_size[0x10];
u8 out_of_seq_cnt[0x1];
@@ -7890,6 +7891,43 @@ struct mlx5_ifc_mcam_reg_bits {
u8 reserved_at_1c0[0x80];
};
+struct mlx5_ifc_qcam_access_reg_cap_mask {
+ u8 qcam_access_reg_cap_mask_127_to_20[0x6C];
+ u8 qpdpm[0x1];
+ u8 qcam_access_reg_cap_mask_18_to_4[0x0F];
+ u8 qdpm[0x1];
+ u8 qpts[0x1];
+ u8 qcap[0x1];
+ u8 qcam_access_reg_cap_mask_0[0x1];
+};
+
+struct mlx5_ifc_qcam_qos_feature_cap_mask {
+ u8 qcam_qos_feature_cap_mask_127_to_1[0x7F];
+ u8 qpts_trust_both[0x1];
+};
+
+struct mlx5_ifc_qcam_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 feature_group[0x8];
+ u8 reserved_at_10[0x8];
+ u8 access_reg_group[0x8];
+ u8 reserved_at_20[0x20];
+
+ union {
+ struct mlx5_ifc_qcam_access_reg_cap_mask reg_cap;
+ u8 reserved_at_0[0x80];
+ } qos_access_reg_cap_mask;
+
+ u8 reserved_at_c0[0x80];
+
+ union {
+ struct mlx5_ifc_qcam_qos_feature_cap_mask feature_cap;
+ u8 reserved_at_0[0x80];
+ } qos_feature_cap_mask;
+
+ u8 reserved_at_1c0[0x80];
+};
+
struct mlx5_ifc_pcap_reg_bits {
u8 reserved_at_0[0x8];
u8 local_port[0x8];
@@ -8540,6 +8578,26 @@ struct mlx5_ifc_qetc_reg_bits {
struct mlx5_ifc_ets_global_config_reg_bits global_configuration;
};
+struct mlx5_ifc_qpdpm_dscp_reg_bits {
+ u8 e[0x1];
+ u8 reserved_at_01[0x0b];
+ u8 prio[0x04];
+};
+
+struct mlx5_ifc_qpdpm_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 local_port[0x8];
+ u8 reserved_at_10[0x10];
+ struct mlx5_ifc_qpdpm_dscp_reg_bits dscp[64];
+};
+
+struct mlx5_ifc_qpts_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 local_port[0x8];
+ u8 reserved_at_10[0x2d];
+ u8 trust_state[0x3];
+};
+
struct mlx5_ifc_qtct_reg_bits {
u8 reserved_at_0[0x8];
u8 port_number[0x8];
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index c59af8ab753a..035f0d4dc9fe 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -179,4 +179,9 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
+
+int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
+int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
+int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
#endif /* __MLX5_PORT_H__ */
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 66d19b611fe4..62af7512dabb 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -221,6 +221,7 @@ enum {
};
enum {
+ MLX5_ETH_WQE_SVLAN = 1 << 0,
MLX5_ETH_WQE_INSERT_VLAN = 1 << 15,
};
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 1c2e8d6b7274..abb6dc2ebbf8 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -687,5 +687,31 @@ struct fsl_mc_device_id {
const char obj_type[16];
};
+/**
+ * struct tb_service_id - Thunderbolt service identifiers
+ * @match_flags: Flags used to match the structure
+ * @protocol_key: Protocol key the service supports
+ * @protocol_id: Protocol id the service supports
+ * @protocol_version: Version of the protocol
+ * @protocol_revision: Revision of the protocol software
+ * @driver_data: Driver specific data
+ *
+ * Thunderbolt XDomain services are exposed as devices where each device
+ * carries the protocol information the service supports. Thunderbolt
+ * XDomain service drivers match against that information.
+ */
+struct tb_service_id {
+ __u32 match_flags;
+ char protocol_key[8 + 1];
+ __u32 protocol_id;
+ __u32 protocol_version;
+ __u32 protocol_revision;
+ kernel_ulong_t driver_data;
+};
+
+#define TBSVC_MATCH_PROTOCOL_KEY 0x0001
+#define TBSVC_MATCH_PROTOCOL_ID 0x0002
+#define TBSVC_MATCH_PROTOCOL_VERSION 0x0004
+#define TBSVC_MATCH_PROTOCOL_REVISION 0x0008
#endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 65a70a7c51c1..5396521a776a 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -6,6 +6,8 @@
#include <linux/pim.h>
#include <linux/rhashtable.h>
#include <net/sock.h>
+#include <net/fib_rules.h>
+#include <net/fib_notifier.h>
#include <uapi/linux/mroute.h>
#ifdef CONFIG_IP_MROUTE
@@ -19,6 +21,7 @@ int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
int ip_mr_init(void);
+bool ipmr_rule_default(const struct fib_rule *rule);
#else
static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
char __user *optval, unsigned int optlen)
@@ -46,10 +49,16 @@ static inline int ip_mroute_opt(int opt)
{
return 0;
}
+
+static inline bool ipmr_rule_default(const struct fib_rule *rule)
+{
+ return true;
+}
#endif
struct vif_device {
struct net_device *dev; /* Device we are using */
+ struct netdev_phys_item_id dev_parent_id; /* Device parent ID */
unsigned long bytes_in,bytes_out;
unsigned long pkt_in,pkt_out; /* Statistics */
unsigned long rate_limit; /* Traffic shaping (NI) */
@@ -59,6 +68,14 @@ struct vif_device {
int link; /* Physical interface index */
};
+struct vif_entry_notifier_info {
+ struct fib_notifier_info info;
+ struct net_device *dev;
+ vifi_t vif_index;
+ unsigned short vif_flags;
+ u32 tb_id;
+};
+
#define VIFF_STATIC 0x8000
#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
@@ -82,9 +99,11 @@ struct mr_table {
/* mfc_flags:
* MFC_STATIC - the entry was added statically (not by a routing daemon)
+ * MFC_OFFLOAD - the entry was offloaded to the hardware
*/
enum {
MFC_STATIC = BIT(0),
+ MFC_OFFLOAD = BIT(1),
};
struct mfc_cache_cmp_arg {
@@ -110,6 +129,7 @@ struct mfc_cache_cmp_arg {
* @wrong_if: number of wrong source interface hits
* @lastuse: time of last use of the group (traffic or update)
* @ttls: OIF TTL threshold array
+ * @refcount: reference count for this entry
* @list: global entry list
* @rcu: used for entry destruction
*/
@@ -139,14 +159,40 @@ struct mfc_cache {
unsigned long wrong_if;
unsigned long lastuse;
unsigned char ttls[MAXVIFS];
+ refcount_t refcount;
} res;
} mfc_un;
struct list_head list;
struct rcu_head rcu;
};
+struct mfc_entry_notifier_info {
+ struct fib_notifier_info info;
+ struct mfc_cache *mfc;
+ u32 tb_id;
+};
+
struct rtmsg;
int ipmr_get_route(struct net *net, struct sk_buff *skb,
__be32 saddr, __be32 daddr,
struct rtmsg *rtm, u32 portid);
+
+#ifdef CONFIG_IP_MROUTE
+void ipmr_cache_free(struct mfc_cache *mfc_cache);
+#else
+static inline void ipmr_cache_free(struct mfc_cache *mfc_cache)
+{
+}
+#endif
+
+static inline void ipmr_cache_put(struct mfc_cache *c)
+{
+ if (refcount_dec_and_test(&c->mfc_un.res.refcount))
+ ipmr_cache_free(c);
+}
+static inline void ipmr_cache_hold(struct mfc_cache *c)
+{
+ refcount_inc(&c->mfc_un.res.refcount);
+}
+
#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2eaac7d75af4..6b274bfe489f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -55,7 +55,7 @@
struct netpoll_info;
struct device;
struct phy_device;
-struct dsa_switch_tree;
+struct dsa_port;
/* 802.11 specific */
struct wireless_dev;
@@ -770,17 +770,20 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb);
enum tc_setup_type {
- TC_SETUP_MQPRIO,
+ TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
TC_SETUP_CLSFLOWER,
TC_SETUP_CLSMATCHALL,
TC_SETUP_CLSBPF,
+ TC_SETUP_BLOCK,
+ TC_SETUP_QDISC_CBS,
+ TC_SETUP_QDISC_RED,
};
-/* These structures hold the attributes of xdp state that are being passed
- * to the netdevice through the xdp op.
+/* These structures hold the attributes of bpf state that are being passed
+ * to the netdevice through the bpf op.
*/
-enum xdp_netdev_command {
+enum bpf_netdev_command {
/* Set or clear a bpf program used in the earliest stages of packet
* rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee
* is responsible for calling bpf_prog_put on any old progs that are
@@ -795,12 +798,17 @@ enum xdp_netdev_command {
* is equivalent to XDP_ATTACHED_DRV.
*/
XDP_QUERY_PROG,
+ /* BPF program for offload callbacks, invoked at program load time. */
+ BPF_OFFLOAD_VERIFIER_PREP,
+ BPF_OFFLOAD_TRANSLATE,
+ BPF_OFFLOAD_DESTROY,
};
+struct bpf_ext_analyzer_ops;
struct netlink_ext_ack;
-struct netdev_xdp {
- enum xdp_netdev_command command;
+struct netdev_bpf {
+ enum bpf_netdev_command command;
union {
/* XDP_SETUP_PROG */
struct {
@@ -813,6 +821,15 @@ struct netdev_xdp {
u8 prog_attached;
u32 prog_id;
};
+ /* BPF_OFFLOAD_VERIFIER_PREP */
+ struct {
+ struct bpf_prog *prog;
+ const struct bpf_ext_analyzer_ops *ops; /* callee set */
+ } verifier;
+ /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */
+ struct {
+ struct bpf_prog *prog;
+ } offload;
};
};
@@ -826,6 +843,11 @@ struct xfrmdev_ops {
};
#endif
+struct dev_ifalias {
+ struct rcu_head rcuhead;
+ char ifalias[];
+};
+
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
@@ -1117,9 +1139,10 @@ struct xfrmdev_ops {
* appropriate rx headroom value allows avoiding skb head copy on
* forward. Setting a negative value resets the rx headroom to the
* default value.
- * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp);
+ * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf);
* This function is used to set or query state related to XDP on the
- * netdevice. See definition of enum xdp_netdev_command for details.
+ * netdevice and manage BPF offload. See definition of
+ * enum bpf_netdev_command for details.
* int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp);
* This function is used to submit a XDP packet for transmit on a
* netdevice.
@@ -1241,7 +1264,8 @@ struct net_device_ops {
u32 flow_id);
#endif
int (*ndo_add_slave)(struct net_device *dev,
- struct net_device *slave_dev);
+ struct net_device *slave_dev,
+ struct netlink_ext_ack *extack);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
netdev_features_t (*ndo_fix_features)(struct net_device *dev,
@@ -1307,8 +1331,8 @@ struct net_device_ops {
struct sk_buff *skb);
void (*ndo_set_rx_headroom)(struct net_device *dev,
int needed_headroom);
- int (*ndo_xdp)(struct net_device *dev,
- struct netdev_xdp *xdp);
+ int (*ndo_bpf)(struct net_device *dev,
+ struct netdev_bpf *bpf);
int (*ndo_xdp_xmit)(struct net_device *dev,
struct xdp_buff *xdp);
void (*ndo_xdp_flush)(struct net_device *dev);
@@ -1551,6 +1575,8 @@ enum netdev_priv_flags {
*
* @rx_handler: handler for received packets
* @rx_handler_data: XXX: need comments on this one
+ * @miniq_ingress: ingress/clsact qdisc specific data for
+ * ingress processing
* @ingress_queue: XXX: need comments on this one
* @broadcast: hw bcast address
*
@@ -1568,7 +1594,8 @@ enum netdev_priv_flags {
* @tx_global_lock: XXX: need comments on this one
*
* @xps_maps: XXX: need comments on this one
- *
+ * @miniq_egress: clsact qdisc specific data for
+ * egress processing
* @watchdog_timeo: Represents the timeout that is used by
* the watchdog (see dev_watchdog())
* @watchdog_timer: List of timers
@@ -1632,7 +1659,7 @@ enum netdev_priv_flags {
struct net_device {
char name[IFNAMSIZ];
struct hlist_node name_hlist;
- char *ifalias;
+ struct dev_ifalias __rcu *ifalias;
/*
* I/O specific fields
* FIXME: Merge these and struct ifmap into one
@@ -1752,7 +1779,7 @@ struct net_device {
struct vlan_info __rcu *vlan_info;
#endif
#if IS_ENABLED(CONFIG_NET_DSA)
- struct dsa_switch_tree *dsa_ptr;
+ struct dsa_port *dsa_ptr;
#endif
#if IS_ENABLED(CONFIG_TIPC)
struct tipc_bearer __rcu *tipc_ptr;
@@ -1787,7 +1814,7 @@ struct net_device {
void __rcu *rx_handler_data;
#ifdef CONFIG_NET_CLS_ACT
- struct tcf_proto __rcu *ingress_cl_list;
+ struct mini_Qdisc __rcu *miniq_ingress;
#endif
struct netdev_queue __rcu *ingress_queue;
#ifdef CONFIG_NETFILTER_INGRESS
@@ -1818,7 +1845,7 @@ struct net_device {
struct xps_dev_maps __rcu *xps_maps;
#endif
#ifdef CONFIG_NET_CLS_ACT
- struct tcf_proto __rcu *egress_cl_list;
+ struct mini_Qdisc __rcu *miniq_egress;
#endif
/* These may be needed for future network-power-down code. */
@@ -2304,7 +2331,8 @@ int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
struct netdev_notifier_info {
- struct net_device *dev;
+ struct net_device *dev;
+ struct netlink_ext_ack *extack;
};
struct netdev_notifier_change_info {
@@ -2329,6 +2357,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
struct net_device *dev)
{
info->dev = dev;
+ info->extack = NULL;
}
static inline struct net_device *
@@ -2337,6 +2366,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
return info->dev;
}
+static inline struct netlink_ext_ack *
+netdev_notifier_info_to_extack(const struct netdev_notifier_info *info)
+{
+ return info->extack;
+}
+
int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
@@ -3246,6 +3281,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_core(struct sk_buff *skb);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
@@ -3275,6 +3311,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags,
unsigned int gchanges);
int dev_change_name(struct net_device *, const char *);
int dev_set_alias(struct net_device *, const char *, size_t);
+int dev_get_alias(const struct net_device *, char *, size_t);
int dev_change_net_namespace(struct net_device *, struct net *, const char *);
int __dev_set_mtu(struct net_device *, int);
int dev_set_mtu(struct net_device *, int);
@@ -3290,10 +3327,10 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
-typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp);
+typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, u32 flags);
-u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id);
+u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t xdp_op, u32 *prog_id);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
@@ -3907,10 +3944,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
-int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
+int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev,
+ struct netlink_ext_ack *extack);
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
- void *upper_priv, void *upper_info);
+ void *upper_priv, void *upper_info,
+ struct netlink_ext_ack *extack);
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev);
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
@@ -4297,6 +4336,31 @@ void netdev_notice(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
void netdev_info(const struct net_device *dev, const char *format, ...);
+#define netdev_level_once(level, dev, fmt, ...) \
+do { \
+ static bool __print_once __read_mostly; \
+ \
+ if (!__print_once) { \
+ __print_once = true; \
+ netdev_printk(level, dev, fmt, ##__VA_ARGS__); \
+ } \
+} while (0)
+
+#define netdev_emerg_once(dev, fmt, ...) \
+ netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
+#define netdev_alert_once(dev, fmt, ...) \
+ netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
+#define netdev_crit_once(dev, fmt, ...) \
+ netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
+#define netdev_err_once(dev, fmt, ...) \
+ netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
+#define netdev_warn_once(dev, fmt, ...) \
+ netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
+#define netdev_notice_once(dev, fmt, ...) \
+ netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
+#define netdev_info_once(dev, fmt, ...) \
+ netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
+
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
@@ -4337,6 +4401,10 @@ do { \
WARN(1, "netdevice: %s%s\n" format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
+#define netdev_WARN_ONCE(dev, condition, format, arg...) \
+ WARN_ONCE(1, "netdevice: %s%s\n" format, netdev_name(dev) \
+ netdev_reg_state(dev), ##args)
+
/* netif printk helpers, similar to netdev_printk */
#define netif_printk(priv, type, level, dev, fmt, args...) \
@@ -4411,15 +4479,7 @@ do { \
* Why 16. Because with 16 the only overlap we get on a hash of the
* low nibble of the protocol value is RARP/SNAP/X.25.
*
- * NOTE: That is no longer true with the addition of VLAN tags. Not
- * sure which should go first, but I bet it won't make much
- * difference if we are running VLANs. The good news is that
- * this protocol won't be in the list unless compiled in, so
- * the average user (w/out VLANs) will not be adversely affected.
- * --BLG
- *
* 0800 IP
- * 8100 802.1Q VLAN
* 0001 802.3
* 0002 AX.25
* 0004 802.2
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 6ddb4a5da371..49b4257ce1ea 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -17,9 +17,6 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
}
enum netlink_skb_flags {
- NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */
- NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */
- NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */
NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */
};
diff --git a/include/linux/of.h b/include/linux/of.h
index 43b5034c6a1e..d3dea1d1e3a9 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -681,12 +681,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np,
return -ENOSYS;
}
-static inline int of_property_read_u32_index(const struct device_node *np,
- const char *propname, u32 index, u32 *out_value)
-{
- return -ENOSYS;
-}
-
static inline int of_property_read_u8_array(const struct device_node *np,
const char *propname, u8 *out_values, size_t sz)
{
@@ -713,16 +707,14 @@ static inline int of_property_read_u64_array(const struct device_node *np,
return -ENOSYS;
}
-static inline int of_property_read_string(const struct device_node *np,
- const char *propname,
- const char **out_string)
+static inline int of_property_read_u32_index(const struct device_node *np,
+ const char *propname, u32 index, u32 *out_value)
{
return -ENOSYS;
}
-static inline int of_property_read_string_helper(const struct device_node *np,
- const char *propname,
- const char **out_strs, size_t sz, int index)
+static inline int of_property_read_u64_index(const struct device_node *np,
+ const char *propname, u32 index, u64 *out_value)
{
return -ENOSYS;
}
@@ -750,12 +742,51 @@ static inline int of_n_size_cells(struct device_node *np)
return 0;
}
+static inline int of_property_read_variable_u8_array(const struct device_node *np,
+ const char *propname, u8 *out_values,
+ size_t sz_min, size_t sz_max)
+{
+ return -ENOSYS;
+}
+
+static inline int of_property_read_variable_u16_array(const struct device_node *np,
+ const char *propname, u16 *out_values,
+ size_t sz_min, size_t sz_max)
+{
+ return -ENOSYS;
+}
+
+static inline int of_property_read_variable_u32_array(const struct device_node *np,
+ const char *propname,
+ u32 *out_values,
+ size_t sz_min,
+ size_t sz_max)
+{
+ return -ENOSYS;
+}
+
static inline int of_property_read_u64(const struct device_node *np,
const char *propname, u64 *out_value)
{
return -ENOSYS;
}
+static inline int of_property_read_variable_u64_array(const struct device_node *np,
+ const char *propname,
+ u64 *out_values,
+ size_t sz_min,
+ size_t sz_max)
+{
+ return -ENOSYS;
+}
+
+static inline int of_property_read_string(const struct device_node *np,
+ const char *propname,
+ const char **out_string)
+{
+ return -ENOSYS;
+}
+
static inline int of_property_match_string(const struct device_node *np,
const char *propname,
const char *string)
@@ -763,6 +794,13 @@ static inline int of_property_match_string(const struct device_node *np,
return -ENOSYS;
}
+static inline int of_property_read_string_helper(const struct device_node *np,
+ const char *propname,
+ const char **out_strs, size_t sz, int index)
+{
+ return -ENOSYS;
+}
+
static inline struct device_node *of_parse_phandle(const struct device_node *np,
const char *phandle_name,
int index)
diff --git a/include/linux/once.h b/include/linux/once.h
index 6790884d3c57..9225ee6d96c7 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -6,7 +6,7 @@
#include <linux/jump_label.h>
bool __do_once_start(bool *done, unsigned long *flags);
-void __do_once_done(bool *done, struct static_key *once_key,
+void __do_once_done(bool *done, struct static_key_true *once_key,
unsigned long *flags);
/* Call a function exactly once. The idea of DO_ONCE() is to perform
@@ -39,8 +39,8 @@ void __do_once_done(bool *done, struct static_key *once_key,
({ \
bool ___ret = false; \
static bool ___done = false; \
- static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \
- if (static_key_true(&___once_key)) { \
+ static DEFINE_STATIC_KEY_TRUE(___once_key); \
+ if (static_branch_unlikely(&___once_key)) { \
unsigned long ___flags; \
___ret = __do_once_start(&___done, &___flags); \
if (unlikely(___ret)) { \
diff --git a/include/linux/phy.h b/include/linux/phy.h
index d78cd01ea513..dc82a07cb4fd 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -451,6 +451,8 @@ struct phy_device {
struct phy_led_trigger *phy_led_triggers;
unsigned int phy_num_led_triggers;
struct phy_led_trigger *last_triggered;
+
+ struct phy_led_trigger *led_link_trigger;
#endif
/*
diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index dd7a3b86bb9e..e755954d85fd 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type {
enum qed_ll2_tx_dest {
QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */
QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */
+ QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */
QED_LL2_TX_DEST_MAX
};
@@ -101,6 +102,7 @@ struct qed_ll2_comp_rx_data {
void *cookie;
dma_addr_t rx_buf_addr;
u16 parse_flags;
+ u16 err_flags;
u16 vlan;
bool b_last_packet;
u8 connection_handle;
@@ -149,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt,
dma_addr_t first_frag_addr,
bool b_last_fragment, bool b_last_packet);
+typedef
+void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle,
+ u32 opaque_data_0, u32 opaque_data_1);
+
struct qed_ll2_cbs {
qed_ll2_complete_rx_packet_cb rx_comp_cb;
qed_ll2_release_rx_packet_cb rx_release_cb;
qed_ll2_complete_tx_packet_cb tx_comp_cb;
qed_ll2_release_tx_packet_cb tx_release_cb;
+ qed_ll2_slowpath_cb slowpath_cb;
void *cookie;
};
@@ -170,6 +177,7 @@ struct qed_ll2_acquire_data_inputs {
enum qed_ll2_tx_dest tx_dest;
enum qed_ll2_error_handle ai_err_packet_too_big;
enum qed_ll2_error_handle ai_err_no_buf;
+ bool secondary_queue;
u8 gsi_enable;
};
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 54bcd970bfd3..2032ce2eb20b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -18,9 +18,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
u32 id, long expires, u32 error);
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
+void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags, int *new_nsid);
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
unsigned change, u32 event,
- gfp_t flags);
+ gfp_t flags, int *new_nsid);
void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
gfp_t flags);
diff --git a/include/linux/security.h b/include/linux/security.h
index ce6265960d6c..73f1ef625d40 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1730,6 +1730,54 @@ static inline void securityfs_remove(struct dentry *dentry)
#endif
+#ifdef CONFIG_BPF_SYSCALL
+union bpf_attr;
+struct bpf_map;
+struct bpf_prog;
+struct bpf_prog_aux;
+#ifdef CONFIG_SECURITY
+extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
+extern int security_bpf_prog(struct bpf_prog *prog);
+extern int security_bpf_map_alloc(struct bpf_map *map);
+extern void security_bpf_map_free(struct bpf_map *map);
+extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
+extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
+#else
+static inline int security_bpf(int cmd, union bpf_attr *attr,
+ unsigned int size)
+{
+ return 0;
+}
+
+static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+ return 0;
+}
+
+static inline int security_bpf_prog(struct bpf_prog *prog)
+{
+ return 0;
+}
+
+static inline int security_bpf_map_alloc(struct bpf_map *map)
+{
+ return 0;
+}
+
+static inline void security_bpf_map_free(struct bpf_map *map)
+{ }
+
+static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+{
+ return 0;
+}
+
+static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
+{ }
+#endif /* CONFIG_SECURITY */
+#endif /* CONFIG_BPF_SYSCALL */
+
#ifdef CONFIG_SECURITY
static inline char *alloc_secdata(void)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d448a4804aea..54fe91183a8e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
- unsigned short _unused;
- unsigned char nr_frags;
+ __u8 __unused;
+ __u8 meta_len;
+ __u8 nr_frags;
__u8 tx_flags;
unsigned short gso_size;
/* Warning: this field is not always filled in (UFO)! */
@@ -499,7 +500,6 @@ struct skb_shared_info {
struct skb_shared_hwtstamps hwtstamps;
unsigned int gso_type;
u32 tskey;
- __be32 ip6_frag_id;
/*
* Warning : all fields before dataref are cleared in __alloc_skb()
@@ -616,6 +616,7 @@ typedef unsigned char *sk_buff_data_t;
* @nf_trace: netfilter packet trace flag
* @protocol: Packet protocol from driver
* @destructor: Destruct function
+ * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
* @_nfct: Associated connection, if any (with nfctinfo bits)
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
@@ -661,8 +662,12 @@ struct sk_buff {
struct sk_buff *prev;
union {
- ktime_t tstamp;
- u64 skb_mstamp;
+ struct net_device *dev;
+ /* Some protocols might use this space to store information,
+ * while device pointer would be NULL.
