Skip to content

Commit

Permalink
sync header to latest net-next (iovisor#1932)
Browse files Browse the repository at this point in the history 
all program types, map types and helpers are added based on latest net-next.

Signed-off-by: Yonghong Song <[email protected]>
  • Loading branch information
@yonghong-song
yonghong-song committed Aug 17, 2018
1 parent 36ce112 commit 3835b2d
Show file tree
Hide file tree
Showing 6 changed files with 322 additions and 22 deletions.
8 changes: 8 additions & 0 deletions docs/kernel-versions.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,8 @@ Socket references (array) | 4.14 | [`174a79ff9515`](https://git.kernel.org/cgit/
CPU references | 4.15 | [`6710e1126934`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=6710e1126934d8b4372b4d2f9ae1646cd3f151bf)
AF_XDP socket (XSK) references | 4.18 | [`fbfc504a24f5`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=fbfc504a24f53f7ebe128ab55cb5dba634f4ece8)
Socket references (hashmap) | 4.18 | [`81110384441a`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=81110384441a59cff47430f20f049e69b98c17f4)
cgroup storage | 4.19 | [`de9cbbaadba5`](https://github.com/torvalds/linux/commit/de9cbbaadba5adf88a19e46df61f7054000838f6)
reuseport sockarray | 4.19 | [`5dc4c4b7d4e8`](https://github.com/torvalds/linux/commit/5dc4c4b7d4e8115e7cde96a030f98cb3ab2e458c)

