summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/atm_suni.h12
-rw-r--r--include/linux/avf/virtchnl.h278
-rw-r--r--include/linux/bpf.h94
-rw-r--r--include/linux/bpf_local_storage.h3
-rw-r--r--include/linux/bpf_lsm.h22
-rw-r--r--include/linux/bpf_types.h8
-rw-r--r--include/linux/bpf_verifier.h3
-rw-r--r--include/linux/dsa/ocelot.h5
-rw-r--r--include/linux/etherdevice.h4
-rw-r--r--include/linux/ethtool.h9
-rw-r--r--include/linux/filter.h31
-rw-r--r--include/linux/if_bridge.h40
-rw-r--r--include/linux/if_rmnet.h65
-rw-r--r--include/linux/marvell_phy.h1
-rw-r--r--include/linux/mlx5/device.h2
-rw-r--r--include/linux/mlx5/driver.h12
-rw-r--r--include/linux/netdevice.h129
-rw-r--r--include/linux/pcs/pcs-xpcs.h5
-rw-r--r--include/linux/phy.h1
-rw-r--r--include/linux/phylink.h2
-rw-r--r--include/linux/platform_data/hirschmann-hellcreek.h1
-rw-r--r--include/linux/ppp_channel.h3
-rw-r--r--include/linux/ptp_pch.h22
-rw-r--r--include/linux/qed/qed_chain.h8
-rw-r--r--include/linux/sched.h5
-rw-r--r--include/linux/skbuff.h32
-rw-r--r--include/linux/skmsg.h82
-rw-r--r--include/linux/stmmac.h34
-rw-r--r--include/net/dsa.h16
-rw-r--r--include/net/flow_dissector.h6
-rw-r--r--include/net/flow_offload.h6
-rw-r--r--include/net/gro.h13
-rw-r--r--include/net/ipv6.h1
-rw-r--r--include/net/lapb.h2
-rw-r--r--include/net/mptcp.h9
-rw-r--r--include/net/netfilter/ipv6/nf_conntrack_ipv6.h3
-rw-r--r--include/net/netfilter/nf_flow_table.h61
-rw-r--r--include/net/netfilter/nf_tables.h9
-rw-r--r--include/net/netns/ipv4.h1
-rw-r--r--include/net/nexthop.h72
-rw-r--r--include/net/pkt_sched.h9
-rw-r--r--include/net/psample.h21
-rw-r--r--include/net/sch_generic.h14
-rw-r--r--include/net/switchdev.h1
-rw-r--r--include/net/tc_act/tc_police.h52
-rw-r--r--include/net/tcp.h41
-rw-r--r--include/net/udp.h4
-rw-r--r--include/net/xdp_sock.h19
-rw-r--r--include/soc/mscc/ocelot.h25
-rw-r--r--include/trace/events/xdp.h62
-rw-r--r--include/uapi/linux/bpf.h762
-rw-r--r--include/uapi/linux/btf.h5
-rw-r--r--include/uapi/linux/if_fddi.h2
-rw-r--r--include/uapi/linux/nexthop.h47
-rw-r--r--include/uapi/linux/pkt_cls.h2
-rw-r--r--include/uapi/linux/psample.h7
-rw-r--r--include/uapi/linux/rtnetlink.h8
57 files changed, 1889 insertions, 304 deletions
diff --git a/include/linux/atm_suni.h b/include/linux/atm_suni.h
deleted file mode 100644
index 84f3aab54468..000000000000
--- a/include/linux/atm_suni.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* atm_suni.h - Driver-specific declarations of the SUNI driver (for use by
- driver-specific utilities) */
-
-/* Written 1998,2000 by Werner Almesberger, EPFL ICA */
-
-
-#ifndef LINUX_ATM_SUNI_H
-#define LINUX_ATM_SUNI_H
-
-/* everything obsoleted */
-
-#endif
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 40bad71865ea..47482049f640 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -136,6 +136,9 @@ enum virtchnl_ops {
VIRTCHNL_OP_DISABLE_CHANNELS = 31,
VIRTCHNL_OP_ADD_CLOUD_FILTER = 32,
VIRTCHNL_OP_DEL_CLOUD_FILTER = 33,
+ /* opcode 34 - 46 are reserved */
+ VIRTCHNL_OP_ADD_FDIR_FILTER = 47,
+ VIRTCHNL_OP_DEL_FDIR_FILTER = 48,
};
/* These macros are used to generate compilation errors if a structure/union
@@ -247,6 +250,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000
#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000
#define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000
+#define VIRTCHNL_VF_OFFLOAD_FDIR_PF 0X10000000
/* Define below the capability flags that are not offloads */
#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080
@@ -559,6 +563,11 @@ enum virtchnl_action {
/* action types */
VIRTCHNL_ACTION_DROP = 0,
VIRTCHNL_ACTION_TC_REDIRECT,
+ VIRTCHNL_ACTION_PASSTHRU,
+ VIRTCHNL_ACTION_QUEUE,
+ VIRTCHNL_ACTION_Q_REGION,
+ VIRTCHNL_ACTION_MARK,
+ VIRTCHNL_ACTION_COUNT,
};
enum virtchnl_flow_type {
@@ -668,6 +677,269 @@ enum virtchnl_vfr_states {
VIRTCHNL_VFR_VFACTIVE,
};
+#define VIRTCHNL_MAX_NUM_PROTO_HDRS 32
+#define PROTO_HDR_SHIFT 5
+#define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
+#define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1)
+
+/* VF use these macros to configure each protocol header.
+ * Specify which protocol headers and protocol header fields base on
+ * virtchnl_proto_hdr_type and virtchnl_proto_hdr_field.
+ * @param hdr: a struct of virtchnl_proto_hdr
+ * @param hdr_type: ETH/IPV4/TCP, etc
+ * @param field: SRC/DST/TEID/SPI, etc
+ */
+#define VIRTCHNL_ADD_PROTO_HDR_FIELD(hdr, field) \
+ ((hdr)->field_selector |= BIT((field) & PROTO_HDR_FIELD_MASK))
+#define VIRTCHNL_DEL_PROTO_HDR_FIELD(hdr, field) \
+ ((hdr)->field_selector &= ~BIT((field) & PROTO_HDR_FIELD_MASK))
+#define VIRTCHNL_TEST_PROTO_HDR_FIELD(hdr, val) \
+ ((hdr)->field_selector & BIT((val) & PROTO_HDR_FIELD_MASK))
+#define VIRTCHNL_GET_PROTO_HDR_FIELD(hdr) ((hdr)->field_selector)
+
+#define VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, hdr_type, field) \
+ (VIRTCHNL_ADD_PROTO_HDR_FIELD(hdr, \
+ VIRTCHNL_PROTO_HDR_ ## hdr_type ## _ ## field))
+#define VIRTCHNL_DEL_PROTO_HDR_FIELD_BIT(hdr, hdr_type, field) \
+ (VIRTCHNL_DEL_PROTO_HDR_FIELD(hdr, \
+ VIRTCHNL_PROTO_HDR_ ## hdr_type ## _ ## field))
+
+#define VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, hdr_type) \
+ ((hdr)->type = VIRTCHNL_PROTO_HDR_ ## hdr_type)
+#define VIRTCHNL_GET_PROTO_HDR_TYPE(hdr) \
+ (((hdr)->type) >> PROTO_HDR_SHIFT)
+#define VIRTCHNL_TEST_PROTO_HDR_TYPE(hdr, val) \
+ ((hdr)->type == ((val) >> PROTO_HDR_SHIFT))
+#define VIRTCHNL_TEST_PROTO_HDR(hdr, val) \
+ (VIRTCHNL_TEST_PROTO_HDR_TYPE((hdr), (val)) && \
+ VIRTCHNL_TEST_PROTO_HDR_FIELD((hdr), (val)))
+
+/* Protocol header type within a packet segment. A segment consists of one or
+ * more protocol headers that make up a logical group of protocol headers. Each
+ * logical group of protocol headers encapsulates or is encapsulated using/by
+ * tunneling or encapsulation protocols for network virtualization.
+ */
+enum virtchnl_proto_hdr_type {
+ VIRTCHNL_PROTO_HDR_NONE,
+ VIRTCHNL_PROTO_HDR_ETH,
+ VIRTCHNL_PROTO_HDR_S_VLAN,
+ VIRTCHNL_PROTO_HDR_C_VLAN,
+ VIRTCHNL_PROTO_HDR_IPV4,
+ VIRTCHNL_PROTO_HDR_IPV6,
+ VIRTCHNL_PROTO_HDR_TCP,
+ VIRTCHNL_PROTO_HDR_UDP,
+ VIRTCHNL_PROTO_HDR_SCTP,
+ VIRTCHNL_PROTO_HDR_GTPU_IP,
+ VIRTCHNL_PROTO_HDR_GTPU_EH,
+ VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN,
+ VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP,
+ VIRTCHNL_PROTO_HDR_PPPOE,
+ VIRTCHNL_PROTO_HDR_L2TPV3,
+ VIRTCHNL_PROTO_HDR_ESP,
+ VIRTCHNL_PROTO_HDR_AH,
+ VIRTCHNL_PROTO_HDR_PFCP,
+};
+
+/* Protocol header field within a protocol header. */
+enum virtchnl_proto_hdr_field {
+ /* ETHER */
+ VIRTCHNL_PROTO_HDR_ETH_SRC =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_ETH),
+ VIRTCHNL_PROTO_HDR_ETH_DST,
+ VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE,
+ /* S-VLAN */
+ VIRTCHNL_PROTO_HDR_S_VLAN_ID =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_S_VLAN),
+ /* C-VLAN */
+ VIRTCHNL_PROTO_HDR_C_VLAN_ID =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_C_VLAN),
+ /* IPV4 */
+ VIRTCHNL_PROTO_HDR_IPV4_SRC =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV4),
+ VIRTCHNL_PROTO_HDR_IPV4_DST,
+ VIRTCHNL_PROTO_HDR_IPV4_DSCP,
+ VIRTCHNL_PROTO_HDR_IPV4_TTL,
+ VIRTCHNL_PROTO_HDR_IPV4_PROT,
+ /* IPV6 */
+ VIRTCHNL_PROTO_HDR_IPV6_SRC =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV6),
+ VIRTCHNL_PROTO_HDR_IPV6_DST,
+ VIRTCHNL_PROTO_HDR_IPV6_TC,
+ VIRTCHNL_PROTO_HDR_IPV6_HOP_LIMIT,
+ VIRTCHNL_PROTO_HDR_IPV6_PROT,
+ /* TCP */
+ VIRTCHNL_PROTO_HDR_TCP_SRC_PORT =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_TCP),
+ VIRTCHNL_PROTO_HDR_TCP_DST_PORT,
+ /* UDP */
+ VIRTCHNL_PROTO_HDR_UDP_SRC_PORT =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_UDP),
+ VIRTCHNL_PROTO_HDR_UDP_DST_PORT,
+ /* SCTP */
+ VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_SCTP),
+ VIRTCHNL_PROTO_HDR_SCTP_DST_PORT,
+ /* GTPU_IP */
+ VIRTCHNL_PROTO_HDR_GTPU_IP_TEID =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_IP),
+ /* GTPU_EH */
+ VIRTCHNL_PROTO_HDR_GTPU_EH_PDU =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_EH),
+ VIRTCHNL_PROTO_HDR_GTPU_EH_QFI,
+ /* PPPOE */
+ VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_PPPOE),
+ /* L2TPV3 */
+ VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_L2TPV3),
+ /* ESP */
+ VIRTCHNL_PROTO_HDR_ESP_SPI =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_ESP),
+ /* AH */
+ VIRTCHNL_PROTO_HDR_AH_SPI =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_AH),
+ /* PFCP */
+ VIRTCHNL_PROTO_HDR_PFCP_S_FIELD =
+ PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_PFCP),
+ VIRTCHNL_PROTO_HDR_PFCP_SEID,
+};
+
+struct virtchnl_proto_hdr {
+ enum virtchnl_proto_hdr_type type;
+ u32 field_selector; /* a bit mask to select field for header type */
+ u8 buffer[64];
+ /**
+ * binary buffer in network order for specific header type.
+ * For example, if type = VIRTCHNL_PROTO_HDR_IPV4, a IPv4
+ * header is expected to be copied into the buffer.
+ */
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_proto_hdr);
+
+struct virtchnl_proto_hdrs {
+ u8 tunnel_level;
+ /**
+ * specify where protocol header start from.
+ * 0 - from the outer layer
+ * 1 - from the first inner layer
+ * 2 - from the second inner layer
+ * ....
