Commit 5054de51 authored by 4ast's avatar 4ast Committed by GitHub

Merge pull request #1389 from iovisor/yhs_dev

sync src/cc/compat/linux headers with latest net-next
parents 0e8c031b 044263b4
...@@ -30,9 +30,14 @@ ...@@ -30,9 +30,14 @@
#define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_LE BPF_TO_LE
#define BPF_FROM_BE BPF_TO_BE #define BPF_FROM_BE BPF_TO_BE
/* jmp encodings */
#define BPF_JNE 0x50 /* jump != */ #define BPF_JNE 0x50 /* jump != */
#define BPF_JLT 0xa0 /* LT is unsigned, '<' */
#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */
#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
#define BPF_CALL 0x80 /* function call */ #define BPF_CALL 0x80 /* function call */
#define BPF_EXIT 0x90 /* function return */ #define BPF_EXIT 0x90 /* function return */
...@@ -87,6 +92,7 @@ enum bpf_cmd { ...@@ -87,6 +92,7 @@ enum bpf_cmd {
BPF_PROG_GET_FD_BY_ID, BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD, BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
}; };
enum bpf_map_type { enum bpf_map_type {
...@@ -104,6 +110,8 @@ enum bpf_map_type { ...@@ -104,6 +110,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_LPM_TRIE,
BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY_OF_MAPS,
BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
}; };
enum bpf_prog_type { enum bpf_prog_type {
...@@ -121,6 +129,7 @@ enum bpf_prog_type { ...@@ -121,6 +129,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_OUT,
BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_LWT_XMIT,
BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
}; };
enum bpf_attach_type { enum bpf_attach_type {
...@@ -128,16 +137,54 @@ enum bpf_attach_type { ...@@ -128,16 +137,54 @@ enum bpf_attach_type {
BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_EGRESS,
BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_SOCK_OPS, BPF_CGROUP_SOCK_OPS,
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
__MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
}; };
#define MAX_BPF_ATTACH_TYPE __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 /* cgroup-bpf attach flags 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 * 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_OVERRIDE (1U << 0)
#define BPF_F_ALLOW_MULTI (1U << 1)
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will perform strict alignment checking as if the kernel * verifier will perform strict alignment checking as if the kernel
...@@ -153,6 +200,7 @@ enum bpf_attach_type { ...@@ -153,6 +200,7 @@ enum bpf_attach_type {
#define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */ #define BPF_EXIST 2 /* update existing element */
/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0) #define BPF_F_NO_PREALLOC (1U << 0)
/* Instead of having one common LRU list in the /* Instead of having one common LRU list in the
* BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
...@@ -161,6 +209,13 @@ enum bpf_attach_type { ...@@ -161,6 +209,13 @@ enum bpf_attach_type {
* across different LRU lists. * across different LRU lists.
*/ */
#define BPF_F_NO_COMMON_LRU (1U << 1) #define BPF_F_NO_COMMON_LRU (1U << 1)
/* 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
union bpf_attr { union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */ struct { /* anonymous struct used by BPF_MAP_CREATE command */
...@@ -168,8 +223,14 @@ union bpf_attr { ...@@ -168,8 +223,14 @@ union bpf_attr {
__u32 key_size; /* size of key in bytes */ __u32 key_size; /* size of key in bytes */
__u32 value_size; /* size of value in bytes */ __u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */ __u32 max_entries; /* max number of entries in a map */
__u32 map_flags; /* prealloc or not */ __u32 map_flags; /* BPF_MAP_CREATE related
* flags defined above.
*/
__u32 inner_map_fd; /* fd pointing to the inner map */ __u32 inner_map_fd; /* fd pointing to the inner map */
__u32 numa_node; /* numa node (effective only if
* BPF_F_NUMA_NODE is set).
