summaryrefslogtreecommitdiffstats
path: root/tools/include/uapi/linux/bpf.h
diff options
context:
space:
mode:
Diffstat (limited to 'tools/include/uapi/linux/bpf.h')
-rw-r--r--tools/include/uapi/linux/bpf.h264
1 files changed, 253 insertions, 11 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 30f2ce76b517..db6bdc375126 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -17,7 +17,7 @@
#define BPF_ALU64 0x07 /* alu mode in double word width */
/* ld/ldx fields */
-#define BPF_DW 0x18 /* double word */
+#define BPF_DW 0x18 /* double word (64-bit) */
#define BPF_XADD 0xc0 /* exclusive add */
/* alu/jmp fields */
@@ -93,6 +93,7 @@ enum bpf_cmd {
BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
+ BPF_PROG_QUERY,
};
enum bpf_map_type {
@@ -112,6 +113,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
@@ -130,6 +132,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_XMIT,
BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_CGROUP_DEVICE,
};
enum bpf_attach_type {
@@ -139,16 +142,53 @@ enum bpf_attach_type {
BPF_CGROUP_SOCK_OPS,
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_DEVICE,
__MAX_BPF_ATTACH_TYPE
};
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ * cgrp2 (OVERRIDE prog C) ->
+ * cgrp3 (MULTI prog D) ->
+ * cgrp4 (OVERRIDE prog E) ->
+ * cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+#define BPF_F_ALLOW_MULTI (1U << 1)
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will perform strict alignment checking as if the kernel
@@ -157,8 +197,14 @@ enum bpf_attach_type {
*/
#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
#define BPF_PSEUDO_MAP_FD 1
+/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
+ * offset to another bpf function
+ */
+#define BPF_PSEUDO_CALL 1
+
/* flags for BPF_MAP_UPDATE_ELEM command */
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
@@ -176,6 +222,15 @@ enum bpf_attach_type {
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE (1U << 2)
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY (1U << 3)
+#define BPF_F_WRONLY (1U << 4)
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
@@ -189,6 +244,8 @@ union bpf_attr {
__u32 numa_node; /* numa node (effective only if
* BPF_F_NUMA_NODE is set).
*/
+ char map_name[BPF_OBJ_NAME_LEN];
+ __u32 map_ifindex; /* ifindex of netdev to create on */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -211,11 +268,14 @@ union bpf_attr {
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
__u32 prog_flags;
+ char prog_name[BPF_OBJ_NAME_LEN];
+ __u32 prog_ifindex; /* ifindex of netdev to prep for */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
+ __u32 file_flags;
};
struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -243,6 +303,7 @@ union bpf_attr {
__u32 map_id;
};
__u32 next_id;
+ __u32 open_flags;
};
struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -250,6 +311,15 @@ union bpf_attr {
__u32 info_len;
__aligned_u64 info;
} info;
+
+ struct { /* anonymous struct used by BPF_PROG_QUERY command */
+ __u32 target_fd; /* container object to query */
+ __u32 attach_type;
+ __u32 query_flags;
+ __u32 attach_flags;
+ __aligned_u64 prog_ids;
+ __u32 prog_cnt;
+ } query;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -554,14 +624,32 @@ union bpf_attr {
* int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
* Calls setsockopt. Not all opts are available, only those with
* integer optvals plus TCP_CONGESTION.
- * Supported levels: SOL_SOCKET and IPROTO_TCP
+ * Supported levels: SOL_SOCKET and IPPROTO_TCP
+ * @bpf_socket: pointer to bpf_socket
+ * @level: SOL_SOCKET or IPPROTO_TCP
+ * @optname: option name
+ * @optval: pointer to option value
+ * @optlen: length of optval in bytes
+ * Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ * Calls getsockopt. Not all opts are available.
+ * Supported levels: IPPROTO_TCP
* @bpf_socket: pointer to bpf_socket
- * @level: SOL_SOCKET or IPROTO_TCP
+ * @level: IPPROTO_TCP
* @optname: option name
* @optval: pointer to option value
- * @optlen: length of optval in byes
+ * @optlen: length of optval in bytes
* Return: 0 or negative error
*
+ * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
+ * Set callback flags for sock_ops
+ * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
+ * @flags: flags value
+ * Return: 0 for no error
+ * -EINVAL if there is no full tcp socket
+ * bits in flags that are not supported by current kernel
+ *
* int bpf_skb_adjust_room(skb, len_diff, mode, flags)
* Grow or shrink room in sk_buff.
