From df3e7d673da4bd4acab333f28851eccf00ca9f87 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Apr 2020 09:25:57 -0700 Subject: [PATCH] sync to latest libbpf sync to libbpf v0.0.8. Add newer helpers to helpers.h, libbpf.c error reporting and docs. --- docs/kernel-versions.md | 8 +- introspection/bps.c | 1 + src/cc/compat/linux/virtual_bpf.h | 340 +++++++++++++++++++++++------- src/cc/export/helpers.h | 27 ++- src/cc/libbpf | 2 +- src/cc/libbpf.c | 6 + 6 files changed, 304 insertions(+), 80 deletions(-) diff --git a/docs/kernel-versions.md b/docs/kernel-versions.md index 8732ddb60c90..416f70076140 100644 --- a/docs/kernel-versions.md +++ b/docs/kernel-versions.md @@ -165,6 +165,7 @@ Helper | Kernel version | License | Commit | `BPF_FUNC_csum_update()` | 4.9 | | [`36bbef52c7eb`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=36bbef52c7eb646ed6247055a2acd3851e317857) `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_current_ancestor_cgroup_id()` | 5.6 | | [`b4490c5c4e02`](https://github.com/torvalds/linux/commit/b4490c5c4e023f09b7d27c9a9d3e7ad7d09ea6bf) `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) @@ -174,6 +175,8 @@ Helper | Kernel version | License | Commit | `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_listener_sock()` | 5.1 | | [`dbafd7ddd623`](https://kernel.googlesource.com/pub/scm/linux/kernel/git/davem/net-next/+/dbafd7ddd62369b2f3926ab847cbf8fc40e800b7) `BPF_FUNC_get_local_storage()` | 4.19 | | [`cd3394317653`](https://github.com/torvalds/linux/commit/cd3394317653837e2eb5c5d0904a8996102af9fc) +`BPF_FUNC_get_netns_cookie()` | 5.6 | | [`b4490c5c4e02`](https://github.com/torvalds/linux/commit/b4490c5c4e023f09b7d27c9a9d3e7ad7d09ea6bf) +`BPF_FUNC_get_ns_current_pid_tgid()` | 5.6 | | [`b4490c5c4e02`](https://github.com/torvalds/linux/commit/b4490c5c4e023f09b7d27c9a9d3e7ad7d09ea6bf) `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) @@ -218,6 +221,7 @@ Helper | Kernel version | License | Commit | `BPF_FUNC_rc_keydown()` | 4.18 | GPL | [`f4364dcfc86d`](https://git.kernel.org/cgit/linux/kernel/git/bpf/bpf-next.git/commit/?id=f4364dcfc86df7c1ca47b256eaf6b6d0cdd0d936) `BPF_FUNC_rc_pointer_rel()` | 5.0 | GPL | [`01d3240a04f4`](https://github.com/torvalds/linux/commit/01d3240a04f4c09392e13c77b54d4423ebce2d72) `BPF_FUNC_rc_repeat()` | 4.18 | GPL | [`f4364dcfc86d`](https://git.kernel.org/cgit/linux/kernel/git/bpf/bpf-next.git/commit/?id=f4364dcfc86df7c1ca47b256eaf6b6d0cdd0d936) +`BPF_FUNC_read_branch_records()` | 5.6 | GPL | [`fff7b64355ea`](https://github.com/torvalds/linux/commit/fff7b64355eac6e29b50229ad1512315bc04b44e) `BPF_FUNC_redirect()` | 4.4 | | [`27b29f63058d`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=27b29f63058d26c6c1742f1993338280d5a41dc6) `BPF_FUNC_redirect_map()` | 4.14 | | [`97f91a7cf04f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=97f91a7cf04ff605845c20948b8a80e54cbd3376) `BPF_FUNC_send_signal()` | 5.3 | | [`8b401f9ed244`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=8b401f9ed2441ad9e219953927a842d24ed051fc) @@ -225,6 +229,7 @@ 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_assign()` | 5.6 | | [`cf7fbe660f2d`](https://github.com/torvalds/linux/commit/cf7fbe660f2dbd738ab58aea8e9b0ca6ad232449) `BPF_FUNC_sk_fullsock()` | 5.1 | | [`46f8bc92758c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=46f8bc92758c6259bcf945e9216098661c1587cd) `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) @@ -275,6 +280,7 @@ Helper | Kernel version | License | Commit | `BPF_FUNC_xdp_adjust_head()` | 4.10 | | [`17bedab27231`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=17bedab2723145d17b14084430743549e6943d03) `BPF_FUNC_xdp_adjust_meta()` | 4.15 | | [`de8f3a83b0a0`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=de8f3a83b0a0fddb2cf56e7a718127e9619ea3da) `BPF_FUNC_xdp_adjust_tail()` | 4.18 | | [`b32cc5b9a346`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=b32cc5b9a346319c171e3ad905e0cddda032b5eb) +`BPF_FUNC_xdp_output()` | 5.6 | GPL | [`d831ee84bfc9`](https://github.com/torvalds/linux/commit/d831ee84bfc9173eecf30dbbc2553ae81b996c60) `BPF_FUNC_override_return()` | 4.16 | GPL | [`9802d86585db`](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=9802d86585db91655c7d1929a4f6bbe0952ea88e) `BPF_FUNC_sock_ops_cb_flags_set()` | 4.16 | | [`b13d88072172`](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b13d880721729384757f235166068c315326f4a1) @@ -321,5 +327,5 @@ 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_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()`