*/
char map_name[BPF_OBJ_NAME_LEN];
}; };
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
...@@ -192,6 +253,7 @@ union bpf_attr { ...@@ -192,6 +253,7 @@ union bpf_attr {
__aligned_u64 log_buf; /* user supplied buffer */ __aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */ __u32 kern_version; /* checked when prog_type=kprobe */
__u32 prog_flags; __u32 prog_flags;
char prog_name[BPF_OBJ_NAME_LEN];
}; };
struct { /* anonymous struct used by BPF_OBJ_* commands */ struct { /* anonymous struct used by BPF_OBJ_* commands */
...@@ -231,6 +293,15 @@ union bpf_attr { ...@@ -231,6 +293,15 @@ union bpf_attr {
__u32 info_len; __u32 info_len;
__aligned_u64 info; __aligned_u64 info;
} 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))); } __attribute__((aligned(8)));
/* BPF helper function descriptions: /* BPF helper function descriptions:
...@@ -294,7 +365,7 @@ union bpf_attr { ...@@ -294,7 +365,7 @@ union bpf_attr {
* jump into another BPF program * jump into another BPF program
* @ctx: context pointer passed to next program * @ctx: context pointer passed to next program
* @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
* @index: index inside array that selects specific program to run * @index: 32-bit index inside array that selects specific program to run
* Return: 0 on success or negative error * Return: 0 on success or negative error
* *
* int bpf_clone_redirect(skb, ifindex, flags) * int bpf_clone_redirect(skb, ifindex, flags)
...@@ -344,9 +415,21 @@ union bpf_attr { ...@@ -344,9 +415,21 @@ union bpf_attr {
* int bpf_redirect(ifindex, flags) * int bpf_redirect(ifindex, flags)
* redirect to another netdev * redirect to another netdev
* @ifindex: ifindex of the net device * @ifindex: ifindex of the net device
* @flags: bit 0 - if set, redirect to ingress instead of egress * @flags:
* cls_bpf:
* bit 0 - if set, redirect to ingress instead of egress
* other bits - reserved * other bits - reserved
* Return: TC_ACT_REDIRECT * xdp_bpf:
* all bits - reserved
* Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
* xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
*
* int bpf_redirect_map(map, key, flags)
* redirect to endpoint in map
* @map: pointer to dev map
* @key: index in map to lookup
* @flags: --
* Return: XDP_REDIRECT on success or XDP_ABORT on error
* *
* u32 bpf_get_route_realm(skb) * u32 bpf_get_route_realm(skb)
* retrieve a dst's tclassid * retrieve a dst's tclassid
...@@ -539,6 +622,41 @@ union bpf_attr { ...@@ -539,6 +622,41 @@ union bpf_attr {
* @mode: operation mode (enum bpf_adj_room_mode) * @mode: operation mode (enum bpf_adj_room_mode)
* @flags: reserved for future use * @flags: reserved for future use
* Return: 0 on success or negative error code * Return: 0 on success or negative error code
*
* int bpf_sk_redirect_map(map, key, flags)
* Redirect skb to a sock in map using key as a lookup key for the
* sock in map.