## XDP

Expand Down Expand Up @@ -150,11 +152,13 @@ Helper | Kernel version | License | Commit |
`BPF_FUNC_current_task_under_cgroup()` | 4.9 | | [`60d20f9195b2`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=60d20f9195b260bdf0ac10c275ae9f6016f9c069)
`BPF_FUNC_fib_lookup()` | 4.18 | GPL | [`87f5fc7e48dd`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=87f5fc7e48dd3175b30dd03b41564e1a8e136323)
`BPF_FUNC_get_cgroup_classid()` | 4.3 | | [`8d20aabe1c76`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=8d20aabe1c76cccac544d9fcc3ad7823d9e98a2d)
`BPF_FUNC_get_current_cgroup_id()` | 4.18 | | [`bf6fa2c893c5`](https://github.com/torvalds/linux/commit/bf6fa2c893c5237b48569a13fa3c673041430b6c)
`BPF_FUNC_get_current_comm()` | 4.2 | | [`ffeedafbf023`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=ffeedafbf0236f03aeb2e8db273b3e5ae5f5bc89)
`BPF_FUNC_get_current_pid_tgid()` | 4.2 | | [`ffeedafbf023`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=ffeedafbf0236f03aeb2e8db273b3e5ae5f5bc89)
`BPF_FUNC_get_current_task()` | 4.8 | GPL | [`606274c5abd8`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=606274c5abd8e245add01bc7145a8cbb92b69ba8)
`BPF_FUNC_get_current_uid_gid()` | 4.2 | | [`ffeedafbf023`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=ffeedafbf0236f03aeb2e8db273b3e5ae5f5bc89)
`BPF_FUNC_get_hash_recalc()` | 4.8 | | [`13c5c240f789`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=13c5c240f789bbd2bcacb14a23771491485ae61f)
`BPF_FUNC_get_local_storage()` | 4.19 | | [`cd3394317653`](https://github.com/torvalds/linux/commit/cd3394317653837e2eb5c5d0904a8996102af9fc)
`BPF_FUNC_get_numa_node_id()` | 4.10 | | [`2d0e30c30f84`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=2d0e30c30f84d08dc16f0f2af41f1b8a85f0755e)
`BPF_FUNC_get_prandom_u32()` | 4.1 | | [`03e69b508b6f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=03e69b508b6f7c51743055c9f61d1dfeadf4b635)
`BPF_FUNC_get_route_realm()` | 4.4 | | [`c46646d0484f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=c46646d0484f5d08e2bede9b45034ba5b8b489cc)
Expand Down Expand Up @@ -195,11 +199,14 @@ Helper | Kernel version | License | Commit |
`BPF_FUNC_setsockopt()` | 4.13 | | [`8c4b4c7e9ff0`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=8c4b4c7e9ff0447995750d9329949fa082520269)
`BPF_FUNC_sk_redirect_hash()` | 4.18 | | [`81110384441a`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=81110384441a59cff47430f20f049e69b98c17f4)
`BPF_FUNC_sk_redirect_map()` | 4.14 | | [`174a79ff9515`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=174a79ff9515f400b9a6115643dafd62a635b7e6)
`BPF_FUNC_sk_select_reuseport()` | 4.19 | | [`2dbb9b9e6df6`](https://github.com/torvalds/linux/commit/2dbb9b9e6df67d444fbe425c7f6014858d337adf)
`BPF_FUNC_skb_adjust_room()` | 4.13 | | [`2be7e212d541`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=2be7e212d5419a400d051c84ca9fdd083e5aacac)
`BPF_FUNC_skb_ancestor_cgroup_id()` | 4.19 | | [`7723628101aa`](https://github.com/torvalds/linux/commit/7723628101aaeb1d723786747529b4ea65c5b5c5)
`BPF_FUNC_skb_change_head()` | 4.10 | | [`3a0af8fd61f9`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=3a0af8fd61f90920f6fa04e4f1e9a6a73c1b4fd2)
`BPF_FUNC_skb_change_proto()` | 4.8 | | [`6578171a7ff0`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=6578171a7ff0c31dc73258f93da7407510abf085)
`BPF_FUNC_skb_change_tail()` | 4.9 | | [`5293efe62df8`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=5293efe62df81908f2e90c9820c7edcc8e61f5e9)
`BPF_FUNC_skb_change_type()` | 4.8 | | [`d2485c4242a8`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d2485c4242a826fdf493fd3a27b8b792965b9b9e)
`BPF_FUNC_skb_cgroup_id()` | 4.18 | | [`cb20b08ead40`](https://github.com/torvalds/linux/commit/cb20b08ead401fd17627a36f035c0bf5bfee5567)
`BPF_FUNC_skb_get_tunnel_key()` | 4.3 | | [`d3aa45ce6b94`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d3aa45ce6b94c65b83971257317867db13e5f492)
`BPF_FUNC_skb_get_tunnel_opt()` | 4.6 | | [`14ca0751c96f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=14ca0751c96f8d3d0f52e8ed3b3236f8b34d3460)
`BPF_FUNC_skb_get_xfrm_state()` | 4.18 | | [`12bed760a78d`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=12bed760a78da6e12ac8252fec64d019a9eac523)
Expand Down Expand Up @@ -259,6 +266,7 @@ The list of program types and supported helper functions can be retrieved with:
|`BPF_PROG_TYPE_CGROUP_SOCK_ADDR`|`BPF_FUNC_get_current_uid_gid()` <br> `BPF_FUNC_bind()` <br> `BPF_FUNC_get_socket_cookie()` <br> `Base functions`|
|`BPF_PROG_TYPE_LWT_SEG6LOCAL`|`BPF_FUNC_lwt_seg6_store_bytes()` <br> `BPF_FUNC_lwt_seg6_action()` <br> `BPF_FUNC_lwt_seg6_adjust_srh()` <br> `LWT functions`|
|`BPF_PROG_TYPE_LIRC_MODE2`|`BPF_FUNC_rc_repeat()` <br> `BPF_FUNC_rc_keydown()` <br> `BPF_FUNC_map_lookup_elem()` <br> `BPF_FUNC_map_update_elem()` <br> `BPF_FUNC_map_delete_elem()` <br> `BPF_FUNC_ktime_get_ns()` <br> `BPF_FUNC_tail_call()` <br> `BPF_FUNC_get_prandom_u32()` <br> `BPF_FUNC_trace_printk()`|
|`BPF_PROG_TYPE_SK_REUSEPORT`|`BPF_FUNC_sk_select_reuseport()` <br> `BPF_FUNC_skb_load_bytes()` <br> `BPF_FUNC_load_bytes_relative()` <br> `Base functions`|

|Function Group| Functions|
|------------------|-------|
Expand Down
3 changes: 3 additions & 0 deletions introspection/bps.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ static const char * const prog_type_strings[] = {
[BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint",
[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
[BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2",
[BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport",
};

static const char * const map_type_strings[] = {
Expand All @@ -58,6 +59,8 @@ static const char * const map_type_strings[] = {
[BPF_MAP_TYPE_SOCKMAP] = "sockmap",
[BPF_MAP_TYPE_CPUMAP] = "cpumap",
[BPF_MAP_TYPE_SOCKHASH] = "sockhash",
[BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage",
[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
};