+ * UDP receive path is one user.
+ */
+ unsigned long dev_scratch;
};
};
struct rb_node rbnode; /* used in netem & tcp stack */
@@ -670,12 +675,8 @@ struct sk_buff {
struct sock *sk;
union {
- struct net_device *dev;
- /* Some protocols might use this space to store information,
- * while device pointer would be NULL.
- * UDP receive path is one user.
- */
- unsigned long dev_scratch;
+ ktime_t tstamp;
+ u64 skb_mstamp;
};
/*
* This is the control buffer. It is free to use for every
@@ -685,8 +686,14 @@ struct sk_buff {
*/
char cb[48] __aligned(8);
- unsigned long _skb_refdst;
- void (*destructor)(struct sk_buff *skb);
+ union {
+ struct {
+ unsigned long _skb_refdst;
+ void (*destructor)(struct sk_buff *skb);
+ };
+ struct list_head tcp_tsorted_anchor;
+ };
+
#ifdef CONFIG_XFRM
struct sec_path *sp;
#endif
@@ -771,6 +778,7 @@ struct sk_buff {
__u8 remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV
__u8 offload_fwd_mark:1;
+ __u8 offload_mr_fwd_mark:1;
#endif
#ifdef CONFIG_NET_CLS_ACT
__u8 tc_skip_classify:1;
@@ -1457,27 +1465,8 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
}
/**
- * skb_header_release - release reference to header
- * @skb: buffer to operate on
- *
- * Drop a reference to the header part of the buffer. This is done
- * by acquiring a payload reference. You must not read from the header
- * part of skb->data after this.
- * Note : Check if you can use __skb_header_release() instead.
- */
-static inline void skb_header_release(struct sk_buff *skb)
-{
- BUG_ON(skb->nohdr);
- skb->nohdr = 1;
- atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
-}
-
-/**
* __skb_header_release - release reference to header
* @skb: buffer to operate on
- *
- * Variant of skb_header_release() assuming skb is private to caller.
- * We can avoid one atomic operation.
*/
static inline void __skb_header_release(struct sk_buff *skb)
{
@@ -3168,6 +3157,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
return __skb_grow(skb, len);
}
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+#define skb_rb_first(root) rb_to_skb(rb_first(root))
+#define skb_rb_last(root) rb_to_skb(rb_last(root))
+#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode))
+#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode))
+
#define skb_queue_walk(queue, skb) \
for (skb = (queue)->next; \
skb != (struct sk_buff *)(queue); \
@@ -3182,6 +3177,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
for (; skb != (struct sk_buff *)(queue); \
skb = skb->next)
+#define skb_rbtree_walk(skb, root) \
+ for (skb = skb_rb_first(root); skb != NULL; \
+ skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from(skb) \
+ for (; skb != NULL; \
+ skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from_safe(skb, tmp) \
+ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \
+ skb = tmp)
+
#define skb_queue_walk_from_safe(queue, skb, tmp) \
for (tmp = skb->next; \
skb != (struct sk_buff *)(queue); \
@@ -3419,6 +3426,69 @@ static inline ktime_t net_invalid_timestamp(void)
return 0;
}
+static inline u8 skb_metadata_len(const struct sk_buff *skb)
+{
+ return skb_shinfo(skb)->meta_len;
+}
+
+static inline void *skb_metadata_end(const struct sk_buff *skb)
+{
+ return skb_mac_header(skb);
+}
+
+static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
+ const struct sk_buff *skb_b,
+ u8 meta_len)
+{
+ const void *a = skb_metadata_end(skb_a);
+ const void *b = skb_metadata_end(skb_b);
+ /* Using more efficient varaiant than plain call to memcmp(). */
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+ u64 diffs = 0;
+
+ switch (meta_len) {
+#define __it(x, op) (x -= sizeof(u##op))
+#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
+ case 32: diffs |= __it_diff(a, b, 64);
+ case 24: diffs |= __it_diff(a, b, 64);
+ case 16: diffs |= __it_diff(a, b, 64);
+ case 8: diffs |= __it_diff(a, b, 64);
+ break;
+ case 28: diffs |= __it_diff(a, b, 64);
+ case 20: diffs |= __it_diff(a, b, 64);
+ case 12: diffs |= __it_diff(a, b, 64);
+ case 4: diffs |= __it_diff(a, b, 32);
+ break;
+ }
+ return diffs;
+#else
+ return memcmp(a - meta_len, b - meta_len, meta_len);
+#endif
+}
+
+static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
+ const struct sk_buff *skb_b)
+{
+ u8 len_a = skb_metadata_len(skb_a);
+ u8 len_b = skb_metadata_len(skb_b);
+
+ if (!(len_a | len_b))
+ return false;
+
+ return len_a != len_b ?
+ true : __skb_metadata_differs(skb_a, skb_b, len_a);
+}
+
+static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len)
+{
+ skb_shinfo(skb)->meta_len = meta_len;
+}
+
+static inline void skb_metadata_clear(struct sk_buff *skb)
+{
+ skb_metadata_set(skb, 0);
+}
+
struct sk_buff *skb_clone_sk(struct sk_buff *skb);
#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4aa40ef02d32..df5d97a85e1a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -85,7 +85,6 @@ struct tcp_sack_block {
/*These are used to set the sack_ok field in struct tcp_options_received */
#define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
-#define TCP_FACK_ENABLED (1 << 1) /*1 = FACK is enabled locally*/
#define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
struct tcp_options_received {
@@ -98,7 +97,8 @@ struct tcp_options_received {
tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */
dsack : 1, /* D-SACK is scheduled */
wscale_ok : 1, /* Wscale seen on SYN packet */
- sack_ok : 4, /* SACK seen on SYN packet */
+ sack_ok : 3, /* SACK seen on SYN packet */
+ smc_ok : 1, /* SMC seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
u8 num_sacks; /* Number of SACK blocks */
@@ -110,6 +110,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+#if IS_ENABLED(CONFIG_SMC)
+ rx_opt->smc_ok = 0;
+#endif
}
/* This is the max number of SACKS that we'll generate and process. It's safe
@@ -191,6 +194,7 @@ struct tcp_sock {
u32 tsoffset; /* timestamp offset */
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
+ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
u32 snd_wl1; /* Sequence for window update */
u32 snd_wnd; /* The window we expect to receive */
@@ -205,8 +209,13 @@ struct tcp_sock {
u64 mstamp; /* (Re)sent time of the skb */
u32 rtt_us; /* Associated RTT */
u32 end_seq; /* Ending TCP sequence of the skb */
- u8 advanced; /* mstamp advanced since last lost marking */
- u8 reord; /* reordering detected */
+ u32 last_delivered; /* tp->delivered at last reo_wnd adj */
+ u8 reo_wnd_steps; /* Allowed reordering window */
+#define TCP_RACK_RECOVERY_THRESH 16
+ u8 reo_wnd_persist:5, /* No. of recovery since last adj */
+ dsack_seen:1, /* Whether DSACK seen after last adj */
+ advanced:1, /* mstamp advanced since last lost marking */
+ reord:1; /* reordering detected */
} rack;
u16 advmss; /* Advertised MSS */
u32 chrono_start; /* Start time in jiffies of a TCP chrono */
@@ -214,7 +223,8 @@ struct tcp_sock {
u8 chrono_type:2, /* current chronograph type */
rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
- unused:4;
+ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
+ unused:3;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
unused1 : 1,
@@ -227,7 +237,8 @@ struct tcp_sock {
syn_fastopen_ch:1, /* Active TFO re-enabling probe */
syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
save_syn:1, /* Save headers of SYN packet */
- is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
+ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+ syn_smc:1; /* SYN includes SMC */
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
/* RTT measurement */
@@ -282,7 +293,6 @@ struct tcp_sock {
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */
- u32 fackets_out; /* FACK'd packets */
struct hrtimer pacing_timer;
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
new file mode 100644
index 000000000000..7b69853188b1
--- /dev/null
+++ b/include/linux/thunderbolt.h
@@ -0,0 +1,598 @@
+/*
+ * Thunderbolt service API
+ *
+ * Copyright (C) 2014 Andreas Noever <andreas.noever@gmail.com>
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Michael Jamet <michael.jamet@intel.com>
+ * Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef THUNDERBOLT_H_
+#define THUNDERBOLT_H_
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/mod_devicetable.h>
+#include <linux/pci.h>
+#include <linux/uuid.h>
+#include <linux/workqueue.h>
+
+enum tb_cfg_pkg_type {
+ TB_CFG_PKG_READ = 1,
+ TB_CFG_PKG_WRITE = 2,
+ TB_CFG_PKG_ERROR = 3,
+ TB_CFG_PKG_NOTIFY_ACK = 4,
+ TB_CFG_PKG_EVENT = 5,
+ TB_CFG_PKG_XDOMAIN_REQ = 6,
+ TB_CFG_PKG_XDOMAIN_RESP = 7,
+ TB_CFG_PKG_OVERRIDE = 8,
+ TB_CFG_PKG_RESET = 9,
+ TB_CFG_PKG_ICM_EVENT = 10,
+ TB_CFG_PKG_ICM_CMD = 11,
+ TB_CFG_PKG_ICM_RESP = 12,
+ TB_CFG_PKG_PREPARE_TO_SLEEP = 13,
+};
+
+/**
+ * enum tb_security_level - Thunderbolt security level
+ * @TB_SECURITY_NONE: No security, legacy mode
+ * @TB_SECURITY_USER: User approval required at minimum
+ * @TB_SECURITY_SECURE: One time saved key required at minimum
+ * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB)
+ */
+enum tb_security_level {
+ TB_SECURITY_NONE,
+ TB_SECURITY_USER,
+ TB_SECURITY_SECURE,
+ TB_SECURITY_DPONLY,
+};
+
+/**
+ * struct tb - main thunderbolt bus structure
+ * @dev: Domain device
+ * @lock: Big lock. Must be held when accessing any struct
+ * tb_switch / struct tb_port.
+ * @nhi: Pointer to the NHI structure
+ * @ctl: Control channel for this domain
+ * @wq: Ordered workqueue for all domain specific work
+ * @root_switch: Root switch of this domain
+ * @cm_ops: Connection manager specific operations vector
+ * @index: Linux assigned domain number
+ * @security_level: Current security level
+ * @privdata: Private connection manager specific data
+ */
+struct tb {
+ struct device dev;
+ struct mutex lock;
+ struct tb_nhi *nhi;
+ struct tb_ctl *ctl;
+ struct workqueue_struct *wq;
+ struct tb_switch *root_switch;
+ const struct tb_cm_ops *cm_ops;
+ int index;
+ enum tb_security_level security_level;
+ unsigned long privdata[0];
+};
+
+extern struct bus_type tb_bus_type;
+extern struct device_type tb_service_type;
+extern struct device_type tb_xdomain_type;
+
+#define TB_LINKS_PER_PHY_PORT 2
+
+static inline unsigned int tb_phy_port_from_link(unsigned int link)
+{
+ return (link - 1) / TB_LINKS_PER_PHY_PORT;
+}
+
+/**
+ * struct tb_property_dir - XDomain property directory
+ * @uuid: Directory UUID or %NULL if root directory
+ * @properties: List of properties in this directory
+ *
+ * User needs to provide serialization if needed.
+ */
+struct tb_property_dir {
+ const uuid_t *uuid;
+ struct list_head properties;
+};
+
+enum tb_property_type {
+ TB_PROPERTY_TYPE_UNKNOWN = 0x00,
+ TB_PROPERTY_TYPE_DIRECTORY = 0x44,
+ TB_PROPERTY_TYPE_DATA = 0x64,
+ TB_PROPERTY_TYPE_TEXT = 0x74,
+ TB_PROPERTY_TYPE_VALUE = 0x76,
+};
+
+#define TB_PROPERTY_KEY_SIZE 8
+
+/**
+ * struct tb_property - XDomain property
+ * @list: Used to link properties together in a directory
+ * @key: Key for the property (always terminated).
+ * @type: Type of the property
+ * @length: Length of the property data in dwords
+ * @value: Property value
+ *
+ * Users use @type to determine which field in @value is filled.
+ */
+struct tb_property {
+ struct list_head list;
+ char key[TB_PROPERTY_KEY_SIZE + 1];
+ enum tb_property_type type;
+ size_t length;
+ union {
+ struct tb_property_dir *dir;
+ u8 *data;
+ char *text;
+ u32 immediate;
+ } value;
+};
+
+struct tb_property_dir *tb_property_parse_dir(const u32 *block,
+ size_t block_len);
+ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block,
+ size_t block_len);
+struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid);
+void tb_property_free_dir(struct tb_property_dir *dir);
+int tb_property_add_immediate(struct tb_property_dir *parent, const char *key,
+ u32 value);
+int tb_property_add_data(struct tb_property_dir *parent, const char *key,
+ const void *buf, size_t buflen);
+int tb_property_add_text(struct tb_property_dir *parent, const char *key,
+ const char *text);
+int tb_property_add_dir(struct tb_property_dir *parent, const char *key,
+ struct tb_property_dir *dir);
+void tb_property_remove(struct tb_property *tb_property);
+struct tb_property *tb_property_find(struct tb_property_dir *dir,
+ const char *key, enum tb_property_type type);
+struct tb_property *tb_property_get_next(struct tb_property_dir *dir,
+ struct tb_property *prev);
+
+#define tb_property_for_each(dir, property) \
+ for (property = tb_property_get_next(dir, NULL); \
+ property; \
+ property = tb_property_get_next(dir, property))
+
+int tb_register_property_dir(const char *key, struct tb_property_dir *dir);
+void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir);
+
+/**
+ * struct tb_xdomain - Cross-domain (XDomain) connection
+ * @dev: XDomain device
+ * @tb: Pointer to the domain
+ * @remote_uuid: UUID of the remote domain (host)
+ * @local_uuid: Cached local UUID
+ * @route: Route string the other domain can be reached
+ * @vendor: Vendor ID of the remote domain
+ * @device: Device ID of the demote domain
+ * @lock: Lock to serialize access to the following fields of this structure
+ * @vendor_name: Name of the vendor (or %NULL if not known)
+ * @device_name: Name of the device (or %NULL if not known)
+ * @is_unplugged: The XDomain is unplugged
+ * @resume: The XDomain is being resumed
+ * @transmit_path: HopID which the remote end expects us to transmit
+ * @transmit_ring: Local ring (hop) where outgoing packets are pushed
+ * @receive_path: HopID which we expect the remote end to transmit
+ * @receive_ring: Local ring (hop) where incoming packets arrive
+ * @service_ids: Used to generate IDs for the services
+ * @properties: Properties exported by the remote domain
+ * @property_block_gen: Generation of @properties
+ * @properties_lock: Lock protecting @properties.
+ * @get_properties_work: Work used to get remote domain properties
+ * @properties_retries: Number of times left to read properties
+ * @properties_changed_work: Work used to notify the remote domain that
+ * our properties have changed
+ * @properties_changed_retries: Number of times left to send properties
+ * changed notification
+ * @link: Root switch link the remote domain is connected (ICM only)
+ * @depth: Depth in the chain the remote domain is connected (ICM only)
+ *
+ * This structure represents connection across two domains (hosts).
+ * Each XDomain contains zero or more services which are exposed as
+ * &struct tb_service objects.
+ *
+ * Service drivers may access this structure if they need to enumerate
+ * non-standard properties but they need hold @lock when doing so
+ * because properties can be changed asynchronously in response to
+ * changes in the remote domain.
+ */
+struct tb_xdomain {
+ struct device dev;
+ struct tb *tb;
+ uuid_t *remote_uuid;
+ const uuid_t *local_uuid;
+ u64 route;
+ u16 vendor;
+ u16 device;
+ struct mutex lock;
+ const char *vendor_name;
+ const char *device_name;
+ bool is_unplugged;
+ bool resume;
+ u16 transmit_path;
+ u16 transmit_ring;
+ u16 receive_path;
+ u16 receive_ring;
+ struct ida service_ids;
+ struct tb_property_dir *properties;
+ u32 property_block_gen;
+ struct delayed_work get_properties_work;
+ int properties_retries;
+ struct delayed_work properties_changed_work;
+ int properties_changed_retries;
+ u8 link;
+ u8 depth;
+};
+
+int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path,
+ u16 transmit_ring, u16 receive_path,
+ u16 receive_ring);
+int tb_xdomain_disable_paths(struct tb_xdomain *xd);
+struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid);
+
+static inline struct tb_xdomain *
+tb_xdomain_find_by_uuid_locked(struct tb *tb, const uuid_t *uuid)
+{
+ struct tb_xdomain *xd;
+
+ mutex_lock(&tb->lock);
+ xd = tb_xdomain_find_by_uuid(tb, uuid);
+ mutex_unlock(&tb->lock);
+
+ return xd;
+}
+
+static inline struct tb_xdomain *tb_xdomain_get(struct tb_xdomain *xd)
+{
+ if (xd)
+ get_device(&xd->dev);
+ return xd;
+}
+
+static inline void tb_xdomain_put(struct tb_xdomain *xd)
+{
+ if (xd)
+ put_device(&xd->dev);
+}
+
+static inline bool tb_is_xdomain(const struct device *dev)
+{
+ return dev->type == &tb_xdomain_type;
+}
+
+static inline struct tb_xdomain *tb_to_xdomain(struct device *dev)
+{
+ if (tb_is_xdomain(dev))
+ return container_of(dev, struct tb_xdomain, dev);
+ return NULL;
+}
+
+int tb_xdomain_response(struct tb_xdomain *xd, const void *response,
+ size_t size, enum tb_cfg_pkg_type type);
+int tb_xdomain_request(struct tb_xdomain *xd, const void *request,
+ size_t request_size, enum tb_cfg_pkg_type request_type,
+ void *response, size_t response_size,
+ enum tb_cfg_pkg_type response_type,
+ unsigned int timeout_msec);
+
+/**
+ * tb_protocol_handler - Protocol specific handler
+ * @uuid: XDomain messages with this UUID are dispatched to this handler
+ * @callback: Callback called with the XDomain message. Returning %1
+ * here tells the XDomain core that the message was handled
+ * by this handler and should not be forwared to other
+ * handlers.
+ * @data: Data passed with the callback
+ * @list: Handlers are linked using this
+ *
+ * Thunderbolt services can hook into incoming XDomain requests by
+ * registering protocol handler. Only limitation is that the XDomain
+ * discovery protocol UUID cannot be registered since it is handled by
+ * the core XDomain code.
+ *
+ * The @callback must check that the message is really directed to the
+ * service the driver implements.
+ */
+struct tb_protocol_handler {
+ const uuid_t *uuid;
+ int (*callback)(const void *buf, size_t size, void *data);
+ void *data;
+ struct list_head list;
+};
+
+int tb_register_protocol_handler(struct tb_protocol_handler *handler);
+void tb_unregister_protocol_handler(struct tb_protocol_handler *handler);
+
+/**
+ * struct tb_service - Thunderbolt service
+ * @dev: XDomain device
+ * @id: ID of the service (shown in sysfs)
+ * @key: Protocol key from the properties directory
+ * @prtcid: Protocol ID from the properties directory
+ * @prtcvers: Protocol version from the properties directory
+ * @prtcrevs: Protocol software revision from the properties directory
+ * @prtcstns: Protocol settings mask from the properties directory
+ *
+ * Each domain exposes set of services it supports as collection of
+ * properties. For each service there will be one corresponding
+ * &struct tb_service. Service drivers are bound to these.
+ */
+struct tb_service {
+ struct device dev;
+ int id;
+ const char *key;
+ u32 prtcid;
+ u32 prtcvers;
+ u32 prtcrevs;
+ u32 prtcstns;
+};
+
+static inline struct tb_service *tb_service_get(struct tb_service *svc)
+{
+ if (svc)
+ get_device(&svc->dev);
+ return svc;
+}
+
+static inline void tb_service_put(struct tb_service *svc)
+{
+ if (svc)
+ put_device(&svc->dev);
+}
+
+static inline bool tb_is_service(const struct device *dev)
+{
+ return dev->type == &tb_service_type;
+}
+
+static inline struct tb_service *tb_to_service(struct device *dev)
+{
+ if (tb_is_service(dev))
+ return container_of(dev, struct tb_service, dev);
+ return NULL;
+}
+
+/**
+ * tb_service_driver - Thunderbolt service driver
+ * @driver: Driver structure
+ * @probe: Called when the driver is probed
+ * @remove: Called when the driver is removed (optional)
+ * @shutdown: Called at shutdown time to stop the service (optional)
+ * @id_table: Table of service identifiers the driver supports
+ */
+struct tb_service_driver {
+ struct device_driver driver;
+ int (*probe)(struct tb_service *svc, const struct tb_service_id *id);
+ void (*remove)(struct tb_service *svc);
+ void (*shutdown)(struct tb_service *svc);
+ const struct tb_service_id *id_table;
+};
+
+#define TB_SERVICE(key, id) \
+ .match_flags = TBSVC_MATCH_PROTOCOL_KEY | \
+ TBSVC_MATCH_PROTOCOL_ID, \
+ .protocol_key = (key), \
+ .protocol_id = (id)
+
+int tb_register_service_driver(struct tb_service_driver *drv);
+void tb_unregister_service_driver(struct tb_service_driver *drv);
+
+static inline void *tb_service_get_drvdata(const struct tb_service *svc)
+{
+ return dev_get_drvdata(&svc->dev);
+}
+
+static inline void tb_service_set_drvdata(struct tb_service *svc, void *data)
+{
+ dev_set_drvdata(&svc->dev, data);
+}
+
+static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc)
+{
+ return tb_to_xdomain(svc->dev.parent);
+}
+
+/**
+ * struct tb_nhi - thunderbolt native host interface
+ * @lock: Must be held during ring creation/destruction. Is acquired by
+ * interrupt_work when dispatching interrupts to individual rings.
+ * @pdev: Pointer to the PCI device
+ * @iobase: MMIO space of the NHI
+ * @tx_rings: All Tx rings available on this host controller
+ * @rx_rings: All Rx rings available on this host controller
+ * @msix_ida: Used to allocate MSI-X vectors for rings
+ * @going_away: The host controller device is about to disappear so when
+ * this flag is set, avoid touching the hardware anymore.
+ * @interrupt_work: Work scheduled to handle ring interrupt when no
+ * MSI-X is used.
+ * @hop_count: Number of rings (end point hops) supported by NHI.
+ */
+struct tb_nhi {
+ spinlock_t lock;
+ struct pci_dev *pdev;
+ void __iomem *iobase;
+ struct tb_ring **tx_rings;
+ struct tb_ring **rx_rings;
+ struct ida msix_ida;
+ bool going_away;
+ struct work_struct interrupt_work;
+ u32 hop_count;
+};
+
+/**
+ * struct tb_ring - thunderbolt TX or RX ring associated with a NHI
+ * @lock: Lock serializing actions to this ring. Must be acquired after
+ * nhi->lock.
+ * @nhi: Pointer to the native host controller interface
+ * @size: Size of the ring
+ * @hop: Hop (DMA channel) associated with this ring
+ * @head: Head of the ring (write next descriptor here)
+ * @tail: Tail of the ring (complete next descriptor here)
+ * @descriptors: Allocated descriptors for this ring
+ * @queue: Queue holding frames to be transferred over this ring
+ * @in_flight: Queue holding frames that are currently in flight
+ * @work: Interrupt work structure
+ * @is_tx: Is the ring Tx or Rx
+ * @running: Is the ring running
+ * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise.