+ **/
+ int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
+ struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs);
+
+/* action configuration for FDIR */
+struct virtchnl_filter_action {
+ enum virtchnl_action type;
+ union {
+ /* used for queue and qgroup action */
+ struct {
+ u16 index;
+ u8 region;
+ } queue;
+ /* used for count action */
+ struct {
+ /* share counter ID with other flow rules */
+ u8 shared;
+ u32 id; /* counter ID */
+ } count;
+ /* used for mark action */
+ u32 mark_id;
+ u8 reserve[32];
+ } act_conf;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_filter_action);
+
+#define VIRTCHNL_MAX_NUM_ACTIONS 8
+
+struct virtchnl_filter_action_set {
+ /* action number must be less then VIRTCHNL_MAX_NUM_ACTIONS */
+ int count;
+ struct virtchnl_filter_action actions[VIRTCHNL_MAX_NUM_ACTIONS];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(292, virtchnl_filter_action_set);
+
+/* pattern and action for FDIR rule */
+struct virtchnl_fdir_rule {
+ struct virtchnl_proto_hdrs proto_hdrs;
+ struct virtchnl_filter_action_set action_set;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(2604, virtchnl_fdir_rule);
+
+/* Status returned to VF after VF requests FDIR commands
+ * VIRTCHNL_FDIR_SUCCESS
+ * VF FDIR related request is successfully done by PF
+ * The request can be OP_ADD/DEL.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE
+ * OP_ADD_FDIR_FILTER request is failed due to no Hardware resource.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_EXIST
+ * OP_ADD_FDIR_FILTER request is failed due to the rule is already existed.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_CONFLICT
+ * OP_ADD_FDIR_FILTER request is failed due to conflict with existing rule.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST
+ * OP_DEL_FDIR_FILTER request is failed due to this rule doesn't exist.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_INVALID
+ * OP_ADD_FDIR_FILTER request is failed due to parameters validation
+ * or HW doesn't support.
+ *
+ * VIRTCHNL_FDIR_FAILURE_RULE_TIMEOUT
+ * OP_ADD/DEL_FDIR_FILTER request is failed due to timing out
+ * for programming.
+ */
+enum virtchnl_fdir_prgm_status {
+ VIRTCHNL_FDIR_SUCCESS = 0,
+ VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE,
+ VIRTCHNL_FDIR_FAILURE_RULE_EXIST,
+ VIRTCHNL_FDIR_FAILURE_RULE_CONFLICT,
+ VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST,
+ VIRTCHNL_FDIR_FAILURE_RULE_INVALID,
+ VIRTCHNL_FDIR_FAILURE_RULE_TIMEOUT,
+};
+
+/* VIRTCHNL_OP_ADD_FDIR_FILTER
+ * VF sends this request to PF by filling out vsi_id,
+ * validate_only and rule_cfg. PF will return flow_id
+ * if the request is successfully done and return add_status to VF.
+ */
+struct virtchnl_fdir_add {
+ u16 vsi_id; /* INPUT */
+ /*
+ * 1 for validating a fdir rule, 0 for creating a fdir rule.
+ * Validate and create share one ops: VIRTCHNL_OP_ADD_FDIR_FILTER.
+ */
+ u16 validate_only; /* INPUT */
+ u32 flow_id; /* OUTPUT */
+ struct virtchnl_fdir_rule rule_cfg; /* INPUT */
+ enum virtchnl_fdir_prgm_status status; /* OUTPUT */
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(2616, virtchnl_fdir_add);
+
+/* VIRTCHNL_OP_DEL_FDIR_FILTER
+ * VF sends this request to PF by filling out vsi_id
+ * and flow_id. PF will return del_status to VF.
+ */
+struct virtchnl_fdir_del {
+ u16 vsi_id; /* INPUT */
+ u16 pad;
+ u32 flow_id; /* INPUT */
+ enum virtchnl_fdir_prgm_status status; /* OUTPUT */
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
+
/**
* virtchnl_vc_validate_vf_msg
* @ver: Virtchnl version info
@@ -828,6 +1100,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
case VIRTCHNL_OP_DEL_CLOUD_FILTER:
valid_len = sizeof(struct virtchnl_filter);
break;
+ case VIRTCHNL_OP_ADD_FDIR_FILTER:
+ valid_len = sizeof(struct virtchnl_fdir_add);
+ break;
+ case VIRTCHNL_OP_DEL_FDIR_FILTER:
+ valid_len = sizeof(struct virtchnl_fdir_del);
+ break;
/* These are always errors coming from the VF. */
case VIRTCHNL_OP_EVENT:
case VIRTCHNL_OP_UNKNOWN:
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3625f019767d..39dce9d3c3a5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_local_storage;
struct bpf_local_storage_map;
struct kobject;
struct mem_cgroup;
+struct bpf_func_state;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@@ -118,6 +119,9 @@ struct bpf_map_ops {
void *owner, u32 size);
struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
+ /* Misc helpers.*/
+ int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
+
/* map_meta_equal must be implemented for maps that can be
* used as an inner map. It is a runtime check to ensure
* an inner map can be inserted to an outer map.
@@ -130,6 +134,13 @@ struct bpf_map_ops {
bool (*map_meta_equal)(const struct bpf_map *meta0,
const struct bpf_map *meta1);
+
+ int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env,
+ struct bpf_func_state *caller,
+ struct bpf_func_state *callee);
+ int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn,
+ void *callback_ctx, u64 flags);
+
/* BTF name and id of struct allocated by map_alloc */
const char * const map_btf_name;
int *map_btf_id;
@@ -296,6 +307,8 @@ enum bpf_arg_type {
ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */
ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */
+ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */
+ ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */
__BPF_ARG_TYPE_MAX,
};
@@ -412,6 +425,8 @@ enum bpf_reg_type {
PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */
PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */
+ PTR_TO_FUNC, /* reg points to a bpf program function */
+ PTR_TO_MAP_KEY, /* reg points to a map element key */
};
/* The information passed from prog-specific *_is_valid_access
@@ -507,6 +522,11 @@ enum bpf_cgroup_storage_type {
*/
#define MAX_BPF_FUNC_ARGS 12
+/* The maximum number of arguments passed through registers
+ * a single function may have.
+ */
+#define MAX_BPF_FUNC_REG_ARGS 5
+
struct btf_func_model {
u8 ret_size;
u8 nr_args;
@@ -1397,6 +1417,10 @@ void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
+int map_set_for_each_callback_args(struct bpf_verifier_env *env,
+ struct bpf_func_state *caller,
+ struct bpf_func_state *callee);
+
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);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
@@ -1446,9 +1470,9 @@ struct btf *bpf_get_btf_vmlinux(void);
/* Map specifics */
struct xdp_buff;
struct sk_buff;
+struct bpf_dtab_netdev;
+struct bpf_cpu_map_entry;
-struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
-struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
void __dev_flush(void);
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx);
@@ -1458,7 +1482,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
bool dev_map_can_have_prog(struct bpf_map *map);
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_flush(void);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx);
@@ -1487,6 +1510,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
+int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
@@ -1516,6 +1542,7 @@ struct bpf_prog *bpf_prog_by_id(u32 id);
struct bpf_link *bpf_link_by_id(u32 id);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
+void bpf_task_storage_free(struct task_struct *task);
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
@@ -1585,17 +1612,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
return -EOPNOTSUPP;
}
-static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map,
- u32 key)
-{
- return NULL;
-}
-
-static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map,
- u32 key)
-{
- return NULL;
-}
static inline bool dev_map_can_have_prog(struct bpf_map *map)
{
return false;
@@ -1607,6 +1623,7 @@ static inline void __dev_flush(void)
struct xdp_buff;
struct bpf_dtab_netdev;
+struct bpf_cpu_map_entry;
static inline
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
@@ -1631,12 +1648,6 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
return 0;
}
-static inline
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
-{
- return NULL;
-}
-
static inline void __cpu_map_flush(void)
{
}
@@ -1687,6 +1698,13 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
return -ENOTSUPP;
}
+static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ return -ENOTSUPP;
+}
+
static inline void bpf_map_put(struct bpf_map *map)
{
}
@@ -1701,6 +1719,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
{
return NULL;
}
+
+static inline void bpf_task_storage_free(struct task_struct *task)
+{
+}
#endif /* CONFIG_BPF_SYSCALL */
void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
@@ -1785,22 +1807,24 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
}
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
-#if defined(CONFIG_BPF_STREAM_PARSER)
-int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
- struct bpf_prog *old, u32 which);
+#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
void sock_map_unhash(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
+
+void bpf_sk_reuseport_detach(struct sock *sk);
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+ void *value);
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags);
#else
-static inline int sock_map_prog_update(struct bpf_map *map,
- struct bpf_prog *prog,
- struct bpf_prog *old, u32 which)
+static inline void bpf_sk_reuseport_detach(struct sock *sk)
{
- return -EOPNOTSUPP;
}
+#ifdef CONFIG_BPF_SYSCALL
static inline int sock_map_get_from_fd(const union bpf_attr *attr,
struct bpf_prog *prog)
{
@@ -1818,20 +1842,7 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void
{
return -EOPNOTSUPP;
}
-#endif /* CONFIG_BPF_STREAM_PARSER */
-#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
-void bpf_sk_reuseport_detach(struct sock *sk);
-int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
- void *value);
-int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
- void *value, u64 map_flags);
-#else
-static inline void bpf_sk_reuseport_detach(struct sock *sk)
-{
-}
-
-#ifdef CONFIG_BPF_SYSCALL
static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
void *key, void *value)
{
@@ -1903,6 +1914,9 @@ extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
extern const struct bpf_func_proto bpf_sock_from_file_proto;
extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto;
+extern const struct bpf_func_proto bpf_task_storage_get_proto;
+extern const struct bpf_func_proto bpf_task_storage_delete_proto;
+extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
const struct bpf_func_proto *bpf_tracing_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index b2c9463f36a1..b902c580c48d 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -126,7 +126,8 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
struct bpf_local_storage_map *smap,
bool cacheit_lockit);
-void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap,
+ int __percpu *busy_counter);
int bpf_local_storage_map_check_btf(const struct bpf_map *map,
const struct btf *btf,
diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index 0d1c33ace398..479c101546ad 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -38,21 +38,9 @@ static inline struct bpf_storage_blob *bpf_inode(
return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
}
-static inline struct bpf_storage_blob *bpf_task(
- const struct task_struct *task)
-{
- if (unlikely(!task->security))
- return NULL;
-
- return task->security + bpf_lsm_blob_sizes.lbs_task;
-}
-
extern const struct bpf_func_proto bpf_inode_storage_get_proto;
extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
-extern const struct bpf_func_proto bpf_task_storage_get_proto;
-extern const struct bpf_func_proto bpf_task_storage_delete_proto;
void bpf_inode_storage_free(struct inode *inode);
-void bpf_task_storage_free(struct task_struct *task);
#else /* !CONFIG_BPF_LSM */
@@ -73,20 +61,10 @@ static inline struct bpf_storage_blob *bpf_inode(
return NULL;
}
-static inline struct bpf_storage_blob *bpf_task(
- const struct task_struct *task)
-{
- return NULL;
-}
-
static inline void bpf_inode_storage_free(struct inode *inode)
{
}
-static inline void bpf_task_storage_free(struct task_struct *task)
-{
-}
-
#endif /* CONFIG_BPF_LSM */
#endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 99f7fd657d87..f883f01a5061 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -103,19 +103,17 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
-#if defined(CONFIG_BPF_STREAM_PARSER)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
-#endif
#ifdef CONFIG_BPF_LSM
BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
#endif
#ifdef CONFIG_INET
+BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
#endif
#endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 971b33aca13d..51c2ffa3d901 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -68,6 +68,8 @@ struct bpf_reg_state {
unsigned long raw1;
unsigned long raw2;
} raw;
+
+ u32 subprogno; /* for PTR_TO_FUNC */
};
/* For PTR_TO_PACKET, used to find other pointers with the same variable
* offset, so they can share range knowledge.
@@ -204,6 +206,7 @@ struct bpf_func_state {
int acquired_refs;
struct bpf_reference_state *refs;
int allocated_stack;
+ bool in_callback_fn;
struct bpf_stack_state *stack;
};
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index 4265f328681a..c6bc45ae5e03 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -160,11 +160,6 @@ static inline void ocelot_xfh_get_src_port(void *extraction, u64 *src_port)
packing(extraction, src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0);
}
-static inline void ocelot_xfh_get_cpuq(void *extraction, u64 *cpuq)
-{
- packing(extraction, cpuq, 28, 20, OCELOT_TAG_LEN, UNPACK, 0);
-}
-
static inline void ocelot_xfh_get_qos_class(void *extraction, u64 *qos_class)
{
packing(extraction, qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0);
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2e5debc0373c..330345b1be54 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -11,7 +11,7 @@
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
- * Relocated to include/linux where it belongs by Alan Cox
+ * Relocated to include/linux where it belongs by Alan Cox
* <gw4pts@gw4pts.ampr.org>
*/
#ifndef _LINUX_ETHERDEVICE_H
@@ -29,7 +29,7 @@ struct device;
int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
unsigned char *arch_get_platform_mac_address(void);
int nvmem_get_mac_address(struct device *dev, void *addrbuf);
-u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len);
+u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len);
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
extern const struct header_ops eth_header_ops;
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ec4cd3921c67..3583f7fc075c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -571,4 +571,13 @@ struct ethtool_phy_ops {
*/
void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops);
+/**
+ * ethtool_sprintf - Write formatted string to ethtool string data
+ * @data: Pointer to start of string to update
+ * @fmt: Format of string to write
+ *
+ * Write formatted string to data. Update data to point at start of
+ * next string.
+ */
+extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
#endif /* _LINUX_ETHTOOL_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3b00fc906ccd..b2b85b2cad8e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -646,7 +646,8 @@ struct bpf_redirect_info {
u32 flags;
u32 tgt_index;
void *tgt_value;
- struct bpf_map *map;
+ u32 map_id;
+ enum bpf_map_type map_type;
u32 kern_flags;
struct bpf_nh_params nh;
};
@@ -1472,4 +1473,32 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
}
#endif /* IS_ENABLED(CONFIG_IPV6) */
+static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
+ void *lookup_elem(struct bpf_map *map, u32 key))
+{
+ struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+ /* Lower bits of the flags are used as return code on lookup failure */
+ if (unlikely(flags > XDP_TX))
+ return XDP_ABORTED;
+
+ ri->tgt_value = lookup_elem(map, ifindex);
+ if (unlikely(!ri->tgt_value)) {
+ /* If the lookup fails we want to clear out the state in the
+ * redirect_info struct completely, so that if an eBPF program
+ * performs multiple lookups, the last one always takes
+ * precedence.