* @map: pointer to sockmap
* @key: key to lookup sock in map
* @flags: reserved for future use
* Return: SK_REDIRECT
*
* int bpf_sock_map_update(skops, map, key, flags)
* @skops: pointer to bpf_sock_ops
* @map: pointer to sockmap to update
* @key: key to insert/update sock in map
* @flags: same flags as map update elem
*
* int bpf_xdp_adjust_meta(xdp_md, delta)
* Adjust the xdp_md.data_meta by delta
* @xdp_md: pointer to xdp_md
* @delta: An positive/negative integer to be added to xdp_md.data_meta
* Return: 0 on success or negative on error
*
* int bpf_perf_event_read_value(map, flags, buf, buf_size)
* read perf event counter value and perf event enabled/running time
* @map: pointer to perf_event_array map
* @flags: index of event in the map or bitmask flags
* @buf: buf to fill
* @buf_size: size of the buf
* Return: 0 on success or negative error code
*
* int bpf_perf_prog_read_value(ctx, buf, buf_size)
* read perf prog attached perf event counter and enabled/running time
* @ctx: pointer to ctx
* @buf: buf to fill
* @buf_size: size of the buf
* Return : 0 on success or negative error code
*/ */
#define __BPF_FUNC_MAPPER(FN) \ #define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \ FN(unspec), \
...@@ -591,7 +709,13 @@ union bpf_attr { ...@@ -591,7 +709,13 @@ union bpf_attr {
FN(get_socket_uid), \ FN(get_socket_uid), \
FN(set_hash), \ FN(set_hash), \
FN(setsockopt), \ FN(setsockopt), \
FN(skb_adjust_room), FN(skb_adjust_room), \
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),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper /* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call * function eBPF program intends to call
...@@ -635,7 +759,9 @@ enum bpf_func_id { ...@@ -635,7 +759,9 @@ enum bpf_func_id {
#define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2) #define BPF_F_DONT_FRAGMENT (1ULL << 2)
/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ /* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
*/
#define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
/* BPF_FUNC_perf_event_output for sk_buff input context. */ /* BPF_FUNC_perf_event_output for sk_buff input context. */
...@@ -668,6 +794,18 @@ struct __sk_buff { ...@@ -668,6 +794,18 @@ struct __sk_buff {
__u32 data; __u32 data;
__u32 data_end; __u32 data_end;
__u32 napi_id; __u32 napi_id;
/* 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 */
__u32 remote_ip6[4]; /* Stored in network byte order */
__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 { struct bpf_tunnel_key {
...@@ -703,20 +841,23 @@ struct bpf_sock { ...@@ -703,20 +841,23 @@ struct bpf_sock {
__u32 family; __u32 family;
__u32 type; __u32 type;
__u32 protocol; __u32 protocol;
__u32 mark;
__u32 priority;
}; };
#define XDP_PACKET_HEADROOM 256 #define XDP_PACKET_HEADROOM 256
/* User return codes for XDP prog type. /* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other * A valid XDP program must return one of these defined values. All other
* return codes are reserved for future use. Unknown return codes will result * return codes are reserved for future use. Unknown return codes will
* in packet drop. * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
*/ */
enum xdp_action { enum xdp_action {
XDP_ABORTED = 0, XDP_ABORTED = 0,
XDP_DROP, XDP_DROP,
XDP_PASS, XDP_PASS,
XDP_TX, XDP_TX,
XDP_REDIRECT,
}; };
/* user accessible metadata for XDP packet hook /* user accessible metadata for XDP packet hook
...@@ -725,6 +866,13 @@ enum xdp_action { ...@@ -725,6 +866,13 @@ enum xdp_action {
struct xdp_md { struct xdp_md {
__u32 data; __u32 data;
__u32 data_end; __u32 data_end;
__u32 data_meta;
};
enum sk_action {
SK_ABORTED = 0,
SK_DROP,
SK_REDIRECT,
}; };
#define BPF_TAG_SIZE 8 #define BPF_TAG_SIZE 8
...@@ -737,6 +885,11 @@ struct bpf_prog_info { ...@@ -737,6 +885,11 @@ struct bpf_prog_info {
__u32 xlated_prog_len; __u32 xlated_prog_len;
__aligned_u64 jited_prog_insns; __aligned_u64 jited_prog_insns;
__aligned_u64 xlated_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];
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