+ * @vector: MSI-X vector number the ring uses (only set if @irq is > 0)
+ * @flags: Ring specific flags
+ * @sof_mask: Bit mask used to detect start of frame PDF
+ * @eof_mask: Bit mask used to detect end of frame PDF
+ * @start_poll: Called when ring interrupt is triggered to start
+ * polling. Passing %NULL keeps the ring in interrupt mode.
+ * @poll_data: Data passed to @start_poll
+ */
+struct tb_ring {
+ spinlock_t lock;
+ struct tb_nhi *nhi;
+ int size;
+ int hop;
+ int head;
+ int tail;
+ struct ring_desc *descriptors;
+ dma_addr_t descriptors_dma;
+ struct list_head queue;
+ struct list_head in_flight;
+ struct work_struct work;
+ bool is_tx:1;
+ bool running:1;
+ int irq;
+ u8 vector;
+ unsigned int flags;
+ u16 sof_mask;
+ u16 eof_mask;
+ void (*start_poll)(void *data);
+ void *poll_data;
+};
+
+/* Leave ring interrupt enabled on suspend */
+#define RING_FLAG_NO_SUSPEND BIT(0)
+/* Configure the ring to be in frame mode */
+#define RING_FLAG_FRAME BIT(1)
+/* Enable end-to-end flow control */
+#define RING_FLAG_E2E BIT(2)
+
+struct ring_frame;
+typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled);
+
+/**
+ * enum ring_desc_flags - Flags for DMA ring descriptor
+ * %RING_DESC_ISOCH: Enable isonchronous DMA (Tx only)
+ * %RING_DESC_CRC_ERROR: In frame mode CRC check failed for the frame (Rx only)
+ * %RING_DESC_COMPLETED: Descriptor completed (set by NHI)
+ * %RING_DESC_POSTED: Always set this
+ * %RING_DESC_BUFFER_OVERRUN: RX buffer overrun
+ * %RING_DESC_INTERRUPT: Request an interrupt on completion
+ */
+enum ring_desc_flags {
+ RING_DESC_ISOCH = 0x1,
+ RING_DESC_CRC_ERROR = 0x1,
+ RING_DESC_COMPLETED = 0x2,
+ RING_DESC_POSTED = 0x4,
+ RING_DESC_BUFFER_OVERRUN = 0x04,
+ RING_DESC_INTERRUPT = 0x8,
+};
+
+/**
+ * struct ring_frame - For use with ring_rx/ring_tx
+ * @buffer_phy: DMA mapped address of the frame
+ * @callback: Callback called when the frame is finished (optional)
+ * @list: Frame is linked to a queue using this
+ * @size: Size of the frame in bytes (%0 means %4096)
+ * @flags: Flags for the frame (see &enum ring_desc_flags)
+ * @eof: End of frame protocol defined field
+ * @sof: Start of frame protocol defined field
+ */
+struct ring_frame {
+ dma_addr_t buffer_phy;
+ ring_cb callback;
+ struct list_head list;
+ u32 size:12;
+ u32 flags:12;
+ u32 eof:4;
+ u32 sof:4;
+};
+
+/* Minimum size for ring_rx */
+#define TB_FRAME_SIZE 0x100
+
+struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
+ unsigned int flags);
+struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
+ unsigned int flags, u16 sof_mask, u16 eof_mask,
+ void (*start_poll)(void *), void *poll_data);
+void tb_ring_start(struct tb_ring *ring);
+void tb_ring_stop(struct tb_ring *ring);
+void tb_ring_free(struct tb_ring *ring);
+
+int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame);
+
+/**
+ * tb_ring_rx() - enqueue a frame on an RX ring
+ * @ring: Ring to enqueue the frame
+ * @frame: Frame to enqueue
+ *
+ * @frame->buffer, @frame->buffer_phy have to be set. The buffer must
+ * contain at least %TB_FRAME_SIZE bytes.
+ *
+ * @frame->callback will be invoked with @frame->size, @frame->flags,
+ * @frame->eof, @frame->sof set once the frame has been received.
+ *
+ * If ring_stop() is called after the packet has been enqueued
+ * @frame->callback will be called with canceled set to true.
+ *
+ * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame)
+{
+ WARN_ON(ring->is_tx);
+ return __tb_ring_enqueue(ring, frame);
+}
+
+/**
+ * tb_ring_tx() - enqueue a frame on an TX ring
+ * @ring: Ring the enqueue the frame
+ * @frame: Frame to enqueue
+ *
+ * @frame->buffer, @frame->buffer_phy, @frame->size, @frame->eof and
+ * @frame->sof have to be set.
+ *
+ * @frame->callback will be invoked with once the frame has been transmitted.
+ *
+ * If ring_stop() is called after the packet has been enqueued @frame->callback
+ * will be called with canceled set to true.
+ *
+ * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame)
+{
+ WARN_ON(!ring->is_tx);
+ return __tb_ring_enqueue(ring, frame);
+}
+
+/* Used only when the ring is in polling mode */
+struct ring_frame *tb_ring_poll(struct tb_ring *ring);
+void tb_ring_poll_complete(struct tb_ring *ring);
+
+/**
+ * tb_ring_dma_device() - Return device used for DMA mapping
+ * @ring: Ring whose DMA device is retrieved
+ *
+ * Use this function when you are mapping DMA for buffers that are
+ * passed to the ring for sending/receiving.
+ */
+static inline struct device *tb_ring_dma_device(struct tb_ring *ring)
+{
+ return &ring->nhi->pdev->dev;
+}
+
+#endif /* THUNDERBOLT_H_ */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2bcb4dc6df1a..84014ecfa67f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,14 +272,37 @@ struct trace_event_call {
#ifdef CONFIG_PERF_EVENTS
int perf_refcount;
struct hlist_head __percpu *perf_events;
- struct bpf_prog *prog;
- struct perf_event *bpf_prog_owner;
+ struct bpf_prog_array __rcu *prog_array;
int (*perf_perm)(struct trace_event_call *,
struct perf_event *);
#endif
};
+#ifdef CONFIG_PERF_EVENTS
+static inline bool bpf_prog_array_valid(struct trace_event_call *call)
+{
+ /*
+ * This inline function checks whether call->prog_array
+ * is valid or not. The function is called in various places,
+ * outside rcu_read_lock/unlock, as a heuristic to speed up execution.
+ *
+ * If this function returns true, and later call->prog_array
+ * becomes false inside rcu_read_lock/unlock region,
+ * we bail out then. If this function return false,
+ * there is a risk that we might miss a few events if the checking
+ * were delayed until inside rcu_read_lock/unlock region and
+ * call->prog_array happened to become non-NULL then.
+ *
+ * Here, READ_ONCE() is used instead of rcu_access_pointer().
+ * rcu_access_pointer() requires the actual definition of
+ * "struct bpf_prog_array" while READ_ONCE() only needs
+ * a declaration of the same type.
+ */
+ return !!READ_ONCE(call->prog_array);
+}
+#endif
+
static inline const char *
trace_event_name(struct trace_event_call *call)
{
@@ -436,12 +459,23 @@ trace_trigger_soft_disabled(struct trace_event_file *file)
}
#ifdef CONFIG_BPF_EVENTS
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx);
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
+int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
+void perf_event_detach_bpf_prog(struct perf_event *event);
#else
-static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
return 1;
}
+
+static inline int
+perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void perf_event_detach_bpf_prog(struct perf_event *event) { }
+
#endif
enum {
@@ -512,6 +546,7 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
{
perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event);
}
+
#endif
#endif /* _LINUX_TRACE_EVENT_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index a10a3b1813f3..fd08df74c466 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -94,8 +94,7 @@ struct tc_action_ops {
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int, const struct tc_action_ops *);
void (*stats_update)(struct tc_action *, u64, u32, u64);
- int (*get_dev)(const struct tc_action *a, struct net *net,
- struct net_device **mirred_dev);
+ struct net_device *(*get_dev)(const struct tc_action *a);
};
struct tc_action_net {
@@ -178,4 +177,38 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
#endif
}
+typedef int tc_setup_cb_t(enum tc_setup_type type,
+ void *type_data, void *cb_priv);
+
+#ifdef CONFIG_NET_CLS_ACT
+int tc_setup_cb_egdev_register(const struct net_device *dev,
+ tc_setup_cb_t *cb, void *cb_priv);
+void tc_setup_cb_egdev_unregister(const struct net_device *dev,
+ tc_setup_cb_t *cb, void *cb_priv);
+int tc_setup_cb_egdev_call(const struct net_device *dev,
+ enum tc_setup_type type, void *type_data,
+ bool err_stop);
+#else
+static inline
+int tc_setup_cb_egdev_register(const struct net_device *dev,
+ tc_setup_cb_t *cb, void *cb_priv)
+{
+ return 0;
+}
+
+static inline
+void tc_setup_cb_egdev_unregister(const struct net_device *dev,
+ tc_setup_cb_t *cb, void *cb_priv)
+{
+}
+
+static inline
+int tc_setup_cb_egdev_call(const struct net_device *dev,
+ enum tc_setup_type type, void *type_data,
+ bool err_stop)
+{
+ return 0;
+}
+#endif
+
#endif
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 35f5aabd432f..b623b65a79d1 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -56,11 +56,9 @@ struct prefix_info {
struct in6_validator_info {
struct in6_addr i6vi_addr;
struct inet6_dev *i6vi_dev;
+ struct netlink_ext_ack *extack;
};
-#define IN6_ADDR_HSIZE_SHIFT 4
-#define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT)
-
int addrconf_init(void);
void addrconf_cleanup(void);
@@ -95,8 +93,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
u32 banned_flags);
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
u32 banned_flags);
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
- bool match_wildcard);
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+ bool match_wildcard);
void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
@@ -208,7 +206,7 @@ void ipv6_mc_remap(struct inet6_dev *idev);
void ipv6_mc_init_dev(struct inet6_dev *idev);
void ipv6_mc_destroy_dev(struct inet6_dev *idev);
int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed);
-void addrconf_dad_failure(struct inet6_ifaddr *ifp);
+void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp);
bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
const struct in6_addr *src_addr);
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 3ac79150291f..2b3a6eec4570 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -49,17 +49,19 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
unsigned long,
s64,
gfp_t,
- rxrpc_notify_rx_t);
+ rxrpc_notify_rx_t,
+ bool);
int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
struct msghdr *, size_t,
rxrpc_notify_end_tx_t);
int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
- void *, size_t, size_t *, bool, u32 *);
+ void *, size_t, size_t *, bool, u32 *, u16 *);
bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
u32, int, const char *);
void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *);
+u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
rxrpc_user_attach_call_t, unsigned long, gfp_t);
void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
@@ -67,5 +69,6 @@ int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *, struct key *);
int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *,
enum rxrpc_call_completion *, u32 *);
+u32 rxrpc_kernel_check_life(struct socket *, struct rxrpc_call *);
#endif /* _NET_RXRPC_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f9fb566e75cf..9324ac2d9ff2 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -22,11 +22,13 @@
#include "vsock_addr.h"
-/* vsock-specific sock->sk_state constants */
-#define VSOCK_SS_LISTEN 255
-
#define LAST_RESERVED_PORT 1023
+#define VSOCK_HASH_SIZE 251
+extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+extern spinlock_t vsock_table_lock;
+
#define vsock_sk(__sk) ((struct vsock_sock *)__sk)
#define sk_vsock(__vsk) (&(__vsk)->sk)
@@ -175,6 +177,18 @@ const struct vsock_transport *vsock_core_get_transport(void);
/**** UTILS ****/
+/* vsock_table_lock must be held */
+static inline bool __vsock_in_bound_table(struct vsock_sock *vsk)
+{
+ return !list_empty(&vsk->bound_table);
+}
+
+/* vsock_table_lock must be held */
+static inline bool __vsock_in_connected_table(struct vsock_sock *vsk)
+{
+ return !list_empty(&vsk->connected_table);
+}
+
void vsock_release_pending(struct sock *pending);
void vsock_add_pending(struct sock *listener, struct sock *pending);
void vsock_remove_pending(struct sock *listener, struct sock *pending);
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 020142bb9735..e89cff0c4c23 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -147,6 +147,9 @@ void bt_err_ratelimited(const char *fmt, ...);
#define bt_dev_dbg(hdev, fmt, ...) \
BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+#define bt_dev_err_ratelimited(hdev, fmt, ...) \
+ BT_ERR_RATELIMITED("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+
/* Connection and socket states */
enum {
BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index fe98f0a5bef0..1668211297a9 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -273,7 +273,7 @@ enum {
#define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */
#define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */
#define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */
-#define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */
+#define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */
/* HCI data types */
#define HCI_COMMAND_PKT 0x01
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b2e68657a216..f801fc940b29 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -330,7 +330,6 @@ static inline void bond_set_active_slave(struct slave *slave)
slave->backup = 0;
bond_queue_slave_event(slave);
bond_lower_state_changed(slave);
- rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
}
}
@@ -340,7 +339,6 @@ static inline void bond_set_backup_slave(struct slave *slave)
slave->backup = 1;
bond_queue_slave_event(slave);
bond_lower_state_changed(slave);
- rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
}
}
@@ -353,7 +351,6 @@ static inline void bond_set_slave_state(struct slave *slave,
slave->backup = slave_state;
if (notify) {
bond_lower_state_changed(slave);
- rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
bond_queue_slave_event(slave);
slave->should_notify = 0;
} else {
@@ -385,7 +382,6 @@ static inline void bond_slave_state_notify(struct bonding *bond)
bond_for_each_slave(bond, tmp, iter) {
if (tmp->should_notify) {
bond_lower_state_changed(tmp);
- rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
tmp->should_notify = 0;
}
}
@@ -596,7 +592,8 @@ void bond_destroy_sysfs(struct bond_net *net);
void bond_prepare_sysfs_group(struct bonding *bond);
int bond_sysfs_slave_add(struct slave *slave);
void bond_sysfs_slave_del(struct slave *slave);
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+ struct netlink_ext_ack *extack);
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
int bond_set_carrier(struct bonding *bond);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f12fa5245a45..8b8118a7fadb 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4347,19 +4347,6 @@ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
}
/**
- * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11
- * @skb: the 802.3 frame
- * @addr: the device MAC address
- * @iftype: the virtual interface type
- * @bssid: the network bssid (used only for iftype STATION and ADHOC)
- * @qos: build 802.11 QoS data frame
- * Return: 0 on success, or a negative error code.
- */
-int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
- enum nl80211_iftype iftype, const u8 *bssid,
- bool qos);
-
-/**
* ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
*
* Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames.
@@ -5441,9 +5428,6 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
* @req_ie_len: association request IEs length
* @resp_ie: association response IEs (may be %NULL)
* @resp_ie_len: assoc response IEs length
- * @authorized: true if the 802.1X authentication was done by the driver or is
- * not needed (e.g., when Fast Transition protocol was used), false
- * otherwise. Ignored for networks that don't use 802.1X authentication.
*/
struct cfg80211_roam_info {
struct ieee80211_channel *channel;
@@ -5453,7 +5437,6 @@ struct cfg80211_roam_info {
size_t req_ie_len;
const u8 *resp_ie;
size_t resp_ie_len;
- bool authorized;
};
/**
@@ -5478,6 +5461,23 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
gfp_t gfp);
/**
+ * cfg80211_port_authorized - notify cfg80211 of successful security association
+ *
+ * @dev: network device
+ * @bssid: the BSSID of the AP
+ * @gfp: allocation flags
+ *
+ * This function should be called by a driver that supports 4 way handshake
+ * offload after a security association was successfully established (i.e.,
+ * the 4 way handshake was completed successfully). The call to this function
+ * should be preceded with a call to cfg80211_connect_result(),
+ * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to
+ * indicate the 802.11 association.
+ */
+void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid,
+ gfp_t gfp);
+
+/**
* cfg80211_disconnected - notify cfg80211 that connection was dropped
*
* @dev: network device
@@ -5934,7 +5934,8 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
* @ies: the IE buffer
* @ielen: the length of the IE buffer
* @ids: an array with element IDs that are allowed before
- * the split
+ * the split. A WLAN_EID_EXTENSION value means that the next
+ * EID in the list is a sub-element of the EXTENSION IE.
* @n_ids: the size of the element ID array
* @after_ric: array IE types that come after the RIC element
* @n_after_ric: size of the @after_ric array
@@ -5965,7 +5966,8 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
* @ies: the IE buffer
* @ielen: the length of the IE buffer
* @ids: an array with element IDs that are allowed before
- * the split
+ * the split. A WLAN_EID_EXTENSION value means that the next
+ * EID in the list is a sub-element of the EXTENSION IE.
* @n_ids: the size of the element ID array
* @offset: offset where to start splitting in the buffer
*
diff --git a/include/net/dn.h b/include/net/dn.h
index fc0036228d20..56ab0726c641 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -123,13 +123,6 @@ struct dn_scp /* Session Control Port */
unsigned long keepalive;
void (*keepalive_fxn)(struct sock *sk);
- /*
- * This stuff is for the fast timer for delayed acks
- */
- struct timer_list delack_timer;
- int delack_pending;
- void (*delack_fxn)(struct sock *sk);
-
};
static inline struct dn_scp *DN_SK(struct sock *sk)
diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h
index 3a3e33d18456..413a15e5339c 100644
--- a/include/net/dn_nsp.h
+++ b/include/net/dn_nsp.h
@@ -17,7 +17,6 @@
void dn_nsp_send_data_ack(struct sock *sk);
void dn_nsp_send_oth_ack(struct sock *sk);
-void dn_nsp_delayed_ack(struct sock *sk);
void dn_send_conn_ack(struct sock *sk);
void dn_send_conn_conf(struct sock *sk, gfp_t gfp);
void dn_nsp_send_disc(struct sock *sk, unsigned char type,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index dd44d6ce1097..2a05738570d8 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -29,6 +29,7 @@ struct fixed_phy_status;
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = 0,
DSA_TAG_PROTO_BRCM,
+ DSA_TAG_PROTO_BRCM_PREPEND,
DSA_TAG_PROTO_DSA,
DSA_TAG_PROTO_EDSA,
DSA_TAG_PROTO_KSZ,
@@ -116,13 +117,13 @@ struct dsa_switch_tree {
struct raw_notifier_head nh;
/* Tree identifier */
- u32 tree;
+ unsigned int index;
/* Number of switches attached to this tree */
struct kref refcount;
/* Has this tree been applied to the hardware? */
- bool applied;
+ bool setup;
/*
* Configuration data for the platform device that owns
@@ -130,11 +131,6 @@ struct dsa_switch_tree {
*/
struct dsa_platform_data *pd;
- /* Copy of tag_ops->rcv for faster access in hot path */
- struct sk_buff * (*rcv)(struct sk_buff *skb,
- struct net_device *dev,
- struct packet_type *pt);
-
/*
* The switch port to which the CPU is attached.
*/
@@ -144,12 +140,6 @@ struct dsa_switch_tree {
* Data for the individual switch chips.
*/
struct dsa_switch *ds[DSA_MAX_SWITCHES];
-
- /*
- * Tagging protocol operations for adding and removing an
- * encapsulation tag.
- */
- const struct dsa_device_ops *tag_ops;
};
/* TC matchall action types, only mirroring for now */
@@ -175,11 +165,33 @@ struct dsa_mall_tc_entry {
struct dsa_port {
+ /* A CPU port is physically connected to a master device.
+ * A user port exposed to userspace has a slave device.
+ */
+ union {
+ struct net_device *master;
+ struct net_device *slave;
+ };
+
+ /* CPU port tagging operations used by master or slave devices */
+ const struct dsa_device_ops *tag_ops;
+
+ /* Copies for faster access in master receive hot path */
+ struct dsa_switch_tree *dst;
+ struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt);
+
+ enum {
+ DSA_PORT_TYPE_UNUSED = 0,
+ DSA_PORT_TYPE_CPU,
+ DSA_PORT_TYPE_DSA,
+ DSA_PORT_TYPE_USER,
+ } type;
+
struct dsa_switch *ds;
unsigned int index;
const char *name;
- struct dsa_port *cpu_dp;
- struct net_device *netdev;
+ const struct dsa_port *cpu_dp;
struct device_node *dn;
unsigned int ageing_time;
u8 stp_state;
@@ -188,7 +200,6 @@ struct dsa_port {
/*
* Original copy of the master netdev ethtool_ops
*/
- struct ethtool_ops ethtool_ops;
const struct ethtool_ops *orig_ethtool_ops;
};
@@ -199,7 +210,7 @@ struct dsa_switch {
* Parent switch tree, and switch index.
*/
struct dsa_switch_tree *dst;
- int index;
+ unsigned int index;
/* Listener for switch fabric events */
struct notifier_block nb;
@@ -230,9 +241,6 @@ struct dsa_switch {
/*
* Slave mii_bus and devices for the individual ports.