`BPF_FUNC_spin_lock()`
`BPF_FUNC_spin_unlock()` | -|`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()`
`BPF_FUNC_send_signal()`
`BPF_FUNC_probe_read_kernel()`
`BPF_FUNC_probe_read_kernel_str()`
`BPF_FUNC_probe_read_user()`
`BPF_FUNC_probe_read_user_str()`
`BPF_FUNC_send_signal_thread()`| +|`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()`
`BPF_FUNC_send_signal()`
`BPF_FUNC_probe_read_kernel()`
`BPF_FUNC_probe_read_kernel_str()`
`BPF_FUNC_probe_read_user()`
`BPF_FUNC_probe_read_user_str()`
`BPF_FUNC_send_signal_thread()`
`BPF_FUNC_get_ns_current_pid_tgid()`
`BPF_FUNC_xdp_output()`| |`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 c5984c45952b..97868f7f0b6a 100644 --- a/introspection/bps.c +++ b/introspection/bps.c @@ -45,6 +45,7 @@ static const char * const prog_type_strings[] = { [BPF_PROG_TYPE_TRACING] = "tracing", [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", [BPF_PROG_TYPE_EXT] = "ext", + [BPF_PROG_TYPE_LSM] = "lsm", }; static const char * const map_type_strings[] = { diff --git a/src/cc/compat/linux/virtual_bpf.h b/src/cc/compat/linux/virtual_bpf.h index 7b6b41d3aca6..17b07c366373 100644 --- a/src/cc/compat/linux/virtual_bpf.h +++ b/src/cc/compat/linux/virtual_bpf.h @@ -74,7 +74,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[0]; /* Arbitrary size */ + __u8 data[]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { @@ -112,6 +112,8 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_BATCH, BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, + BPF_LINK_UPDATE, }; enum bpf_map_type { @@ -182,6 +184,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_TRACING, BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, + BPF_PROG_TYPE_LSM, }; enum bpf_attach_type { @@ -211,6 +214,8 @@ enum bpf_attach_type { BPF_TRACE_RAW_TP, BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, + BPF_LSM_MAC, __MAX_BPF_ATTACH_TYPE }; @@ -326,44 +331,46 @@ enum bpf_attach_type { #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 */ -#define BPF_EXIST 2 /* update existing element */ -#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ +enum { + BPF_ANY = 0, /* create new element or update existing */ + BPF_NOEXIST = 1, /* create new element if it didn't exist */ + BPF_EXIST = 2, /* update existing element */ + BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */ +}; /* flags for BPF_MAP_CREATE command */ -#define BPF_F_NO_PREALLOC (1U << 0) +enum { + BPF_F_NO_PREALLOC = (1U << 0), /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. */ -#define BPF_F_NO_COMMON_LRU (1U << 1) + BPF_F_NO_COMMON_LRU = (1U << 1), /* Specify numa node during map creation */ -#define BPF_F_NUMA_NODE (1U << 2) - -#define BPF_OBJ_NAME_LEN 16U + BPF_F_NUMA_NODE = (1U << 2), /* Flags for accessing BPF object from syscall side. */ -#define BPF_F_RDONLY (1U << 3) -#define BPF_F_WRONLY (1U << 4) + BPF_F_RDONLY = (1U << 3), + BPF_F_WRONLY = (1U << 4), /* Flag for stack_map, store build_id+offset instead of pointer */ -#define BPF_F_STACK_BUILD_ID (1U << 5) + BPF_F_STACK_BUILD_ID = (1U << 5), /* Zero-initialize hash function seed. This should only be used for testing. */ -#define BPF_F_ZERO_SEED (1U << 6) + BPF_F_ZERO_SEED = (1U << 6), /* Flags for accessing BPF object from program side. */ -#define BPF_F_RDONLY_PROG (1U << 7) -#define BPF_F_WRONLY_PROG (1U << 8) + BPF_F_RDONLY_PROG = (1U << 7), + BPF_F_WRONLY_PROG = (1U << 8), /* Clone map from listener for newly accepted socket */ -#define BPF_F_CLONE (1U << 9) + BPF_F_CLONE = (1U << 9), /* Enable memory-mapping BPF map */ -#define BPF_F_MMAPABLE (1U << 10) + BPF_F_MMAPABLE = (1U << 10), +}; /* Flags for BPF_PROG_QUERY. */ @@ -392,6 +399,8 @@ struct bpf_stack_build_id { }; }; +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -535,7 +544,7 @@ union bpf_attr { __u32 prog_cnt; } query; - struct { + struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ __u64 name; __u32 prog_fd; } raw_tracepoint; @@ -563,6 +572,24 @@ union bpf_attr { __u64 probe_offset; /* output: probe_offset */ __u64 probe_addr; /* output: probe_addr */ } task_fd_query; + + struct { /* struct used by BPF_LINK_CREATE command */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 target_fd; /* object to attach to */ + __u32 attach_type; /* attach type */ + __u32 flags; /* extra flags */ + } link_create; + + struct { /* struct used by BPF_LINK_UPDATE command */ + __u32 link_fd; /* link fd */ + /* new program fd to update link with */ + __u32 new_prog_fd; + __u32 flags; /* extra flags */ + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags */ + __u32 old_prog_fd; + } link_update; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -1046,9 +1073,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1612,13 +1639,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description @@ -2893,6 +2918,114 @@ union bpf_attr { * Obtain the 64bit jiffies * Return * The 64 bit jiffies + * + * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * Description + * For an eBPF program attached to a perf event, retrieve the + * branch records (struct perf_branch_entry) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size + * *size* bytes. + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to + * instead return the number of bytes required to store all the + * branch entries. If this flag is set, *buf* may be NULL. + * + * **-EINVAL** if arguments invalid or **size** not a multiple + * of sizeof(struct perf_branch_entry). + * + * **-ENOENT** if architecture does not support branch records. + * + * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * Description + * Returns 0 on success, values for *pid* and *tgid* as seen from the current + * *namespace* will be returned in *nsdata*. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number + * with nsfs of current task, or if dev conversion to dev_t lost high bits. + * + * **-ENOENT** if pidns does not exists for the current task. + * + * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_netns_cookie(void *ctx) + * Description + * Retrieve the cookie (generated by the kernel) of the network + * namespace the input *ctx* is associated with. The network + * namespace cookie remains stable for its lifetime and provides + * a global identifier that can be assumed unique. If *ctx* is + * NULL, then the helper returns the cookie for the initial + * network namespace. The cookie itself is very similar to that + * of bpf_get_socket_cookie() helper, but for network namespaces + * instead of sockets. + * Return + * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task 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 the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * Description + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EINVAL** Unsupported flags specified. + * * **-ENOENT** Socket is unavailable for assignment. + * * **-ENETUNREACH** Socket is unreachable (wrong netns). + * * **-EOPNOTSUPP** Unsupported operation, for example a + * call from outside of TC ingress. + * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3013,7 +3146,13 @@ union bpf_attr { FN(probe_read_kernel_str), \ FN(tcp_send_ack), \ FN(send_signal_thread), \ - FN(jiffies64), + FN(jiffies64), \ + FN(read_branch_records), \ + FN(get_ns_current_pid_tgid), \ + FN(xdp_output), \ + FN(get_netns_cookie), \ + FN(get_current_ancestor_cgroup_id), \ + FN(sk_assign), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3028,69 +3167,100 @@ enum bpf_func_id { /* All flags used by eBPF helper functions, placed here. */ /* BPF_FUNC_skb_store_bytes flags. */ -#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) -#define BPF_F_INVALIDATE_HASH (1ULL << 1) +enum { + BPF_F_RECOMPUTE_CSUM = (1ULL << 0), + BPF_F_INVALIDATE_HASH = (1ULL << 1), +}; /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. * First 4 bits are for passing the header field