struct bpf_map_info { struct bpf_map_info {
...@@ -746,6 +899,7 @@ struct bpf_map_info { ...@@ -746,6 +899,7 @@ struct bpf_map_info {
__u32 value_size; __u32 value_size;
__u32 max_entries; __u32 max_entries;
__u32 map_flags; __u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
/* User bpf_sock_ops struct to access socket values and specify request ops /* User bpf_sock_ops struct to access socket values and specify request ops
...@@ -800,4 +954,10 @@ enum { ...@@ -800,4 +954,10 @@ enum {
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
struct bpf_perf_event_value {
__u64 counter;
__u64 enabled;
__u64 running;
};
#endif /* _UAPI__LINUX_BPF_H__ */ #endif /* _UAPI__LINUX_BPF_H__ */
...@@ -31,9 +31,14 @@ R"********( ...@@ -31,9 +31,14 @@ R"********(
#define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_LE BPF_TO_LE
#define BPF_FROM_BE BPF_TO_BE #define BPF_FROM_BE BPF_TO_BE
/* jmp encodings */
#define BPF_JNE 0x50 /* jump != */ #define BPF_JNE 0x50 /* jump != */
#define BPF_JLT 0xa0 /* LT is unsigned, '<' */
#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */
#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
#define BPF_CALL 0x80 /* function call */ #define BPF_CALL 0x80 /* function call */
#define BPF_EXIT 0x90 /* function return */ #define BPF_EXIT 0x90 /* function return */
...@@ -88,6 +93,7 @@ enum bpf_cmd { ...@@ -88,6 +93,7 @@ enum bpf_cmd {
BPF_PROG_GET_FD_BY_ID, BPF_PROG_GET_FD_BY_ID,
BPF_MAP_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD, BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
}; };
enum bpf_map_type { enum bpf_map_type {
...@@ -105,6 +111,8 @@ enum bpf_map_type { ...@@ -105,6 +111,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_LPM_TRIE,
BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY_OF_MAPS,
BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
}; };
enum bpf_prog_type { enum bpf_prog_type {
...@@ -122,6 +130,7 @@ enum bpf_prog_type { ...@@ -122,6 +130,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_OUT,
BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_LWT_XMIT,
BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
}; };
enum bpf_attach_type { enum bpf_attach_type {
...@@ -129,16 +138,54 @@ enum bpf_attach_type { ...@@ -129,16 +138,54 @@ enum bpf_attach_type {
BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_EGRESS,
BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_SOCK_OPS, BPF_CGROUP_SOCK_OPS,
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
__MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
}; };
#define MAX_BPF_ATTACH_TYPE __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 /* cgroup-bpf attach flags 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 * 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_OVERRIDE (1U << 0)
#define BPF_F_ALLOW_MULTI (1U << 1)
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will perform strict alignment checking as if the kernel * verifier will perform strict alignment checking as if the kernel
...@@ -162,6 +209,13 @@ enum bpf_attach_type { ...@@ -162,6 +209,13 @@ enum bpf_attach_type {
* across different LRU lists. * across different LRU lists.
*/ */
#define BPF_F_NO_COMMON_LRU (1U << 1) #define BPF_F_NO_COMMON_LRU (1U << 1)
/* 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
union bpf_attr { union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */ struct { /* anonymous struct used by BPF_MAP_CREATE command */
...@@ -169,8 +223,14 @@ union bpf_attr { ...@@ -169,8 +223,14 @@ union bpf_attr {
__u32 key_size; /* size of key in bytes */ __u32 key_size; /* size of key in bytes */
__u32 value_size; /* size of value in bytes */ __u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */ __u32 max_entries; /* max number of entries in a map */
__u32 map_flags; /* prealloc or not */ __u32 map_flags; /* BPF_MAP_CREATE related
* flags defined above.
*/
__u32 inner_map_fd; /* fd pointing to the inner map */ __u32 inner_map_fd; /* fd pointing to the inner map */
__u32 numa_node; /* numa node (effective only if
* BPF_F_NUMA_NODE is set).