*/
- u32 dsa_port_mask;
- u32 cpu_port_mask;
- u32 enabled_port_mask;
u32 phys_mii_mask;
struct mii_bus *slave_mii_bus;
@@ -251,19 +259,41 @@ struct dsa_switch {
struct dsa_port ports[];
};
+static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
+{
+ return &ds->ports[p];
+}
+
+static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
+{
+ return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
+}
+
static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
{
- return !!(ds->cpu_port_mask & (1 << p));
+ return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU;
}
static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
{
- return !!((ds->dsa_port_mask) & (1 << p));
+ return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA;
+}
+
+static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
+{
+ return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER;
}
-static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p)
+static inline u32 dsa_user_ports(struct dsa_switch *ds)
{
- return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p);
+ u32 mask = 0;
+ int p;
+
+ for (p = 0; p < ds->num_ports; p++)
+ if (dsa_is_user_port(ds, p))
+ mask |= BIT(p);
+
+ return mask;
}
static inline u8 dsa_upstream_port(struct dsa_switch *ds)
@@ -292,10 +322,10 @@ struct dsa_switch_ops {
struct device *host_dev, int sw_addr,
void **priv);
- enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds);
+ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
+ int port);
int (*setup)(struct dsa_switch *ds);
- int (*set_addr)(struct dsa_switch *ds, u8 *addr);
u32 (*get_phy_flags)(struct dsa_switch *ds, int port);
/*
@@ -475,4 +505,54 @@ static inline int dsa_switch_resume(struct dsa_switch *ds)
}
#endif /* CONFIG_PM_SLEEP */
+enum dsa_notifier_type {
+ DSA_PORT_REGISTER,
+ DSA_PORT_UNREGISTER,
+};
+
+struct dsa_notifier_info {
+ struct net_device *dev;
+};
+
+struct dsa_notifier_register_info {
+ struct dsa_notifier_info info; /* must be first */
+ struct net_device *master;
+ unsigned int port_number;
+ unsigned int switch_number;
+};
+
+static inline struct net_device *
+dsa_notifier_info_to_dev(const struct dsa_notifier_info *info)
+{
+ return info->dev;
+}
+
+#if IS_ENABLED(CONFIG_NET_DSA)
+int register_dsa_notifier(struct notifier_block *nb);
+int unregister_dsa_notifier(struct notifier_block *nb);
+int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+ struct dsa_notifier_info *info);
+#else
+static inline int register_dsa_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int unregister_dsa_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev,
+ struct dsa_notifier_info *info)
+{
+ return NOTIFY_DONE;
+}
+#endif
+
+/* Broadcom tag specific helpers to insert and extract queue/port number */
+#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q)
+#define BRCM_TAG_GET_PORT(v) ((v) >> 8)
+#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff)
+
#endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 694c2e6ae618..b091fd536098 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -102,7 +102,7 @@ struct dst_entry {
union {
struct dst_entry *next;
struct rtable __rcu *rt_next;
- struct rt6_info *rt6_next;
+ struct rt6_info __rcu *rt6_next;
struct dn_route __rcu *dn_next;
};
};
@@ -256,17 +256,18 @@ static inline void dst_hold(struct dst_entry *dst)
WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0);
}
-static inline void dst_use(struct dst_entry *dst, unsigned long time)
+static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
{
- dst_hold(dst);
- dst->__use++;
- dst->lastuse = time;
+ if (unlikely(time != dst->lastuse)) {
+ dst->__use++;
+ dst->lastuse = time;
+ }
}
-static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
+static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time)
{
- dst->__use++;
- dst->lastuse = time;
+ dst_hold(dst);
+ dst_use_noref(dst, time);
}
static inline struct dst_entry *dst_clone(struct dst_entry *dst)
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 91bc7bdf6bf5..56cb3c38569a 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -25,7 +25,7 @@ struct metadata_dst {
} u;
};
-static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb)
{
struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
@@ -35,7 +35,8 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
return NULL;
}
-static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+static inline struct ip_tunnel_info *
+skb_tunnel_info(const struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
struct dst_entry *dst;
@@ -87,6 +88,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
void metadata_dst_free(struct metadata_dst *);
struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
gfp_t flags);
+void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst);
struct metadata_dst __percpu *
metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags);
diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h
index 669b9716dc7a..c91ec732afd6 100644
--- a/include/net/fib_notifier.h
+++ b/include/net/fib_notifier.h
@@ -9,6 +9,7 @@
struct fib_notifier_info {
struct net *net;
int family;
+ struct netlink_ext_ack *extack;
};
enum fib_event_type {
@@ -20,6 +21,8 @@ enum fib_event_type {
FIB_EVENT_RULE_DEL,
FIB_EVENT_NH_ADD,
FIB_EVENT_NH_DEL,
+ FIB_EVENT_VIF_ADD,
+ FIB_EVENT_VIF_DEL,
};
struct fib_notifier_ops {
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 22aba321282d..9a074776f70b 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -84,11 +84,11 @@ struct flow_dissector_key_ipv6_addrs {
};
/**
- * struct flow_dissector_key_tipc_addrs:
- * @srcnode: source node address
+ * struct flow_dissector_key_tipc:
+ * @key: source node address combined with selector
*/
-struct flow_dissector_key_tipc_addrs {
- __be32 srcnode;
+struct flow_dissector_key_tipc {
+ __be32 key;
};
/**
@@ -100,7 +100,7 @@ struct flow_dissector_key_addrs {
union {
struct flow_dissector_key_ipv4_addrs v4addrs;
struct flow_dissector_key_ipv6_addrs v6addrs;
- struct flow_dissector_key_tipc_addrs tipcaddrs;
+ struct flow_dissector_key_tipc tipckey;
};
};
@@ -192,7 +192,7 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */
FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */
FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
- FLOW_DISSECTOR_KEY_TIPC_ADDRS, /* struct flow_dissector_key_tipc_addrs */
+ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */
FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */
FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_flow_vlan */
FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */
diff --git a/include/net/fq.h b/include/net/fq.h
index 6d8521a30c5c..ac944a686840 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -90,6 +90,13 @@ typedef void fq_skb_free_t(struct fq *,
struct fq_flow *,
struct sk_buff *);
+/* Return %true to filter (drop) the frame. */
+typedef bool fq_skb_filter_t(struct fq *,
+ struct fq_tin *,
+ struct fq_flow *,
+ struct sk_buff *,
+ void *);
+
typedef struct fq_flow *fq_flow_get_default_t(struct fq *,
struct fq_tin *,
int idx,
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index ac1a2317941e..be7c0fab3478 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -12,24 +12,22 @@
/* functions that are embedded into includer */
-static struct sk_buff *fq_flow_dequeue(struct fq *fq,
- struct fq_flow *flow)
+static void fq_adjust_removal(struct fq *fq,
+ struct fq_flow *flow,
+ struct sk_buff *skb)
{
struct fq_tin *tin = flow->tin;
- struct fq_flow *i;
- struct sk_buff *skb;
-
- lockdep_assert_held(&fq->lock);
-
- skb = __skb_dequeue(&flow->queue);
- if (!skb)
- return NULL;
tin->backlog_bytes -= skb->len;
tin->backlog_packets--;
flow->backlog -= skb->len;
fq->backlog--;
fq->memory_usage -= skb->truesize;
+}
+
+static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow)
+{
+ struct fq_flow *i;
if (flow->backlog == 0) {
list_del_init(&flow->backlogchain);
@@ -43,6 +41,21 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq,
list_move_tail(&flow->backlogchain,
&i->backlogchain);
}
+}
+
+static struct sk_buff *fq_flow_dequeue(struct fq *fq,
+ struct fq_flow *flow)
+{
+ struct sk_buff *skb;
+
+ lockdep_assert_held(&fq->lock);
+
+ skb = __skb_dequeue(&flow->queue);
+ if (!skb)
+ return NULL;
+
+ fq_adjust_removal(fq, flow, skb);
+ fq_rejigger_backlog(fq, flow);
return skb;
}
@@ -191,6 +204,45 @@ static void fq_tin_enqueue(struct fq *fq,
}
}
+static void fq_flow_filter(struct fq *fq,
+ struct fq_flow *flow,
+ fq_skb_filter_t filter_func,
+ void *filter_data,
+ fq_skb_free_t free_func)
+{
+ struct fq_tin *tin = flow->tin;
+ struct sk_buff *skb, *tmp;
+
+ lockdep_assert_held(&fq->lock);
+
+ skb_queue_walk_safe(&flow->queue, skb, tmp) {
+ if (!filter_func(fq, tin, flow, skb, filter_data))
+ continue;
+
+ __skb_unlink(skb, &flow->queue);
+ fq_adjust_removal(fq, flow, skb);
+ free_func(fq, tin, flow, skb);
+ }
+
+ fq_rejigger_backlog(fq, flow);
+}
+
+static void fq_tin_filter(struct fq *fq,
+ struct fq_tin *tin,
+ fq_skb_filter_t filter_func,
+ void *filter_data,
+ fq_skb_free_t free_func)
+{
+ struct fq_flow *flow;
+
+ lockdep_assert_held(&fq->lock);
+
+ list_for_each_entry(flow, &tin->new_flows, flowchain)
+ fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
+ list_for_each_entry(flow, &tin->old_flows, flowchain)
+ fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
+}
+
static void fq_flow_reset(struct fq *fq,
struct fq_flow *flow,
fq_skb_free_t free_func)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13e4c89a8231..0358745ea059 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -169,9 +169,9 @@ enum inet_csk_ack_state_t {
};
void inet_csk_init_xmit_timers(struct sock *sk,
- void (*retransmit_handler)(unsigned long),
- void (*delack_handler)(unsigned long),
- void (*keepalive_handler)(unsigned long));
+ void (*retransmit_handler)(struct timer_list *),
+ void (*delack_handler)(struct timer_list *),
+ void (*keepalive_handler)(struct timer_list *));
void inet_csk_clear_xmit_timers(struct sock *sk);
static inline void inet_csk_schedule_ack(struct sock *sk)
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index d30e4c869438..482a1b705362 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -134,11 +134,6 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
return 1;
}
-static inline void IP6_ECN_clear(struct ipv6hdr *iph)
-{
- *(__be32*)iph &= ~htonl(INET_ECN_MASK << 20);
-}
-
static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
{
dscp &= ~INET_ECN_MASK;
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index a6e4edd8d4a2..351f0c3cdcd9 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -96,7 +96,7 @@ struct inet_frags {
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
- void (*frag_expire)(unsigned long data);
+ void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
};
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index db8162dd8c0b..2135c9ba6ac3 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -92,7 +92,8 @@ struct inet_request_sock {
wscale_ok : 1,
ecn_ok : 1,
acked : 1,
- no_srccheck: 1;
+ no_srccheck: 1,
+ smc_ok : 1;
kmemcheck_bitfield_end(flags);
u32 ir_mark;
union {
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index d060d711a624..10c913816032 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -29,6 +29,14 @@
#define FIB6_TABLE_HASHSZ 1
#endif
+#define RT6_DEBUG 2
+
+#if RT6_DEBUG >= 3
+#define RT6_TRACE(x...) pr_debug(x)
+#else
+#define RT6_TRACE(x...) do { ; } while (0)
+#endif
+
struct rt6_info;
struct fib6_config {
@@ -60,25 +68,30 @@ struct fib6_config {
};
struct fib6_node {
- struct fib6_node *parent;
- struct fib6_node *left;
- struct fib6_node *right;
+ struct fib6_node __rcu *parent;
+ struct fib6_node __rcu *left;
+ struct fib6_node __rcu *right;
#ifdef CONFIG_IPV6_SUBTREES
- struct fib6_node *subtree;
+ struct fib6_node __rcu *subtree;
#endif
- struct rt6_info *leaf;
+ struct rt6_info __rcu *leaf;
__u16 fn_bit; /* bit key */
__u16 fn_flags;
int fn_sernum;
- struct rt6_info *rr_ptr;
+ struct rt6_info __rcu *rr_ptr;
struct rcu_head rcu;
};
+struct fib6_gc_args {
+ int timeout;
+ int more;
+};
+
#ifndef CONFIG_IPV6_SUBTREES
#define FIB6_SUBTREE(fn) NULL
#else
-#define FIB6_SUBTREE(fn) ((fn)->subtree)
+#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1))
#endif
struct mx6_config {
@@ -98,6 +111,22 @@ struct rt6key {
struct fib6_table;
+struct rt6_exception_bucket {
+ struct hlist_head chain;
+ int depth;
+};
+
+struct rt6_exception {
+ struct hlist_node hlist;
+ struct rt6_info *rt6i;
+ unsigned long stamp;
+ struct rcu_head rcu;
+};
+
+#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10
+#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
+#define FIB6_MAX_DEPTH 5
+
struct rt6_info {
struct dst_entry dst;
@@ -134,14 +163,25 @@ struct rt6_info {
struct inet6_dev *rt6i_idev;
struct rt6_info * __percpu *rt6i_pcpu;
+ struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 rt6i_metric;
u32 rt6i_pmtu;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
+ u8 exception_bucket_flushed:1,
+ unused:7;
};
+#define for_each_fib6_node_rt_rcu(fn) \
+ for (rt = rcu_dereference((fn)->leaf); rt; \
+ rt = rcu_dereference(rt->dst.rt6_next))
+
+#define for_each_fib6_walker_rt(w) \
+ for (rt = (w)->leaf; rt; \
+ rt = rcu_dereference_protected(rt->dst.rt6_next, 1))
+
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
{
return ((struct rt6_info *)dst)->rt6i_idev;
@@ -188,6 +228,8 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
if (fn) {
*cookie = fn->fn_sernum;
+ /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */
+ smp_rmb();
status = true;
}
@@ -248,7 +290,6 @@ struct fib6_walker {
struct fib6_node *root, *node;
struct rt6_info *leaf;
enum fib6_walk_state state;
- bool prune;
unsigned int skip;
unsigned int count;
int (*func)(struct fib6_walker *);
@@ -256,12 +297,15 @@ struct fib6_walker {
};
struct rt6_statistics {
- __u32 fib_nodes;
- __u32 fib_route_nodes;
- __u32 fib_rt_alloc; /* permanent routes */
- __u32 fib_rt_entries; /* rt entries in table */
- __u32 fib_rt_cache; /* cache routes */
- __u32 fib_discarded_routes;
+ __u32 fib_nodes; /* all fib6 nodes */
+ __u32 fib_route_nodes; /* intermediate nodes */
+ __u32 fib_rt_entries; /* rt entries in fib table */
+ __u32 fib_rt_cache; /* cached rt entries in exception table */
+ __u32 fib_discarded_routes; /* total number of routes delete */
+
+ /* The following stats are not protected by any lock */
+ atomic_t fib_rt_alloc; /* total number of routes alloced */
+ atomic_t fib_rt_uncache; /* rt entries in uncached list */
};
#define RTN_TL_ROOT 0x0001
@@ -277,7 +321,7 @@ struct rt6_statistics {
struct fib6_table {
struct hlist_node tb6_hlist;
u32 tb6_id;
- rwlock_t tb6_lock;
+ spinlock_t tb6_lock;
struct fib6_node tb6_root;
struct inet_peer_base tb6_peers;
unsigned int flags;
@@ -325,7 +369,8 @@ struct fib6_node *fib6_lookup(struct fib6_node *root,
struct fib6_node *fib6_locate(struct fib6_node *root,
const struct in6_addr *daddr, int dst_len,
- const struct in6_addr *saddr, int src_len);
+ const struct in6_addr *saddr, int src_len,
+ bool exact_match);
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
void *arg);
@@ -358,6 +403,8 @@ void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
+void fib6_update_sernum(struct rt6_info *rt);
+
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
int fib6_rules_init(void);
void fib6_rules_cleanup(void);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index bee528135cf1..18e442ea93d8 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -96,6 +96,11 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
int ip6_ins_rt(struct rt6_info *);
int ip6_del_rt(struct rt6_info *);
+void rt6_flush_exceptions(struct rt6_info *rt);
+int rt6_remove_exception_rt(struct rt6_info *rt);
+void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
+ unsigned long now);
+
static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1a7f7e424320..f80524396c06 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -122,9 +122,6 @@ struct fib_info {
#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
int fib_nhs;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- int fib_weight;
-#endif
struct rcu_head rcu;
struct fib_nh fib_nh[0];
#define fib_dev fib_nh[0].nh_dev
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index eb2321a13506..24628f6b09bf 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -259,7 +259,8 @@ int ip_tunnel_get_iflink(const struct net_device *dev);
int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname);
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
+void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
+ struct rtnl_link_ops *ops);
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6eac5cf8f1e6..ec14f0d5a3a1 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -51,6 +51,46 @@
#define IPV6_DEFAULT_HOPLIMIT 64
#define IPV6_DEFAULT_MCASTHOPS 1
+/* Limits on Hop-by-Hop and Destination options.
+ *
+ * Per RFC8200 there is no limit on the maximum number or lengths of options in
+ * Hop-by-Hop or Destination options other then the packet must fit in an MTU.
+ * We allow configurable limits in order to mitigate potential denial of
+ * service attacks.
+ *
+ * There are three limits that may be set:
+ * - Limit the number of options in a Hop-by-Hop or Destination options
+ * extension header
+ * - Limit the byte length of a Hop-by-Hop or Destination options extension
+ * header
+ * - Disallow unknown options
+ *
+ * The limits are expressed in corresponding sysctls:
+ *
+ * ipv6.sysctl.max_dst_opts_cnt
+ * ipv6.sysctl.max_hbh_opts_cnt
+ * ipv6.sysctl.max_dst_opts_len
+ * ipv6.sysctl.max_hbh_opts_len
+ *
+ * max_*_opts_cnt is the number of TLVs that are allowed for Destination
+ * options or Hop-by-Hop options. If the number is less than zero then unknown
+ * TLVs are disallowed and the number of known options that are allowed is the
+ * absolute value. Setting the value to INT_MAX indicates no limit.
+ *
+ * max_*_opts_len is the length limit in bytes of a Destination or
+ * Hop-by-Hop options extension header. Setting the value to INT_MAX
+ * indicates no length limit.
+ *
+ * If a limit is exceeded when processing an extension header the packet is
+ * silently discarded.
+ */
+
+/* Default limits for Hop-by-Hop and Destination options */
+#define IP6_DEFAULT_MAX_DST_OPTS_CNT 8
+#define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8
+#define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */
+#define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */
+
/*
* Addr type
*
@@ -300,8 +340,8 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl)
void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
-int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
- struct icmp6hdr *thdr, int len);
+void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len);
int ip6_ra_control(struct sock *sk, int sel);
@@ -727,7 +767,6 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
__be32 ipv6_select_ident(struct net *net,
const struct in6_addr *daddr,
const struct in6_addr *saddr);
-void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
int ip6_dst_hoplimit(struct dst_entry *dst);
diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h
index f3be818e73c1..e766300b3e99 100644
--- a/include/net/llc_c_ac.h
+++ b/include/net/llc_c_ac.h
@@ -171,10 +171,10 @@ int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb);
int llc_conn_ac_send_i_rsp_as_ack(struct sock *sk, struct sk_buff *skb);
int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb);
-void llc_conn_busy_tmr_cb(unsigned long timeout_data);
-void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data);
-void llc_conn_ack_tmr_cb(unsigned long timeout_data);
-void llc_conn_rej_tmr_cb(unsigned long timeout_data);
+void llc_conn_busy_tmr_cb(struct timer_list *t);
+void llc_conn_pf_cycle_tmr_cb(struct timer_list *t);
+void llc_conn_ack_tmr_cb(struct timer_list *t);
+void llc_conn_rej_tmr_cb(struct timer_list *t);
void llc_conn_set_p_flag(struct sock *sk, u8 value);
#endif /* LLC_C_AC_H */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 885690fa39c8..cc9073e45be9 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5441,8 +5441,14 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
*/
void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn);
+/**
+ * ieee80211_manage_rx_ba_offl - helper to queue an RX BA work
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback
+ * @addr: station mac address
+ * @tid: the rx tid
+ */
void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr,
- unsigned int bit);
+ unsigned int tid);
/**
* ieee80211_start_rx_ba_session_offl - start a Rx BA session
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index a964366a7ef5..e421f86af043 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -191,8 +191,8 @@ struct neigh_hash_table {
struct neigh_table {
int family;
- int entry_size;
- int key_len;
+ unsigned int entry_size;
+ unsigned int key_len;
__be16 protocol;
__u32 (*hash)(const void *pkey,
const struct net_device *dev,
diff --git a/include/net/netevent.h b/include/net/netevent.h
index f728d9cad170..40e7bab68490 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -26,6 +26,7 @@ enum netevent_notif_type {
NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */
NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
+ NETEVENT_MULTIPATH_HASH_UPDATE, /* arg is struct net ptr */
};
int register_netevent_notifier(struct notifier_block *nb);
diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index 2cc728ef8cd0..4ed1040bbe4a 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -11,7 +11,7 @@
#define _NF_CONNTRACK_IPV4_H
-extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
+const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index 79a335c0d8b8..9cd55be95853 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -2,7 +2,7 @@
#ifndef _NF_CONNTRACK_IPV6_H
#define _NF_CONNTRACK_IPV6_H
-extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6;
+extern const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6;
extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6;
extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6;
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 510192eb7e9d..7ef56c13698a 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -43,7 +43,6 @@ struct nf_conntrack_l4proto {
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
- u_int8_t pf,
unsigned int *timeouts);
/* Called when a new connection for this protocol found;
@@ -76,7 +75,7 @@ struct nf_conntrack_l4proto {
int (*tuple_to_nlattr)(struct sk_buff *skb,
const struct nf_conntrack_tuple *t);
/* Calculate tuple nlattr size */
- int (*nlattr_tuple_size)(void);
+ unsigned int (*nlattr_tuple_size)(void);
int (*nlattr_to_tuple)(struct nlattr *tb[],
struct nf_conntrack_tuple *t);
const struct nla_policy *nla_policy;
@@ -146,15 +145,27 @@ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple);
int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
struct nf_conntrack_tuple *t);
-int nf_ct_port_nlattr_tuple_size(void);
+unsigned int nf_ct_port_nlattr_tuple_size(void);
extern const struct nla_policy nf_ct_port_nla_policy[];
#ifdef CONFIG_SYSCTL
-#define LOG_INVALID(net, proto) \
- ((net)->ct.sysctl_log_invalid == (proto) || \
- (net)->ct.sysctl_log_invalid == IPPROTO_RAW)
+__printf(3, 4) __cold
+void nf_ct_l4proto_log_invalid(const struct sk_buff *skb,
+ const struct nf_conn *ct,
+ const char *fmt, ...);
+__printf(5, 6) __cold
+void nf_l4proto_log_invalid(const struct sk_buff *skb,
+ struct net *net,
+ u16 pf, u8 protonum,
+ const char *fmt, ...);
#else
-static inline int LOG_INVALID(struct net *net, int proto) { return 0; }
+static inline __printf(5, 6) __cold
+void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net,
+ u16 pf, u8 protonum, const char *fmt, ...) {}
+static inline __printf(3, 4) __cold
+void nf_ct_l4proto_log_invalid(const struct sk_buff *skb,
+ const struct nf_conn *ct,
+ const char *fmt, ...) { }
#endif /* CONFIG_SYSCTL */
#endif /*_NF_CONNTRACK_PROTOCOL_H*/
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 470c1c71e7f4..fecc6112c768 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -312,6 +312,7 @@ struct nft_expr;
* @flush: deactivate element in the next generation
* @remove: remove element from set
* @walk: iterate over all set elemeennts
+ * @get: get set elements
* @privsize: function to return size of set private data
* @init: initialize private data of new set instance
* @destroy: destroy private data of set instance
@@ -351,6 +352,10 @@ struct nft_set_ops {
void (*walk)(const struct nft_ctx *ctx,
struct nft_set *set,
struct nft_set_iter *iter);
+ void * (*get)(const struct net *net,
+ const struct nft_set *set,
+ const struct nft_set_elem *elem,
+ unsigned int flags);
unsigned int (*privsize)(const struct nlattr * const nla[],
const struct nft_set_desc *desc);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 8fcff2837484..44668c29701a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -37,6 +37,8 @@ struct inet_timewait_death_row {
int sysctl_max_tw_buckets;
};
+struct tcp_fastopen_context;
+
struct netns_ipv4 {
#ifdef CONFIG_SYSCTL
struct ctl_table_header *forw_hdr;
@@ -53,6 +55,7 @@ struct netns_ipv4 {
struct fib_table __rcu *fib_main;
struct fib_table __rcu *fib_default;
#endif
+ bool fib_has_custom_local_routes;
#ifdef CONFIG_IP_ROUTE_CLASSID
int fib_num_tclassid_users;
#endif
@@ -126,8 +129,43 @@ struct netns_ipv4 {
int sysctl_tcp_sack;
int sysctl_tcp_window_scaling;
int sysctl_tcp_timestamps;
+ int sysctl_tcp_early_retrans;
+ int sysctl_tcp_recovery;
+ int sysctl_tcp_thin_linear_timeouts;
+ int sysctl_tcp_slow_start_after_idle;
+ int sysctl_tcp_retrans_collapse;
+ int sysctl_tcp_stdurg;
+ int sysctl_tcp_rfc1337;
+ int sysctl_tcp_abort_on_overflow;
+ int sysctl_tcp_fack;
+ int sysctl_tcp_max_reordering;
+ int sysctl_tcp_dsack;
+ int sysctl_tcp_app_win;
+ int sysctl_tcp_adv_win_scale;
+ int sysctl_tcp_frto;
+ int sysctl_tcp_nometrics_save;
+ int sysctl_tcp_moderate_rcvbuf;
+ int sysctl_tcp_tso_win_divisor;
+ int sysctl_tcp_workaround_signed_windows;
+ int sysctl_tcp_limit_output_bytes;
+ int sysctl_tcp_challenge_ack_limit;
+ int sysctl_tcp_min_tso_segs;
+ int sysctl_tcp_min_rtt_wlen;
+ int sysctl_tcp_autocorking;
+ int sysctl_tcp_invalid_ratelimit;
+ int sysctl_tcp_pacing_ss_ratio;
+ int sysctl_tcp_pacing_ca_ratio;
+ int sysctl_tcp_wmem[3];
+ int sysctl_tcp_rmem[3];
struct inet_timewait_death_row tcp_death_row;
int sysctl_max_syn_backlog;
+ int sysctl_tcp_fastopen;
+ const struct tcp_congestion_ops __rcu *tcp_congestion_control;
+ struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
+ spinlock_t tcp_fastopen_ctx_lock;
+ unsigned int sysctl_tcp_fastopen_blackhole_timeout;
+ atomic_t tfo_active_disable_times;
+ unsigned long tfo_active_disable_stamp;
#ifdef CONFIG_NET_L3_MASTER_DEV
int sysctl_udp_l3mdev_accept;
@@ -163,6 +201,9 @@ struct netns_ipv4 {
struct fib_notifier_ops *notifier_ops;
unsigned int fib_seq; /* protected by rtnl_mutex */
+ struct fib_notifier_ops *ipmr_notifier_ops;
+ unsigned int ipmr_seq; /* protected by rtnl_mutex */
+
atomic_t rt_genid;
};
#endif
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index dc825a5ddd7f..987cc4569cb8 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -38,6 +38,10 @@ struct netns_sysctl_ipv6 {
int idgen_delay;
int flowlabel_state_ranges;
int flowlabel_reflect;
+ int max_dst_opts_cnt;
+ int max_hbh_opts_cnt;
+ int max_dst_opts_len;
+ int max_hbh_opts_len;
};
struct netns_ipv6 {
@@ -90,6 +94,11 @@ struct netns_ipv6 {
atomic_t fib6_sernum;
struct seg6_pernet_data *seg6_data;
struct fib_notifier_ops *notifier_ops;
+ struct {
+ struct hlist_head head;
+ spinlock_t lock;
+ u32 seq;
+ } ip6addrlbl_table;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/include/net/nsh.h b/include/net/nsh.h
index a1eaea20be96..350b1ad11c7f 100644
--- a/include/net/nsh.h
+++ b/include/net/nsh.h
@@ -304,4 +304,7 @@ static inline void nsh_set_flags_ttl_len(struct nshhdr *nsh, u8 flags,
NSH_FLAGS_MASK | NSH_TTL_MASK | NSH_LEN_MASK);
}
+int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh);
+int nsh_pop(struct sk_buff *skb);
+
#endif /* __NET_NSH_H */
diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h
index 039cc29cb4a8..51e1a2a45d02 100644
--- a/include/net/phonet/phonet.h
+++ b/include/net/phonet/phonet.h
@@ -108,8 +108,10 @@ struct phonet_protocol {
int sock_type;
};
-int phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp);
-void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp);
+int phonet_proto_register(unsigned int protocol,
+ const struct phonet_protocol *pp);
+void phonet_proto_unregister(unsigned int protocol,
+ const struct phonet_protocol *pp);
int phonet_sysctl_init(void);
void phonet_sysctl_exit(void);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 8826747ef83e..0105445cab83 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -19,6 +19,19 @@ struct tcf_walker {
int register_tcf_proto_ops(struct tcf_proto_ops *ops);
int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
+enum tcf_block_binder_type {
+ TCF_BLOCK_BINDER_TYPE_UNSPEC,
+ TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+ TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
+};
+
+struct tcf_block_ext_info {
+ enum tcf_block_binder_type binder_type;
+ tcf_chain_head_change_t *chain_head_change;
+ void *chain_head_change_priv;
+};
+
+struct tcf_block_cb;
bool tcf_queue_work(struct work_struct *work);
#ifdef CONFIG_NET_CLS
@@ -26,15 +39,52 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
bool create);
void tcf_chain_put(struct tcf_chain *chain);
int tcf_block_get(struct tcf_block **p_block,
- struct tcf_proto __rcu **p_filter_chain);
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q);
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei);
void tcf_block_put(struct tcf_block *block);
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei);
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+ return block->q;
+}
+
+static inline struct net_device *tcf_block_dev(struct tcf_block *block)
+{
+ return tcf_block_q(block)->dev_queue->dev;
+}
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident);
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb);
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv);
+int tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv);
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb);
+void tcf_block_cb_unregister(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident);
+
int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res, bool compat_mode);
#else
static inline
int tcf_block_get(struct tcf_block **p_block,
- struct tcf_proto __rcu **p_filter_chain)
+ struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+ return 0;
+}
+
+static inline
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
{
return 0;
}
@@ -43,6 +93,86 @@ static inline void tcf_block_put(struct tcf_block *block)
{
}
+static inline
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
+{
+}
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+ return NULL;
+}
+
+static inline struct net_device *tcf_block_dev(struct tcf_block *block)
+{
+ return NULL;
+}
+
+static inline
+int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb,
+ void *cb_priv)
+{
+ return 0;
+}
+
+static inline
+void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
+ void *cb_priv)
+{
+}
+
+static inline
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+ return NULL;
+}
+
+static inline
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{
+ return NULL;
+}
+
+static inline
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+}
+
+static inline
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+ return 0;
+}
+
+static inline
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv)
+{
+ return NULL;
+}
+
+static inline
+int tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv)
+{
+ return 0;
+}
+
+static inline
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+{
+}
+
+static inline
+void tcf_block_cb_unregister(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{
+}
+
static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res, bool compat_mode)
{
@@ -57,36 +187,43 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
}
static inline unsigned long
-cls_set_class(struct tcf_proto *tp, unsigned long *clp,
- unsigned long cl)
+cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
{
unsigned long old_cl;
-
- tcf_tree_lock(tp);
+
+ sch_tree_lock(q);
old_cl = __cls_set_class(clp, cl);
- tcf_tree_unlock(tp);
-
+ sch_tree_unlock(q);
return old_cl;
}
static inline void
tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
{
+ struct Qdisc *q = tp->chain->block->q;
unsigned long cl;
- cl = tp->q->ops->cl_ops->bind_tcf(tp->q, base, r->classid);
- cl = cls_set_class(tp, &r->class, cl);
+ /* Check q as it is not set for shared blocks. In that case,
+ * setting class is not supported.