* @skb: pointer to skb
@@ -583,6 +671,31 @@ union bpf_attr {
* @map: pointer to sockmap to update
* @key: key to insert/update sock in map
* @flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ * Adjust the xdp_md.data_meta by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data_meta
+ * Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ * read perf event counter value and perf event enabled/running time
+ * @map: pointer to perf_event_array map
+ * @flags: index of event in the map or bitmask flags
+ * @buf: buf to fill
+ * @buf_size: size of the buf
+ * Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ * read perf prog attached perf event counter and enabled/running time
+ * @ctx: pointer to ctx
+ * @buf: buf to fill
+ * @buf_size: size of the buf
+ * Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ * @pt_regs: pointer to struct pt_regs
+ * @rc: the return value to set
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -639,6 +752,12 @@ union bpf_attr {
FN(redirect_map), \
FN(sk_redirect_map), \
FN(sock_map_update), \
+ FN(xdp_adjust_meta), \
+ FN(perf_event_read_value), \
+ FN(perf_prog_read_value), \
+ FN(getsockopt), \
+ FN(override_return), \
+ FN(sock_ops_cb_flags_set),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -682,7 +801,9 @@ enum bpf_func_id {
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
#define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
/* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -716,7 +837,7 @@ struct __sk_buff {
__u32 data_end;
__u32 napi_id;
- /* accessed by BPF_PROG_TYPE_sk_skb types */
+ /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
__u32 local_ip4; /* Stored in network byte order */
@@ -724,6 +845,9 @@ struct __sk_buff {
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ /* ... here. */
+
+ __u32 data_meta;
};
struct bpf_tunnel_key {
@@ -784,6 +908,10 @@ enum xdp_action {
struct xdp_md {
__u32 data;
__u32 data_end;
+ __u32 data_meta;
+ /* Below access go through struct xdp_rxq_info */
+ __u32 ingress_ifindex; /* rxq->dev->ifindex */
+ __u32 rx_queue_index; /* rxq->queue_index */
};
enum sk_action {
@@ -801,6 +929,14 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
+ __u64 load_time; /* ns since boottime */
+ __u32 created_by_uid;
+ __u32 nr_map_ids;
+ __aligned_u64 map_ids;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u64 netns_dev;
+ __u64 netns_ino;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -810,6 +946,10 @@ struct bpf_map_info {
__u32 value_size;
__u32 max_entries;
__u32 map_flags;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u64 netns_dev;
+ __u64 netns_ino;
} __attribute__((aligned(8)));
/* User bpf_sock_ops struct to access socket values and specify request ops
@@ -821,8 +961,9 @@ struct bpf_map_info {
struct bpf_sock_ops {
__u32 op;
union {
- __u32 reply;
- __u32 replylong[4];
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
};
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
@@ -831,8 +972,45 @@ struct bpf_sock_ops {
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u32 lost_out;
+ __u32 sacked_out;
+ __u32 sk_txhash;
+ __u64 bytes_received;
+ __u64 bytes_acked;
};
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently
+ * supported cb flags
+ */
+
/* List of known BPF sock_ops operators.
* New entries can only be added at the end
*/
@@ -859,9 +1037,73 @@ enum {
BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control
* needs ECN
*/
+ BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is
+ * based on the path and may be
+ * dependent on the congestion control
+ * algorithm. In general it indicates
+ * a congestion threshold. RTTs above
+ * this indicate congestion
+ */
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ * Arg3: return value of
+ * tcp_transmit_skb (0 => success)
+ */
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
+struct bpf_perf_event_value {
+ __u64 counter;
+ __u64 enabled;
+ __u64 running;
+};
+
+#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
+#define BPF_DEVCG_ACC_READ (1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE (1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK (1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
+ __u32 major;
+ __u32 minor;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
OpenPOWER on IntegriCloud