size. */ -#define BPF_F_HDR_FIELD_MASK 0xfULL +enum { + BPF_F_HDR_FIELD_MASK = 0xfULL, +}; /* BPF_FUNC_l4_csum_replace flags. */ -#define BPF_F_PSEUDO_HDR (1ULL << 4) -#define BPF_F_MARK_MANGLED_0 (1ULL << 5) -#define BPF_F_MARK_ENFORCE (1ULL << 6) +enum { + BPF_F_PSEUDO_HDR = (1ULL << 4), + BPF_F_MARK_MANGLED_0 = (1ULL << 5), + BPF_F_MARK_ENFORCE = (1ULL << 6), +}; /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -#define BPF_F_INGRESS (1ULL << 0) +enum { + BPF_F_INGRESS = (1ULL << 0), +}; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ -#define BPF_F_TUNINFO_IPV6 (1ULL << 0) +enum { + BPF_F_TUNINFO_IPV6 = (1ULL << 0), +}; /* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ -#define BPF_F_SKIP_FIELD_MASK 0xffULL -#define BPF_F_USER_STACK (1ULL << 8) +enum { + BPF_F_SKIP_FIELD_MASK = 0xffULL, + BPF_F_USER_STACK = (1ULL << 8), /* flags used by BPF_FUNC_get_stackid only. */ -#define BPF_F_FAST_STACK_CMP (1ULL << 9) -#define BPF_F_REUSE_STACKID (1ULL << 10) + BPF_F_FAST_STACK_CMP = (1ULL << 9), + BPF_F_REUSE_STACKID = (1ULL << 10), /* flags used by BPF_FUNC_get_stack only. */ -#define BPF_F_USER_BUILD_ID (1ULL << 11) + BPF_F_USER_BUILD_ID = (1ULL << 11), +}; /* BPF_FUNC_skb_set_tunnel_key flags. */ -#define BPF_F_ZERO_CSUM_TX (1ULL << 1) -#define BPF_F_DONT_FRAGMENT (1ULL << 2) -#define BPF_F_SEQ_NUMBER (1ULL << 3) +enum { + BPF_F_ZERO_CSUM_TX = (1ULL << 1), + BPF_F_DONT_FRAGMENT = (1ULL << 2), + BPF_F_SEQ_NUMBER = (1ULL << 3), +}; /* 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 +enum { + BPF_F_INDEX_MASK = 0xffffffffULL, + BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, /* BPF_FUNC_perf_event_output for sk_buff input context. */ -#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + BPF_F_CTXLEN_MASK = (0xfffffULL << 32), +}; /* Current network namespace */ -#define BPF_F_CURRENT_NETNS (-1L) +enum { + BPF_F_CURRENT_NETNS = (-1L), +}; /* BPF_FUNC_skb_adjust_room flags. */ -#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) +enum { + BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), + BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), + BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), +}; -#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff -#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 +enum { + BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff, + BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56, +}; -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) -#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) -#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) #define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ BPF_ADJ_ROOM_ENCAP_L2_MASK) \ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) /* BPF_FUNC_sysctl_get_name flags. */ -#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +enum { + BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), +}; /* BPF_FUNC_sk_storage_get flags */ -#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) +enum { + BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), +}; + +/* BPF_FUNC_read_branch_records flags. */ +enum { + BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), +}; /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { @@ -3156,6 +3326,7 @@ struct __sk_buff { __u32 wire_len; __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); + __u32 gso_size; }; struct bpf_tunnel_key { @@ -3508,13 +3679,14 @@ struct bpf_sock_ops { }; /* 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_RTT_CB_FLAG (1<<3) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently - * supported cb flags - */ +enum { + BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0), + BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), + BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), + BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), +/* Mask of all currently supported cb flags */ + BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, +}; /* List of known BPF sock_ops operators. * New entries can only be added at the end @@ -3593,8 +3765,10 @@ enum { 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 */ +enum { + TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ + TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ +}; struct bpf_perf_event_value { __u64 counter; @@ -3602,12 +3776,16 @@ struct bpf_perf_event_value { __u64 running; }; -#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) -#define BPF_DEVCG_ACC_READ (1ULL << 1) -#define BPF_DEVCG_ACC_WRITE (1ULL << 2) +enum { + BPF_DEVCG_ACC_MKNOD = (1ULL << 0), + BPF_DEVCG_ACC_READ = (1ULL << 1), + BPF_DEVCG_ACC_WRITE = (1ULL << 2), +}; -#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) -#define BPF_DEVCG_DEV_CHAR (1ULL << 1) +enum { + BPF_DEVCG_DEV_BLOCK = (1ULL << 0), + BPF_DEVCG_DEV_CHAR = (1ULL << 1), +}; struct bpf_cgroup_dev_ctx { /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ @@ -3623,8 +3801,10 @@ struct bpf_raw_tracepoint_args { /* DIRECT: Skip the FIB rules and go to FIB table associated with device * OUTPUT: Do lookup from egress perspective; default is ingress */ -#define BPF_FIB_LOOKUP_DIRECT (1U << 0) -#define BPF_FIB_LOOKUP_OUTPUT (1U << 1) +enum { + BPF_FIB_LOOKUP_DIRECT = (1U << 0), + BPF_FIB_LOOKUP_OUTPUT = (1U << 1), +}; enum { BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ @@ -3696,9 +3876,11 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; -#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) +enum { + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0), + BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1), + BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2), +}; struct bpf_flow_keys { __u16 nhoff; @@ -3764,5 +3946,9 @@ struct bpf_sockopt { __s32 retval; }; +struct bpf_pidns_info { + __u32 pid; + __u32 tgid; +}; #endif /* _UAPI__LINUX_BPF_H__ */ )********" diff --git a/src/cc/export/helpers.h b/src/cc/export/helpers.h index 590f4d8dfd8b..b38b3f200d5f 100644 --- a/src/cc/export/helpers.h +++ b/src/cc/export/helpers.h @@ -614,11 +614,36 @@ static int (*bpf_probe_read_user_str)(void *dst, __u32 size, static int (*bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *)BPF_FUNC_probe_read_kernel_str; +static int (*bpf_tcp_send_ack)(void *tp, __u32 rcv_nxt) = + (void *)BPF_FUNC_tcp_send_ack; +static int (*bpf_send_signal_thread)(__u32 sig) = + (void *)BPF_FUNC_send_signal_thread; +static __u64 (*bpf_jiffies64)(void) = (void *)BPF_FUNC_jiffies64; + +struct bpf_perf_event_data; +static int (*bpf_read_branch_records)(struct bpf_perf_event_data *ctx, void *buf, + __u32 size, __u64 flags) = + (void *)BPF_FUNC_read_branch_records; +static int (*bpf_get_ns_current_pid_tgid)(__u64 dev, __u64 ino, + struct bpf_pidns_info *nsdata, + __u32 size) = + (void *)BPF_FUNC_get_ns_current_pid_tgid; + +struct bpf_map; +static int (*bpf_xdp_output)(void *ctx, struct bpf_map *map, __u64 flags, + void *data, __u64 size) = + (void *)BPF_FUNC_xdp_output; +static __u64 (*bpf_get_netns_cookie)(void *ctx) = (void *)BPF_FUNC_get_netns_cookie; +static __u64 (*bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = + (void *)BPF_FUNC_get_current_ancestor_cgroup_id; + +struct sk_buff; +static int (*bpf_sk_assign)(struct sk_buff *skb, struct bpf_sock *sk, __u64 flags) = + (void *)BPF_FUNC_sk_assign; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions */ -struct sk_buff; unsigned long long load_byte(void *skb, unsigned long long off) asm("llvm.bpf.load.byte"); unsigned long long load_half(void *skb, diff --git a/src/cc/libbpf b/src/cc/libbpf index 9f0d55c24afb..6a1615c263b6 160000 --- a/src/cc/libbpf +++ b/src/cc/libbpf @@ -1 +1 @@ -Subproject commit 9f0d55c24afbd7b3aaf04cc3f99299115e4d0a98 +Subproject commit 6a1615c263b679c17ecb292fa897f159e826dc10 diff --git a/src/cc/libbpf.c b/src/cc/libbpf.c index a610e01da17f..0ce8267484ca 100644 --- a/src/cc/libbpf.c +++ b/src/cc/libbpf.c @@ -215,6 +215,12 @@ static struct bpf_helper helpers[] = { {"tcp_send_ack", "5.5"}, {"send_signal_thread", "5.5"}, {"jiffies64", "5.5"}, + {"read_branch_records", "5.6"}, + {"get_ns_current_pid_tgid", "5.6"}, + {"xdp_output", "5.6"}, + {"get_netns_cookie", "5.6"}, + {"get_current_ancestor_cgroup_id", "5.6"}, + {"sk_assign", "5.6"}, }; static uint64_t ptr_to_u64(void *ptr)