+ */
+ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
+ ri->map_type = BPF_MAP_TYPE_UNSPEC;
+ return flags;
+ }
+
+ ri->tgt_index = ifindex;
+ ri->map_id = map->id;
+ ri->map_type = map->map_type;
+
+ return XDP_REDIRECT;
+}
+
#endif /* __LINUX_FILTER_H__ */
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index b979005ea39c..2cc35038a8ca 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -69,6 +69,8 @@ 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);
+int br_mdb_replay(struct net_device *br_dev, struct net_device *dev,
+ struct notifier_block *nb, struct netlink_ext_ack *extack);
#else
static inline int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list)
@@ -93,6 +95,13 @@ static inline bool br_multicast_router(const struct net_device *dev)
{
return false;
}
+static inline int br_mdb_replay(struct net_device *br_dev,
+ struct net_device *dev,
+ struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
#endif
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
@@ -102,6 +111,8 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid);
int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto);
int br_vlan_get_info(const struct net_device *dev, u16 vid,
struct bridge_vlan_info *p_vinfo);
+int br_vlan_replay(struct net_device *br_dev, struct net_device *dev,
+ struct notifier_block *nb, struct netlink_ext_ack *extack);
#else
static inline bool br_vlan_enabled(const struct net_device *dev)
{
@@ -128,6 +139,14 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
{
return -EINVAL;
}
+
+static inline int br_vlan_replay(struct net_device *br_dev,
+ struct net_device *dev,
+ struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
#endif
#if IS_ENABLED(CONFIG_BRIDGE)
@@ -136,6 +155,10 @@ struct net_device *br_fdb_find_port(const struct net_device *br_dev,
__u16 vid);
void br_fdb_clear_offload(const struct net_device *dev, u16 vid);
bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
+u8 br_port_get_stp_state(const struct net_device *dev);
+clock_t br_get_ageing_time(struct net_device *br_dev);
+int br_fdb_replay(struct net_device *br_dev, struct net_device *dev,
+ struct notifier_block *nb);
#else
static inline struct net_device *
br_fdb_find_port(const struct net_device *br_dev,
@@ -154,6 +177,23 @@ br_port_flag_is_set(const struct net_device *dev, unsigned long flag)
{
return false;
}
+
+static inline u8 br_port_get_stp_state(const struct net_device *dev)
+{
+ return BR_STATE_DISABLED;
+}
+
+static inline clock_t br_get_ageing_time(struct net_device *br_dev)
+{
+ return 0;
+}
+
+static inline int br_fdb_replay(struct net_device *br_dev,
+ struct net_device *dev,
+ struct notifier_block *nb)
+{
+ return -EOPNOTSUPP;
+}
#endif
#endif
diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h
index 9661416a9bb4..4efb537f57f3 100644
--- a/include/linux/if_rmnet.h
+++ b/include/linux/if_rmnet.h
@@ -6,50 +6,43 @@
#define _LINUX_IF_RMNET_H_
struct rmnet_map_header {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
- u8 pad_len:6;
- u8 reserved_bit:1;
- u8 cd_bit:1;
-#elif defined (__BIG_ENDIAN_BITFIELD)
- u8 cd_bit:1;
- u8 reserved_bit:1;
- u8 pad_len:6;
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
- u8 mux_id;
- __be16 pkt_len;
+ u8 flags; /* MAP_CMD_FLAG, MAP_PAD_LEN_MASK */
+ u8 mux_id;
+ __be16 pkt_len; /* Length of packet, including pad */
} __aligned(1);
+/* rmnet_map_header flags field:
+ * PAD_LEN: number of pad bytes following packet data
+ * CMD: 1 = packet contains a MAP command; 0 = packet contains data
+ */
+#define MAP_PAD_LEN_MASK GENMASK(5, 0)
+#define MAP_CMD_FLAG BIT(7)
+
struct rmnet_map_dl_csum_trailer {
- u8 reserved1;
-#if defined(__LITTLE_ENDIAN_BITFIELD)
- u8 valid:1;
- u8 reserved2:7;
-#elif defined (__BIG_ENDIAN_BITFIELD)
- u8 reserved2:7;
- u8 valid:1;
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
- u16 csum_start_offset;
- u16 csum_length;
+ u8 reserved1;
+ u8 flags; /* MAP_CSUM_DL_VALID_FLAG */
+ __be16 csum_start_offset;
+ __be16 csum_length;
__be16 csum_value;
} __aligned(1);
+/* rmnet_map_dl_csum_trailer flags field:
+ * VALID: 1 = checksum and length valid; 0 = ignore them
+ */
+#define MAP_CSUM_DL_VALID_FLAG BIT(0)
+
struct rmnet_map_ul_csum_header {
__be16 csum_start_offset;
-#if defined(__LITTLE_ENDIAN_BITFIELD)
- u16 csum_insert_offset:14;
- u16 udp_ind:1;
- u16 csum_enabled:1;
-#elif defined (__BIG_ENDIAN_BITFIELD)
- u16 csum_enabled:1;
- u16 udp_ind:1;
- u16 csum_insert_offset:14;
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
+ __be16 csum_info; /* MAP_CSUM_UL_* */
} __aligned(1);
+/* csum_info field:
+ * OFFSET: where (offset in bytes) to insert computed checksum
+ * UDP: 1 = UDP checksum (zero checkum means no checksum)
+ * ENABLED: 1 = checksum computation requested
+ */
+#define MAP_CSUM_UL_OFFSET_MASK GENMASK(13, 0)
+#define MAP_CSUM_UL_UDP_FLAG BIT(14)
+#define MAP_CSUM_UL_ENABLED_FLAG BIT(15)
+
#endif /* !(_LINUX_IF_RMNET_H_) */
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 52b1610eae68..274abd5fbac3 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -24,6 +24,7 @@
#define MARVELL_PHY_ID_88E3016 0x01410e60
#define MARVELL_PHY_ID_88X3310 0x002b09a0
#define MARVELL_PHY_ID_88E2110 0x002b09b0
+#define MARVELL_PHY_ID_88X2222 0x01410f10
/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index dc3d2508f5c6..92a029a800a0 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1142,6 +1142,8 @@ enum mlx5_flex_parser_protos {
MLX5_FLEX_PROTO_GENEVE = 1 << 3,
MLX5_FLEX_PROTO_CW_MPLS_GRE = 1 << 4,
MLX5_FLEX_PROTO_CW_MPLS_UDP = 1 << 5,
+ MLX5_FLEX_PROTO_ICMP = 1 << 8,
+ MLX5_FLEX_PROTO_ICMPV6 = 1 << 9,
};
/* MLX5 DEV CAPs */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 53b89631a1d9..23bb01d7c9b9 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -644,10 +644,14 @@ struct mlx5_td {
};
struct mlx5e_resources {
- u32 pdn;
- struct mlx5_td td;
- struct mlx5_core_mkey mkey;
- struct mlx5_sq_bfreg bfreg;
+ struct mlx5e_hw_objs {
+ u32 pdn;
+ struct mlx5_td td;
+ struct mlx5_core_mkey mkey;
+ struct mlx5_sq_bfreg bfreg;
+ } hw_objs;
+ struct devlink_port dl_port;
+ struct net_device *uplink_netdev;
};
enum mlx5_sw_icm_type {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 87a5d186faff..f57b70fc251f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -756,6 +756,13 @@ struct rx_queue_attribute {
const char *buf, size_t len);
};
+/* XPS map type and offset of the xps map within net_device->xps_maps[]. */
+enum xps_map_type {
+ XPS_CPUS = 0,
+ XPS_RXQS,
+ XPS_MAPS_MAX,
+};
+
#ifdef CONFIG_XPS
/*
* This structure holds an XPS map which can be of variable length. The
@@ -773,9 +780,19 @@ struct xps_map {
/*
* This structure holds all XPS maps for device. Maps are indexed by CPU.
+ *
+ * We keep track of the number of cpus/rxqs used when the struct is allocated,
+ * in nr_ids. This will help not accessing out-of-bound memory.
+ *
+ * We keep track of the number of traffic classes used when the struct is
+ * allocated, in num_tc. This will be used to navigate the maps, to ensure we're
+ * not crossing its upper bound, as the original dev->num_tc can be updated in
+ * the meantime.
*/
struct xps_dev_maps {
struct rcu_head rcu;
+ unsigned int nr_ids;
+ s16 num_tc;
struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */
};
@@ -833,6 +850,59 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
+enum net_device_path_type {
+ DEV_PATH_ETHERNET = 0,
+ DEV_PATH_VLAN,
+ DEV_PATH_BRIDGE,
+ DEV_PATH_PPPOE,
+ DEV_PATH_DSA,
+};
+
+struct net_device_path {
+ enum net_device_path_type type;
+ const struct net_device *dev;
+ union {
+ struct {
+ u16 id;
+ __be16 proto;
+ u8 h_dest[ETH_ALEN];
+ } encap;
+ struct {
+ enum {
+ DEV_PATH_BR_VLAN_KEEP,
+ DEV_PATH_BR_VLAN_TAG,
+ DEV_PATH_BR_VLAN_UNTAG,
+ DEV_PATH_BR_VLAN_UNTAG_HW,
+ } vlan_mode;
+ u16 vlan_id;
+ __be16 vlan_proto;
+ } bridge;
+ struct {
+ int port;
+ u16 proto;
+ } dsa;
+ };
+};
+
+#define NET_DEVICE_PATH_STACK_MAX 5
+#define NET_DEVICE_PATH_VLAN_MAX 2
+
+struct net_device_path_stack {
+ int num_paths;
+ struct net_device_path path[NET_DEVICE_PATH_STACK_MAX];
+};
+
+struct net_device_path_ctx {
+ const struct net_device *dev;
+ const u8 *daddr;
+
+ int num_vlans;
+ struct {
+ u16 id;
+ __be16 proto;
+ } vlan[NET_DEVICE_PATH_VLAN_MAX];
+};
+
enum tc_setup_type {
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
@@ -1267,6 +1337,8 @@ struct netdev_net_notifier {
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
+ * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
+ * Get the forwarding path to reach the real device from the HW destination address
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1473,6 +1545,8 @@ struct net_device_ops {
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
+ int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
+ struct net_device_path *path);
};
/**
@@ -1520,6 +1594,8 @@ struct net_device_ops {
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
* @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
+ * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
+ * skb_headlen(skb) == 0 (data starts from frag0)
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
@@ -1553,6 +1629,7 @@ enum netdev_priv_flags {
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
IFF_LIVE_RENAME_OK = 1<<30,
+ IFF_TX_SKB_NO_LINEAR = 1<<31,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
@@ -1579,12 +1656,14 @@ enum netdev_priv_flags {
#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE
#define IFF_TEAM IFF_TEAM
#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED
+#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM
#define IFF_MACSEC IFF_MACSEC
#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER
#define IFF_FAILOVER IFF_FAILOVER
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK
+#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR
/* Specifies the type of the struct net_device::ml_priv pointer */
enum netdev_ml_priv_type {
@@ -1760,8 +1839,7 @@ enum netdev_ml_priv_type {
* @tx_queue_len: Max frames per queue allowed
* @tx_global_lock: XXX: need comments on this one
* @xdp_bulkq: XDP device bulk queue
- * @xps_cpus_map: all CPUs map for XPS device
- * @xps_rxqs_map: all RXQs map for XPS device
+ * @xps_maps: all CPUs/RXQs maps for XPS device
*
* @xps_maps: XXX: need comments on this one
* @miniq_egress: clsact qdisc specific data for
@@ -1773,6 +1851,7 @@ enum netdev_ml_priv_type {
*
* @proto_down_reason: reason a netdev interface is held down
* @pcpu_refcnt: Number of references to this device
+ * @dev_refcnt: Number of references to this device
* @todo_list: Delayed register/unregister
* @link_watch_list: XXX: need comments on this one
*
@@ -2057,8 +2136,7 @@ struct net_device {
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS
- struct xps_dev_maps __rcu *xps_cpus_map;
- struct xps_dev_maps __rcu *xps_rxqs_map;
+ struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
#endif
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc __rcu *miniq_egress;
@@ -2074,7 +2152,12 @@ struct net_device {
u32 proto_down_reason;
struct list_head todo_list;
+
+#ifdef CONFIG_PCPU_DEV_REFCNT
int __percpu *pcpu_refcnt;
+#else
+ refcount_t dev_refcnt;
+#endif
struct list_head link_watch_list;
@@ -2846,6 +2929,8 @@ void dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack);
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
@@ -3424,6 +3509,24 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
}
/**
+ * netdev_queue_set_dql_min_limit - set dql minimum limit
+ * @dev_queue: pointer to transmit queue
+ * @min_limit: dql minimum limit
+ *
+ * Forces xmit_more() to return true until the minimum threshold
+ * defined by @min_limit is reached (or until the tx queue is
+ * empty). Warning: to be use with care, misuse will impact the
+ * latency.