#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
Expand Down
159 changes: 148 additions & 11 deletions src/cc/compat/linux/bpf.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
__u8 data[0]; /* Arbitrary size */
};

struct bpf_cgroup_storage_key {
__u64 cgroup_inode_id; /* cgroup inode id */
__u32 attach_type; /* program attach type */
};

/* BPF syscall commands, see bpf(2) man-page for details. */
enum bpf_cmd {
BPF_MAP_CREATE,
Expand Down Expand Up @@ -120,6 +125,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_CPUMAP,
BPF_MAP_TYPE_XSKMAP,
BPF_MAP_TYPE_SOCKHASH,
BPF_MAP_TYPE_CGROUP_STORAGE,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
};

enum bpf_prog_type {
Expand All @@ -144,6 +151,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_PROG_TYPE_LWT_SEG6LOCAL,
BPF_PROG_TYPE_LIRC_MODE2,
BPF_PROG_TYPE_SK_REUSEPORT,
};

enum bpf_attach_type {
Expand Down Expand Up @@ -1371,6 +1379,20 @@ union bpf_attr {
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
* *skb*, but gets socket from **struct bpf_sock_addr** contex.
* Return
* A 8-byte long non-decreasing number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
* *skb*, but gets socket from **struct bpf_sock_ops** contex.
* Return
* A 8-byte long non-decreasing number.
*
* u32 bpf_get_socket_uid(struct sk_buff *skb)
* Return
* The owner UID of the socket associated to *skb*. If the socket
Expand Down Expand Up @@ -1826,7 +1848,7 @@ union bpf_attr {
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
* int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
* int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
* Description
* This helper is similar to **bpf_skb_load_bytes**\ () in that
* it provides an easy way to load *len* bytes from *offset*
Expand Down Expand Up @@ -1857,7 +1879,8 @@ union bpf_attr {
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
* is set to metric from route (IPv4/IPv6 only).
* is set to metric from route (IPv4/IPv6 only), and ifindex
* is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
Expand All @@ -1873,9 +1896,10 @@ union bpf_attr {
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
* Egress device index on success, 0 if packet needs to continue
* up the stack for further processing or a negative error in case
* of failure.
* * < 0 if any input argument is invalid
* * 0 on success (packet is forwarded, nexthop neighbor exists)
* * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
* packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
Expand Down Expand Up @@ -2031,7 +2055,6 @@ union bpf_attr {
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
*
* Return
* 0
*
Expand All @@ -2051,9 +2074,73 @@ union bpf_attr {
* This helper is only available is the kernel was compiled with
* the **CONFIG_BPF_LIRC_MODE2** configuration option set to
* "**y**".
*
* Return
* 0
*
* uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
* Description
* Return the cgroup v2 id of the socket associated with the *skb*.
* This is roughly similar to the **bpf_get_cgroup_classid**\ ()
* helper for cgroup v1 by providing a tag resp. identifier that
* can be matched on or used for map lookups e.g. to implement
* policy. The cgroup v2 id of a given path in the hierarchy is
* exposed in user space through the f_handle API in order to get
* to the same 64-bit id.
*
* This helper can be used on TC egress path, but not on ingress,
* and is available only if the kernel was compiled with the
* **CONFIG_SOCK_CGROUP_DATA** configuration option.
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
* u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
* Description
* Return id of cgroup v2 that is ancestor of cgroup associated
* with the *skb* at the *ancestor_level*. The root cgroup is at
* *ancestor_level* zero and each step down the hierarchy
* increments the level. If *ancestor_level* == level of cgroup
* associated with *skb*, then return value will be same as that
* of **bpf_skb_cgroup_id**\ ().
*
* The helper is useful to implement policies based on cgroups
* that are upper in hierarchy than immediate cgroup associated
* with *skb*.
*
* The format of returned id and helper limitations are same as in
* **bpf_skb_cgroup_id**\ ().
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
* void* get_local_storage(void *map, u64 flags)
* Description
* Get the pointer to the local storage area.
* The type and the size of the local storage is defined
* by the *map* argument.
* The *flags* meaning is specific for each map type,
* and has to be 0 for cgroup local storage.
*
* Depending on the bpf program type, a local storage area
* can be shared between multiple instances of the bpf program,
* running simultaneously.
*
* A user should care about the synchronization by himself.
* For example, by using the BPF_STX_XADD instruction to alter
* the shared data.
* Return
* Pointer to the local storage area.
*
* int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
* Description
* Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map
* It checks the selected sk is matching the incoming
* request in the skb.
* Return
* 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
Expand Down Expand Up @@ -2134,7 +2221,12 @@ union bpf_attr {
FN(lwt_seg6_adjust_srh), \
FN(lwt_seg6_action), \
FN(rc_repeat), \
FN(rc_keydown),
FN(rc_keydown), \
FN(skb_cgroup_id), \
FN(get_current_cgroup_id), \
FN(get_local_storage), \
FN(sk_select_reuseport), \
FN(skb_ancestor_cgroup_id),

