diff --git a/docs/kernel-versions.md b/docs/kernel-versions.md index fc855096f0e5..af42c8fe13c3 100644 --- a/docs/kernel-versions.md +++ b/docs/kernel-versions.md @@ -104,6 +104,9 @@ AF_XDP socket (XSK) references | 4.18 | [`fbfc504a24f5`](https://git.kernel.org/ 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) +precpu cgroup storage | 4.20 | [`b741f1630346`](https://github.com/torvalds/linux/commit/b741f1630346defcbc8cc60f1a2bdae8b3b0036f) +queue | 4.20 | [`f1a2e44a3aec`](https://github.com/torvalds/linux/commit/f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92) +stack | 4.20 | [`f1a2e44a3aec`](https://github.com/torvalds/linux/commit/f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92) ## XDP @@ -178,10 +181,14 @@ Helper | Kernel version | License | Commit | `BPF_FUNC_lwt_seg6_store_bytes()` | 4.18 | | [`fe94cc290f53`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=fe94cc290f535709d3c5ebd1e472dfd0aec7ee79) `BPF_FUNC_map_delete_elem()` | 3.19 | | [`d0003ec01c66`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d0003ec01c667b731c139e23de3306a8b328ccf5) `BPF_FUNC_map_lookup_elem()` | 3.19 | | [`d0003ec01c66`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d0003ec01c667b731c139e23de3306a8b328ccf5) +`BPF_FUNC_map_peek_elem()` | 3.20 | | [`f1a2e44a3aec`](https://github.com/torvalds/linux/commit/f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92) +`BPF_FUNC_map_pop_elem()` | 3.20 | | [`f1a2e44a3aec`](https://github.com/torvalds/linux/commit/f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92) +`BPF_FUNC_map_push_elem()` | 3.20 | | [`f1a2e44a3aec`](https://github.com/torvalds/linux/commit/f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92) `BPF_FUNC_map_update_elem()` | 3.19 | | [`d0003ec01c66`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d0003ec01c667b731c139e23de3306a8b328ccf5) `BPF_FUNC_msg_apply_bytes()` | 4.17 | | [`2a100317c9eb`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=2a100317c9ebc204a166f16294884fbf9da074ce) `BPF_FUNC_msg_cork_bytes()` | 4.17 | | [`91843d540a13`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=91843d540a139eb8070bcff8aa10089164436deb) `BPF_FUNC_msg_pull_data()` | 4.17 | | [`015632bb30da`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=015632bb30daaaee64e1bcac07570860e0bf3092) +`BPF_FUNC_msg_push_data()` | 4.20 | | [`6fff607e2f14`](https://github.com/torvalds/linux/commit/6fff607e2f14bd7c63c06c464a6f93b8efbabe28) `BPF_FUNC_msg_redirect_hash()` | 4.18 | | [`81110384441a`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=81110384441a59cff47430f20f049e69b98c17f4) `BPF_FUNC_msg_redirect_map()` | 4.17 | | [`4f738adba30a`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=4f738adba30a7cfc006f605707e7aee847ffefa0) `BPF_FUNC_perf_event_output()` | 4.4 | GPL | [`a43eec304259`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=a43eec304259a6c637f4014a6d4767159b6a3aa3) @@ -198,8 +205,11 @@ Helper | Kernel version | License | Commit | `BPF_FUNC_set_hash()` | 4.13 | | [`ded092cd73c2`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=ded092cd73c2c56a394b936f86897f29b2e131c0) `BPF_FUNC_set_hash_invalid()` | 4.9 | | [`7a4b28c6cc9f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=7a4b28c6cc9ffac50f791b99cc7e46106436e5d8) `BPF_FUNC_setsockopt()` | 4.13 | | [`8c4b4c7e9ff0`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=8c4b4c7e9ff0447995750d9329949fa082520269) +`BPF_FUNC_sk_lookup_tcp()` | 4.20 | | [`6acc9b432e67`](https://github.com/torvalds/linux/commit/6acc9b432e6714d72d7d77ec7c27f6f8358d0c71) +`BPF_FUNC_sk_lookup_udp()` | 4.20 | | [`6acc9b432e67`](https://github.com/torvalds/linux/commit/6acc9b432e6714d72d7d77ec7c27f6f8358d0c71) `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_release()` | 4.20 | | [`6acc9b432e67`](https://github.com/torvalds/linux/commit/6acc9b432e6714d72d7d77ec7c27f6f8358d0c71) `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) @@ -260,9 +270,9 @@ The list of program types and supported helper functions can be retrieved with: |`BPF_PROG_TYPE_LWT_OUT`| `LWT functions`
`Base functions`| |`BPF_PROG_TYPE_LWT_XMIT`| `BPF_FUNC_skb_get_tunnel_key()`
`BPF_FUNC_skb_set_tunnel_key()`
`BPF_FUNC_skb_get_tunnel_opt()`
`BPF_FUNC_skb_set_tunnel_opt()`
`BPF_FUNC_redirect()`
`BPF_FUNC_clone_redirect()`
`BPF_FUNC_skb_change_tail()`
`BPF_FUNC_skb_change_head()`
`BPF_FUNC_skb_store_bytes()`
`BPF_FUNC_csum_update()`
`BPF_FUNC_l3_csum_replace()`
`BPF_FUNC_l4_csum_replace()`
`BPF_FUNC_set_hash_invalid()`
`LWT functions`| |`BPF_PROG_TYPE_SOCK_OPS`|`BPF_FUNC_setsockopt()`
`BPF_FUNC_getsockopt()`
`BPF_FUNC_sock_ops_cb_flags_set()`
`BPF_FUNC_sock_map_update()`
`BPF_FUNC_sock_hash_update()`
`BPF_FUNC_get_socket_cookie()`
`Base functions`| -|`BPF_PROG_TYPE_SK_SKB`|`BPF_FUNC_skb_store_bytes()`
`BPF_FUNC_skb_load_bytes()`
`BPF_FUNC_skb_pull_data()`
`BPF_FUNC_skb_change_tail()`
`BPF_FUNC_skb_change_head()`
`BPF_FUNC_get_socket_cookie()`
`BPF_FUNC_get_socket_uid()`
`BPF_FUNC_sk_redirect_map()`
`BPF_FUNC_sk_redirect_hash()`
`Base functions`| +|`BPF_PROG_TYPE_SK_SKB`|`BPF_FUNC_skb_store_bytes()`
`BPF_FUNC_skb_load_bytes()`
`BPF_FUNC_skb_pull_data()`
`BPF_FUNC_skb_change_tail()`
`BPF_FUNC_skb_change_head()`
`BPF_FUNC_get_socket_cookie()`
`BPF_FUNC_get_socket_uid()`
`BPF_FUNC_sk_redirect_map()`
`BPF_FUNC_sk_redirect_hash()`
`BPF_FUNC_sk_lookup_tcp()`
`BPF_FUNC_sk_lookup_udp()`
`BPF_FUNC_sk_release()`
`Base functions`| |`BPF_PROG_TYPE_CGROUP_DEVICE`|`BPF_FUNC_map_lookup_elem()`
`BPF_FUNC_map_update_elem()`
`BPF_FUNC_map_delete_elem()`
`BPF_FUNC_get_current_uid_gid()`
`BPF_FUNC_trace_printk()`| -|`BPF_PROG_TYPE_SK_MSG`|`BPF_FUNC_msg_redirect_map()`
`BPF_FUNC_msg_redirect_hash()`
`BPF_FUNC_msg_apply_bytes()`
`BPF_FUNC_msg_cork_bytes()`
`BPF_FUNC_msg_pull_data()`
`Base functions`| +|`BPF_PROG_TYPE_SK_MSG`|`BPF_FUNC_msg_redirect_map()`
`BPF_FUNC_msg_redirect_hash()`
`BPF_FUNC_msg_apply_bytes()`
`BPF_FUNC_msg_cork_bytes()`
`BPF_FUNC_msg_pull_data()`
`BPF_FUNC_msg_push_data()`
`Base functions`| |`BPF_PROG_TYPE_RAW_TRACEPOINT`|`BPF_FUNC_perf_event_output()`
`BPF_FUNC_get_stackid()`
`BPF_FUNC_get_stack()`