*/
char map_name[BPF_OBJ_NAME_LEN];
}; };
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
...@@ -193,6 +253,7 @@ union bpf_attr { ...@@ -193,6 +253,7 @@ union bpf_attr {
__aligned_u64 log_buf; /* user supplied buffer */ __aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */ __u32 kern_version; /* checked when prog_type=kprobe */
__u32 prog_flags; __u32 prog_flags;
char prog_name[BPF_OBJ_NAME_LEN];
}; };
struct { /* anonymous struct used by BPF_OBJ_* commands */ struct { /* anonymous struct used by BPF_OBJ_* commands */
...@@ -232,6 +293,15 @@ union bpf_attr { ...@@ -232,6 +293,15 @@ union bpf_attr {
__u32 info_len; __u32 info_len;
__aligned_u64 info; __aligned_u64 info;
} 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))); } __attribute__((aligned(8)));
/* BPF helper function descriptions: /* BPF helper function descriptions:
...@@ -295,7 +365,7 @@ union bpf_attr { ...@@ -295,7 +365,7 @@ union bpf_attr {
* jump into another BPF program * jump into another BPF program
* @ctx: context pointer passed to next program * @ctx: context pointer passed to next program
* @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
* @index: index inside array that selects specific program to run * @index: 32-bit index inside array that selects specific program to run
* Return: 0 on success or negative error * Return: 0 on success or negative error
* *
* int bpf_clone_redirect(skb, ifindex, flags) * int bpf_clone_redirect(skb, ifindex, flags)
...@@ -345,9 +415,20 @@ union bpf_attr { ...@@ -345,9 +415,20 @@ union bpf_attr {
* int bpf_redirect(ifindex, flags) * int bpf_redirect(ifindex, flags)
* redirect to another netdev * redirect to another netdev
* @ifindex: ifindex of the net device * @ifindex: ifindex of the net device
* @flags: bit 0 - if set, redirect to ingress instead of egress * @flags:
* cls_bpf:
* bit 0 - if set, redirect to ingress instead of egress
* other bits - reserved * other bits - reserved
* Return: TC_ACT_REDIRECT * xdp_bpf:
* all bits - reserved
* Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
* xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
* int bpf_redirect_map(map, key, flags)
* redirect to endpoint in map
* @map: pointer to dev map
* @key: index in map to lookup
* @flags: --
* Return: XDP_REDIRECT on success or XDP_ABORT on error
* *
* u32 bpf_get_route_realm(skb) * u32 bpf_get_route_realm(skb)
* retrieve a dst's tclassid * retrieve a dst's tclassid
...@@ -540,6 +621,41 @@ union bpf_attr { ...@@ -540,6 +621,41 @@ union bpf_attr {
* @mode: operation mode (enum bpf_adj_room_mode) * @mode: operation mode (enum bpf_adj_room_mode)
* @flags: reserved for future use * @flags: reserved for future use
* Return: 0 on success or negative error code * Return: 0 on success or negative error code
*
* int bpf_sk_redirect_map(map, key, flags)
* Redirect skb to a sock in map using key as a lookup key for the
* sock in map.
* @map: pointer to sockmap
* @key: key to lookup sock in map
* @flags: reserved for future use
* Return: SK_REDIRECT
*
* int bpf_sock_map_update(skops, map, key, flags)
* @skops: pointer to bpf_sock_ops
* @map: pointer to sockmap to update
* @key: key to insert/update sock in map
* @flags: same flags as map update elem
*
* int bpf_xdp_adjust_meta(xdp_md, delta)
* Adjust the xdp_md.data_meta by delta
* @xdp_md: pointer to xdp_md
* @delta: An positive/negative integer to be added to xdp_md.data_meta
* Return: 0 on success or negative on error
*
* int bpf_perf_event_read_value(map, flags, buf, buf_size)
* read perf event counter value and perf event enabled/running time
* @map: pointer to perf_event_array map
* @flags: index of event in the map or bitmask flags
* @buf: buf to fill
* @buf_size: size of the buf
* Return: 0 on success or negative error code
*
* int bpf_perf_prog_read_value(ctx, buf, buf_size)
* read perf prog attached perf event counter and enabled/running time