/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
Expand Down Expand Up @@ -2251,7 +2343,7 @@ struct bpf_tunnel_key {
};
__u8 tunnel_tos;
__u8 tunnel_ttl;
__u16 tunnel_ext;
__u16 tunnel_ext; /* Padding, future use. */
__u32 tunnel_label;
};

Expand All @@ -2262,6 +2354,7 @@ struct bpf_xfrm_state {
__u32 reqid;
__u32 spi; /* Stored in network byte order */
__u16 family;
__u16 ext; /* Padding, future use. */
union {
__u32 remote_ipv4; /* Stored in network byte order */
__u32 remote_ipv6[4]; /* Stored in network byte order */
Expand Down Expand Up @@ -2350,6 +2443,30 @@ struct sk_msg_md {
__u32 local_port; /* stored in host byte order */
};

struct sk_reuseport_md {
/*
* Start of directly accessible data. It begins from
* the tcp/udp header.
*/
void *data;
void *data_end; /* End of directly accessible data */
/*
* Total length of packet (starting from the tcp/udp header).
* Note that the directly accessible bytes (data_end - data)
* could be less than this "len". Those bytes could be
* indirectly read by a helper "bpf_skb_load_bytes()".
*/
__u32 len;
/*
* Eth protocol in the mac header (network byte order). e.g.
* ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
*/
__u32 eth_protocol;
__u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
__u32 bind_inany; /* Is sock bound to an INANY address? */
__u32 hash; /* A hash of the packet 4 tuples */
};

#define BPF_TAG_SIZE 8

struct bpf_prog_info {
Expand Down Expand Up @@ -2384,6 +2501,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 :32;
__u64 netns_dev;
__u64 netns_ino;
__u32 btf_id;
Expand Down Expand Up @@ -2530,6 +2648,9 @@ enum {
* Arg1: old_state
* Arg2: new_state
*/
BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
* socket transition to LISTEN state.
*/
};

/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
Expand Down Expand Up @@ -2587,6 +2708,18 @@ struct bpf_raw_tracepoint_args {
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)

enum {
BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
};

struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
Expand All @@ -2600,12 +2733,16 @@ struct bpf_fib_lookup {

/* total length of packet from network header - used for MTU check */
__u16 tot_len;
__u32 ifindex; /* L3 device index for lookup */

/* input: L3 device index for lookup
* output: device index from FIB lookup
*/
__u32 ifindex;

union {
/* inputs to lookup */
__u8 tos; /* AF_INET */
__be32 flowlabel; /* AF_INET6 */
__be32 flowinfo; /* AF_INET6, flow_label + priority */

/* output: metric of fib result (IPv4/IPv6 only) */
__u32 rt_metric;
Expand Down
Loading

0 comments on commit 3835b2d

Please sign in to comment.