+ */
+ if (!q)
+ return;
+ cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+ cl = cls_set_class(q, &r->class, cl);
if (cl)
- tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+ q->ops->cl_ops->unbind_tcf(q, cl);
}
static inline void
tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
{
+ struct Qdisc *q = tp->chain->block->q;
unsigned long cl;
+ if (!q)
+ return;
if ((cl = __cls_set_class(&r->class, 0)) != 0)
- tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+ q->ops->cl_ops->unbind_tcf(q, cl);
}
struct tcf_exts {
@@ -232,8 +369,6 @@ void tcf_exts_destroy(struct tcf_exts *exts);
void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
-int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
- struct net_device **hw_dev);
/**
* struct tcf_pkt_info - packet information
@@ -433,11 +568,24 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
}
#endif /* CONFIG_NET_CLS_IND */
+int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
+ enum tc_setup_type type, void *type_data, bool err_stop);
+
+enum tc_block_command {
+ TC_BLOCK_BIND,
+ TC_BLOCK_UNBIND,
+};
+
+struct tc_block_offload {
+ enum tc_block_command command;
+ enum tcf_block_binder_type binder_type;
+ struct tcf_block *block;
+};
+
struct tc_cls_common_offload {
u32 chain_index;
__be16 protocol;
u32 prio;
- u32 classid;
};
static inline void
@@ -447,7 +595,6 @@ tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
cls_common->chain_index = tp->chain->index;
cls_common->protocol = tp->protocol;
cls_common->prio = tp->prio;
- cls_common->classid = tp->classid;
}
struct tc_cls_u32_knode {
@@ -487,11 +634,7 @@ struct tc_cls_u32_offload {
static inline bool tc_can_offload(const struct net_device *dev)
{
- if (!(dev->features & NETIF_F_HW_TC))
- return false;
- if (!dev->netdev_ops->ndo_setup_tc)
- return false;
- return true;
+ return dev->features & NETIF_F_HW_TC;
}
static inline bool tc_skip_hw(u32 flags)
@@ -499,13 +642,6 @@ static inline bool tc_skip_hw(u32 flags)
return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false;
}
-static inline bool tc_should_offload(const struct net_device *dev, u32 flags)
-{
- if (tc_skip_hw(flags))
- return false;
- return tc_can_offload(dev);
-}
-
static inline bool tc_skip_sw(u32 flags)
{
return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false;
@@ -542,7 +678,7 @@ struct tc_cls_flower_offload {
struct fl_flow_key *mask;
struct fl_flow_key *key;
struct tcf_exts *exts;
- bool egress_dev;
+ u32 classid;
};
enum tc_matchall_command {
@@ -574,6 +710,15 @@ struct tc_cls_bpf_offload {
u32 gen_flags;
};
+struct tc_mqprio_qopt_offload {
+ /* struct tc_mqprio_qopt must always be the first element */
+ struct tc_mqprio_qopt qopt;
+ u16 mode;
+ u16 shaper;
+ u32 flags;
+ u64 min_rate[TC_QOPT_MAX_QUEUE];
+ u64 max_rate[TC_QOPT_MAX_QUEUE];
+};
/* This structure holds cookie structure that is passed from user
* to the kernel for actions and classifiers
@@ -582,4 +727,34 @@ struct tc_cookie {
u8 *data;
u32 len;
};
+
+enum tc_red_command {
+ TC_RED_REPLACE,
+ TC_RED_DESTROY,
+ TC_RED_STATS,
+ TC_RED_XSTATS,
+};
+
+struct tc_red_qopt_offload_params {
+ u32 min;
+ u32 max;
+ u32 probability;
+ bool is_ecn;
+};
+struct tc_red_qopt_offload_stats {
+ struct gnet_stats_basic_packed *bstats;
+ struct gnet_stats_queue *qstats;
+};
+
+struct tc_red_qopt_offload {
+ enum tc_red_command command;
+ u32 handle;
+ u32 parent;
+ union {
+ struct tc_red_qopt_offload_params set;
+ struct tc_red_qopt_offload_stats stats;
+ struct red_stats *xstats;
+ };
+};
+
#endif
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index b3869f97d37d..d1f413f06c72 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -5,7 +5,9 @@
#include <linux/jiffies.h>
#include <linux/ktime.h>
#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
#include <net/sch_generic.h>
+#include <net/net_namespace.h>
#include <uapi/linux/pkt_sched.h>
#define DEFAULT_TX_QUEUE_LEN 1000
@@ -134,17 +136,18 @@ static inline unsigned int psched_mtu(const struct net_device *dev)
return dev->mtu + dev->hard_header_len;
}
-static inline bool is_classid_clsact_ingress(u32 classid)
+static inline struct net *qdisc_net(struct Qdisc *q)
{
- /* This also returns true for ingress qdisc */
- return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) &&
- TC_H_MIN(classid) != TC_H_MIN(TC_H_MIN_EGRESS);
+ return dev_net(q->dev_queue->dev);
}
-static inline bool is_classid_clsact_egress(u32 classid)
-{
- return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) &&
- TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS);
-}
+struct tc_cbs_qopt_offload {
+ u8 enable;
+ s32 queue;
+ s32 hicredit;
+ s32 locredit;
+ s32 idleslope;
+ s32 sendslope;
+};
#endif
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 23e22054aa60..347015515a7d 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -150,6 +150,8 @@ struct fastopen_queue {
spinlock_t lock;
int qlen; /* # of pending (TCP_SYN_RECV) reqs */
int max_qlen; /* != 0 iff TFO is currently enabled */
+
+ struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */
};
/** struct request_sock_queue - queue of request_socks
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 7b938fbeebc1..ead018744ff5 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -94,9 +94,6 @@ struct rtnl_link_ops {
int slave_maxtype;
const struct nla_policy *slave_policy;
- int (*slave_validate)(struct nlattr *tb[],
- struct nlattr *data[],
- struct netlink_ext_ack *extack);
int (*slave_changelink)(struct net_device *dev,
struct net_device *slave_dev,
struct nlattr *tb[],
@@ -155,8 +152,6 @@ struct rtnl_af_ops {
size_t (*get_stats_af_size)(const struct net_device *dev);
};
-void __rtnl_af_unregister(struct rtnl_af_ops *ops);
-
void rtnl_af_register(struct rtnl_af_ops *ops);
void rtnl_af_unregister(struct rtnl_af_ops *ops);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 236bfe5b2ffe..65d0d25f2648 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -95,7 +95,6 @@ struct Qdisc {
unsigned long state;
struct Qdisc *next_sched;
struct sk_buff *skb_bad_txq;
- struct rcu_head rcu_head;
int padded;
refcount_t refcnt;
@@ -262,9 +261,12 @@ struct qdisc_skb_cb {
unsigned char data[QDISC_CB_PRIV_LEN];
};
+typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
+
struct tcf_chain {
struct tcf_proto __rcu *filter_chain;
- struct tcf_proto __rcu **p_filter_chain;
+ tcf_chain_head_change_t *chain_head_change;
+ void *chain_head_change_priv;
struct list_head list;
struct tcf_block *block;
u32 index; /* chain index */
@@ -273,6 +275,9 @@ struct tcf_chain {
struct tcf_block {
struct list_head chain_list;
+ struct net *net;
+ struct Qdisc *q;
+ struct list_head cb_list;
struct work_struct work;
};
@@ -361,9 +366,6 @@ static inline void sch_tree_unlock(const struct Qdisc *q)
spin_unlock_bh(qdisc_root_sleeping_lock(q));
}
-#define tcf_tree_lock(tp) sch_tree_lock((tp)->q)
-#define tcf_tree_unlock(tp) sch_tree_unlock((tp)->q)
-
extern struct Qdisc noop_qdisc;
extern struct Qdisc_ops noop_qdisc_ops;
extern struct Qdisc_ops pfifo_fast_ops;
@@ -413,6 +415,13 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id)
return NULL;
}
+static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid)
+{
+ u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY;
+
+ return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL;
+}
+
int qdisc_class_hash_init(struct Qdisc_class_hash *);
void qdisc_class_hash_insert(struct Qdisc_class_hash *,
struct Qdisc_class_common *);
@@ -896,4 +905,36 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
+/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
+ * The fast path only needs to access filter list and to update stats
+ */
+struct mini_Qdisc {
+ struct tcf_proto *filter_list;
+ struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+ struct gnet_stats_queue __percpu *cpu_qstats;
+ struct rcu_head rcu;
+};
+
+static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq,
+ const struct sk_buff *skb)
+{
+ bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb);
+}
+
+static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq)
+{
+ this_cpu_inc(miniq->cpu_qstats->drops);
+}
+
+struct mini_Qdisc_pair {
+ struct mini_Qdisc miniq1;
+ struct mini_Qdisc miniq2;
+ struct mini_Qdisc __rcu **p_miniq;
+};
+
+void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
+ struct tcf_proto *tp_head);
+void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
+ struct mini_Qdisc __rcu **p_miniq);
+
#endif
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 88233cf8b8d4..70fb397f65b0 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -72,7 +72,7 @@ typedef enum sctp_disposition (sctp_state_fn_t) (
const union sctp_subtype type,
void *arg,
struct sctp_cmd_seq *commands);
-typedef void (sctp_timer_event_t) (unsigned long);
+typedef void (sctp_timer_event_t) (struct timer_list *);
struct sctp_sm_table_entry {
sctp_state_fn_t *fn;
const char *name;
@@ -314,10 +314,10 @@ int sctp_do_sm(struct net *net, enum sctp_event event_type,
void *event_arg, gfp_t gfp);
/* 2nd level prototypes */
-void sctp_generate_t3_rtx_event(unsigned long peer);
-void sctp_generate_heartbeat_event(unsigned long peer);
-void sctp_generate_reconf_event(unsigned long peer);
-void sctp_generate_proto_unreach_event(unsigned long peer);
+void sctp_generate_t3_rtx_event(struct timer_list *t);
+void sctp_generate_heartbeat_event(struct timer_list *t);
+void sctp_generate_reconf_event(struct timer_list *t);
+void sctp_generate_proto_unreach_event(struct timer_list *t);
void sctp_ootb_pkt_free(struct sctp_packet *packet);
diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h
new file mode 100644
index 000000000000..c676550a4c7d
--- /dev/null
+++ b/include/net/sctp/stream_sched.h
@@ -0,0 +1,72 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * These are definitions used by the stream schedulers, defined in RFC
+ * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11)
+ *
+ * This SCTP implementation 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, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation 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 GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresses:
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#ifndef __sctp_stream_sched_h__
+#define __sctp_stream_sched_h__
+
+struct sctp_sched_ops {
+ /* Property handling for a given stream */
+ int (*set)(struct sctp_stream *stream, __u16 sid, __u16 value,
+ gfp_t gfp);
+ int (*get)(struct sctp_stream *stream, __u16 sid, __u16 *value);
+
+ /* Init the specific scheduler */
+ int (*init)(struct sctp_stream *stream);
+ /* Init a stream */
+ int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+ /* Frees the entire thing */
+ void (*free)(struct sctp_stream *stream);
+
+ /* Enqueue a chunk */
+ void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg);
+ /* Dequeue a chunk */
+ struct sctp_chunk *(*dequeue)(struct sctp_outq *q);
+ /* Called only if the chunk fit the packet */
+ void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk);
+ /* Sched all chunks already enqueued */
+ void (*sched_all)(struct sctp_stream *steam);
+ /* Unched all chunks already enqueued */
+ void (*unsched_all)(struct sctp_stream *steam);
+};
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+ enum sctp_sched_type sched);
+int sctp_sched_get_sched(struct sctp_association *asoc);
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+ __u16 value, gfp_t gfp);
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+ __u16 *value);
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch);
+
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch);
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream);
+
+#endif /* __sctp_stream_sched_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0477945de1a3..16f949eef52f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -380,6 +380,7 @@ struct sctp_sender_hb_info {
int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
gfp_t gfp);
+int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid);
void sctp_stream_free(struct sctp_stream *stream);
void sctp_stream_clear(struct sctp_stream *stream);
void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new);
@@ -529,8 +530,12 @@ struct sctp_chunk {
/* How many times this chunk have been sent, for prsctp RTX policy */
int sent_count;
- /* This is our link to the per-transport transmitted list. */
- struct list_head transmitted_list;
+ union {
+ /* This is our link to the per-transport transmitted list. */
+ struct list_head transmitted_list;
+ /* List in specific stream outq */
+ struct list_head stream_list;
+ };
/* This field is used by chunks that hold fragmented data.
* For the first fragment this is the list that holds the rest of
@@ -640,6 +645,11 @@ void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *,
union sctp_addr *);
const union sctp_addr *sctp_source(const struct sctp_chunk *chunk);
+static inline __u16 sctp_chunk_stream_no(struct sctp_chunk *ch)
+{
+ return ntohs(ch->subh.data_hdr->stream);
+}
+
enum {
SCTP_ADDR_NEW, /* new address added to assoc/ep */
SCTP_ADDR_SRC, /* address can be used as source */
@@ -1012,6 +1022,9 @@ struct sctp_outq {
/* Data pending that has never been transmitted. */
struct list_head out_chunk_list;
+ /* Stream scheduler being used */
+ struct sctp_sched_ops *sched;
+
unsigned int out_qlen; /* Total length of queued data chunks. */
/* Error of send failed, may used in SCTP_SEND_FAILED event. */
@@ -1315,11 +1328,37 @@ struct sctp_inithdr_host {
__u32 initial_tsn;
};
+struct sctp_stream_priorities {
+ /* List of priorities scheduled */
+ struct list_head prio_sched;
+ /* List of streams scheduled */
+ struct list_head active;
+ /* The next stream stream in line */
+ struct sctp_stream_out_ext *next;
+ __u16 prio;
+};
+
+struct sctp_stream_out_ext {
+ __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+ __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+ struct list_head outq; /* chunks enqueued by this stream */
+ union {
+ struct {
+ /* Scheduled streams list */
+ struct list_head prio_list;
+ struct sctp_stream_priorities *prio_head;
+ };
+ /* Fields used by RR scheduler */
+ struct {
+ struct list_head rr_list;
+ };
+ };
+};
+
struct sctp_stream_out {
__u16 ssn;
__u8 state;
- __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
- __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+ struct sctp_stream_out_ext *ext;
};
struct sctp_stream_in {
@@ -1331,6 +1370,22 @@ struct sctp_stream {
struct sctp_stream_in *in;
__u16 outcnt;
__u16 incnt;
+ /* Current stream being sent, if any */
+ struct sctp_stream_out *out_curr;
+ union {
+ /* Fields used by priority scheduler */
+ struct {
+ /* List of priorities scheduled */
+ struct list_head prio_list;
+ };
+ /* Fields used by RR scheduler */
+ struct {
+ /* List of streams scheduled */
+ struct list_head rr_list;
+ /* The next stream stream in line */
+ struct sctp_stream_out_ext *rr_next;
+ };
+ };
};
#define SCTP_STREAM_CLOSED 0x00
diff --git a/include/net/sock.h b/include/net/sock.h
index a6b9a8d1a6df..f8715c5af37d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -60,7 +60,7 @@
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/cgroup-defs.h>
-
+#include <linux/rbtree.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
@@ -267,6 +267,7 @@ struct sock_common {
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
+ * @sk_pacing_shift: scaling factor for TCP Small Queues
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
@@ -397,7 +398,10 @@ struct sock {
int sk_wmem_queued;
refcount_t sk_wmem_alloc;
unsigned long sk_tsq_flags;
- struct sk_buff *sk_send_head;
+ union {
+ struct sk_buff *sk_send_head;
+ struct rb_root tcp_rtx_queue;
+ };
struct sk_buff_head sk_write_queue;
__s32 sk_peek_off;
int sk_write_pending;
@@ -448,6 +452,7 @@ struct sock {
kmemcheck_bitfield_end(flags);
u16 sk_gso_max_segs;
+ u8 sk_pacing_shift;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
@@ -734,10 +739,10 @@ static inline void sk_add_bind_node(struct sock *sk,
*
*/
#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \
- for (pos = rcu_dereference((head)->first); \
+ for (pos = rcu_dereference(hlist_first_rcu(head)); \
pos != NULL && \
({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \
- pos = rcu_dereference(pos->next))
+ pos = rcu_dereference(hlist_next_rcu(pos)))
static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
@@ -1098,8 +1103,12 @@ struct proto {
*/
unsigned long *memory_pressure;
long *sysctl_mem;
+
int *sysctl_wmem;
int *sysctl_rmem;
+ u32 sysctl_wmem_offset;
+ u32 sysctl_rmem_offset;
+
int max_header;
bool no_autobind;
@@ -2387,4 +2396,22 @@ extern int sysctl_optmem_max;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
+static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_wmem ? */
+ if (proto->sysctl_wmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+
+ return *proto->sysctl_wmem;
+}
+
+static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_rmem ? */
+ if (proto->sysctl_rmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+
+ return *proto->sysctl_rmem;
+}
+
#endif /* _SOCK_H */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d767b7991887..39bc855d7fee 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -51,6 +51,7 @@ enum switchdev_attr_id {
SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING,
SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED,
+ SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
};
struct switchdev_attr {
@@ -75,6 +76,7 @@ enum switchdev_obj_id {
SWITCHDEV_OBJ_ID_UNDEFINED,
SWITCHDEV_OBJ_ID_PORT_VLAN,
SWITCHDEV_OBJ_ID_PORT_MDB,
+ SWITCHDEV_OBJ_ID_HOST_MDB,
};
struct switchdev_obj {
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index e82d93346b63..ef8dd0db70ce 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -34,6 +34,11 @@ static inline bool __is_tcf_gact_act(const struct tc_action *a, int act,
return false;
}
+static inline bool is_tcf_gact_ok(const struct tc_action *a)
+{
+ return __is_tcf_gact_act(a, TC_ACT_OK, false);
+}
+
static inline bool is_tcf_gact_shot(const struct tc_action *a)
{
return __is_tcf_gact_act(a, TC_ACT_SHOT, false);
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index ba6667125bcd..86d13b01b39d 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -7,12 +7,18 @@
#include <linux/rtnetlink.h>
#include <linux/module.h>
-struct tcf_ife_info {
- struct tc_action common;
+struct tcf_ife_params {
u8 eth_dst[ETH_ALEN];
u8 eth_src[ETH_ALEN];
u16 eth_type;
u16 flags;
+
+ struct rcu_head rcu;
+};
+
+struct tcf_ife_info {
+ struct tc_action common;
+ struct tcf_ife_params __rcu *params;
/* list of metaids allowed */
struct list_head metalist;
};
@@ -41,7 +47,7 @@ struct tcf_meta_ops {
struct module *owner;
};
-#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan))
+#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ife-meta-" metan)
int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index b2dbbfaefd22..21d253c9a8c6 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -11,6 +11,7 @@ struct tcf_mirred {
int tcfm_ifindex;
bool tcfm_mac_header_xmit;
struct net_device __rcu *tcfm_dev;
+ struct net *net;
struct list_head tcfm_list;
};
#define to_mirred(a) ((struct tcf_mirred *)a)
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index c2090df944ff..22ae260d6869 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -13,12 +13,17 @@
#include <net/act_api.h>
#include <linux/tc_act/tc_vlan.h>
+struct tcf_vlan_params {
+ int tcfv_action;
+ u16 tcfv_push_vid;
+ __be16 tcfv_push_proto;
+ u8 tcfv_push_prio;
+ struct rcu_head rcu;
+};
+
struct tcf_vlan {
struct tc_action common;
- int tcfv_action;
- u16 tcfv_push_vid;
- __be16 tcfv_push_proto;
- u8 tcfv_push_prio;
+ struct tcf_vlan_params __rcu *vlan_p;
};
#define to_vlan(a) ((struct tcf_vlan *)a)
@@ -33,22 +38,45 @@ static inline bool is_tcf_vlan(const struct tc_action *a)
static inline u32 tcf_vlan_action(const struct tc_action *a)
{
- return to_vlan(a)->tcfv_action;
+ u32 tcfv_action;
+
+ rcu_read_lock();
+ tcfv_action = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_action;
+ rcu_read_unlock();
+
+ return tcfv_action;
}
static inline u16 tcf_vlan_push_vid(const struct tc_action *a)
{
- return to_vlan(a)->tcfv_push_vid;
+ u16 tcfv_push_vid;
+
+ rcu_read_lock();
+ tcfv_push_vid = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_vid;
+ rcu_read_unlock();
+
+ return tcfv_push_vid;
}
static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
{
- return to_vlan(a)->tcfv_push_proto;
+ __be16 tcfv_push_proto;
+
+ rcu_read_lock();
+ tcfv_push_proto = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_proto;
+ rcu_read_unlock();
+
+ return tcfv_push_proto;
}
static inline u8 tcf_vlan_push_prio(const struct tc_action *a)
{
- return to_vlan(a)->tcfv_push_prio;
-}
+ u8 tcfv_push_prio;
+ rcu_read_lock();
+ tcfv_push_prio = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_prio;
+ rcu_read_unlock();
+
+ return tcfv_push_prio;
+}
#endif /* __NET_TC_VLAN_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e6d0002a1b0b..85ea578195d4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -45,9 +45,6 @@
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
-
-#include <linux/bpf.h>
-#include <linux/filter.h>
#include <linux/bpf-cgroup.h>
extern struct inet_hashinfo tcp_hashinfo;
@@ -191,6 +188,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
* experimental options. See draft-ietf-tcpm-experimental-options-00.txt
*/
#define TCPOPT_FASTOPEN_MAGIC 0xF989
+#define TCPOPT_SMC_MAGIC 0xE2D4C3D9
/*
* TCP option lengths
@@ -203,6 +201,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOLEN_MD5SIG 18
#define TCPOLEN_FASTOPEN_BASE 2
#define TCPOLEN_EXP_FASTOPEN_BASE 4
+#define TCPOLEN_EXP_SMC_BASE 6
/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED 12
@@ -213,6 +212,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOLEN_SACK_PERBLOCK 8
#define TCPOLEN_MD5SIG_ALIGNED 20
#define TCPOLEN_MSS_ALIGNED 4
+#define TCPOLEN_EXP_SMC_BASE_ALIGNED 8
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
@@ -240,41 +240,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
/* sysctl variables for tcp */
-extern int sysctl_tcp_fastopen;
-extern int sysctl_tcp_retrans_collapse;
-extern int sysctl_tcp_stdurg;
-extern int sysctl_tcp_rfc1337;
-extern int sysctl_tcp_abort_on_overflow;
extern int sysctl_tcp_max_orphans;
-extern int sysctl_tcp_fack;
-extern int sysctl_tcp_reordering;
-extern int sysctl_tcp_max_reordering;
-extern int sysctl_tcp_dsack;
extern long sysctl_tcp_mem[3];
-extern int sysctl_tcp_wmem[3];
-extern int sysctl_tcp_rmem[3];
-extern int sysctl_tcp_app_win;
-extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_frto;
-extern int sysctl_tcp_nometrics_save;
-extern int sysctl_tcp_moderate_rcvbuf;
-extern int sysctl_tcp_tso_win_divisor;
-extern int sysctl_tcp_workaround_signed_windows;
-extern int sysctl_tcp_slow_start_after_idle;
-extern int sysctl_tcp_thin_linear_timeouts;
-extern int sysctl_tcp_thin_dupack;
-extern int sysctl_tcp_early_retrans;
-extern int sysctl_tcp_recovery;
-#define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */
-extern int sysctl_tcp_limit_output_bytes;
-extern int sysctl_tcp_challenge_ack_limit;
-extern int sysctl_tcp_min_tso_segs;
-extern int sysctl_tcp_min_rtt_wlen;
-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;
+#define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */
+#define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -414,9 +384,9 @@ void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
-void tcp_disable_fack(struct tcp_sock *tp);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
+void tcp_init_transfer(struct sock *sk, int bpf_op);
unsigned int tcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -551,7 +521,13 @@ void tcp_xmit_retransmit_queue(struct sock *);
void tcp_simple_retransmit(struct sock *);
void tcp_enter_recovery(struct sock *sk, bool ece_ack);
int tcp_trim_head(struct sock *, struct sk_buff *, u32);
-int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
+enum tcp_queue {
+ TCP_FRAG_IN_WRITE_QUEUE,
+ TCP_FRAG_IN_RTX_QUEUE,
+};
+int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
+ struct sk_buff *skb, u32 len,
+ unsigned int mss_now, gfp_t gfp);
void tcp_send_probe0(struct sock *);
void tcp_send_partial(struct sock *);
@@ -796,16 +772,10 @@ struct tcp_skb_cb {
u16 tcp_gso_segs;
u16 tcp_gso_size;
};
-
- /* Used to stash the receive timestamp while this skb is in the
- * out of order queue, as skb->tstamp is overwritten by the
- * rbnode.
- */
- ktime_t swtstamp;
};
__u8 tcp_flags; /* TCP header flags. (tcp[13]) */
- __u8 sacked; /* State flags for SACK/FACK. */
+ __u8 sacked; /* State flags for SACK. */
#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */
#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */
#define TCPCB_LOST 0x04 /* SKB is lost */
@@ -1032,8 +1002,8 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
void tcp_assign_congestion_control(struct sock *sk);
void tcp_init_congestion_control(struct sock *sk);
void tcp_cleanup_congestion_control(struct sock *sk);
-int tcp_set_default_congestion_control(const char *name);
-void tcp_get_default_congestion_control(char *name);
+int tcp_set_default_congestion_control(struct net *net, const char *name);
+void tcp_get_default_congestion_control(struct net *net, char *name);
void tcp_get_available_congestion_control(char *buf, size_t len);
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
@@ -1047,7 +1017,7 @@ 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, bool *ecn_ca);
+u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
char *tcp_ca_get_name_by_key(u32 key, char *buffer);
#else
@@ -1095,7 +1065,6 @@ void tcp_rate_check_app_limited(struct sock *sk);
*
* tcp_is_sack - SACK enabled
* tcp_is_reno - No SACK
- * tcp_is_fack - FACK enabled, implies SACK enabled
*/
static inline int tcp_is_sack(const struct tcp_sock *tp)
{
@@ -1107,16 +1076,6 @@ static inline bool tcp_is_reno(const struct tcp_sock *tp)
return !tcp_is_sack(tp);
}
-static inline bool tcp_is_fack(const struct tcp_sock *tp)
-{
- return tp->rx_opt.sack_ok & TCP_FACK_ENABLED;
-}
-
-static inline void tcp_enable_fack(struct tcp_sock *tp)
-{
- tp->rx_opt.sack_ok |= TCP_FACK_ENABLED;
-}
-
static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
return tp->sacked_out + tp->lost_out;
@@ -1309,7 +1268,7 @@ 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 ||
+ if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out ||
ca_ops->cong_control)
return;
delta = tcp_jiffies32 - tp->lsndtime;
@@ -1318,13 +1277,14 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk)
}
/* Determine a window scaling and initial window to offer. */
-void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
+void tcp_select_initial_window(const struct sock *sk, int __space,
+ __u32 mss, __u32 *rcv_wnd,
__u32 *window_clamp, int wscale_ok,
__u8 *rcv_wscale, __u32 init_rcv_wnd);
-static inline int tcp_win_from_space(int space)
+static inline int tcp_win_from_space(const struct sock *sk, int space)
{
- int tcp_adv_win_scale = sysctl_tcp_adv_win_scale;
+ int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
return tcp_adv_win_scale <= 0 ?
(space>>(-tcp_adv_win_scale)) :
@@ -1334,13 +1294,13 @@ static inline int tcp_win_from_space(int space)
/* Note: caller must be prepared to deal with negative returns */
static inline int tcp_space(const struct sock *sk)
{
- return tcp_win_from_space(sk->sk_rcvbuf -
+ return tcp_win_from_space(sk, sk->sk_rcvbuf -
atomic_read(&sk->sk_rmem_alloc));
}
static inline int tcp_full_space(const struct sock *sk)
{
- return tcp_win_from_space(sk->sk_rcvbuf);
+ return tcp_win_from_space(sk, sk->sk_rcvbuf);
}
extern void tcp_openreq_init_rwin(struct request_sock *req,
@@ -1561,14 +1521,16 @@ struct tcp_fastopen_request {
int copied; /* queued in tcp_connect() */
};
void tcp_free_fastopen_req(struct tcp_sock *tp);
-
-extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-int tcp_fastopen_reset_cipher(void *key, unsigned int len);
+void tcp_fastopen_destroy_cipher(struct sock *sk);
+void tcp_fastopen_ctx_destroy(struct net *net);
+int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
+ void *key, unsigned int len);
void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
- struct tcp_fastopen_cookie *foc);
-void tcp_fastopen_init_key_once(bool publish);
+ struct tcp_fastopen_cookie *foc,
+ const struct dst_entry *dst);
+void tcp_fastopen_init_key_once(struct net *net);
bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie);
bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
@@ -1601,52 +1563,46 @@ enum tcp_chrono {
void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type);
void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type);
-/* write queue abstraction */
-static inline void tcp_write_queue_purge(struct sock *sk)
+/* This helper is needed, because skb->tcp_tsorted_anchor uses
+ * the same memory storage than skb->destructor/_skb_refdst
+ */
+static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb)
{
- struct sk_buff *skb;
-
- tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
- while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
- sk_wmem_free_skb(sk, skb);
- sk_mem_reclaim(sk);
- tcp_clear_all_retrans_hints(tcp_sk(sk));
+ skb->destructor = NULL;
+ skb->_skb_refdst = 0UL;
}
-static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
-{
- return skb_peek(&sk->sk_write_queue);
+#define tcp_skb_tsorted_save(skb) { \
+ unsigned long _save = skb->_skb_refdst; \
+ skb->_skb_refdst = 0UL;
+
+#define tcp_skb_tsorted_restore(skb) \
+ skb->_skb_refdst = _save; \
}
-static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
+void tcp_write_queue_purge(struct sock *sk);
+
+static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
{
- return skb_peek_tail(&sk->sk_write_queue);
+ return skb_rb_first(&sk->tcp_rtx_queue);
}
-static inline struct sk_buff *tcp_write_queue_next(const struct sock *sk,
- const struct sk_buff *skb)
+static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
{
- return skb_queue_next(&sk->sk_write_queue, skb);
+ return skb_peek(&sk->sk_write_queue);
}
-static inline struct sk_buff *tcp_write_queue_prev(const struct sock *sk,
- const struct sk_buff *skb)
+static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk)
{
- return skb_queue_prev(&sk->sk_write_queue, skb);
+ return skb_peek_tail(&sk->sk_write_queue);
}
-#define tcp_for_write_queue(skb, sk) \
- skb_queue_walk(&(sk)->sk_write_queue, skb)
-
-#define tcp_for_write_queue_from(skb, sk) \
- skb_queue_walk_from(&(sk)->sk_write_queue, skb)
-
#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
static inline struct sk_buff *tcp_send_head(const struct sock *sk)
{
- return sk->sk_send_head;
+ return skb_peek(&sk->sk_write_queue);
}
static inline bool tcp_skb_is_last(const struct sock *sk,
@@ -1655,27 +1611,25 @@ static inline bool tcp_skb_is_last(const struct sock *sk,
return skb_queue_is_last(&sk->sk_write_queue, skb);
}
-static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff *skb)
+static inline bool tcp_write_queue_empty(const struct sock *sk)
{
- if (tcp_skb_is_last(sk, skb))
- sk->sk_send_head = NULL;
- else
- sk->sk_send_head = tcp_write_queue_next(sk, skb);
+ return skb_queue_empty(&sk->sk_write_queue);
}
-static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
+static inline bool tcp_rtx_queue_empty(const struct sock *sk)
{
- if (sk->sk_send_head == skb_unlinked) {
- sk->sk_send_head = NULL;
- tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
- }
- if (tcp_sk(sk)->highest_sack == skb_unlinked)
- tcp_sk(sk)->highest_sack = NULL;
+ return RB_EMPTY_ROOT(&sk->tcp_rtx_queue);
+}
+
+static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
+{
+ return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
}
-static inline void tcp_init_send_head(struct sock *sk)
+static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
{
- sk->sk_send_head = NULL;
+ if (tcp_write_queue_empty(sk))
+ tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
}
static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
@@ -1688,26 +1642,8 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb
__tcp_add_write_queue_tail(sk, skb);
/* Queue it, remembering where we must start sending. */
- if (sk->sk_send_head == NULL) {
- sk->sk_send_head = skb;
+ if (sk->sk_write_queue.next == skb)
tcp_chrono_start(sk, TCP_CHRONO_BUSY);
-
- if (tcp_sk(sk)->highest_sack == NULL)
- tcp_sk(sk)->highest_sack = skb;
- }
-}
-
-static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
-{
- __skb_queue_head(&sk->sk_write_queue, skb);
-}
-
-/* Insert buff after skb on the write queue of sk. */
-static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
- struct sk_buff *buff,
- struct sock *sk)
-{
- __skb_queue_after(&sk->sk_write_queue, skb, buff);
}
/* Insert new before skb on the write queue of sk. */
@@ -1716,19 +1652,27 @@ static inline void tcp_insert_write_queue_before(struct sk_buff *new,
struct sock *sk)
{
__skb_queue_before(&sk->sk_write_queue, skb, new);
-
- if (sk->sk_send_head == skb)
- sk->sk_send_head = new;
}
static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
{
+ tcp_skb_tsorted_anchor_cleanup(skb);
__skb_unlink(skb, &sk->sk_write_queue);
}
-static inline bool tcp_write_queue_empty(struct sock *sk)
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb);
+
+static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk)
{
- return skb_queue_empty(&sk->sk_write_queue);
+ tcp_skb_tsorted_anchor_cleanup(skb);
+ rb_erase(&skb->rbnode, &sk->tcp_rtx_queue);
+}
+
+static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk)
+{
+ list_del(&skb->tcp_tsorted_anchor);
+ tcp_rtx_queue_unlink(skb, sk);
+ sk_wmem_free_skb(sk, skb);
}
static inline void tcp_push_pending_frames(struct sock *sk)
@@ -1757,8 +1701,7 @@ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
{
- tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL :
- tcp_write_queue_next(sk, skb);
+ tcp_sk(sk)->highest_sack = skb_rb_next(skb);
}
static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
@@ -1768,7 +1711,7 @@ static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
static inline void tcp_highest_sack_reset(struct sock *sk)
{
- tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
+ tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk);
}
/* Called when old skb is about to be deleted and replaced by new skb */
@@ -1934,11 +1877,12 @@ extern void tcp_rack_mark_lost(struct sock *sk);
extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
u64 xmit_time);
extern void tcp_rack_reo_timeout(struct sock *sk);
+extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs);
/* At how many usecs into the future should the RTO fire? */
static inline s64 tcp_rto_delta_us(const struct sock *sk)
{
- const struct sk_buff *skb = tcp_write_queue_head(sk);
+ const struct sk_buff *skb = tcp_rtx_queue_head(sk);
u32 rto = inet_csk(sk)->icsk_rto;
u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto);
@@ -2115,4 +2059,8 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
{
return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
}
+
+#if IS_ENABLED(CONFIG_SMC)
+extern struct static_key_false tcp_have_smc;
+#endif
#endif /* _TCP_H */
diff --git a/include/net/tipc.h b/include/net/tipc.h
new file mode 100644
index 000000000000..07670ec022a7
--- /dev/null
+++ b/include/net/tipc.h
@@ -0,0 +1,62 @@
+/*
+ * include/net/tipc.h: Include file for TIPC message header routines
+ *
+ * Copyright (c) 2017 Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_HDR_H
+#define _TIPC_HDR_H
+
+#include <linux/random.h>
+
+#define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */
+
+struct tipc_basic_hdr {
+ __be32 w[4];
+};
+
+static inline u32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
+{
+ u32 w0 = ntohl(hdr->w[0]);
+ bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK;
+ int key;
+
+ /* Return source node identity as key */
+ if (likely(!keepalive_msg))
+ return hdr->w[3];
+
+ /* Spread PROBE/PROBE_REPLY messages across the cores */
+ get_random_bytes(&key, sizeof(key));
+ return key;
+}
+
+#endif
diff --git a/include/net/tls.h b/include/net/tls.h
index b89d397dd62f..936cfc5cab7d 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -35,6 +35,10 @@
#define _TLS_OFFLOAD_H
#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <net/tcp.h>
#include <uapi/linux/tls.h>
@@ -83,6 +87,8 @@ struct tls_context {
void *priv_ctx;
+ u8 tx_conf:2;
+
u16 prepend_size;
u16 tag_size;
u16 overhead_size;
@@ -97,7 +103,6 @@ struct tls_context {
u16 pending_open_record_frags;
int (*push_pending_record)(struct sock *sk, int flags);
- void (*free_resources)(struct sock *sk);
void (*sk_write_space)(struct sock *sk);
void (*sk_proto_close)(struct sock *sk, long timeout);
@@ -122,6 +127,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tls_sw_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_sw_close(struct sock *sk, long timeout);
+void tls_sw_free_tx_resources(struct sock *sk);
void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
void tls_icsk_clean_acked(struct sock *sk);
@@ -212,6 +218,21 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
}
+static inline void tls_make_aad(char *buf,
+ size_t size,
+ char *record_sequence,
+ int record_sequence_size,
+ unsigned char record_type)
+{
+ memcpy(buf, record_sequence, record_sequence_size);
+
+ buf[8] = record_type;
+ buf[9] = TLS_1_2_VERSION_MAJOR;
+ buf[10] = TLS_1_2_VERSION_MINOR;
+ buf[11] = size >> 8;
+ buf[12] = size & 0xFF;
+}
+
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index e015e164bac0..dc28a98ce97c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1765,22 +1765,22 @@ static inline int xfrm_acquire_is_on(struct net *net)
}
#endif
-static inline int aead_len(struct xfrm_algo_aead *alg)
+static inline unsigned int aead_len(struct xfrm_algo_aead *alg)
{
return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
}
-static inline int xfrm_alg_len(const struct xfrm_algo *alg)
+static inline unsigned int xfrm_alg_len(const struct xfrm_algo *alg)
{
return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
}
-static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
+static inline unsigned int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
{
return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
}
-static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn)
+static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn)
{
return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32);
}
diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h
index cc749d7099fb..150185647e6b 100644
--- a/include/trace/events/bpf.h
+++ b/include/trace/events/bpf.h
@@ -5,6 +5,9 @@
#if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_BPF_H
+/* These are only used within the BPF_SYSCALL code */
+#ifdef CONFIG_BPF_SYSCALL
+
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/fs.h>
@@ -346,7 +349,7 @@ TRACE_EVENT(bpf_map_next_key,
__print_hex(__get_dynamic_array(nxt), __entry->key_len),
__entry->key_trunc ? " ..." : "")
);
-
+#endif /* CONFIG_BPF_SYSCALL */
#endif /* _TRACE_BPF_H */
#include <trace/define_trace.h>
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index d46e24702765..7e8d48a81b91 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -13,9 +13,9 @@
TRACE_EVENT(fib6_table_lookup,
TP_PROTO(const struct net *net, const struct rt6_info *rt,
- u32 tb_id, const struct flowi6 *flp),
+ struct fib6_table *table, const struct flowi6 *flp),
- TP_ARGS(net, rt, tb_id, flp),
+ TP_ARGS(net, rt, table, flp),
TP_STRUCT__entry(
__field( u32, tb_id )
@@ -35,7 +35,7 @@ TRACE_EVENT(fib6_table_lookup,
TP_fast_assign(
struct in6_addr *in6;
- __entry->tb_id = tb_id;
+ __entry->tb_id = table->tb6_id;
__entry->oif = flp->flowi6_oif;
__entry->iif = flp->flowi6_iif;
__entry->tos = ip6_tclass(flp->flowlabel);
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index 6d31c0520ef3..ec4dade24466 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -48,7 +48,7 @@ TRACE_EVENT(sock_exceed_buf_limit,
strncpy(__entry->name, prot->name, 32);
__entry->sysctl_mem = prot->sysctl_mem;
__entry->allocated = allocated;
- __entry->sysctl_rmem = prot->sysctl_rmem[0];
+ __entry->sysctl_rmem = sk_get_rmem0(sk, prot);
__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
),
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
new file mode 100644
index 000000000000..07cccca6cbf1
--- /dev/null
+++ b/include/trace/events/tcp.h
@@ -0,0 +1,299 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tcp
+
+#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TCP_H
+
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/tracepoint.h>
+#include <net/ipv6.h>
+
+#define tcp_state_name(state) { state, #state }
+#define show_tcp_state_name(val) \
+ __print_symbolic(val, \
+ tcp_state_name(TCP_ESTABLISHED), \
+ tcp_state_name(TCP_SYN_SENT), \
+ tcp_state_name(TCP_SYN_RECV), \
+ tcp_state_name(TCP_FIN_WAIT1), \
+ tcp_state_name(TCP_FIN_WAIT2), \
+ tcp_state_name(TCP_TIME_WAIT), \
+ tcp_state_name(TCP_CLOSE), \
+ tcp_state_name(TCP_CLOSE_WAIT), \
+ tcp_state_name(TCP_LAST_ACK), \
+ tcp_state_name(TCP_LISTEN), \
+ tcp_state_name(TCP_CLOSING), \
+ tcp_state_name(TCP_NEW_SYN_RECV))
+
+/*
+ * tcp event with arguments sk and skb
+ *
+ * Note: this class requires a valid sk pointer; while skb pointer could
+ * be NULL.
+ */
+DECLARE_EVENT_CLASS(tcp_event_sk_skb,
+
+ TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+ TP_ARGS(sk, skb),
+
+ TP_STRUCT__entry(
+ __field(const void *, skbaddr)
+ __field(const void *, skaddr)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ ),
+
+ TP_fast_assign(
+ struct inet_sock *inet = inet_sk(sk);
+ struct in6_addr *pin6;
+ __be32 *p32;
+
+ __entry->skbaddr = skb;
+ __entry->skaddr = sk;
+
+ __entry->sport = ntohs(inet->inet_sport);
+ __entry->dport = ntohs(inet->inet_dport);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = inet->inet_saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6) {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ *pin6 = sk->sk_v6_rcv_saddr;
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ *pin6 = sk->sk_v6_daddr;
+ } else
+#endif
+ {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+ }
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+ __entry->sport, __entry->dport, __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6)
+);
+
+DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb,
+
+ TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+ TP_ARGS(sk, skb)
+);
+
+/*
+ * skb of trace_tcp_send_reset is the skb that caused RST. In case of
+ * active reset, skb should be NULL
+ */
+DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset,
+
+ TP_PROTO(const struct sock *sk, const struct sk_buff *skb),
+
+ TP_ARGS(sk, skb)
+);
+
+/*
+ * tcp event with arguments sk
+ *
+ * Note: this class requires a valid sk pointer.
+ */
+DECLARE_EVENT_CLASS(tcp_event_sk,
+
+ TP_PROTO(const struct sock *sk),
+
+ TP_ARGS(sk),
+
+ TP_STRUCT__entry(
+ __field(const void *, skaddr)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ ),
+
+ TP_fast_assign(
+ struct inet_sock *inet = inet_sk(sk);
+ struct in6_addr *pin6;
+ __be32 *p32;
+
+ __entry->skaddr = sk;
+
+ __entry->sport = ntohs(inet->inet_sport);
+ __entry->dport = ntohs(inet->inet_dport);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = inet->inet_saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6) {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ *pin6 = sk->sk_v6_rcv_saddr;
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ *pin6 = sk->sk_v6_daddr;
+ } else
+#endif
+ {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+ }
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+ __entry->sport, __entry->dport,
+ __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6)
+);
+
+DEFINE_EVENT(tcp_event_sk, tcp_receive_reset,
+
+ TP_PROTO(const struct sock *sk),
+
+ TP_ARGS(sk)
+);
+
+DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock,
+
+ TP_PROTO(const struct sock *sk),
+
+ TP_ARGS(sk)
+);
+
+TRACE_EVENT(tcp_set_state,
+
+ TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),
+
+ TP_ARGS(sk, oldstate, newstate),
+
+ TP_STRUCT__entry(
+ __field(const void *, skaddr)
+ __field(int, oldstate)
+ __field(int, newstate)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ ),
+
+ TP_fast_assign(
+ struct inet_sock *inet = inet_sk(sk);
+ struct in6_addr *pin6;
+ __be32 *p32;
+
+ __entry->skaddr = sk;
+ __entry->oldstate = oldstate;
+ __entry->newstate = newstate;
+
+ __entry->sport = ntohs(inet->inet_sport);
+ __entry->dport = ntohs(inet->inet_dport);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = inet->inet_saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6) {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ *pin6 = sk->sk_v6_rcv_saddr;
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ *pin6 = sk->sk_v6_daddr;
+ } else
+#endif
+ {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+ }
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",
+ __entry->sport, __entry->dport,
+ __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6,
+ show_tcp_state_name(__entry->oldstate),
+ show_tcp_state_name(__entry->newstate))
+);
+
+TRACE_EVENT(tcp_retransmit_synack,
+
+ TP_PROTO(const struct sock *sk, const struct request_sock *req),
+
+ TP_ARGS(sk, req),
+
+ TP_STRUCT__entry(
+ __field(const void *, skaddr)
+ __field(const void *, req)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ ),
+
+ TP_fast_assign(
+ struct inet_request_sock *ireq = inet_rsk(req);
+ struct in6_addr *pin6;
+ __be32 *p32;
+
+ __entry->skaddr = sk;
+ __entry->req = req;
+
+ __entry->sport = ireq->ir_num;
+ __entry->dport = ntohs(ireq->ir_rmt_port);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = ireq->ir_loc_addr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = ireq->ir_rmt_addr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6) {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ *pin6 = ireq->ir_v6_loc_addr;
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ *pin6 = ireq->ir_v6_rmt_addr;
+ } else
+#endif
+ {
+ pin6 = (struct in6_addr *)__entry->saddr_v6;
+ ipv6_addr_set_v4mapped(ireq->ir_loc_addr, pin6);
+ pin6 = (struct in6_addr *)__entry->daddr_v6;
+ ipv6_addr_set_v4mapped(ireq->ir_rmt_addr, pin6);
+ }
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
+ __entry->sport, __entry->dport,
+ __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6)
+);
+
+#endif /* _TRACE_TCP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 810e94160c12..4cd0f05d0113 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -137,14 +137,90 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
__entry->map_id, __entry->map_index)
);
+#define devmap_ifindex(fwd, map) \
+ (!fwd ? 0 : \
+ (!map ? 0 : \
+ ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \
+ ((struct net_device *)fwd)->ifindex : 0)))
+
#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
- trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
0, map, idx)
#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
- trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
err, map, idx)
+TRACE_EVENT(xdp_cpumap_kthread,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int sched),
+
+ TP_ARGS(map_id, processed, drops, sched),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, sched)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->sched = sched;
+ ),
+
+ TP_printk("kthread"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " sched=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int to_cpu),
+
+ TP_ARGS(map_id, processed, drops, to_cpu),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, to_cpu)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->to_cpu = to_cpu;
+ ),
+
+ TP_printk("enqueue"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " to_cpu=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->to_cpu)
+);
+
#endif /* _TRACE_XDP_H */
#include <trace/define_trace.h>
diff --git a/include/trace/perf.h b/include/trace/perf.h
index e4b249821684..dbc6c74defc3 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -35,7 +35,6 @@ perf_trace_##call(void *__data, proto) \
struct trace_event_call *event_call = __data; \
struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
struct trace_event_raw_##call *entry; \
- struct bpf_prog *prog = event_call->prog; \
struct pt_regs *__regs; \
u64 __count = 1; \
struct task_struct *__task = NULL; \
@@ -47,8 +46,9 @@ perf_trace_##call(void *__data, proto) \
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
\
head = this_cpu_ptr(event_call->perf_events); \
- if (!prog && __builtin_constant_p(!__task) && !__task && \
- hlist_empty(head)) \
+ if (!bpf_prog_array_valid(event_call) && \
+ __builtin_constant_p(!__task) && !__task && \
+ hlist_empty(head)) \
return; \
\
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index a83ddb7b63db..efd641c8a5d6 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -24,20 +24,6 @@
/**
* enum batadv_tt_client_flags - TT client specific flags
- * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
- * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new
- * update telling its new real location has not been received/sent yet
- * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface.
- * This information is used by the "AP Isolation" feature
- * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
- * information is used by the Extended Isolation feature
- * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table
- * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has
- * not been announced yet
- * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept
- * in the table for one more originator interval for consistency purposes
- * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of
- * the network but no nnode has already announced it
*
* Bits from 0 to 7 are called _remote flags_ because they are sent on the wire.
* Bits from 8 to 15 are called _local flags_ because they are used for local
@@ -48,160 +34,385 @@
* in the TT CRC computation.
*/
enum batadv_tt_client_flags {
+ /**
+ * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
+ */
BATADV_TT_CLIENT_DEL = (1 << 0),
+
+ /**
+ * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and
+ * the new update telling its new real location has not been
+ * received/sent yet
+ */
BATADV_TT_CLIENT_ROAM = (1 << 1),
+
+ /**
+ * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi
+ * interface. This information is used by the "AP Isolation" feature
+ */
BATADV_TT_CLIENT_WIFI = (1 << 4),
+
+ /**
+ * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
+ * information is used by the Extended Isolation feature
+ */
BATADV_TT_CLIENT_ISOLA = (1 << 5),
+
+ /**
+ * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from
+ * the table
+ */
BATADV_TT_CLIENT_NOPURGE = (1 << 8),
+
+ /**
+ * @BATADV_TT_CLIENT_NEW: this client has been added to the local table
+ * but has not been announced yet
+ */
BATADV_TT_CLIENT_NEW = (1 << 9),
+
+ /**
+ * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it
+ * is kept in the table for one more originator interval for consistency
+ * purposes
+ */
BATADV_TT_CLIENT_PENDING = (1 << 10),
+
+ /**
+ * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be
+ * part of the network but no nnode has already announced it
+ */
BATADV_TT_CLIENT_TEMP = (1 << 11),
};
/**
* enum batadv_nl_attrs - batman-adv netlink attributes
- *
- * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
- * @BATADV_ATTR_VERSION: batman-adv version string
- * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
- * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
- * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
- * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
- * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
- * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
- * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface
- * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
- * @BATADV_ATTR_TPMETER_RESULT: result of run (see batadv_tp_meter_status)
- * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
- * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
- * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
- * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
- * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active
- * @BATADV_ATTR_TT_ADDRESS: Client MAC address
- * @BATADV_ATTR_TT_TTVN: Translation table version
- * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version
- * @BATADV_ATTR_TT_CRC32: CRC32 over translation table
- * @BATADV_ATTR_TT_VID: VLAN ID
- * @BATADV_ATTR_TT_FLAGS: Translation table client flags
- * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best
- * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen
- * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address
- * @BATADV_ATTR_TQ: TQ to neighbour
- * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour
- * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth
- * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth
- * @BATADV_ATTR_ROUTER: Gateway router MAC address
- * @BATADV_ATTR_BLA_OWN: Flag indicating own originator
- * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address
- * @BATADV_ATTR_BLA_VID: BLA VLAN ID
- * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address
- * @BATADV_ATTR_BLA_CRC: BLA CRC
- * @__BATADV_ATTR_AFTER_LAST: internal use
- * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
- * @BATADV_ATTR_MAX: highest attribute number currently defined
*/
enum batadv_nl_attrs {
+ /**
+ * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
+ */
BATADV_ATTR_UNSPEC,
+
+ /**
+ * @BATADV_ATTR_VERSION: batman-adv version string
+ */
BATADV_ATTR_VERSION,
+
+ /**
+ * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
+ */
BATADV_ATTR_ALGO_NAME,
+
+ /**
+ * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
+ */
BATADV_ATTR_MESH_IFINDEX,
+
+ /**
+ * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
+ */
BATADV_ATTR_MESH_IFNAME,
+
+ /**
+ * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
+ */
BATADV_ATTR_MESH_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
+ */
BATADV_ATTR_HARD_IFINDEX,
+
+ /**
+ * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
+ */
BATADV_ATTR_HARD_IFNAME,
+
+ /**
+ * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv
+ * interface
+ */
BATADV_ATTR_HARD_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
+ */
BATADV_ATTR_ORIG_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TPMETER_RESULT: result of run (see
+ * batadv_tp_meter_status)
+ */
BATADV_ATTR_TPMETER_RESULT,
+
+ /**
+ * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
+ */
BATADV_ATTR_TPMETER_TEST_TIME,
+
+ /**
+ * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
+ */
BATADV_ATTR_TPMETER_BYTES,
+
+ /**
+ * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
+ */
BATADV_ATTR_TPMETER_COOKIE,
+
+ /**
+ * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
+ */
BATADV_ATTR_PAD,
+
+ /**
+ * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active
+ */
BATADV_ATTR_ACTIVE,
+
+ /**
+ * @BATADV_ATTR_TT_ADDRESS: Client MAC address
+ */
BATADV_ATTR_TT_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TT_TTVN: Translation table version
+ */
BATADV_ATTR_TT_TTVN,
+
+ /**
+ * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version
+ */
BATADV_ATTR_TT_LAST_TTVN,
+
+ /**
+ * @BATADV_ATTR_TT_CRC32: CRC32 over translation table
+ */
BATADV_ATTR_TT_CRC32,
+
+ /**
+ * @BATADV_ATTR_TT_VID: VLAN ID
+ */
BATADV_ATTR_TT_VID,
+
+ /**
+ * @BATADV_ATTR_TT_FLAGS: Translation table client flags
+ */
BATADV_ATTR_TT_FLAGS,
+
+ /**
+ * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best
+ */
BATADV_ATTR_FLAG_BEST,
+
+ /**
+ * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen
+ */
BATADV_ATTR_LAST_SEEN_MSECS,
+
+ /**
+ * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address
+ */
BATADV_ATTR_NEIGH_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TQ: TQ to neighbour
+ */
BATADV_ATTR_TQ,
+
+ /**
+ * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour
+ */
BATADV_ATTR_THROUGHPUT,
+
+ /**
+ * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth
+ */
BATADV_ATTR_BANDWIDTH_UP,
+
+ /**
+ * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth
+ */
BATADV_ATTR_BANDWIDTH_DOWN,
+
+ /**
+ * @BATADV_ATTR_ROUTER: Gateway router MAC address
+ */
BATADV_ATTR_ROUTER,
+
+ /**
+ * @BATADV_ATTR_BLA_OWN: Flag indicating own originator
+ */
BATADV_ATTR_BLA_OWN,
+
+ /**
+ * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address
+ */
BATADV_ATTR_BLA_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_BLA_VID: BLA VLAN ID
+ */
BATADV_ATTR_BLA_VID,
+
+ /**
+ * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address
+ */
BATADV_ATTR_BLA_BACKBONE,
+
+ /**
+ * @BATADV_ATTR_BLA_CRC: BLA CRC
+ */
BATADV_ATTR_BLA_CRC,
+
/* add attributes above here, update the policy in netlink.c */
+
+ /**
+ * @__BATADV_ATTR_AFTER_LAST: internal use
+ */
__BATADV_ATTR_AFTER_LAST,
+
+ /**
+ * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
+ */
NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST,
+
+ /**
+ * @BATADV_ATTR_MAX: highest attribute number currently defined
+ */
BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1
};
/**
* enum batadv_nl_commands - supported batman-adv netlink commands
- *
- * @BATADV_CMD_UNSPEC: unspecified command to catch errors
- * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device
- * @BATADV_CMD_TP_METER: Start a tp meter session
- * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
- * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms.
- * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces
- * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
- * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations
- * @BATADV_CMD_GET_ORIGINATORS: Query list of originators
- * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours
- * @BATADV_CMD_GET_GATEWAYS: Query list of gateways
- * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims
- * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance backbones
- * @__BATADV_CMD_AFTER_LAST: internal use
- * @BATADV_CMD_MAX: highest used command number
*/
enum batadv_nl_commands {
+ /**
+ * @BATADV_CMD_UNSPEC: unspecified command to catch errors
+ */
BATADV_CMD_UNSPEC,
+
+ /**
+ * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv
+ * device
+ */
BATADV_CMD_GET_MESH_INFO,
+
+ /**
+ * @BATADV_CMD_TP_METER: Start a tp meter session
+ */
BATADV_CMD_TP_METER,
+
+ /**
+ * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
+ */
BATADV_CMD_TP_METER_CANCEL,
+
+ /**
+ * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms.
+ */
BATADV_CMD_GET_ROUTING_ALGOS,
+
+ /**
+ * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces
+ */
BATADV_CMD_GET_HARDIFS,
+
+ /**
+ * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
+ */
BATADV_CMD_GET_TRANSTABLE_LOCAL,
+
+ /**
+ * @BATADV_CMD_GET_TRANSTABLE_GLOBAL: Query list of global translations
+ */
BATADV_CMD_GET_TRANSTABLE_GLOBAL,
+
+ /**
+ * @BATADV_CMD_GET_ORIGINATORS: Query list of originators
+ */
BATADV_CMD_GET_ORIGINATORS,
+
+ /**
+ * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours
+ */
BATADV_CMD_GET_NEIGHBORS,
+
+ /**
+ * @BATADV_CMD_GET_GATEWAYS: Query list of gateways
+ */
BATADV_CMD_GET_GATEWAYS,
+
+ /**
+ * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims
+ */
BATADV_CMD_GET_BLA_CLAIM,
+
+ /**
+ * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance
+ * backbones
+ */
BATADV_CMD_GET_BLA_BACKBONE,
+
/* add new commands above here */
+
+ /**
+ * @__BATADV_CMD_AFTER_LAST: internal use
+ */
__BATADV_CMD_AFTER_LAST,
+
+ /**
+ * @BATADV_CMD_MAX: highest used command number
+ */
BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1
};
/**
* enum batadv_tp_meter_reason - reason of a tp meter test run stop
- * @BATADV_TP_REASON_COMPLETE: sender finished tp run
- * @BATADV_TP_REASON_CANCEL: sender was stopped during run
- * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or didn't
- * answer
- * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
- * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node already
- * ongoing
- * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
- * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
- * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
*/
enum batadv_tp_meter_reason {
+ /**
+ * @BATADV_TP_REASON_COMPLETE: sender finished tp run
+ */
BATADV_TP_REASON_COMPLETE = 3,
+
+ /**
+ * @BATADV_TP_REASON_CANCEL: sender was stopped during run
+ */
BATADV_TP_REASON_CANCEL = 4,
+
/* error status >= 128 */
+
+ /**
+ * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or
+ * didn't answer
+ */
BATADV_TP_REASON_DST_UNREACHABLE = 128,
+
+ /**
+ * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
+ */
BATADV_TP_REASON_RESEND_LIMIT = 129,
+
+ /**
+ * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node
+ * already ongoing
+ */
BATADV_TP_REASON_ALREADY_ONGOING = 130,
+
+ /**
+ * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
+ */
BATADV_TP_REASON_MEMORY_ERROR = 131,
+
+ /**
+ * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
+ */
BATADV_TP_REASON_CANT_SEND = 132,
+
+ /**
+ * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
+ */
BATADV_TP_REASON_TOO_MANY = 133,
};
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 30f2ce76b517..e880ae6434ee 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -93,6 +93,7 @@ enum bpf_cmd {
BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
+ BPF_PROG_QUERY,
};
enum bpf_map_type {
@@ -112,6 +113,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
@@ -130,6 +132,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_XMIT,
BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_CGROUP_DEVICE,
};
enum bpf_attach_type {
@@ -139,16 +142,53 @@ enum bpf_attach_type {
BPF_CGROUP_SOCK_OPS,
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_DEVICE,
__MAX_BPF_ATTACH_TYPE
};
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ * cgrp2 (OVERRIDE prog C) ->
+ * cgrp3 (MULTI prog D) ->
+ * cgrp4 (OVERRIDE prog E) ->
+ * cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+#define BPF_F_ALLOW_MULTI (1U << 1)
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will perform strict alignment checking as if the kernel
@@ -176,6 +216,15 @@ enum bpf_attach_type {
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE (1U << 2)
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY (1U << 3)
+#define BPF_F_WRONLY (1U << 4)
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
@@ -189,6 +238,7 @@ union bpf_attr {
__u32 numa_node; /* numa node (effective only if
* BPF_F_NUMA_NODE is set).
*/
+ char map_name[BPF_OBJ_NAME_LEN];
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -211,11 +261,14 @@ union bpf_attr {
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
__u32 prog_flags;
+ char prog_name[BPF_OBJ_NAME_LEN];
+ __u32 prog_target_ifindex; /* ifindex of netdev to prep for */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
+ __u32 file_flags;
};
struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -243,6 +296,7 @@ union bpf_attr {
__u32 map_id;
};
__u32 next_id;
+ __u32 open_flags;
};
struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -250,6 +304,15 @@ union bpf_attr {
__u32 info_len;
__aligned_u64 info;
} info;
+
+ struct { /* anonymous struct used by BPF_PROG_QUERY command */
+ __u32 target_fd; /* container object to query */
+ __u32 attach_type;
+ __u32 query_flags;
+ __u32 attach_flags;
+ __aligned_u64 prog_ids;
+ __u32 prog_cnt;
+ } query;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -554,12 +617,22 @@ union bpf_attr {
* int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
* Calls setsockopt. Not all opts are available, only those with
* integer optvals plus TCP_CONGESTION.
- * Supported levels: SOL_SOCKET and IPROTO_TCP
+ * Supported levels: SOL_SOCKET and IPPROTO_TCP
+ * @bpf_socket: pointer to bpf_socket
+ * @level: SOL_SOCKET or IPPROTO_TCP
+ * @optname: option name
+ * @optval: pointer to option value
+ * @optlen: length of optval in bytes
+ * Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ * Calls getsockopt. Not all opts are available.
+ * Supported levels: IPPROTO_TCP
* @bpf_socket: pointer to bpf_socket
- * @level: SOL_SOCKET or IPROTO_TCP
+ * @level: IPPROTO_TCP
* @optname: option name
* @optval: pointer to option value
- * @optlen: length of optval in byes
+ * @optlen: length of optval in bytes
* Return: 0 or negative error
*
* int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -583,6 +656,27 @@ union bpf_attr {
* @map: pointer to sockmap to update
* @key: key to insert/update sock in map
* @flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ * Adjust the xdp_md.data_meta by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data_meta
+ * Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ * read perf event counter value and perf event enabled/running time
+ * @map: pointer to perf_event_array map
+ * @flags: index of event in the map or bitmask flags
+ * @buf: buf to fill
+ * @buf_size: size of the buf
+ * Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ * read perf prog attached perf event counter and enabled/running time
+ * @ctx: pointer to ctx
+ * @buf: buf to fill
+ * @buf_size: size of the buf
+ * Return : 0 on success or negative error code
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -639,6 +733,10 @@ union bpf_attr {
FN(redirect_map), \
FN(sk_redirect_map), \
FN(sock_map_update), \
+ FN(xdp_adjust_meta), \
+ FN(perf_event_read_value), \
+ FN(perf_prog_read_value), \
+ FN(getsockopt),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -682,7 +780,9 @@ enum bpf_func_id {
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
#define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
/* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -716,7 +816,7 @@ struct __sk_buff {
__u32 data_end;
__u32 napi_id;
- /* accessed by BPF_PROG_TYPE_sk_skb types */
+ /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
__u32 local_ip4; /* Stored in network byte order */
@@ -724,6 +824,9 @@ struct __sk_buff {
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ /* ... here. */
+
+ __u32 data_meta;
};
struct bpf_tunnel_key {
@@ -784,6 +887,7 @@ enum xdp_action {
struct xdp_md {
__u32 data;
__u32 data_end;
+ __u32 data_meta;
};
enum sk_action {
@@ -793,6 +897,10 @@ enum sk_action {
#define BPF_TAG_SIZE 8
+enum bpf_prog_status {
+ BPF_PROG_STATUS_DEV_BOUND = (1 << 0),
+};
+
struct bpf_prog_info {
__u32 type;
__u32 id;
@@ -801,6 +909,13 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
+ __u64 load_time; /* ns since boottime */
+ __u32 created_by_uid;
+ __u32 nr_map_ids;
+ __aligned_u64 map_ids;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u32 status;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -810,6 +925,7 @@ struct bpf_map_info {
__u32 value_size;
__u32 max_entries;
__u32 map_flags;
+ char name[BPF_OBJ_NAME_LEN];
} __attribute__((aligned(8)));
/* User bpf_sock_ops struct to access socket values and specify request ops
@@ -859,9 +975,35 @@ enum {
BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control
* needs ECN
*/
+ BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is
+ * based on the path and may be
+ * dependent on the congestion control
+ * algorithm. In general it indicates
+ * a congestion threshold. RTTs above
+ * this indicate congestion
+ */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
+struct bpf_perf_event_value {
+ __u64 counter;
+ __u64 enabled;
+ __u64 running;
+};
+
+#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
+#define BPF_DEVCG_ACC_READ (1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE (1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK (1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+ __u32 access_type; /* (access << 16) | type */
+ __u32 major;
+ __u32 minor;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h
index b6170a6af7c2..2c0c6453c3f4 100644
--- a/include/uapi/linux/dcbnl.h
+++ b/include/uapi/linux/dcbnl.h
@@ -206,6 +206,7 @@ struct cee_pfc {
#define IEEE_8021QAZ_APP_SEL_STREAM 2
#define IEEE_8021QAZ_APP_SEL_DGRAM 3
#define IEEE_8021QAZ_APP_SEL_ANY 4
+#define IEEE_8021QAZ_APP_SEL_DSCP 5
/* This structure contains the IEEE 802.1Qaz APP managed object. This
* object is also used for the CEE std as well.
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1f00f0cd6790..19fc02660e0c 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -159,6 +159,8 @@ enum {
IFLA_PAD,
IFLA_XDP,
IFLA_EVENT,
+ IFLA_NEW_NETNSID,
+ IFLA_IF_NETNSID,
__IFLA_MAX
};
@@ -326,6 +328,8 @@ enum {
IFLA_BRPORT_MCAST_TO_UCAST,
IFLA_BRPORT_VLAN_TUNNEL,
IFLA_BRPORT_BCAST_FLOOD,
+ IFLA_BRPORT_GROUP_FWD_MASK,
+ IFLA_BRPORT_NEIGH_SUPPRESS,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -463,6 +467,7 @@ enum macsec_validation_type {
enum {
IFLA_IPVLAN_UNSPEC,
IFLA_IPVLAN_MODE,
+ IFLA_IPVLAN_FLAGS,
__IFLA_IPVLAN_MAX
};
@@ -475,6 +480,9 @@ enum ipvlan_mode {
IPVLAN_MODE_MAX
};
+#define IPVLAN_F_PRIVATE 0x01
+#define IPVLAN_F_VEPA 0x02
+
/* VXLAN section */
enum {
IFLA_VXLAN_UNSPEC,
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 47ab4bc62e31..030d3e6d6029 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -61,6 +61,8 @@
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
#define IFF_TAP 0x0002
+#define IFF_NAPI 0x0010
+#define IFF_NAPI_FRAGS 0x0020
#define IFF_NO_PI 0x1000
/* This flag has no real effect */
#define IFF_ONE_QUEUE 0x2000
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 383b850aeb88..e68dadbd6d45 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -85,6 +85,7 @@ enum tunnel_encap_types {
TUNNEL_ENCAP_NONE,
TUNNEL_ENCAP_FOU,
TUNNEL_ENCAP_GUE,
+ TUNNEL_ENCAP_MPLS,
};
#define TUNNEL_ENCAP_FLAG_CSUM (1<<0)
diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h
index f54853288f99..483b77af4eb8 100644
--- a/include/uapi/linux/ila.h
+++ b/include/uapi/linux/ila.h
@@ -17,6 +17,8 @@ enum {
ILA_ATTR_DIR, /* u32 */
ILA_ATTR_PAD,
ILA_ATTR_CSUM_MODE, /* u8 */
+ ILA_ATTR_IDENT_TYPE, /* u8 */
+ ILA_ATTR_HOOK_TYPE, /* u8 */
__ILA_ATTR_MAX,
};
@@ -41,6 +43,25 @@ enum {
ILA_CSUM_ADJUST_TRANSPORT,
ILA_CSUM_NEUTRAL_MAP,
ILA_CSUM_NO_ACTION,
+ ILA_CSUM_NEUTRAL_MAP_AUTO,
+};
+
+enum {
+ ILA_ATYPE_IID = 0,
+ ILA_ATYPE_LUID,
+ ILA_ATYPE_VIRT_V4,
+ ILA_ATYPE_VIRT_UNI_V6,
+ ILA_ATYPE_VIRT_MULTI_V6,
+ ILA_ATYPE_NONLOCAL_ADDR,
+ ILA_ATYPE_RSVD_1,
+ ILA_ATYPE_RSVD_2,
+
+ ILA_ATYPE_USE_FORMAT = 32, /* Get type from type field in identifier */
+};
+
+enum {
+ ILA_HOOK_ROUTE_OUTPUT,
+ ILA_HOOK_ROUTE_INPUT,
};
#endif /* _UAPI_LINUX_ILA_H */
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 2c002ffa9d6f..ed291e55f024 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -285,6 +285,7 @@ struct in6_flowlabel_req {
#define IPV6_TRANSPARENT 75
#define IPV6_UNICAST_IF 76
#define IPV6_RECVFRAGSIZE 77
+#define IPV6_FREEBIND 78
/*
* Multicast Routing:
diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h
index 51f29308ac6d..0245269b037c 100644
--- a/include/uapi/linux/ip6_tunnel.h
+++ b/include/uapi/linux/ip6_tunnel.h
@@ -21,6 +21,8 @@
#define IP6_TNL_F_RCV_DSCP_COPY 0x10
/* copy fwmark from inner packet */
#define IP6_TNL_F_USE_ORIG_FWMARK 0x20
+/* allow remote endpoint on the local node */
+#define IP6_TNL_F_ALLOW_LOCAL_REMOTE 0x40
struct ip6_tnl_parm {
char name[IFNAMSIZ]; /* name of tunnel device */
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index b22a9c4e1b12..9c0f4a92bcff 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -186,6 +186,7 @@ enum {
DEVCONF_ADDR_GEN_MODE,
DEVCONF_DISABLE_POLICY,
DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN,
+ DEVCONF_NDISC_TCLASS,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index a96eb17ad6fc..593800a18799 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -29,7 +29,7 @@
#define RTF_ROUTEINFO 0x00800000 /* route information - RA */
-#define RTF_CACHE 0x01000000 /* cache entry */
+#define RTF_CACHE 0x01000000 /* read-only: can not be set by user */
#define RTF_FLOW 0x02000000 /* flow significant route */
#define RTF_POLICY 0x04000000 /* policy route */
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 399f39ff8048..f6e3c8c9c744 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -89,6 +89,7 @@
* @NFC_CMD_ACTIVATE_TARGET: Request NFC controller to reactivate target.
* @NFC_CMD_VENDOR: Vendor specific command, to be implemented directly
* from the driver in order to support hardware specific operations.
+ * @NFC_CMD_DEACTIVATE_TARGET: Request NFC controller to deactivate target.
*/
enum nfc_commands {
NFC_CMD_UNSPEC,
@@ -121,6 +122,7 @@ enum nfc_commands {
NFC_CMD_SE_IO,
NFC_CMD_ACTIVATE_TARGET,
NFC_CMD_VENDOR,
+ NFC_CMD_DEACTIVATE_TARGET,
/* private: internal use only */
__NFC_CMD_AFTER_LAST
};
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 51626b4175c0..f882fe1f9709 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -569,13 +569,14 @@
* authentication/association or not receiving a response from the AP.
* Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as
* well to remain backwards compatible.
- * @NL80211_CMD_ROAM: notifcation indicating the card/driver roamed by itself.
- * When the driver roamed in a network that requires 802.1X authentication,
- * %NL80211_ATTR_PORT_AUTHORIZED should be set if the 802.1X authentication
- * was done by the driver or if roaming was done using Fast Transition
- * protocol (in which case 802.1X authentication is not needed). If
- * %NL80211_ATTR_PORT_AUTHORIZED is not set, user space is responsible for
- * the 802.1X authentication.
+ * When establishing a security association, drivers that support 4 way
+ * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when
+ * the 4 way handshake is completed successfully.
+ * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself.
+ * When a security association was established with the new AP (e.g. if
+ * the FT protocol was used for roaming or the driver completed the 4 way
+ * handshake), this event should be followed by an
+ * %NL80211_CMD_PORT_AUTHORIZED event.
* @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify
* userspace that a connection was dropped by the AP or due to other
* reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and
@@ -982,6 +983,14 @@
* @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
* configured PMK for the authenticator address identified by
* &NL80211_ATTR_MAC.
+ * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way
+ * handshake was completed successfully by the driver. The BSSID is
+ * specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake
+ * offload should send this event after indicating 802.11 association with
+ * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed
+ * &NL80211_CMD_DISCONNECT should be indicated instead.
+ *
+ * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded.
*
* @NL80211_CMD_MAX: highest used command number
* @__NL80211_CMD_AFTER_LAST: internal use
@@ -1185,6 +1194,10 @@ enum nl80211_commands {
NL80211_CMD_SET_PMK,
NL80211_CMD_DEL_PMK,
+ NL80211_CMD_PORT_AUTHORIZED,
+
+ NL80211_CMD_RELOAD_REGDB,
+
/* add new commands above here */
/* used to define NL80211_CMD_MAX below */
@@ -1407,8 +1420,12 @@ enum nl80211_commands {
*
* @NL80211_ATTR_USE_MFP: Whether management frame protection (IEEE 802.11w) is
* used for the association (&enum nl80211_mfp, represented as a u32);
- * this attribute can be used
- * with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests
+ * this attribute can be used with %NL80211_CMD_ASSOCIATE and
+ * %NL80211_CMD_CONNECT requests. %NL80211_MFP_OPTIONAL is not allowed for
+ * %NL80211_CMD_ASSOCIATE since user space SME is expected and hence, it
+ * must have decided whether to use management frame protection or not.
+ * Setting %NL80211_MFP_OPTIONAL with a %NL80211_CMD_CONNECT request will
+ * let the driver (or the firmware) decide whether to use MFP or not.
*
* @NL80211_ATTR_STA_FLAGS2: Attribute containing a
* &struct nl80211_sta_flag_update.
@@ -2134,10 +2151,7 @@ enum nl80211_commands {
* in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it
* wants to use the supported offload of the 4-way handshake.
* @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT.
- * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED
- * notification indicating that that 802.1X authentication was done by
- * the driver or is not needed (because roaming used the Fast Transition
- * protocol).
+ * @NL80211_ATTR_PORT_AUTHORIZED: (reserved)
*
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -3947,10 +3961,12 @@ enum nl80211_key_type {
* enum nl80211_mfp - Management frame protection state
* @NL80211_MFP_NO: Management frame protection not used
* @NL80211_MFP_REQUIRED: Management frame protection required
+ * @NL80211_MFP_OPTIONAL: Management frame protection is optional
*/
enum nl80211_mfp {
NL80211_MFP_NO,
NL80211_MFP_REQUIRED,
+ NL80211_MFP_OPTIONAL,
};
enum nl80211_wpa_versions {
@@ -4914,6 +4930,17 @@ enum nl80211_feature_flags {
* handshake with 802.1X in station mode (will pass EAP frames to the host
* and accept the set_pmk/del_pmk commands), doing it in the host might not
* be supported.
+ * @NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME: Driver is capable of overriding
+ * the max channel attribute in the FILS request params IE with the
+ * actual dwell time.
+ * @NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP: Driver accepts broadcast probe
+ * response
+ * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE: Driver supports sending
+ * the first probe request in each channel at rate of at least 5.5Mbps.
+ * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports
+ * probe request tx deferral and suppression
+ * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL
+ * value in %NL80211_ATTR_USE_MFP.
*
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -4936,6 +4963,11 @@ enum nl80211_ext_feature_index {
NL80211_EXT_FEATURE_FILS_SK_OFFLOAD,
NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK,
NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X,
+ NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME,
+ NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP,
+ NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE,
+ NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION,
+ NL80211_EXT_FEATURE_MFP_OPTIONAL,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
@@ -5012,12 +5044,28 @@ enum nl80211_timeout_reason {
* locally administered 1, multicast 0) is assumed.
* This flag must not be requested when the feature isn't supported, check
* the nl80211 feature flags for the device.
+ * @NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME: fill the dwell time in the FILS
+ * request parameters IE in the probe request
+ * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses
+ * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at
+ * rate of at least 5.5M. In case non OCE AP is dicovered in the channel,
+ * only the first probe req in the channel will be sent in high rate.
+ * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request
+ * tx deferral (dot11FILSProbeDelay shall be set to 15ms)
+ * and suppression (if it has received a broadcast Probe Response frame,
+ * Beacon frame or FILS Discovery frame from an AP that the STA considers
+ * a suitable candidate for (re-)association - suitable in terms of
+ * SSID and/or RSSI
*/
enum nl80211_scan_flags {
- NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0,
- NL80211_SCAN_FLAG_FLUSH = 1<<1,
- NL80211_SCAN_FLAG_AP = 1<<2,
- NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3,
+ NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0,
+ NL80211_SCAN_FLAG_FLUSH = 1<<1,
+ NL80211_SCAN_FLAG_AP = 1<<2,
+ NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3,
+ NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME = 1<<4,
+ NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5,
+ NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6,
+ NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7,
};
/**
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 36d0b161e066..4265d7f9e1f2 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -258,6 +258,8 @@ enum ovs_vport_attr {
/* receiving upcalls */
OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */
OVS_VPORT_ATTR_PAD,
+ OVS_VPORT_ATTR_IFINDEX,
+ OVS_VPORT_ATTR_NETNSID,
__OVS_VPORT_ATTR_MAX
};
@@ -334,6 +336,7 @@ enum ovs_key_attr {
OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */
OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */
OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */
+ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */
#ifdef __KERNEL__
OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */
@@ -360,6 +363,7 @@ enum ovs_tunnel_key_attr {
OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */
OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */
OVS_TUNNEL_KEY_ATTR_PAD,
+ OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */
__OVS_TUNNEL_KEY_ATTR_MAX
};
@@ -492,6 +496,30 @@ struct ovs_key_ct_tuple_ipv6 {
__u8 ipv6_proto;
};
+enum ovs_nsh_key_attr {
+ OVS_NSH_KEY_ATTR_UNSPEC,
+ OVS_NSH_KEY_ATTR_BASE, /* struct ovs_nsh_key_base. */
+ OVS_NSH_KEY_ATTR_MD1, /* struct ovs_nsh_key_md1. */
+ OVS_NSH_KEY_ATTR_MD2, /* variable-length octets for MD type 2. */
+ __OVS_NSH_KEY_ATTR_MAX
+};
+
+#define OVS_NSH_KEY_ATTR_MAX (__OVS_NSH_KEY_ATTR_MAX - 1)
+
+struct ovs_nsh_key_base {
+ __u8 flags;
+ __u8 ttl;
+ __u8 mdtype;
+ __u8 np;
+ __be32 path_hdr;
+};
+
+#define NSH_MD1_CONTEXT_SIZE 4
+
+struct ovs_nsh_key_md1 {
+ __be32 context[NSH_MD1_CONTEXT_SIZE];
+};
+
/**
* enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
* @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow
@@ -807,6 +835,11 @@ struct ovs_action_push_eth {
* packet.
* @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the
* packet.
+ * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet.
+ * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet.
+ * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet.
+ * @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the
+ * packet, or modify the packet (e.g., change the DSCP field).
*
* 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
@@ -836,6 +869,10 @@ enum ovs_action_attr {
OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */
OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */
OVS_ACTION_ATTR_POP_ETH, /* No argument. */
+ OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */
+ OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */
+ OVS_ACTION_ATTR_POP_NSH, /* No argument. */
+ OVS_ACTION_ATTR_METER, /* u32 meter ID. */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
@@ -849,4 +886,55 @@ enum ovs_action_attr {
#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1)
+/* Meters. */
+#define OVS_METER_FAMILY "ovs_meter"
+#define OVS_METER_MCGROUP "ovs_meter"
+#define OVS_METER_VERSION 0x1
+
+enum ovs_meter_cmd {
+ OVS_METER_CMD_UNSPEC,
+ OVS_METER_CMD_FEATURES, /* Get features supported by the datapath. */
+ OVS_METER_CMD_SET, /* Add or modify a meter. */
+ OVS_METER_CMD_DEL, /* Delete a meter. */
+ OVS_METER_CMD_GET /* Get meter stats. */
+};
+
+enum ovs_meter_attr {
+ OVS_METER_ATTR_UNSPEC,
+ OVS_METER_ATTR_ID, /* u32 meter ID within datapath. */
+ OVS_METER_ATTR_KBPS, /* No argument. If set, units in kilobits
+ * per second. Otherwise, units in
+ * packets per second.
+ */
+ OVS_METER_ATTR_STATS, /* struct ovs_flow_stats for the meter. */
+ OVS_METER_ATTR_BANDS, /* Nested attributes for meter bands. */
+ OVS_METER_ATTR_USED, /* u64 msecs last used in monotonic time. */
+ OVS_METER_ATTR_CLEAR, /* Flag to clear stats, used. */
+ OVS_METER_ATTR_MAX_METERS, /* u32 number of meters supported. */
+ OVS_METER_ATTR_MAX_BANDS, /* u32 max number of bands per meter. */
+ OVS_METER_ATTR_PAD,
+ __OVS_METER_ATTR_MAX
+};
+
+#define OVS_METER_ATTR_MAX (__OVS_METER_ATTR_MAX - 1)
+
+enum ovs_band_attr {
+ OVS_BAND_ATTR_UNSPEC,
+ OVS_BAND_ATTR_TYPE, /* u32 OVS_METER_BAND_TYPE_* constant. */
+ OVS_BAND_ATTR_RATE, /* u32 band rate in meter units (see above). */
+ OVS_BAND_ATTR_BURST, /* u32 burst size in meter units. */
+ OVS_BAND_ATTR_STATS, /* struct ovs_flow_stats for the band. */
+ __OVS_BAND_ATTR_MAX
+};
+
+#define OVS_BAND_ATTR_MAX (__OVS_BAND_ATTR_MAX - 1)
+
+enum ovs_meter_band_type {
+ OVS_METER_BAND_TYPE_UNSPEC,
+ OVS_METER_BAND_TYPE_DROP, /* Drop exceeding packets. */
+ __OVS_METER_BAND_TYPE_MAX
+};
+
+#define OVS_METER_BAND_TYPE_MAX (__OVS_METER_BAND_TYPE_MAX - 1)
+
#endif /* _LINUX_OPENVSWITCH_H */
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 703cd9df6cef..af3cc2f4e1ad 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -75,6 +75,7 @@ struct tc_estimator {
#define TC_H_INGRESS (0xFFFFFFF1U)
#define TC_H_CLSACT TC_H_INGRESS
+#define TC_H_MIN_PRIORITY 0xFFE0U
#define TC_H_MIN_INGRESS 0xFFF2U
#define TC_H_MIN_EGRESS 0xFFF3U
@@ -255,6 +256,7 @@ struct tc_red_qopt {
#define TC_RED_ECN 1
#define TC_RED_HARDDROP 2
#define TC_RED_ADAPTATIVE 4
+#define TC_RED_OFFLOADED 8
};
struct tc_red_xstats {
@@ -535,6 +537,9 @@ enum {
TCA_NETEM_ECN,
TCA_NETEM_RATE64,
TCA_NETEM_PAD,
+ TCA_NETEM_LATENCY64,
+ TCA_NETEM_JITTER64,
+ TCA_NETEM_SLOT,
__TCA_NETEM_MAX,
};
@@ -572,6 +577,13 @@ struct tc_netem_rate {
__s32 cell_overhead;
};
+struct tc_netem_slot {
+ __s64 min_delay; /* nsec */
+ __s64 max_delay;
+ __s32 max_packets;
+ __s32 max_bytes;
+};
+
enum {
NETEM_LOSS_UNSPEC,
NETEM_LOSS_GI, /* General Intuitive - 4 state model */
@@ -626,6 +638,22 @@ enum {
#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+enum {
+ TC_MQPRIO_MODE_DCB,
+ TC_MQPRIO_MODE_CHANNEL,
+ __TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+ TC_MQPRIO_SHAPER_DCB,
+ TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */
+ __TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
struct tc_mqprio_qopt {
__u8 num_tc;
__u8 prio_tc_map[TC_QOPT_BITMASK + 1];
@@ -634,6 +662,22 @@ struct tc_mqprio_qopt {
__u16 offset[TC_QOPT_MAX_QUEUE];
};
+#define TC_MQPRIO_F_MODE 0x1
+#define TC_MQPRIO_F_SHAPER 0x2
+#define TC_MQPRIO_F_MIN_RATE 0x4
+#define TC_MQPRIO_F_MAX_RATE 0x8
+
+enum {
+ TCA_MQPRIO_UNSPEC,
+ TCA_MQPRIO_MODE,
+ TCA_MQPRIO_SHAPER,
+ TCA_MQPRIO_MIN_RATE64,
+ TCA_MQPRIO_MAX_RATE64,
+ __TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
/* SFB */
enum {
@@ -872,4 +916,23 @@ struct tc_pie_xstats {
__u32 maxq; /* maximum queue size */
__u32 ecn_mark; /* packets marked with ecn*/
};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
#endif
diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h
index 5d9aab1f1893..f7e2fb3d752b 100644
--- a/include/uapi/linux/qrtr.h
+++ b/include/uapi/linux/qrtr.h
@@ -5,10 +5,45 @@
#include <linux/socket.h>
#include <linux/types.h>
+#define QRTR_NODE_BCAST 0xffffffffu
+#define QRTR_PORT_CTRL 0xfffffffeu
+
struct sockaddr_qrtr {
__kernel_sa_family_t sq_family;
__u32 sq_node;
__u32 sq_port;
};
+enum qrtr_pkt_type {
+ QRTR_TYPE_DATA = 1,
+ QRTR_TYPE_HELLO = 2,
+ QRTR_TYPE_BYE = 3,
+ QRTR_TYPE_NEW_SERVER = 4,
+ QRTR_TYPE_DEL_SERVER = 5,
+ QRTR_TYPE_DEL_CLIENT = 6,
+ QRTR_TYPE_RESUME_TX = 7,
+ QRTR_TYPE_EXIT = 8,
+ QRTR_TYPE_PING = 9,
+ QRTR_TYPE_NEW_LOOKUP = 10,
+ QRTR_TYPE_DEL_LOOKUP = 11,
+};
+
+struct qrtr_ctrl_pkt {
+ __le32 cmd;
+
+ union {
+ struct {
+ __le32 service;
+ __le32 instance;
+ __le32 node;
+ __le32 port;
+ } server;
+
+ struct {
+ __le32 node;
+ __le32 port;
+ } client;
+ };
+} __packed;
+
#endif /* _LINUX_QRTR_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index a6d37c2ea355..d8b5f80c2ea6 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -431,6 +431,8 @@ enum {
#define RTAX_QUICKACK RTAX_QUICKACK
RTAX_CC_ALGO,
#define RTAX_CC_ALGO RTAX_CC_ALGO
+ RTAX_FASTOPEN_NO_COOKIE,
+#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE
__RTAX_MAX
};
diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h
index 9656aad8f8f7..9d4afea308a4 100644
--- a/include/uapi/linux/rxrpc.h
+++ b/include/uapi/linux/rxrpc.h
@@ -20,12 +20,12 @@
* RxRPC socket address
*/
struct sockaddr_rxrpc {
- sa_family_t srx_family; /* address family */
- u16 srx_service; /* service desired */
- u16 transport_type; /* type of transport socket (SOCK_DGRAM) */
- u16 transport_len; /* length of transport address */
+ __kernel_sa_family_t srx_family; /* address family */
+ __u16 srx_service; /* service desired */
+ __u16 transport_type; /* type of transport socket (SOCK_DGRAM) */
+ __u16 transport_len; /* length of transport address */
union {
- sa_family_t family; /* transport address family */
+ __kernel_sa_family_t family; /* transport address family */
struct sockaddr_in sin; /* IPv4 transport address */
struct sockaddr_in6 sin6; /* IPv6 transport address */
} transport;
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index cfe971296835..d9adab32dbee 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -123,6 +123,8 @@ typedef __s32 sctp_assoc_t;
#define SCTP_RESET_ASSOC 120
#define SCTP_ADD_STREAMS 121
#define SCTP_SOCKOPT_PEELOFF_FLAGS 122
+#define SCTP_STREAM_SCHEDULER 123
+#define SCTP_STREAM_SCHEDULER_VALUE 124
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
@@ -815,6 +817,12 @@ struct sctp_assoc_value {
uint32_t assoc_value;
};
+struct sctp_stream_value {
+ sctp_assoc_t assoc_id;
+ uint16_t stream_id;
+ uint16_t stream_value;
+};
+
/*
* 7.2.2 Peer Address Information
*
@@ -1089,4 +1097,12 @@ struct sctp_add_streams {
uint16_t sas_outstrms;
};
+/* SCTP Stream schedulers */
+enum sctp_sched_type {
+ SCTP_SS_FCFS,
+ SCTP_SS_PRIO,
+ SCTP_SS_RR,
+ SCTP_SS_MAX = SCTP_SS_RR
+};
+
#endif /* _UAPI_SCTP_H */
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 0d941cdd8e8c..33a70ece462f 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -191,7 +191,6 @@ enum
LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */
LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */
LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */
- LINUX_MIB_TCPFACKREORDER, /* TCPFACKReorder */
LINUX_MIB_TCPSACKREORDER, /* TCPSACKReorder */
LINUX_MIB_TCPRENOREORDER, /* TCPRenoReorder */
LINUX_MIB_TCPTSREORDER, /* TCPTSReorder */
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
index 020696e07345..5dd671cf5776 100644
--- a/include/uapi/linux/tc_act/tc_mirred.h
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -10,13 +10,13 @@
#define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
#define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/
#define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */
-
+
struct tc_mirred {
tc_gen;
int eaction; /* one of IN/EGRESS_MIRROR/REDIR */
__u32 ifindex; /* ifindex of egress port */
};
-
+
enum {
TCA_MIRRED_UNSPEC,
TCA_MIRRED_TM,
@@ -25,5 +25,5 @@ enum {
__TCA_MIRRED_MAX
};
#define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
-
+
#endif
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 6a64beeecfad..b4a4f64635fa 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -120,6 +120,8 @@ enum {
#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
struct tcp_repair_opt {
__u32 opt_code;
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 77123614e973..35f79d1f8c3a 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -232,6 +232,21 @@ struct sockaddr_tipc {
#define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */
#define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */
#define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */
+#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */
+#define TIPC_GROUP_LEAVE 136 /* No argument */
+
+/*
+ * Flag values
+ */
+#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */
+#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */
+
+struct tipc_group_req {
+ __u32 type; /* group id */
+ __u32 instance; /* member id */
+ __u32 scope; /* zone/cluster/node */
+ __u32 flags;
+};
/*
* Maximum sizes of TIPC bearer-related names (including terminating NULL)
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index d5e0682ab837..293b2cdad88d 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -35,10 +35,6 @@
#define _UAPI_LINUX_TLS_H
#include <linux/types.h>
-#include <asm/byteorder.h>
-#include <linux/socket.h>
-#include <linux/tcp.h>
-#include <net/tcp.h>
/* TLS socket options */
#define TLS_TX 1 /* Set transmit parameters */
diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h
new file mode 100644
index 000000000000..14cd7dc5a187
--- /dev/null
+++ b/include/uapi/linux/vm_sockets_diag.h
@@ -0,0 +1,33 @@
+/* AF_VSOCK sock_diag(7) interface for querying open sockets */
+
+#ifndef _UAPI__VM_SOCKETS_DIAG_H__
+#define _UAPI__VM_SOCKETS_DIAG_H__
+
+#include <linux/types.h>
+
+/* Request */
+struct vsock_diag_req {
+ __u8 sdiag_family; /* must be AF_VSOCK */
+ __u8 sdiag_protocol; /* must be 0 */
+ __u16 pad; /* must be 0 */
+ __u32 vdiag_states; /* query bitmap (e.g. 1 << TCP_LISTEN) */
+ __u32 vdiag_ino; /* must be 0 (reserved) */
+ __u32 vdiag_show; /* must be 0 (reserved) */
+ __u32 vdiag_cookie[2];
+};
+
+/* Response */
+struct vsock_diag_msg {
+ __u8 vdiag_family; /* AF_VSOCK */
+ __u8 vdiag_type; /* SOCK_STREAM or SOCK_DGRAM */
+ __u8 vdiag_state; /* sk_state (e.g. TCP_LISTEN) */
+ __u8 vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */
+ __u32 vdiag_src_cid;
+ __u32 vdiag_src_port;
+ __u32 vdiag_dst_cid;
+ __u32 vdiag_dst_port;
+ __u32 vdiag_ino;
+ __u32 vdiag_cookie[2];
+};
+
+#endif /* _UAPI__VM_SOCKETS_DIAG_H__ */