+ */
+static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue,
+ unsigned int min_limit)
+{
+#ifdef CONFIG_BQL
+ dev_queue->dql.min_limit = min_limit;
+#endif
+}
+
+/**
* netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
*
@@ -3688,7 +3791,7 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index);
int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
- u16 index, bool is_rxqs_map);
+ u16 index, enum xps_map_type type);
/**
* netif_attr_test_mask - Test a CPU or Rx queue set in a mask
@@ -3783,7 +3886,7 @@ static inline int netif_set_xps_queue(struct net_device *dev,
static inline int __netif_set_xps_queue(struct net_device *dev,
const unsigned long *mask,
- u16 index, bool is_rxqs_map)
+ u16 index, enum xps_map_type type)
{
return 0;
}
@@ -4026,7 +4129,11 @@ void netdev_run_todo(void);
*/
static inline void dev_put(struct net_device *dev)
{
+#ifdef CONFIG_PCPU_DEV_REFCNT
this_cpu_dec(*dev->pcpu_refcnt);
+#else
+ refcount_dec(&dev->dev_refcnt);
+#endif
}
/**
@@ -4037,7 +4144,11 @@ static inline void dev_put(struct net_device *dev)
*/
static inline void dev_hold(struct net_device *dev)
{
+#ifdef CONFIG_PCPU_DEV_REFCNT
this_cpu_inc(*dev->pcpu_refcnt);
+#else
+ refcount_inc(&dev->dev_refcnt);
+#endif
}
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
@@ -4172,7 +4283,7 @@ static inline bool netif_oper_up(const struct net_device *dev)
*
* Check if device has not been removed from system.
*/
-static inline bool netif_device_present(struct net_device *dev)
+static inline bool netif_device_present(const struct net_device *dev)
{
return test_bit(__LINK_STATE_PRESENT, &dev->state);
}
@@ -4611,6 +4722,7 @@ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
+extern int netdev_unregister_timeout_secs;
extern int weight_p;
extern int dev_weight_rx_bias;
extern int dev_weight_tx_bias;
@@ -5287,6 +5399,9 @@ do { \
#define PTYPE_HASH_SIZE (16)
#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
+extern struct list_head ptype_all __read_mostly;
+extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
+
extern struct net_device *blackhole_netdev;
#endif /* _LINUX_NETDEVICE_H */
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index 351c1c9aedc5..2cb5188a7ef1 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -10,10 +10,15 @@
#include <linux/phy.h>
#include <linux/phylink.h>
+/* AN mode */
+#define DW_AN_C73 1
+#define DW_AN_C37_SGMII 2
+
struct mdio_xpcs_args {
__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
struct mii_bus *bus;
int addr;
+ int an_mode;
};
struct mdio_xpcs_ops {
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 1a12e4436b5b..8e2cf84b2318 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1532,6 +1532,7 @@ int genphy_c45_read_mdix(struct phy_device *phydev);
int genphy_c45_pma_read_abilities(struct phy_device *phydev);
int genphy_c45_read_status(struct phy_device *phydev);
int genphy_c45_config_aneg(struct phy_device *phydev);
+int genphy_c45_loopback(struct phy_device *phydev, bool enable);
/* Generic C45 PHY driver */
extern struct phy_driver genphy_c45_driver;
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index d81a714cfbbd..fd2acfd9b597 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -64,6 +64,7 @@ enum phylink_op_type {
* @pcs_poll: MAC PCS cannot provide link change interrupt
* @poll_fixed_state: if true, starts link_poll,
* if MAC link is at %MLO_AN_FIXED mode.
+ * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND
* @get_fixed_state: callback to execute to determine the fixed link state,
* if MAC link is at %MLO_AN_FIXED mode.
*/
@@ -72,6 +73,7 @@ struct phylink_config {
enum phylink_op_type type;
bool pcs_poll;
bool poll_fixed_state;
+ bool ovr_an_inband;
void (*get_fixed_state)(struct phylink_config *config,
struct phylink_link_state *state);
};
diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h
index 388846766bb2..6a000df5541f 100644
--- a/include/linux/platform_data/hirschmann-hellcreek.h
+++ b/include/linux/platform_data/hirschmann-hellcreek.h
@@ -12,6 +12,7 @@
#include <linux/types.h>
struct hellcreek_platform_data {
+ const char *name; /* Switch name */
int num_ports; /* Amount of switch ports */
int is_100_mbits; /* Is it configured to 100 or 1000 mbit/s */
int qbv_support; /* Qbv support on front TSN ports */
diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h
index 98966064ee68..91f9a928344e 100644
--- a/include/linux/ppp_channel.h
+++ b/include/linux/ppp_channel.h
@@ -28,6 +28,9 @@ struct ppp_channel_ops {
int (*start_xmit)(struct ppp_channel *, struct sk_buff *);
/* Handle an ioctl call that has come in via /dev/ppp. */
int (*ioctl)(struct ppp_channel *, unsigned int, unsigned long);
+ int (*fill_forward_path)(struct net_device_path_ctx *,
+ struct net_device_path *,
+ const struct ppp_channel *);
};
struct ppp_channel {
diff --git a/include/linux/ptp_pch.h b/include/linux/ptp_pch.h
new file mode 100644
index 000000000000..51818198c292
--- /dev/null
+++ b/include/linux/ptp_pch.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PTP PCH
+ *
+ * Copyright 2019 Linaro Ltd.
+ *
+ * Author Lee Jones <lee.jones@linaro.org>
+ */
+
+#ifndef _PTP_PCH_H_
+#define _PTP_PCH_H_
+
+void pch_ch_control_write(struct pci_dev *pdev, u32 val);
+u32 pch_ch_event_read(struct pci_dev *pdev);
+void pch_ch_event_write(struct pci_dev *pdev, u32 val);
+u32 pch_src_uuid_lo_read(struct pci_dev *pdev);
+u32 pch_src_uuid_hi_read(struct pci_dev *pdev);
+u64 pch_rx_snap_read(struct pci_dev *pdev);
+u64 pch_tx_snap_read(struct pci_dev *pdev);
+int pch_set_station_address(u8 *addr, struct pci_dev *pdev);
+
+#endif /* _PTP_PCH_H_ */
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index e339b48de32d..f34dbd0db795 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -19,7 +19,7 @@ enum qed_chain_mode {
/* Each Page contains a next pointer at its end */
QED_CHAIN_MODE_NEXT_PTR,
- /* Chain is a single page (next ptr) is unrequired */
+ /* Chain is a single page (next ptr) is not required */
QED_CHAIN_MODE_SINGLE,
/* Page pointers are located in a side list */
@@ -56,13 +56,13 @@ struct qed_chain_pbl_u32 {
};
struct qed_chain_u16 {
- /* Cyclic index of next element to produce/consme */
+ /* Cyclic index of next element to produce/consume */
u16 prod_idx;
u16 cons_idx;
};
struct qed_chain_u32 {
- /* Cyclic index of next element to produce/consme */
+ /* Cyclic index of next element to produce/consume */
u32 prod_idx;
u32 cons_idx;
};
@@ -270,7 +270,7 @@ static inline dma_addr_t qed_chain_get_pbl_phys(const struct qed_chain *chain)
/**
* @brief qed_chain_advance_page -
*
- * Advance the next element accros pages for a linked chain
+ * Advance the next element across pages for a linked chain
*
* @param p_chain
* @param p_next_elem
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ef00bb22164c..e5b7d9054473 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -42,6 +42,7 @@ struct audit_context;
struct backing_dev_info;
struct bio_list;
struct blk_plug;
+struct bpf_local_storage;
struct capture_control;
struct cfs_rq;
struct fs_struct;
@@ -1351,6 +1352,10 @@ struct task_struct {
/* Used by LSM modules for access restriction: */
void *security;
#endif
+#ifdef CONFIG_BPF_SYSCALL
+ /* Used by BPF task local storage */
+ struct bpf_local_storage __rcu *bpf_storage;
+#endif
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
unsigned long lowest_stack;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f2c9ee71cb2c..c8def85fcc22 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -657,6 +657,7 @@ typedef unsigned char *sk_buff_data_t;
* @protocol: Packet protocol from driver
* @destructor: Destruct function
* @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
+ * @_sk_redir: socket redirection information for skmsg
* @_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
@@ -756,6 +757,9 @@ struct sk_buff {
void (*destructor)(struct sk_buff *skb);
};
struct list_head tcp_tsorted_anchor;
+#ifdef CONFIG_NET_SOCK_MSG
+ unsigned long _sk_redir;
+#endif
};
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
@@ -1137,7 +1141,7 @@ static inline bool skb_fclone_busy(const struct sock *sk,
return skb->fclone == SKB_FCLONE_ORIG &&
refcount_read(&fclones->fclone_ref) > 1 &&
- fclones->skb2.sk == sk;
+ READ_ONCE(fclones->skb2.sk) == sk;
}
/**
@@ -1289,10 +1293,10 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
void __skb_get_hash(struct sk_buff *skb);
u32 __skb_get_hash_symmetric(const struct sk_buff *skb);
u32 skb_get_poff(const struct sk_buff *skb);
-u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+u32 __skb_get_poff(const struct sk_buff *skb, const void *data,
const struct flow_keys_basic *keys, int hlen);
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
- void *data, int hlen_proto);
+ const void *data, int hlen_proto);
static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
int thoff, u8 ip_proto)
@@ -1311,9 +1315,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
bool __skb_flow_dissect(const struct net *net,
const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
- void *target_container,
- void *data, __be16 proto, int nhoff, int hlen,
- unsigned int flags);
+ void *target_container, const void *data,
+ __be16 proto, int nhoff, int hlen, unsigned int flags);
static inline bool skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
@@ -1335,9 +1338,9 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
static inline bool
skb_flow_dissect_flow_keys_basic(const struct net *net,
const struct sk_buff *skb,
- struct flow_keys_basic *flow, void *data,
- __be16 proto, int nhoff, int hlen,
- unsigned int flags)
+ struct flow_keys_basic *flow,
+ const void *data, __be16 proto,
+ int nhoff, int hlen, unsigned int flags)
{
memset(flow, 0, sizeof(*flow));
return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow,
@@ -3675,14 +3678,13 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
__wsum csum);
static inline void * __must_check
-__skb_header_pointer(const struct sk_buff *skb, int offset,
- int len, void *data, int hlen, void *buffer)
+__skb_header_pointer(const struct sk_buff *skb, int offset, int len,
+ const void *data, int hlen, void *buffer)
{
- if (hlen - offset >= len)
- return data + offset;
+ if (likely(hlen - offset >= len))
+ return (void *)data + offset;
- if (!skb ||
- skb_copy_bits(skb, offset, buffer, len) < 0)
+ if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
return NULL;
return buffer;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 8edbbf5f2f93..6c09d94be2e9 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -56,8 +56,8 @@ struct sk_msg {
struct sk_psock_progs {
struct bpf_prog *msg_parser;
- struct bpf_prog *skb_parser;
- struct bpf_prog *skb_verdict;
+ struct bpf_prog *stream_parser;
+ struct bpf_prog *stream_verdict;
};
enum sk_psock_state_bits {
@@ -70,12 +70,6 @@ struct sk_psock_link {
void *link_raw;
};
-struct sk_psock_parser {
- struct strparser strp;
- bool enabled;
- void (*saved_data_ready)(struct sock *sk);
-};
-
struct sk_psock_work_state {
struct sk_buff *skb;
u32 len;
@@ -90,7 +84,9 @@ struct sk_psock {
u32 eval;
struct sk_msg *cork;
struct sk_psock_progs progs;
- struct sk_psock_parser parser;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ struct strparser strp;
+#endif
struct sk_buff_head ingress_skb;
struct list_head ingress_msg;
unsigned long state;
@@ -100,6 +96,7 @@ struct sk_psock {
void (*saved_unhash)(struct sock *sk);
void (*saved_close)(struct sock *sk, long timeout);
void (*saved_write_space)(struct sock *sk);
+ void (*saved_data_ready)(struct sock *sk);
struct proto *sk_proto;
struct sk_psock_work_state work_state;
struct work_struct work;
@@ -305,9 +302,25 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err)
struct sk_psock *sk_psock_init(struct sock *sk, int node);
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
+#else
+static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
+{
+}
+
+static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
+{
+}
+#endif
+
void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock);
void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock);
@@ -327,8 +340,6 @@ static inline void sk_psock_free_link(struct sk_psock_link *link)
struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock);
-void __sk_psock_purge_ingress_msg(struct sk_psock *psock);
-
static inline void sk_psock_cork_free(struct sk_psock *psock)
{
if (psock->cork) {
@@ -389,7 +400,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk)
return psock;
}
-void sk_psock_stop(struct sock *sk, struct sk_psock *psock);
void sk_psock_drop(struct sock *sk, struct sk_psock *psock);
static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
@@ -400,8 +410,8 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
{
- if (psock->parser.enabled)
- psock->parser.saved_data_ready(sk);
+ if (psock->saved_data_ready)
+ psock->saved_data_ready(sk);
else
sk->sk_data_ready(sk);
}
@@ -430,8 +440,8 @@ static inline int psock_replace_prog(struct bpf_prog **pprog,
static inline void psock_progs_drop(struct sk_psock_progs *progs)
{
psock_set_prog(&progs->msg_parser, NULL);
- psock_set_prog(&progs->skb_parser, NULL);
- psock_set_prog(&progs->skb_verdict, NULL);
+ psock_set_prog(&progs->stream_parser, NULL);
+ psock_set_prog(&progs->stream_verdict, NULL);
}
int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
@@ -440,6 +450,44 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
{
if (!psock)
return false;
- return psock->parser.enabled;
+ return !!psock->saved_data_ready;
+}
+
+#if IS_ENABLED(CONFIG_NET_SOCK_MSG)
+
+/* We only have one bit so far. */
+#define BPF_F_PTR_MASK ~(BPF_F_INGRESS)
+
+static inline bool skb_bpf_ingress(const struct sk_buff *skb)
+{
+ unsigned long sk_redir = skb->_sk_redir;
+
+ return sk_redir & BPF_F_INGRESS;
+}
+
+static inline void skb_bpf_set_ingress(struct sk_buff *skb)
+{
+ skb->_sk_redir |= BPF_F_INGRESS;
+}
+
+static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir,
+ bool ingress)
+{
+ skb->_sk_redir = (unsigned long)sk_redir;
+ if (ingress)
+ skb->_sk_redir |= BPF_F_INGRESS;
+}
+
+static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb)
+{
+ unsigned long sk_redir = skb->_sk_redir;
+
+ return (struct sock *)(sk_redir & BPF_F_PTR_MASK);
+}
+
+static inline void skb_bpf_redirect_clear(struct sk_buff *skb)
+{
+ skb->_sk_redir = 0;
}
+#endif /* CONFIG_NET_SOCK_MSG */
#endif /* _LINUX_SKMSG_H */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index a302982de2d7..febdb43d27e5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -81,6 +81,7 @@
struct stmmac_mdio_bus_data {
unsigned int phy_mask;
unsigned int has_xpcs;
+ unsigned int xpcs_an_inband;
int *irqs;
int probed_phy_irq;
bool needs_reset;
@@ -143,6 +144,32 @@ struct stmmac_txq_cfg {
int tbs_en;
};
+/* FPE link state */
+enum stmmac_fpe_state {
+ FPE_STATE_OFF = 0,
+ FPE_STATE_CAPABLE = 1,
+ FPE_STATE_ENTERING_ON = 2,
+ FPE_STATE_ON = 3,
+};
+
+/* FPE link-partner hand-shaking mPacket type */
+enum stmmac_mpacket_type {
+ MPACKET_VERIFY = 0,
+ MPACKET_RESPONSE = 1,
+};
+
+enum stmmac_fpe_task_state_t {
+ __FPE_REMOVING,
+ __FPE_TASK_SCHED,
+};
+
+struct stmmac_fpe_cfg {
+ bool enable; /* FPE enable */
+ bool hs_enable; /* FPE handshake enable */
+ enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */
+ enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */
+};
+
struct plat_stmmacenet_data {
int bus_id;
int phy_addr;
@@ -154,6 +181,7 @@ struct plat_stmmacenet_data {
struct device_node *mdio_node;
struct stmmac_dma_cfg *dma_cfg;
struct stmmac_est *est;
+ struct stmmac_fpe_cfg *fpe_cfg;
int clk_csr;
int has_gmac;
int enh_desc;
@@ -180,9 +208,13 @@ struct plat_stmmacenet_data {
void (*fix_mac_speed)(void *priv, unsigned int speed);
int (*serdes_powerup)(struct net_device *ndev, void *priv);
void (*serdes_powerdown)(struct net_device *ndev, void *priv);
+ void (*ptp_clk_freq_config)(void *priv);
int (*init)(struct platform_device *pdev, void *priv);
void (*exit)(struct platform_device *pdev, void *priv);
struct mac_device_info *(*setup)(void *priv);
+ int (*clks_config)(void *priv, bool enabled);
+ int (*crosststamp)(ktime_t *device, struct system_counterval_t *system,
+ void *ctx);
void *bsp_priv;
struct clk *stmmac_clk;
struct clk *pclk;
@@ -203,5 +235,7 @@ struct plat_stmmacenet_data {
u8 vlan_fail_q;
unsigned int eee_usecs_rate;
struct pci_dev *pdev;
+ bool has_crossts;
+ int int_snapshot_num;
};
#endif
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 83a933e563fe..57b2c49f72f4 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -49,10 +49,12 @@ struct phylink_link_state;
#define DSA_TAG_PROTO_XRS700X_VALUE 19
#define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20
#define DSA_TAG_PROTO_SEVILLE_VALUE 21
+#define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE,
DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE,
+ DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE,
DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE,
DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE,
DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE,
@@ -491,6 +493,20 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
return dp->vlan_filtering;
}
+static inline
+struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp)
+{
+ if (!dp->bridge_dev)
+ return NULL;
+
+ if (dp->lag_dev)
+ return dp->lag_dev;
+ else if (dp->hsr_dev)
+ return dp->hsr_dev;
+
+ return dp->slave;
+}
+
typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
bool is_static, void *data);
struct dsa_switch_ops {
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index cc10b10dc3a1..ffd386ea0dbb 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -350,7 +350,7 @@ static inline bool flow_keys_have_l4(const struct flow_keys *keys)
u32 flow_hash_from_keys(struct flow_keys *keys);
void skb_flow_get_icmp_tci(const struct sk_buff *skb,
struct flow_dissector_key_icmp *key_icmp,
- void *data, int thoff, int hlen);
+ const void *data, int thoff, int hlen);
static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector,
enum flow_dissector_key_id key_id)
@@ -368,8 +368,8 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec
struct bpf_flow_dissector {
struct bpf_flow_keys *flow_keys;
const struct sk_buff *skb;
- void *data;
- void *data_end;
+ const void *data;
+ const void *data_end;
};
static inline void
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index e6bd8ebf9ac3..dc5c1e69cd9f 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -147,6 +147,7 @@ enum flow_action_id {
FLOW_ACTION_MPLS_POP,
FLOW_ACTION_MPLS_MANGLE,
FLOW_ACTION_GATE,
+ FLOW_ACTION_PPPOE_PUSH,
NUM_FLOW_ACTIONS,
};
@@ -234,6 +235,8 @@ struct flow_action_entry {
u32 index;
u32 burst;
u64 rate_bytes_ps;
+ u64 burst_pkt;
+ u64 rate_pkt_ps;
u32 mtu;
} police;
struct { /* FLOW_ACTION_CT */
@@ -272,6 +275,9 @@ struct flow_action_entry {
u32 num_entries;
struct action_gate_entry *entries;
} gate;
+ struct { /* FLOW_ACTION_PPPOE_PUSH */
+ u16 sid;
+ } pppoe;
};
struct flow_action_cookie *cookie; /* user defined action cookie */
};
diff --git a/include/net/gro.h b/include/net/gro.h
index 8a6eb5303cc4..01edaf3fdda0 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -3,10 +3,23 @@
#ifndef _NET_IPV6_GRO_H
#define _NET_IPV6_GRO_H
+#include <linux/indirect_call_wrapper.h>
+
+struct list_head;
+struct sk_buff;
+
INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *,
struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
+
+#define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \
+({ \
+ unlikely(gro_recursion_inc_test(skb)) ? \
+ NAPI_GRO_CB(skb)->flush |= 1, NULL : \
+ INDIRECT_CALL_INET(cb, f2, f1, head, skb); \
+})
+
#endif /* _NET_IPV6_GRO_H */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index bd1f396cc9c7..448bf2b34759 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -30,6 +30,7 @@
*/
#define NEXTHDR_HOP 0 /* Hop-by-hop option header. */
+#define NEXTHDR_IPV4 4 /* IPv4 in IPv6 */
#define NEXTHDR_TCP 6 /* TCP segment. */
#define NEXTHDR_UDP 17 /* UDP message. */
#define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */
diff --git a/include/net/lapb.h b/include/net/lapb.h
index eee73442a1ba..124ee122f2c8 100644
--- a/include/net/lapb.h
+++ b/include/net/lapb.h
@@ -92,7 +92,7 @@ struct lapb_cb {
unsigned short n2, n2count;
unsigned short t1, t2;
struct timer_list t1timer, t2timer;
- bool t1timer_stop, t2timer_stop;
+ bool t1timer_running, t2timer_running;
/* Internal control information */
struct sk_buff_head write_queue;
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 5694370be3d4..cea69c801595 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -34,6 +34,13 @@ struct mptcp_ext {
/* one byte hole */
};
+#define MPTCP_RM_IDS_MAX 8
+
+struct mptcp_rm_list {
+ u8 ids[MPTCP_RM_IDS_MAX];
+ u8 nr;
+};
+
struct mptcp_out_options {
#if IS_ENABLED(CONFIG_MPTCP)
u16 suboptions;
@@ -48,7 +55,7 @@ struct mptcp_out_options {
u8 addr_id;
u16 port;
u64 ahmac;
- u8 rm_id;
+ struct mptcp_rm_list rm_list;
u8 join_id;
u8 backup;
u32 nonce;
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index 7b3c873f8839..e95483192d1b 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -4,7 +4,4 @@
extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6;
-#include <linux/sysctl.h>
-extern struct ctl_table nf_ct_ipv6_sysctl_table[];
-
#endif /* _NF_CONNTRACK_IPV6_H*/
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 54c4d5c908a5..4d991c1e93ef 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -86,8 +86,16 @@ static inline bool nf_flowtable_hw_offload(struct nf_flowtable *flowtable)
enum flow_offload_tuple_dir {
FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
- FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
};
+#define FLOW_OFFLOAD_DIR_MAX IP_CT_DIR_MAX
+
+enum flow_offload_xmit_type {
+ FLOW_OFFLOAD_XMIT_NEIGH = 0,
+ FLOW_OFFLOAD_XMIT_XFRM,
+ FLOW_OFFLOAD_XMIT_DIRECT,
+};
+
+#define NF_FLOW_TABLE_ENCAP_MAX 2
struct flow_offload_tuple {
union {
@@ -107,15 +115,28 @@ struct flow_offload_tuple {
u8 l3proto;
u8 l4proto;
+ struct {
+ u16 id;
+ __be16 proto;
+ } encap[NF_FLOW_TABLE_ENCAP_MAX];
/* All members above are keys for lookups, see flow_offload_hash(). */
struct { } __hash;
- u8 dir;
-
+ u8 dir:2,
+ xmit_type:2,
+ encap_num:2,
+ in_vlan_ingress:2;
u16 mtu;
-
- struct dst_entry *dst_cache;
+ union {
+ struct dst_entry *dst_cache;
+ struct {
+ u32 ifidx;
+ u32 hw_ifidx;
+ u8 h_source[ETH_ALEN];
+ u8 h_dest[ETH_ALEN];
+ } out;
+ };
};
struct flow_offload_tuple_rhash {
@@ -158,7 +179,23 @@ static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
struct nf_flow_route {
struct {
- struct dst_entry *dst;
+ struct dst_entry *dst;
+ struct {
+ u32 ifindex;
+ struct {
+ u16 id;
+ __be16 proto;
+ } encap[NF_FLOW_TABLE_ENCAP_MAX];
+ u8 num_encaps:2,
+ ingress_vlans:2;
+ } in;
+ struct {
+ u32 ifindex;
+ u32 hw_ifindex;
+ u8 h_source[ETH_ALEN];
+ u8 h_dest[ETH_ALEN];
+ } out;
+ enum flow_offload_xmit_type xmit_type;
} tuple[FLOW_OFFLOAD_DIR_MAX];
};
@@ -229,12 +266,12 @@ void nf_flow_table_free(struct nf_flowtable *flow_table);
void flow_offload_teardown(struct flow_offload *flow);
-int nf_flow_snat_port(const struct flow_offload *flow,
- struct sk_buff *skb, unsigned int thoff,
- u8 protocol, enum flow_offload_tuple_dir dir);
-int nf_flow_dnat_port(const struct flow_offload *flow,
- struct sk_buff *skb, unsigned int thoff,
- u8 protocol, enum flow_offload_tuple_dir dir);
+void nf_flow_snat_port(const struct flow_offload *flow,
+ struct sk_buff *skb, unsigned int thoff,
+ u8 protocol, enum flow_offload_tuple_dir dir);
+void nf_flow_dnat_port(const struct flow_offload *flow,
+ struct sk_buff *skb, unsigned int thoff,
+ u8 protocol, enum flow_offload_tuple_dir dir);
struct flow_ports {
__be16 source, dest;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 5aaced6bf13e..0cef5ad9768a 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1498,13 +1498,16 @@ struct nft_trans_chain {
struct nft_trans_table {
bool update;
- bool enable;
+ u8 state;
+ u32 flags;
};
#define nft_trans_table_update(trans) \
(((struct nft_trans_table *)trans->data)->update)
-#define nft_trans_table_enable(trans) \
- (((struct nft_trans_table *)trans->data)->enable)
+#define nft_trans_table_state(trans) \
+ (((struct nft_trans_table *)trans->data)->state)
+#define nft_trans_table_flags(trans) \
+ (((struct nft_trans_table *)trans->data)->flags)
struct nft_trans_elem {
struct nft_set *set;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 70a2a085dd1a..9e3cb2722b80 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -11,7 +11,6 @@
#include <linux/rcupdate.h>
#include <linux/siphash.h>
-struct tcpm_hash_bucket;
struct ctl_table_header;
struct ipv4_devconf;
struct fib_rules_ops;
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index a10a319d7eb2..28145f714801 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -40,6 +40,12 @@ struct nh_config {
struct nlattr *nh_grp;
u16 nh_grp_type;
+ u16 nh_grp_res_num_buckets;
+ unsigned long nh_grp_res_idle_timer;
+ unsigned long nh_grp_res_unbalanced_timer;
+ bool nh_grp_res_has_num_buckets;
+ bool nh_grp_res_has_idle_timer;
+ bool nh_grp_res_has_unbalanced_timer;
struct nlattr *nh_encap;
u16 nh_encap_type;
@@ -63,6 +69,32 @@ struct nh_info {
};
};
+struct nh_res_bucket {
+ struct nh_grp_entry __rcu *nh_entry;
+ atomic_long_t used_time;
+ unsigned long migrated_time;
+ bool occupied;
+ u8 nh_flags;
+};
+
+struct nh_res_table {
+ struct net *net;
+ u32 nhg_id;
+ struct delayed_work upkeep_dw;
+
+ /* List of NHGEs that have too few buckets ("uw" for underweight).
+ * Reclaimed buckets will be given to entries in this list.
+ */
+ struct list_head uw_nh_entries;
+ unsigned long unbalanced_since;
+
+ u32 idle_timer;
+ u32 unbalanced_timer;
+
+ u16 num_nh_buckets;
+ struct nh_res_bucket nh_buckets[];
+};
+
struct nh_grp_entry {
struct nexthop *nh;
u8 weight;
@@ -71,6 +103,13 @@ struct nh_grp_entry {
struct {
atomic_t upper_bound;
} mpath;
+ struct {
+ /* Member on uw_nh_entries. */
+ struct list_head uw_nh_entry;
+
+ u16 count_buckets;
+ u16 wants_buckets;
+ } res;
};
struct list_head nh_list;
@@ -80,9 +119,13 @@ struct nh_grp_entry {
struct nh_group {
struct nh_group *spare; /* spare group for removals */
u16 num_nh;
+ bool is_multipath;
bool mpath;
+ bool resilient;
bool fdb_nh;
bool has_v4;
+
+ struct nh_res_table __rcu *res_table;
struct nh_grp_entry nh_entries[];
};
@@ -112,11 +155,15 @@ struct nexthop {
enum nexthop_event_type {
NEXTHOP_EVENT_DEL,
NEXTHOP_EVENT_REPLACE,
+ NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE,
+ NEXTHOP_EVENT_BUCKET_REPLACE,
};
enum nh_notifier_info_type {
NH_NOTIFIER_INFO_TYPE_SINGLE,
NH_NOTIFIER_INFO_TYPE_GRP,
+ NH_NOTIFIER_INFO_TYPE_RES_TABLE,
+ NH_NOTIFIER_INFO_TYPE_RES_BUCKET,
};
struct nh_notifier_single_info {
@@ -143,6 +190,19 @@ struct nh_notifier_grp_info {
struct nh_notifier_grp_entry_info nh_entries[];
};
+struct nh_notifier_res_bucket_info {
+ u16 bucket_index;
+ unsigned int idle_timer_ms;
+ bool force;
+ struct nh_notifier_single_info old_nh;
+ struct nh_notifier_single_info new_nh;
+};
+
+struct nh_notifier_res_table_info {
+ u16 num_nh_buckets;
+ struct nh_notifier_single_info nhs[];
+};
+
struct nh_notifier_info {
struct net *net;
struct netlink_ext_ack *extack;
@@ -151,6 +211,8 @@ struct nh_notifier_info {
union {
struct nh_notifier_single_info *nh;
struct nh_notifier_grp_info *nh_grp;
+ struct nh_notifier_res_table_info *nh_res_table;
+ struct nh_notifier_res_bucket_info *nh_res_bucket;
};
};
@@ -158,6 +220,10 @@ int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack);
int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb);
void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap);
+void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index,
+ bool offload, bool trap);
+void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets,
+ unsigned long *activity);
/* caller is holding rcu or rtnl; no reference taken to nexthop */
struct nexthop *nexthop_find_by_id(struct net *net, u32 id);
@@ -212,7 +278,7 @@ static inline bool nexthop_is_multipath(const struct nexthop *nh)
struct nh_group *nh_grp;
nh_grp = rcu_dereference_rtnl(nh->nh_grp);
- return nh_grp->mpath;
+ return nh_grp->is_multipath;
}
return false;
}
@@ -227,7 +293,7 @@ static inline unsigned int nexthop_num_path(const struct nexthop *nh)
struct nh_group *nh_grp;
nh_grp = rcu_dereference_rtnl(nh->nh_grp);
- if (nh_grp->mpath)
+ if (nh_grp->is_multipath)
rc = nh_grp->num_nh;
}
@@ -308,7 +374,7 @@ struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel)
struct nh_group *nh_grp;
nh_grp = rcu_dereference_rtnl(nh->nh_grp);
- if (nh_grp->mpath) {
+ if (nh_grp->is_multipath) {
nh = nexthop_mpath_select(nh_grp, nhsel);
if (!nh)
return NULL;
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 15b1b30f454e..f5c1bee0cd6a 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -188,4 +188,13 @@ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload
*offload);
void taprio_offload_free(struct tc_taprio_qopt_offload *offload);
+/* Ensure skb_mstamp_ns, which might have been populated with the txtime, is
+ * not mistaken for a software timestamp, because this will otherwise prevent
+ * the dispatch of hardware timestamps to the socket.
+ */
+static inline void skb_txtime_consumed(struct sk_buff *skb)
+{
+ skb->tstamp = ktime_set(0, 0);
+}
+
#endif
diff --git a/include/net/psample.h b/include/net/psample.h
index 68ae16bb0a4a..e328c5127757 100644
--- a/include/net/psample.h
+++ b/include/net/psample.h
@@ -14,6 +14,19 @@ struct psample_group {
struct rcu_head rcu;
};
+struct psample_metadata {
+ u32 trunc_size;
+ int in_ifindex;
+ int out_ifindex;
+ u16 out_tc;
+ u64 out_tc_occ; /* bytes */
+ u64 latency; /* nanoseconds */
+ u8 out_tc_valid:1,
+ out_tc_occ_valid:1,
+ latency_valid:1,
+ unused:5;
+};
+
struct psample_group *psample_group_get(struct net *net, u32 group_num);
void psample_group_take(struct psample_group *group);
void psample_group_put(struct psample_group *group);
@@ -21,15 +34,13 @@ void psample_group_put(struct psample_group *group);
#if IS_ENABLED(CONFIG_PSAMPLE)
void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
- u32 trunc_size, int in_ifindex, int out_ifindex,
- u32 sample_rate);
+ u32 sample_rate, const struct psample_metadata *md);
#else
static inline void psample_sample_packet(struct psample_group *group,
- struct sk_buff *skb, u32 trunc_size,
- int in_ifindex, int out_ifindex,
- u32 sample_rate)
+ struct sk_buff *skb, u32 sample_rate,
+ const struct psample_metadata *md)
{
}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 2d6eb60c58c8..f7a6e14491fb 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1242,6 +1242,20 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
+struct psched_pktrate {
+ u64 rate_pkts_ps; /* packets per second */
+ u32 mult;
+ u8 shift;
+};
+
+static inline u64 psched_pkt2t_ns(const struct psched_pktrate *r,
+ unsigned int pkt_num)
+{
+ return ((u64)pkt_num * r->mult) >> r->shift;
+}
+
+void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64);
+
/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
* The fast path only needs to access filter list and to update stats
*/
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index b7fc7d0f54e2..8c3218177136 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -68,6 +68,7 @@ enum switchdev_obj_id {
};
struct switchdev_obj {
+ struct list_head list;
struct net_device *orig_dev;
enum switchdev_obj_id id;
u32 flags;
diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h
index 6d1e26b709b5..72649512dcdd 100644
--- a/include/net/tc_act/tc_police.h
+++ b/include/net/tc_act/tc_police.h
@@ -10,10 +10,13 @@ struct tcf_police_params {
s64 tcfp_burst;
u32 tcfp_mtu;
s64 tcfp_mtu_ptoks;
+ s64 tcfp_pkt_burst;
struct psched_ratecfg rate;
bool rate_present;
struct psched_ratecfg peak;
bool peak_present;
+ struct psched_pktrate ppsrate;
+ bool pps_present;
struct rcu_head rcu;
};
@@ -24,6 +27,7 @@ struct tcf_police {
spinlock_t tcfp_lock ____cacheline_aligned_in_smp;
s64 tcfp_toks;
s64 tcfp_ptoks;
+ s64 tcfp_pkttoks;
s64 tcfp_t_c;
};
@@ -97,6 +101,54 @@ static inline u32 tcf_police_burst(const struct tc_action *act)
return burst;
}
+static inline u64 tcf_police_rate_pkt_ps(const struct tc_action *act)
+{
+ struct tcf_police *police = to_police(act);
+ struct tcf_police_params *params;
+
+ params = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
+ return params->ppsrate.rate_pkts_ps;
+}
+
+static inline u32 tcf_police_burst_pkt(const struct tc_action *act)
+{
+ struct tcf_police *police = to_police(act);
+ struct tcf_police_params *params;
+ u32 burst;
+
+ params = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
+
+ /*
+ * "rate" pkts "burst" nanoseconds
+ * ------------ * -------------------
+ * 1 second 2^6 ticks
+ *
+ * ------------------------------------
+ * NSEC_PER_SEC nanoseconds
+ * ------------------------
+ * 2^6 ticks
+ *
+ * "rate" pkts "burst" nanoseconds 2^6 ticks
+ * = ------------ * ------------------- * ------------------------
+ * 1 second 2^6 ticks NSEC_PER_SEC nanoseconds
+ *
+ * "rate" * "burst"
+ * = ---------------- pkts/nanosecond
+ * NSEC_PER_SEC^2
+ *
+ *
+ * "rate" * "burst"
+ * = ---------------- pkts/second
+ * NSEC_PER_SEC
+ */
+ burst = div_u64(params->tcfp_pkt_burst * params->ppsrate.rate_pkts_ps,
+ NSEC_PER_SEC);
+
+ return burst;
+}
+
static inline u32 tcf_police_tcfp_mtu(const struct tc_action *act)
{
struct tcf_police *police = to_police(act);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 963cd86d12dd..075de26f449d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -883,36 +883,11 @@ struct tcp_skb_cb {
struct inet6_skb_parm h6;
#endif
} header; /* For incoming skbs */
- struct {
- __u32 flags;
- struct sock *sk_redir;
- void *data_end;
- } bpf;
};
};
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
-static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
-{
- TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
-}
-
-static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb)
-{
- return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS;
-}
-
-static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb)
-{
- return TCP_SKB_CB(skb)->bpf.sk_redir;
-}
-
-static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb)
-{
- TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
-}
-
extern const struct inet_connection_sock_af_ops ipv4_specific;
#if IS_ENABLED(CONFIG_IPV6)
@@ -2222,25 +2197,27 @@ void tcp_update_ulp(struct sock *sk, struct proto *p,
__MODULE_INFO(alias, alias_userspace, name); \
__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
+#ifdef CONFIG_NET_SOCK_MSG
struct sk_msg;
struct sk_psock;
-#ifdef CONFIG_BPF_STREAM_PARSER
+#ifdef CONFIG_BPF_SYSCALL
struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
-#else
-static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
-{
-}
-#endif /* CONFIG_BPF_STREAM_PARSER */
+#endif /* CONFIG_BPF_SYSCALL */
-#ifdef CONFIG_NET_SOCK_MSG
int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
int flags);
int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
struct msghdr *msg, int len, int flags);
#endif /* CONFIG_NET_SOCK_MSG */
+#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG)
+static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+}
+#endif
+
#ifdef CONFIG_CGROUP_BPF
static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
struct sk_buff *skb,
diff --git a/include/net/udp.h b/include/net/udp.h
index a132a02b2f2c..d4d064c59232 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -515,9 +515,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
return segs;
}
-#ifdef CONFIG_BPF_STREAM_PARSER
+#ifdef CONFIG_BPF_SYSCALL
struct sk_psock;
struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
-#endif /* BPF_STREAM_PARSER */
+#endif
#endif /* _UDP_H */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index cc17bc957548..9c0722c6d7ac 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -80,19 +80,6 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
void __xsk_map_flush(void);
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
- u32 key)
-{
- struct xsk_map *m = container_of(map, struct xsk_map, map);
- struct xdp_sock *xs;
-
- if (key >= map->max_entries)
- return NULL;
-
- xs = READ_ONCE(m->xsk_map[key]);
- return xs;
-}
-
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -109,12 +96,6 @@ static inline void __xsk_map_flush(void)
{
}
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
- u32 key)
-{
- return NULL;
-}
-
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 425ff29d9389..68cdc7ceaf4d 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -51,6 +51,7 @@
*/
/* Reserve some destination PGIDs at the end of the range:
+ * PGID_BLACKHOLE: used for not forwarding the frames
* PGID_CPU: used for whitelisting certain MAC addresses, such as the addresses
* of the switch port net devices, towards the CPU port module.
* PGID_UC: the flooding destinations for unknown unicast traffic.
@@ -59,6 +60,7 @@
* PGID_MCIPV6: the flooding destinations for IPv6 multicast traffic.
* PGID_BC: the flooding destinations for broadcast traffic.
*/
+#define PGID_BLACKHOLE 57
#define PGID_CPU 58
#define PGID_UC 59
#define PGID_MC 60
@@ -73,7 +75,7 @@
#define for_each_nonreserved_multicast_dest_pgid(ocelot, pgid) \
for ((pgid) = (ocelot)->num_phys_ports + 1; \
- (pgid) < PGID_CPU; \
+ (pgid) < PGID_BLACKHOLE; \
(pgid)++)
#define for_each_aggr_pgid(ocelot, pgid) \
@@ -611,6 +613,11 @@ struct ocelot_port {
struct net_device *bond;
bool lag_tx_active;
+
+ u16 mrp_ring_id;
+
+ struct net_device *bridge;
+ u8 stp_state;
};
struct ocelot {
@@ -630,10 +637,6 @@ struct ocelot {
int num_frame_refs;
int num_mact_rows;
- struct net_device *hw_bridge_dev;
- u16 bridge_mask;
- u16 bridge_fwd_mask;
-
struct ocelot_port **ports;
u8 base_mac[ETH_ALEN];
@@ -679,12 +682,6 @@ struct ocelot {
/* Protects the PTP clock */
spinlock_t ptp_clock_lock;
struct ptp_pin_desc ptp_pins[OCELOT_PTP_PINS_NUM];
-
-#if IS_ENABLED(CONFIG_BRIDGE_MRP)
- u16 mrp_ring_id;
- struct net_device *mrp_p_port;
- struct net_device *mrp_s_port;
-#endif
};
struct ocelot_policer {
@@ -806,10 +803,10 @@ int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port,
struct switchdev_brport_flags val);
void ocelot_port_bridge_flags(struct ocelot *ocelot, int port,
struct switchdev_brport_flags val);
-int ocelot_port_bridge_join(struct ocelot *ocelot, int port,
- struct net_device *bridge);
-int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
+void ocelot_port_bridge_join(struct ocelot *ocelot, int port,
struct net_device *bridge);
+void ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
+ struct net_device *bridge);
int ocelot_fdb_dump(struct ocelot *ocelot, int port,
dsa_fdb_dump_cb_t *cb, void *data);
int ocelot_fdb_add(struct ocelot *ocelot, int port,
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 76a97176ab81..fcad3645a70b 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -86,19 +86,15 @@ struct _bpf_dtab_netdev {
};
#endif /* __DEVMAP_OBJ_TYPE */
-#define devmap_ifindex(tgt, map) \
- (((map->map_type == BPF_MAP_TYPE_DEVMAP || \
- map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
- ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
-
DECLARE_EVENT_CLASS(xdp_redirect_template,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
- const struct bpf_map *map, u32 index),
+ enum bpf_map_type map_type,
+ u32 map_id, u32 index),
- TP_ARGS(dev, xdp, tgt, err, map, index),
+ TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index),
TP_STRUCT__entry(
__field(int, prog_id)
@@ -111,14 +107,22 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
),
TP_fast_assign(
+ u32 ifindex = 0, map_index = index;
+
+ if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+ ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+ } else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
+ ifindex = index;
+ map_index = 0;
+ }
+
__entry->prog_id = xdp->aux->id;
__entry->act = XDP_REDIRECT;
__entry->ifindex = dev->ifindex;
__entry->err = err;
- __entry->to_ifindex = map ? devmap_ifindex(tgt, map) :
- index;
- __entry->map_id = map ? map->id : 0;
- __entry->map_index = map ? index : 0;
+ __entry->to_ifindex = ifindex;
+ __entry->map_id = map_id;
+ __entry->map_index = map_index;
),
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
@@ -133,45 +137,49 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
- const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, tgt, err, map, index)
+ enum bpf_map_type map_type,
+ u32 map_id, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
- const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, tgt, err, map, index)
+ enum bpf_map_type map_type,
+ u32 map_id, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
-#define _trace_xdp_redirect(dev, xdp, to) \
- trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to)
+#define _trace_xdp_redirect(dev, xdp, to) \
+ trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
-#define _trace_xdp_redirect_err(dev, xdp, to, err) \
- trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to)
+#define _trace_xdp_redirect_err(dev, xdp, to, err) \
+ trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
-#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \
- trace_xdp_redirect(dev, xdp, to, 0, map, index)
+#define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \
+ trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index)
-#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \
- trace_xdp_redirect_err(dev, xdp, to, err, map, index)
+#define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \
+ trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index)
/* not used anymore, but kept around so as not to break old programs */
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
- const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, tgt, err, map, index)
+ enum bpf_map_type map_type,
+ u32 map_id, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
- const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, tgt, err, map, index)
+ enum bpf_map_type map_type,
+ u32 map_id, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
TRACE_EVENT(xdp_cpumap_kthread,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4ba4ef0ff63a..008edc1dc8c1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -93,7 +93,717 @@ union bpf_iter_link_info {
} map;
};
-/* BPF syscall commands, see bpf(2) man-page for details. */
+/* BPF syscall commands, see bpf(2) man-page for more details. */
+/**
+ * DOC: eBPF Syscall Preamble
+ *
+ * The operation to be performed by the **bpf**\ () system call is determined
+ * by the *cmd* argument. Each operation takes an accompanying argument,
+ * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see
+ * below). The size argument is the size of the union pointed to by *attr*.
+ */
+/**
+ * DOC: eBPF Syscall Commands
+ *
+ * BPF_MAP_CREATE
+ * Description
+ * Create a map and return a file descriptor that refers to the
+ * map. The close-on-exec file descriptor flag (see **fcntl**\ (2))
+ * is automatically enabled for the new file descriptor.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_MAP_CREATE** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_LOOKUP_ELEM
+ * Description
+ * Look up an element with a given *key* in the map referred to
+ * by the file descriptor *map_fd*.
+ *
+ * The *flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_ELEM
+ * Description
+ * Create or update an element (key/value pair) in a specified map.
+ *
+ * The *flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create a new element or update an existing element.
+ * **BPF_NOEXIST**
+ * Create a new element only if it did not exist.
+ * **BPF_EXIST**
+ * Update an existing element.
+ * **BPF_F_LOCK**
+ * Update a spin_lock-ed map element.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**,
+ * **E2BIG**, **EEXIST**, or **ENOENT**.
+ *
+ * **E2BIG**
+ * The number of elements in the map reached the
+ * *max_entries* limit specified at map creation time.
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_ELEM
+ * Description
+ * Look up and delete an element by key in a specified map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_KEY
+ * Description
+ * Look up an element by key in a specified map and return the key
+ * of the next element. Can be used to iterate over all elements
+ * in the map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * The following cases can be used to iterate over all elements of
+ * the map:
+ *
+ * * If *key* is not found, the operation returns zero and sets
+ * the *next_key* pointer to the key of the first element.
+ * * If *key* is found, the operation returns zero and sets the
+ * *next_key* pointer to the key of the next element.
+ * * If *key* is the last element, returns -1 and *errno* is set
+ * to **ENOENT**.
+ *
+ * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or
+ * **EINVAL** on error.
+ *
+ * BPF_PROG_LOAD
+ * Description
+ * Verify and load an eBPF program, returning a new file
+ * descriptor associated with the program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES).
+ *
+ * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is
+ * automatically enabled for the new file descriptor.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_PIN
+ * Description
+ * Pin an eBPF program or map referred by the specified *bpf_fd*
+ * to the provided *pathname* on the filesystem.
+ *
+ * The *pathname* argument must not contain a dot (".").
+ *
+ * On success, *pathname* retains a reference to the eBPF object,
+ * preventing deallocation of the object when the original
+ * *bpf_fd* is closed. This allow the eBPF object to live beyond
+ * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent
+ * process.
+ *
+ * Applying **unlink**\ (2) or similar calls to the *pathname*
+ * unpins the object from the filesystem, removing the reference.
+ * If no other file descriptors or filesystem nodes refer to the
+ * same object, it will be deallocated (see NOTES).
+ *
+ * The filesystem type for the parent directory of *pathname* must
+ * be **BPF_FS_MAGIC**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_OBJ_GET
+ * Description
+ * Open a file descriptor for the eBPF object pinned to the
+ * specified *pathname*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_PROG_ATTACH
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook.
+ *
+ * The *attach_type* specifies the eBPF attachment point to
+ * attach the program to, and must be one of *bpf_attach_type*
+ * (see below).
+ *
+ * The *attach_bpf_fd* must be a valid file descriptor for a
+ * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap
+ * or sock_ops type corresponding to the specified *attach_type*.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_TYPE_SK_SKB**,
+ * **BPF_PROG_TYPE_SK_MSG**
+ *
+ * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_DETACH
+ * Description
+ * Detach the eBPF program associated with the *target_fd* at the
+ * hook specified by *attach_type*. The program must have been
+ * previously attached using **BPF_PROG_ATTACH**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_TEST_RUN
+ * Description
+ * Run the eBPF program associated with the *prog_fd* a *repeat*
+ * number of times against a provided program context *ctx_in* and
+ * data *data_in*, and return the modified program context
+ * *ctx_out*, *data_out* (for example, packet data), result of the
+ * execution *retval*, and *duration* of the test run.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * **ENOSPC**
+ * Either *data_size_out* or *ctx_size_out* is too small.
+ * **ENOTSUPP**
+ * This command is not supported by the program type of
+ * the program referred to by *prog_fd*.
+ *
+ * BPF_PROG_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF program currently loaded into the kernel.
+ *
+ * Looks for the eBPF program with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF programs
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF map currently loaded into the kernel.
+ *
+ * Looks for the eBPF map with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF maps
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_PROG_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF program corresponding to
+ * *prog_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF map corresponding to
+ * *map_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_GET_INFO_BY_FD
+ * Description
+ * Obtain information about the eBPF object corresponding to
+ * *bpf_fd*.
+ *
+ * Populates up to *info_len* bytes of *info*, which will be in
+ * one of the following formats depending on the eBPF object type
+ * of *bpf_fd*:
+ *
+ * * **struct bpf_prog_info**
+ * * **struct bpf_map_info**
+ * * **struct bpf_btf_info**
+ * * **struct bpf_link_info**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * specified *attach_type* hook.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_QUERY** always fetches the number of programs
+ * attached and the *attach_flags* which were used to attach those
+ * programs. Additionally, if *prog_ids* is nonzero and the number
+ * of attached programs is less than *prog_cnt*, populates
+ * *prog_ids* with the eBPF program ids of the programs attached
+ * at *target_fd*.
+ *
+ * The following flags may alter the result:
+ *
+ * **BPF_F_QUERY_EFFECTIVE**
+ * Only return information regarding programs which are
+ * currently effective at the specified *target_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_RAW_TRACEPOINT_OPEN
+ * Description
+ * Attach an eBPF program to a tracepoint *name* to access kernel
+ * internal arguments of the tracepoint in their raw form.
+ *
+ * The *prog_fd* must be a valid file descriptor associated with
+ * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**.
+ *
+ * No ABI guarantees are made about the content of tracepoint
+ * arguments exposed to the corresponding eBPF program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_LOAD
+ * Description
+ * Verify and load BPF Type Format (BTF) metadata into the kernel,
+ * returning a new file descriptor associated with the metadata.
+ * BTF is described in more detail at
+ * https://www.kernel.org/doc/html/latest/bpf/btf.html.
+ *
+ * The *btf* parameter must point to valid memory providing
+ * *btf_size* bytes of BTF binary metadata.
+ *
+ * The returned file descriptor can be passed to other **bpf**\ ()
+ * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to
+ * associate the BTF with those objects.
+ *
+ * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional
+ * parameters to specify a *btf_log_buf*, *btf_log_size* and
+ * *btf_log_level* which allow the kernel to return freeform log
+ * output regarding the BTF verification process.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the BPF Type Format (BTF)
+ * corresponding to *btf_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_TASK_FD_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * target process identified by *pid* and *fd*.
+ *
+ * If the *pid* and *fd* are associated with a tracepoint, kprobe
+ * or uprobe perf event, then the *prog_id* and *fd_type* will
+ * be populated with the eBPF program id and file descriptor type
+ * of type **bpf_task_fd_type**. If associated with a kprobe or
+ * uprobe, the *probe_offset* and *probe_addr* will also be
+ * populated. Optionally, if *buf* is provided, then up to
+ * *buf_len* bytes of *buf* will be populated with the name of
+ * the tracepoint, kprobe or uprobe.
+ *
+ * The resulting *prog_id* may be introspected in deeper detail
+ * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_ELEM
+ * Description
+ * Look up an element with the given *key* in the map referred to
+ * by the file descriptor *fd*, and if found, delete the element.
+ *
+ * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
+ * implement this command as a "pop" operation, deleting the top
+ * element rather than one corresponding to *key*.
+ * The *key* and *key_len* parameters should be zeroed when
+ * issuing this operation for these map types.
+ *
+ * This command is only valid for the following map types:
+ * * **BPF_MAP_TYPE_QUEUE**
+ * * **BPF_MAP_TYPE_STACK**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_FREEZE
+ * Description
+ * Freeze the permissions of the specified map.
+ *
+ * Write permissions may be frozen by passing zero *flags*.
+ * Upon success, no future syscall invocations may alter the
+ * map state of *map_fd*. Write operations from eBPF programs
+ * are still possible for a frozen map.
+ *
+ * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_BTF_GET_NEXT_ID
+ * Description
+ * Fetch the next BPF Type Format (BTF) object currently loaded
+ * into the kernel.
+ *
+ * Looks for the BTF object with an id greater than *start_id*
+ * and updates *next_id* on success. If no other BTF objects
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_BATCH
+ * Description
+ * Iterate and fetch multiple elements in a map.