* @ctx: pointer to ctx
* @buf: buf to fill
* @buf_size: size of the buf
* Return : 0 on success or negative error code
*/ */
#define __BPF_FUNC_MAPPER(FN) \ #define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \ FN(unspec), \
...@@ -592,7 +708,13 @@ union bpf_attr { ...@@ -592,7 +708,13 @@ union bpf_attr {
FN(get_socket_uid), \ FN(get_socket_uid), \
FN(set_hash), \ FN(set_hash), \
FN(setsockopt), \ FN(setsockopt), \
FN(skb_adjust_room), FN(skb_adjust_room), \
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),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper /* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call * function eBPF program intends to call
...@@ -636,7 +758,9 @@ enum bpf_func_id { ...@@ -636,7 +758,9 @@ enum bpf_func_id {
#define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2) #define BPF_F_DONT_FRAGMENT (1ULL << 2)
/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ /* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
*/
#define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
/* BPF_FUNC_perf_event_output for sk_buff input context. */ /* BPF_FUNC_perf_event_output for sk_buff input context. */
...@@ -669,6 +793,18 @@ struct __sk_buff { ...@@ -669,6 +793,18 @@ struct __sk_buff {
__u32 data; __u32 data;
__u32 data_end; __u32 data_end;
__u32 napi_id; __u32 napi_id;
/* 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 */
__u32 remote_ip6[4]; /* Stored in network byte order */
__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 { struct bpf_tunnel_key {
...@@ -704,20 +840,23 @@ struct bpf_sock { ...@@ -704,20 +840,23 @@ struct bpf_sock {
__u32 family; __u32 family;
__u32 type; __u32 type;
__u32 protocol; __u32 protocol;
__u32 mark;
__u32 priority;
}; };
#define XDP_PACKET_HEADROOM 256 #define XDP_PACKET_HEADROOM 256
/* User return codes for XDP prog type. /* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other * A valid XDP program must return one of these defined values. All other
* return codes are reserved for future use. Unknown return codes will result * return codes are reserved for future use. Unknown return codes will
* in packet drop. * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
*/ */
enum xdp_action { enum xdp_action {
XDP_ABORTED = 0, XDP_ABORTED = 0,
XDP_DROP, XDP_DROP,
XDP_PASS, XDP_PASS,
XDP_TX, XDP_TX,
XDP_REDIRECT,
}; };
/* user accessible metadata for XDP packet hook /* user accessible metadata for XDP packet hook
...@@ -726,6 +865,13 @@ enum xdp_action { ...@@ -726,6 +865,13 @@ enum xdp_action {
struct xdp_md { struct xdp_md {
__u32 data; __u32 data;
__u32 data_end; __u32 data_end;
__u32 data_meta;
};
enum sk_action {
SK_ABORTED = 0,
SK_DROP,
SK_REDIRECT,
}; };
#define BPF_TAG_SIZE 8 #define BPF_TAG_SIZE 8
...@@ -738,6 +884,11 @@ struct bpf_prog_info { ...@@ -738,6 +884,11 @@ struct bpf_prog_info {
__u32 xlated_prog_len; __u32 xlated_prog_len;
__aligned_u64 jited_prog_insns; __aligned_u64 jited_prog_insns;
__aligned_u64 xlated_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];
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
struct bpf_map_info { struct bpf_map_info {
...@@ -747,6 +898,7 @@ struct bpf_map_info { ...@@ -747,6 +898,7 @@ struct bpf_map_info {
__u32 value_size; __u32 value_size;
__u32 max_entries; __u32 max_entries;
__u32 map_flags; __u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
/* User bpf_sock_ops struct to access socket values and specify request ops /* User bpf_sock_ops struct to access socket values and specify request ops
...@@ -801,5 +953,11 @@ enum { ...@@ -801,5 +953,11 @@ enum {
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
struct bpf_perf_event_value {
__u64 counter;
__u64 enabled;
__u64 running;
};
#endif /* _UAPI__LINUX_BPF_H__ */ #endif /* _UAPI__LINUX_BPF_H__ */
)********" )********"
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment