diff options
Diffstat (limited to 'include/uapi/linux/bpf.h')
| -rw-r--r-- | include/uapi/linux/bpf.h | 602 |
1 files changed, 469 insertions, 133 deletions
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77c6be96d676..f9b7fdd951e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -107,6 +107,12 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, + BPF_LINK_UPDATE, }; enum bpf_map_type { @@ -136,6 +142,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, + BPF_MAP_TYPE_STRUCT_OPS, }; /* Note that tracing related programs such as @@ -173,6 +180,10 @@ enum bpf_prog_type { BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_PROG_TYPE_TRACING, + BPF_PROG_TYPE_STRUCT_OPS, + BPF_PROG_TYPE_EXT, + BPF_PROG_TYPE_LSM, }; enum bpf_attach_type { @@ -199,6 +210,11 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_RECVMSG, BPF_CGROUP_GETSOCKOPT, BPF_CGROUP_SETSOCKOPT, + BPF_TRACE_RAW_TP, + BPF_TRACE_FENTRY, + BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, + BPF_LSM_MAC, __MAX_BPF_ATTACH_TYPE }; @@ -227,6 +243,11 @@ enum bpf_attach_type { * When children program makes decision (like picking TCP CA or sock bind) * parent program has a chance to override it. * + * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of + * programs for a cgroup. Though it's possible to replace an old program at + * any position by also specifying BPF_F_REPLACE flag and position itself in + * replace_bpf_fd attribute. Old program at this position will be released. + * * 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: @@ -245,6 +266,7 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +#define BPF_F_REPLACE (1U << 2) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -308,43 +330,53 @@ 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 */ + BPF_F_MMAPABLE = (1U << 10), +}; + +/* Flags for BPF_PROG_QUERY. */ -/* flags for BPF_PROG_QUERY */ +/* Query effective (directly attached + inherited from ancestor cgroups) + * programs that will be executed for events within a cgroup. + * attach_flags with this flag are returned only for directly attached programs. + */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) enum bpf_stack_build_id_status { @@ -366,6 +398,8 @@ 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 */ @@ -384,6 +418,10 @@ union bpf_attr { __u32 btf_fd; /* fd pointing to a BTF type data */ __u32 btf_key_type_id; /* BTF type_id of the key */ __u32 btf_value_type_id; /* BTF type_id of the value */ + __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel- + * struct stored as the + * map value + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -396,6 +434,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; @@ -420,6 +475,8 @@ union bpf_attr { __u32 line_info_rec_size; /* userspace bpf_line_info size */ __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ + __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + __u32 attach_prog_fd; /* 0 to attach to vmlinux */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -433,6 +490,10 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 replace_bpf_fd; /* previously attached eBPF + * program to replace if + * BPF_F_REPLACE is used + */ }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -482,7 +543,7 @@ 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; @@ -510,6 +571,24 @@ 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 @@ -560,10 +639,13 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read(void *dst, u32 size, const void *src) + * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) * Description * For tracing programs, safely attempt to read *size* bytes from - * address *src* and store the data in *dst*. + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() + * instead. * Return * 0 on success, or a negative error in case of failure. * @@ -794,7 +876,7 @@ union bpf_attr { * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. * - * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * int bpf_get_current_comm(void *buf, u32 size_of_buf) * Description * Copy the **comm** attribute of the current task into *buf* of * *size_of_buf*. The **comm** attribute contains the name of @@ -990,9 +1072,9 @@ 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 @@ -1023,7 +1105,7 @@ union bpf_attr { * The realm of the route for the packet associated to *skb*, or 0 * if none was found. * - * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * int bpf_perf_event_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 @@ -1068,7 +1150,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) * Description * This helper was provided as an easy way to load data from a * packet. It can be used to load *len* bytes from *offset* from @@ -1085,7 +1167,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags) + * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) * Description * Walk a user or a kernel stack and return its id. To achieve * this, the helper needs *ctx*, which is a pointer to the context @@ -1154,7 +1236,7 @@ union bpf_attr { * The checksum result, or a negative error code in case of * failure. * - * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Retrieve tunnel options metadata for the packet associated to * *skb*, and store the raw tunnel option data to the buffer *opt* @@ -1172,7 +1254,7 @@ union bpf_attr { * Return * The size of the option data retrieved. * - * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Set tunnel options metadata for the packet associated to *skb* * to the option data contained in the raw buffer *opt* of *size*. @@ -1425,45 +1507,14 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description - * Copy a NUL terminated string from an unsafe address - * *unsafe_ptr* to *dst*. The *size* should include the - * terminating NUL byte. In case the string length is smaller than - * *size*, the target is not padded with further NUL bytes. If the - * string length is larger than *size*, just *size*-1 bytes are - * copied and the last byte is set to NUL. + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * more details. * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: - * - * :: - * - * SEC("kprobe/sys_open") - * void bpf_sys_open(struct pt_regs *ctx) - * { - * char buf[PATHLEN]; // PATHLEN is defined to 256 - * int res = bpf_probe_read_str(buf, sizeof(buf), - * ctx->di); - * - * // Consume buf, for example push it to - * // userspace via bpf_perf_event_output(); we - * // can use res (the string length) as event - * // size, after checking its boundaries. - * } - * - * In comparison, using **bpf_probe_read()** helper here instead - * to read the string would require to estimate the length at - * compile time, and would often result in copying more memory - * than necessary. - * - * Another useful use case is when parsing individual process - * arguments or individual environment variables navigating - * *current*\ **->mm->arg_start** and *current*\ - * **->mm->env_start**: using this helper and the return value, - * one can quickly iterate at the right offset of the memory area. + * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() + * instead. * Return * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative @@ -1511,7 +1562,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1587,15 +1638,13 @@ 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 bpf_map *map, u32 key, u64 flags) + * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description * Redirect the packet to the socket referenced by *map* (of type * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and @@ -1715,7 +1764,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1947,7 +1996,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. * To achieve this, the helper needs *ctx*, which is a pointer @@ -1980,7 +2029,7 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * - * int bpf_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 void *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* @@ -2033,7 +2082,7 @@ union bpf_attr { * * > 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) + * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. * The *skops* is used as a new value for the entry associated to @@ -2392,7 +2441,7 @@ union bpf_attr { * 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) + * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description * For socket policies, insert *len* bytes into *msg* at offset * *start*. @@ -2408,9 +2457,9 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags) + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description - * Will remove *pop* bytes from a *msg* starting at byte *start*. + * Will remove *len* bytes from a *msg* starting at byte *start*. * This may result in **ENOMEM** errors under certain situations if * an allocation and copy are required due to a full ring buffer. * However, the helper will try to avoid doing the allocation @@ -2505,7 +2554,7 @@ union bpf_attr { * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * - * int bpf_skb_ecn_set_ce(struct sk_buf *skb) + * int bpf_skb_ecn_set_ce(struct sk_buff *skb) * Description * Set ECN (Explicit Congestion Notification) field of IP header * to **CE** (Congestion Encountered) if current value is **ECT** @@ -2712,7 +2761,8 @@ union bpf_attr { * * int bpf_send_signal(u32 sig) * Description - * Send signal *sig* to the current task. + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. * Return * 0 on success or successfully queued. * @@ -2750,6 +2800,231 @@ union bpf_attr { * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies * * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_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 sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user()** helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * Return + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. + * + * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * Description + * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock. + * *rcv_nxt* is the ack_seq to be sent out. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_send_signal_thread(u32 sig) + * Description + * Send signal *sig* to the thread corresponding to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * u64 bpf_jiffies64(void) + * Description + * 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), \ @@ -2862,7 +3137,21 @@ union bpf_attr { FN(sk_storage_get), \ FN(sk_storage_delete), \ FN(send_signal), \ - FN(tcp_gen_syncookie), + FN(tcp_gen_syncookie), \ + FN(skb_output), \ + FN(probe_read_user), \ + FN(probe_read_kernel), \ + FN(probe_read_user_str), \ + FN(probe_read_kernel_str), \ + FN(tcp_send_ack), \ + FN(send_signal_thread), \ + 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 @@ -2877,69 +3166,100 @@ 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 { @@ -3005,6 +3325,7 @@ struct __sk_buff { __u32 wire_len; __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); + __u32 gso_size; }; struct bpf_tunnel_key { @@ -3263,7 +3584,7 @@ struct bpf_map_info { __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; - __u32 :32; + __u32 btf_vmlinux_value_type_id; __u64 netns_dev; __u64 netns_ino; __u32 btf_id; @@ -3357,13 +3678,14 @@ 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 @@ -3442,8 +3764,10 @@ 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; @@ -3451,12 +3775,16 @@ 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_* */ @@ -3472,8 +3800,10 @@ 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 */ @@ -3545,9 +3875,11 @@ 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; @@ -3613,4 +3945,8 @@ struct bpf_sockopt { __s32 retval; }; +struct bpf_pidns_info { + __u32 pid; + __u32 tgid; +}; #endif /* _UAPI__LINUX_BPF_H__ */ |