+ *
+ * Two opaque values are used to manage batch operations,
+ * *in_batch* and *out_batch*. Initially, *in_batch* must be set
+ * to NULL to begin the batched operation. After each subsequent
+ * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
+ * *out_batch* as the *in_batch* for the next operation to
+ * continue iteration from the current point.
+ *
+ * The *keys* and *values* are output parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are copied into the
+ * user buffer, with the keys copied into *keys* and the values
+ * copied into the corresponding indices in *values*.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **ENOSPC** to indicate that *keys* or
+ * *values* is too small to dump an entire bucket during
+ * iteration of a hash-based map type.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_BATCH
+ * Description
+ * Iterate and delete all elements in a map.
+ *
+ * This operation has the same behavior as
+ * **BPF_MAP_LOOKUP_BATCH** with two exceptions:
+ *
+ * * Every element that is successfully returned is also deleted
+ * from the map. This is at least *count* elements. Note that
+ * *count* is both an input and an output parameter.
+ * * Upon returning with *errno* set to **EFAULT**, up to
+ * *count* elements may be deleted without returning the keys
+ * and values of the deleted elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_BATCH
+ * Description
+ * Update multiple elements in a map by *key*.
+ *
+ * The *keys* and *values* are input parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially updated to the
+ * value in the corresponding index in *values*. The *in_batch*
+ * and *out_batch* parameters are ignored and should be zeroed.
+ *
+ * The *elem_flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create new elements or update a existing elements.
+ * **BPF_NOEXIST**
+ * Create new elements only if they do not exist.
+ * **BPF_EXIST**
+ * Update existing elements.
+ * **BPF_F_LOCK**
+ * Update spin_lock-ed map elements. This must be
+ * specified if the map value contains a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or
+ * **E2BIG**. **E2BIG** indicates that the number of elements in
+ * the map reached the *max_entries* limit specified at map
+ * creation time.
+ *
+ * May set *errno* to one of the following error codes under
+ * specific circumstances:
+ *
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_BATCH
+ * Description
+ * Delete multiple elements in a map by *key*.
+ *
+ * The *keys* parameter is an input parameter which must point
+ * to memory large enough to hold *count* items based on the key
+ * size of the map *map_fd*, that is, *key_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially deleted. The
+ * *in_batch*, *out_batch*, and *values* parameters are ignored
+ * and should be zeroed.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements. If
+ * *errno* is **EFAULT**, up to *count* elements may be been
+ * deleted.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_CREATE
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook and return a file descriptor handle for
+ * managing the link.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_UPDATE
+ * Description
+ * Update the eBPF program in the specified *link_fd* to
+ * *new_prog_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF Link corresponding to
+ * *link_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF link currently loaded into the kernel.
+ *
+ * Looks for the eBPF link with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF links
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_ENABLE_STATS
+ * Description
+ * Enable eBPF runtime statistics gathering.
+ *
+ * Runtime statistics gathering for the eBPF runtime is disabled
+ * by default to minimize the corresponding performance overhead.
+ * This command enables statistics globally.
+ *
+ * Multiple programs may independently enable statistics.
+ * After gathering the desired statistics, eBPF runtime statistics
+ * may be disabled again by calling **close**\ (2) for the file
+ * descriptor returned by this function. Statistics will only be
+ * disabled system-wide when all outstanding file descriptors
+ * returned by prior calls for this subcommand are closed.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_ITER_CREATE
+ * Description
+ * Create an iterator on top of the specified *link_fd* (as
+ * previously created using **BPF_LINK_CREATE**) and return a
+ * file descriptor that can be used to trigger the iteration.
+ *
+ * If the resulting file descriptor is pinned to the filesystem
+ * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls
+ * for that path will trigger the iterator to read kernel state
+ * using the eBPF program attached to *link_fd*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_DETACH
+ * Description
+ * Forcefully detach the specified *link_fd* from its
+ * corresponding attachment point.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_BIND_MAP
+ * Description
+ * Bind a map to the lifetime of an eBPF program.
+ *
+ * The map identified by *map_fd* is bound to the program
+ * identified by *prog_fd* and only released when *prog_fd* is
+ * released. This may be used in cases where metadata should be
+ * associated with a program which otherwise does not contain any
+ * references to the map (for example, embedded in the eBPF
+ * program instructions).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * NOTES
+ * eBPF objects (maps and programs) can be shared between processes.
+ *
+ * * After **fork**\ (2), the child inherits file descriptors
+ * referring to the same eBPF objects.
+ * * File descriptors referring to eBPF objects can be transferred over
+ * **unix**\ (7) domain sockets.
+ * * File descriptors referring to eBPF objects can be duplicated in the
+ * usual way, using **dup**\ (2) and similar calls.
+ * * File descriptors referring to eBPF objects can be pinned to the
+ * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2).
+ *
+ * An eBPF object is deallocated only after all file descriptors referring
+ * to the object have been closed and no references remain pinned to the
+ * filesystem or attached (for example, bound to a program or device).
+ */
enum bpf_cmd {
BPF_MAP_CREATE,
BPF_MAP_LOOKUP_ELEM,
@@ -393,6 +1103,15 @@ enum bpf_link_type {
* is struct/union.
*/
#define BPF_PSEUDO_BTF_ID 3
+/* insn[0].src_reg: BPF_PSEUDO_FUNC
+ * insn[0].imm: insn offset to the func
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the function
+ * verifier type: PTR_TO_FUNC.
+ */
+#define BPF_PSEUDO_FUNC 4
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
@@ -720,7 +1439,7 @@ union bpf_attr {
* parsed and used to produce a manual page. The workflow is the following,
* and requires the rst2man utility:
*
- * $ ./scripts/bpf_helpers_doc.py \
+ * $ ./scripts/bpf_doc.py \
* --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
* $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
* $ man /tmp/bpf-helpers.7
@@ -1765,6 +2484,10 @@ union bpf_attr {
* Use with ENCAP_L3/L4 flags to further specify the tunnel
* type; *len* is the length of the inner MAC header.
*
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:
+ * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
+ * L2 type as Ethernet.
+ *
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
@@ -3915,6 +4638,34 @@ union bpf_attr {
* * **BPF_MTU_CHK_RET_FRAG_NEEDED**
* * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
*
+ * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For each element in **map**, call **callback_fn** function with
+ * **map**, **callback_ctx** and other map-specific parameters.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0.
+ *
+ * The following are a list of supported map types and their
+ * respective expected callback signatures:
+ *
+ * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH,
+ * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY
+ *
+ * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx);
+ *
+ * For per_cpu maps, the map_value is the value on the cpu where the
+ * bpf_prog is running.
+ *
+ * If **callback_fn** return 0, the helper will continue to the next
+ * element. If return value is 1, the helper will skip the rest of
+ * elements and return. Other return values are not used now.
+ *
+ * Return
+ * The number of traversed map elements for success, **-EINVAL** for
+ * invalid **flags**.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -4081,6 +4832,7 @@ union bpf_attr {
FN(ima_inode_hash), \
FN(sock_from_file), \
FN(check_mtu), \
+ FN(for_each_map_elem), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4174,6 +4926,7 @@ enum {
BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
+ BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
};
enum {
@@ -5211,7 +5964,10 @@ struct bpf_pidns_info {
/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
struct bpf_sk_lookup {
- __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+ union {
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+ __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */
+ };
__u32 family; /* Protocol family (AF_INET, AF_INET6) */
__u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 5a667107ad2c..d27b1708efe9 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -52,7 +52,7 @@ struct btf_type {
};
};
-#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f)
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
#define BTF_INFO_VLEN(info) ((info) & 0xffff)
#define BTF_INFO_KFLAG(info) ((info) >> 31)
@@ -72,7 +72,8 @@ struct btf_type {
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
#define BTF_KIND_VAR 14 /* Variable */
#define BTF_KIND_DATASEC 15 /* Section */
-#define BTF_KIND_MAX BTF_KIND_DATASEC
+#define BTF_KIND_FLOAT 16 /* Floating point */
+#define BTF_KIND_MAX BTF_KIND_FLOAT
#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
/* For some specific BTF_KIND, "struct btf_type" is immediately
diff --git a/include/uapi/linux/if_fddi.h b/include/uapi/linux/if_fddi.h
index 7239aa9c0766..8df2d9934bcd 100644
--- a/include/uapi/linux/if_fddi.h
+++ b/include/uapi/linux/if_fddi.h
@@ -9,7 +9,7 @@
* Version: @(#)if_fddi.h 1.0.3 Oct 6 2018
*
* Author: Lawrence V. Stefani, <stefani@yahoo.com>
- * Maintainer: Maciej W. Rozycki, <macro@linux-mips.org>
+ * Maintainer: Maciej W. Rozycki, <macro@orcam.me.uk>
*
* if_fddi.h is based on previous if_ether.h and if_tr.h work by
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index 2d4a1e784cf0..d8ffa8c9ca78 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -21,7 +21,10 @@ struct nexthop_grp {
};
enum {
- NEXTHOP_GRP_TYPE_MPATH, /* default type if not specified */
+ NEXTHOP_GRP_TYPE_MPATH, /* hash-threshold nexthop group
+ * default type if not specified
+ */
+ NEXTHOP_GRP_TYPE_RES, /* resilient nexthop group */
__NEXTHOP_GRP_TYPE_MAX,
};
@@ -52,8 +55,50 @@ enum {
NHA_FDB, /* flag; nexthop belongs to a bridge fdb */
/* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+ /* nested; resilient nexthop group attributes */
+ NHA_RES_GROUP,
+ /* nested; nexthop bucket attributes */
+ NHA_RES_BUCKET,
+
__NHA_MAX,
};
#define NHA_MAX (__NHA_MAX - 1)
+
+enum {
+ NHA_RES_GROUP_UNSPEC,
+ /* Pad attribute for 64-bit alignment. */
+ NHA_RES_GROUP_PAD = NHA_RES_GROUP_UNSPEC,
+
+ /* u16; number of nexthop buckets in a resilient nexthop group */
+ NHA_RES_GROUP_BUCKETS,
+ /* clock_t as u32; nexthop bucket idle timer (per-group) */
+ NHA_RES_GROUP_IDLE_TIMER,
+ /* clock_t as u32; nexthop unbalanced timer */
+ NHA_RES_GROUP_UNBALANCED_TIMER,
+ /* clock_t as u64; nexthop unbalanced time */
+ NHA_RES_GROUP_UNBALANCED_TIME,
+
+ __NHA_RES_GROUP_MAX,
+};
+
+#define NHA_RES_GROUP_MAX (__NHA_RES_GROUP_MAX - 1)
+
+enum {
+ NHA_RES_BUCKET_UNSPEC,
+ /* Pad attribute for 64-bit alignment. */
+ NHA_RES_BUCKET_PAD = NHA_RES_BUCKET_UNSPEC,
+
+ /* u16; nexthop bucket index */
+ NHA_RES_BUCKET_INDEX,
+ /* clock_t as u64; nexthop bucket idle time */
+ NHA_RES_BUCKET_IDLE_TIME,
+ /* u32; nexthop id assigned to the nexthop bucket */
+ NHA_RES_BUCKET_NH_ID,
+
+ __NHA_RES_BUCKET_MAX,
+};
+
+#define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1)
+
#endif
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 7ea59cfe1fa7..025c40fef93d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -190,6 +190,8 @@ enum {
TCA_POLICE_PAD,
TCA_POLICE_RATE64,
TCA_POLICE_PEAKRATE64,
+ TCA_POLICE_PKTRATE64,
+ TCA_POLICE_PKTBURST64,
__TCA_POLICE_MAX
#define TCA_POLICE_RESULT TCA_POLICE_RESULT
};
diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
index bff5032c98df..e585db5bf2d2 100644
--- a/include/uapi/linux/psample.h
+++ b/include/uapi/linux/psample.h
@@ -13,6 +13,13 @@ enum {
PSAMPLE_ATTR_GROUP_REFCOUNT,
PSAMPLE_ATTR_TUNNEL,
+ PSAMPLE_ATTR_PAD,
+ PSAMPLE_ATTR_OUT_TC, /* u16 */
+ PSAMPLE_ATTR_OUT_TC_OCC, /* u64, bytes */
+ PSAMPLE_ATTR_LATENCY, /* u64, nanoseconds */
+ PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */
+ PSAMPLE_ATTR_PROTO, /* u16 */
+
__PSAMPLE_ATTR_MAX
};
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 91e4ca064d61..5888492a5257 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -178,6 +178,13 @@ enum {
RTM_GETVLAN,
#define RTM_GETVLAN RTM_GETVLAN
+ RTM_NEWNEXTHOPBUCKET = 116,
+#define RTM_NEWNEXTHOPBUCKET RTM_NEWNEXTHOPBUCKET
+ RTM_DELNEXTHOPBUCKET,
+#define RTM_DELNEXTHOPBUCKET RTM_DELNEXTHOPBUCKET
+ RTM_GETNEXTHOPBUCKET,
+#define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET
+
__RTM_MAX,
#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
};
@@ -283,6 +290,7 @@ enum {
#define RTPROT_MROUTED 17 /* Multicast daemon */
#define RTPROT_KEEPALIVED 18 /* Keepalived daemon */
#define RTPROT_BABEL 42 /* Babel daemon */
+#define RTPROT_OPENR 99 /* Open Routing (Open/R) Routes */
#define RTPROT_BGP 186 /* BGP Routes */
#define RTPROT_ISIS 187 /* ISIS Routes */
#define RTPROT_OSPF 188 /* OSPF Routes */