`Tracing functions`| |`BPF_PROG_TYPE_CGROUP_SOCK_ADDR`|`BPF_FUNC_get_current_uid_gid()`
`BPF_FUNC_bind()`
`BPF_FUNC_get_socket_cookie()`
`Base functions`| |`BPF_PROG_TYPE_LWT_SEG6LOCAL`|`BPF_FUNC_lwt_seg6_store_bytes()`
`BPF_FUNC_lwt_seg6_action()`
`BPF_FUNC_lwt_seg6_adjust_srh()`
`LWT functions`| @@ -272,6 +282,6 @@ The list of program types and supported helper functions can be retrieved with: |Function Group| Functions| |------------------|-------| -|`Base functions`| `BPF_FUNC_map_lookup_elem()`
`BPF_FUNC_map_update_elem()`
`BPF_FUNC_map_delete_elem()`
`BPF_FUNC_get_prandom_u32()`
`BPF_FUNC_get_smp_processor_id()`
`BPF_FUNC_get_numa_node_id()`
`BPF_FUNC_tail_call()`
`BPF_FUNC_ktime_get_ns()`
`BPF_FUNC_trace_printk()`| +|`Base functions`| `BPF_FUNC_map_lookup_elem()`
`BPF_FUNC_map_update_elem()`
`BPF_FUNC_map_delete_elem()`
`BPF_FUNC_map_peek_elem()`
`BPF_FUNC_map_pop_elem()`
`BPF_FUNC_map_push_elem()`
`BPF_FUNC_get_prandom_u32()`
`BPF_FUNC_get_smp_processor_id()`
`BPF_FUNC_get_numa_node_id()`
`BPF_FUNC_tail_call()`
`BPF_FUNC_ktime_get_ns()`
`BPF_FUNC_trace_printk()`| |`Tracing functions`|`BPF_FUNC_map_lookup_elem()`
`BPF_FUNC_map_update_elem()`
`BPF_FUNC_map_delete_elem()`
`BPF_FUNC_probe_read()`
`BPF_FUNC_ktime_get_ns()`
`BPF_FUNC_tail_call()`
`BPF_FUNC_get_current_pid_tgid()`
`BPF_FUNC_get_current_task()`
`BPF_FUNC_get_current_uid_gid()`
`BPF_FUNC_get_current_comm()`
`BPF_FUNC_trace_printk()`
`BPF_FUNC_get_smp_processor_id()`
`BPF_FUNC_get_numa_node_id()`
`BPF_FUNC_perf_event_read()`
`BPF_FUNC_probe_write_user()`
`BPF_FUNC_current_task_under_cgroup()`
`BPF_FUNC_get_prandom_u32()`
`BPF_FUNC_probe_read_str()`
`BPF_FUNC_get_current_cgroup_id()` | |`LWT functions`| `BPF_FUNC_skb_load_bytes()`
`BPF_FUNC_skb_pull_data()`
`BPF_FUNC_csum_diff()`
`BPF_FUNC_get_cgroup_classid()`
`BPF_FUNC_get_route_realm()`
`BPF_FUNC_get_hash_recalc()`
`BPF_FUNC_perf_event_output()`
`BPF_FUNC_get_smp_processor_id()`
`BPF_FUNC_skb_under_cgroup()`| diff --git a/introspection/bps.c b/introspection/bps.c index a809395e36b5..4993b8e70ab9 100644 --- a/introspection/bps.c +++ b/introspection/bps.c @@ -62,6 +62,9 @@ static const char * const map_type_strings[] = { [BPF_MAP_TYPE_SOCKHASH] = "sockhash", [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", + [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "precpu_cgroup_storage", + [BPF_MAP_TYPE_QUEUE] = "queue", + [BPF_MAP_TYPE_STACK] = "stack", }; #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) diff --git a/src/cc/compat/linux/bpf.h b/src/cc/compat/linux/bpf.h index 05b5460c534b..f780fd496c00 100644 --- a/src/cc/compat/linux/bpf.h +++ b/src/cc/compat/linux/bpf.h @@ -103,6 +103,7 @@ enum bpf_cmd { BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { @@ -127,6 +128,9 @@ enum bpf_map_type { BPF_MAP_TYPE_SOCKHASH, BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -461,6 +465,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1432,7 +1458,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -2143,6 +2169,94 @@ union bpf_attr { * request in the skb. * Return * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into msg at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the msg. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2228,7 +2342,14 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2398,6 +2519,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/src/cc/compat/linux/virtual_bpf.h b/src/cc/compat/linux/virtual_bpf.h index 1911ad764452..26039d56964a 100644 --- a/src/cc/compat/linux/virtual_bpf.h +++ b/src/cc/compat/linux/virtual_bpf.h @@ -104,6 +104,7 @@ enum bpf_cmd { BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { @@ -128,6 +129,9 @@ enum bpf_map_type { BPF_MAP_TYPE_SOCKHASH, BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -462,6 +466,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1433,7 +1459,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -2144,6 +2170,94 @@ union bpf_attr { * request in the skb. * Return * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into msg at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the msg. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2229,7 +2343,14 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2399,6 +2520,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/src/cc/export/helpers.h b/src/cc/export/helpers.h index bcca4c9e0f4f..d7065c8af6d0 100755 --- a/src/cc/export/helpers.h +++ b/src/cc/export/helpers.h @@ -415,6 +415,26 @@ static void * (*bpf_get_local_storage)(void *map, u64 flags) = (void *) BPF_FUNC_get_local_storage; static int (*bpf_sk_select_reuseport)(void *reuse, void *map, void *key, u64 flags) = (void *) BPF_FUNC_sk_select_reuseport; +static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx, + struct bpf_sock_tuple *tuple, + int size, unsigned int netns_id, + unsigned long long flags) = + (void *) BPF_FUNC_sk_lookup_tcp; +static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx, + struct bpf_sock_tuple *tuple, + int size, unsigned int netns_id, + unsigned long long flags) = + (void *) BPF_FUNC_sk_lookup_udp; +static int (*bpf_sk_release)(struct bpf_sock *sk) = + (void *) BPF_FUNC_sk_release; +static int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) = + (void *) BPF_FUNC_map_push_elem; +static int bpf_map_pop_elem(struct bpf_map *map, void *value) = + (void *) BPF_FUNC_map_pop_elem; +static int bpf_map_peek_elem(struct bpf_map *map, void *value) = + (void *) BPF_FUNC_map_peek_elem; +static int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) = + (void *) BPF_FUNC_msg_push_data; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/src/cc/libbpf.c b/src/cc/libbpf.c index 7bf3de0e3e8a..8a7caecfd53d 100644 --- a/src/cc/libbpf.c +++ b/src/cc/libbpf.c @@ -173,6 +173,13 @@ static struct bpf_helper helpers[] = { {"get_local_storage", "4.19"}, {"sk_select_reuseport", "4.19"}, {"skb_ancestor_cgroup_id", "4.19"}, + {"sk_lookup_tcp", "4.20"}, + {"sk_lookup_udp", "4.20"}, + {"sk_release", "4.20"}, + {"map_push_elem", "4.20"}, + {"map_pop_elem", "4.20"}, + {"map_peak_elem", "4.20"}, + {"msg_push_data", "4.20"}, }; static uint64_t ptr_to_u64(void *ptr)