diff --git a/headers/linux/bpf.h b/headers/linux/bpf.h index bd28bc76..8790b396 100644 --- a/headers/linux/bpf.h +++ b/headers/linux/bpf.h @@ -5,8 +5,8 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ -#ifndef __LINUX_BPF_H__ -#define __LINUX_BPF_H__ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ #include #include @@ -19,7 +19,9 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#define BPF_MEMSX 0x80 /* load with sign extension */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ /* alu/jmp fields */ #define BPF_MOV 0xb0 /* mov reg to reg */ @@ -43,6 +45,11 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ + /* Register numbers */ enum { BPF_REG_0 = 0, @@ -78,16 +85,784 @@ struct bpf_lpm_trie_key { struct bpf_cgroup_storage_key { __u64 cgroup_inode_id; /* cgroup inode id */ - __u32 attach_type; /* program attach type */ + __u32 attach_type; /* program attach type (enum bpf_attach_type) */ +}; + +enum bpf_cgroup_iter_order { + BPF_CGROUP_ITER_ORDER_UNSPEC = 0, + BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */ + BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */ + BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */ + BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */ }; union bpf_iter_link_info { struct { __u32 map_fd; } map; + struct { + enum bpf_cgroup_iter_order order; + + /* At most one of cgroup_fd and cgroup_id can be non-zero. If + * both are zero, the walk starts from the default cgroup v2 + * root. For walking v1 hierarchy, one should always explicitly + * specify cgroup_fd. + */ + __u32 cgroup_fd; + __u64 cgroup_id; + } cgroup; + /* Parameters of task iterators. */ + struct { + __u32 tid; + __u32 pid; + __u32 pid_fd; + } task; }; -/* BPF syscall commands, see bpf(2) man-page for details. */ +/* BPF syscall commands, see bpf(2) man-page for more details. */ +/** + * DOC: eBPF Syscall Preamble + * + * The operation to be performed by the **bpf**\ () system call is determined + * by the *cmd* argument. Each operation takes an accompanying argument, + * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see + * below). The size argument is the size of the union pointed to by *attr*. + */ +/** + * DOC: eBPF Syscall Commands + * + * BPF_MAP_CREATE + * Description + * Create a map and return a file descriptor that refers to the + * map. The close-on-exec file descriptor flag (see **fcntl**\ (2)) + * is automatically enabled for the new file descriptor. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_MAP_CREATE** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_LOOKUP_ELEM + * Description + * Look up an element with a given *key* in the map referred to + * by the file descriptor *map_fd*. + * + * The *flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_ELEM + * Description + * Create or update an element (key/value pair) in a specified map. + * + * The *flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create a new element or update an existing element. + * **BPF_NOEXIST** + * Create a new element only if it did not exist. + * **BPF_EXIST** + * Update an existing element. + * **BPF_F_LOCK** + * Update a spin_lock-ed map element. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, + * **E2BIG**, **EEXIST**, or **ENOENT**. + * + * **E2BIG** + * The number of elements in the map reached the + * *max_entries* limit specified at map creation time. + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_ELEM + * Description + * Look up and delete an element by key in a specified map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_GET_NEXT_KEY + * Description + * Look up an element by key in a specified map and return the key + * of the next element. Can be used to iterate over all elements + * in the map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * The following cases can be used to iterate over all elements of + * the map: + * + * * If *key* is not found, the operation returns zero and sets + * the *next_key* pointer to the key of the first element. + * * If *key* is found, the operation returns zero and sets the + * *next_key* pointer to the key of the next element. + * * If *key* is the last element, returns -1 and *errno* is set + * to **ENOENT**. + * + * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or + * **EINVAL** on error. + * + * BPF_PROG_LOAD + * Description + * Verify and load an eBPF program, returning a new file + * descriptor associated with the program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES). + * + * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is + * automatically enabled for the new file descriptor. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_PIN + * Description + * Pin an eBPF program or map referred by the specified *bpf_fd* + * to the provided *pathname* on the filesystem. + * + * The *pathname* argument must not contain a dot ("."). + * + * On success, *pathname* retains a reference to the eBPF object, + * preventing deallocation of the object when the original + * *bpf_fd* is closed. This allow the eBPF object to live beyond + * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent + * process. + * + * Applying **unlink**\ (2) or similar calls to the *pathname* + * unpins the object from the filesystem, removing the reference. + * If no other file descriptors or filesystem nodes refer to the + * same object, it will be deallocated (see NOTES). + * + * The filesystem type for the parent directory of *pathname* must + * be **BPF_FS_MAGIC**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_OBJ_GET + * Description + * Open a file descriptor for the eBPF object pinned to the + * specified *pathname*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_PROG_ATTACH + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook. + * + * The *attach_type* specifies the eBPF attachment point to + * attach the program to, and must be one of *bpf_attach_type* + * (see below). + * + * The *attach_bpf_fd* must be a valid file descriptor for a + * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap + * or sock_ops type corresponding to the specified *attach_type*. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_TYPE_SK_SKB**, + * **BPF_PROG_TYPE_SK_MSG** + * + * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_DETACH + * Description + * Detach the eBPF program associated with the *target_fd* at the + * hook specified by *attach_type*. The program must have been + * previously attached using **BPF_PROG_ATTACH**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_TEST_RUN + * Description + * Run the eBPF program associated with the *prog_fd* a *repeat* + * number of times against a provided program context *ctx_in* and + * data *data_in*, and return the modified program context + * *ctx_out*, *data_out* (for example, packet data), result of the + * execution *retval*, and *duration* of the test run. + * + * The sizes of the buffers provided as input and output + * parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must + * be provided in the corresponding variables *ctx_size_in*, + * *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any + * of these parameters are not provided (ie set to NULL), the + * corresponding size field must be zero. + * + * Some program types have particular requirements: + * + * **BPF_PROG_TYPE_SK_LOOKUP** + * *data_in* and *data_out* must be NULL. + * + * **BPF_PROG_TYPE_RAW_TRACEPOINT**, + * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE** + * + * *ctx_out*, *data_in* and *data_out* must be NULL. + * *repeat* must be zero. + * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * **ENOSPC** + * Either *data_size_out* or *ctx_size_out* is too small. + * **ENOTSUPP** + * This command is not supported by the program type of + * the program referred to by *prog_fd*. + * + * BPF_PROG_GET_NEXT_ID + * Description + * Fetch the next eBPF program currently loaded into the kernel. + * + * Looks for the eBPF program with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF programs + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_GET_NEXT_ID + * Description + * Fetch the next eBPF map currently loaded into the kernel. + * + * Looks for the eBPF map with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF maps + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_PROG_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF program corresponding to + * *prog_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF map corresponding to + * *map_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_GET_INFO_BY_FD + * Description + * Obtain information about the eBPF object corresponding to + * *bpf_fd*. + * + * Populates up to *info_len* bytes of *info*, which will be in + * one of the following formats depending on the eBPF object type + * of *bpf_fd*: + * + * * **struct bpf_prog_info** + * * **struct bpf_map_info** + * * **struct bpf_btf_info** + * * **struct bpf_link_info** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_QUERY + * Description + * Obtain information about eBPF programs associated with the + * specified *attach_type* hook. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_QUERY** always fetches the number of programs + * attached and the *attach_flags* which were used to attach those + * programs. Additionally, if *prog_ids* is nonzero and the number + * of attached programs is less than *prog_cnt*, populates + * *prog_ids* with the eBPF program ids of the programs attached + * at *target_fd*. + * + * The following flags may alter the result: + * + * **BPF_F_QUERY_EFFECTIVE** + * Only return information regarding programs which are + * currently effective at the specified *target_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_RAW_TRACEPOINT_OPEN + * Description + * Attach an eBPF program to a tracepoint *name* to access kernel + * internal arguments of the tracepoint in their raw form. + * + * The *prog_fd* must be a valid file descriptor associated with + * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**. + * + * No ABI guarantees are made about the content of tracepoint + * arguments exposed to the corresponding eBPF program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_LOAD + * Description + * Verify and load BPF Type Format (BTF) metadata into the kernel, + * returning a new file descriptor associated with the metadata. + * BTF is described in more detail at + * https://www.kernel.org/doc/html/latest/bpf/btf.html. + * + * The *btf* parameter must point to valid memory providing + * *btf_size* bytes of BTF binary metadata. + * + * The returned file descriptor can be passed to other **bpf**\ () + * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to + * associate the BTF with those objects. + * + * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional + * parameters to specify a *btf_log_buf*, *btf_log_size* and + * *btf_log_level* which allow the kernel to return freeform log + * output regarding the BTF verification process. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_GET_FD_BY_ID + * Description + * Open a file descriptor for the BPF Type Format (BTF) + * corresponding to *btf_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_TASK_FD_QUERY + * Description + * Obtain information about eBPF programs associated with the + * target process identified by *pid* and *fd*. + * + * If the *pid* and *fd* are associated with a tracepoint, kprobe + * or uprobe perf event, then the *prog_id* and *fd_type* will + * be populated with the eBPF program id and file descriptor type + * of type **bpf_task_fd_type**. If associated with a kprobe or + * uprobe, the *probe_offset* and *probe_addr* will also be + * populated. Optionally, if *buf* is provided, then up to + * *buf_len* bytes of *buf* will be populated with the name of + * the tracepoint, kprobe or uprobe. + * + * The resulting *prog_id* may be introspected in deeper detail + * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_LOOKUP_AND_DELETE_ELEM + * Description + * Look up an element with the given *key* in the map referred to + * by the file descriptor *fd*, and if found, delete the element. + * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * + * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types + * implement this command as a "pop" operation, deleting the top + * element rather than one corresponding to *key*. + * The *key* and *key_len* parameters should be zeroed when + * issuing this operation for these map types. + * + * This command is only valid for the following map types: + * * **BPF_MAP_TYPE_QUEUE** + * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_FREEZE + * Description + * Freeze the permissions of the specified map. + * + * Write permissions may be frozen by passing zero *flags*. + * Upon success, no future syscall invocations may alter the + * map state of *map_fd*. Write operations from eBPF programs + * are still possible for a frozen map. + * + * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_BTF_GET_NEXT_ID + * Description + * Fetch the next BPF Type Format (BTF) object currently loaded + * into the kernel. + * + * Looks for the BTF object with an id greater than *start_id* + * and updates *next_id* on success. If no other BTF objects + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_LOOKUP_BATCH + * Description + * Iterate and fetch multiple elements in a map. + * + * Two opaque values are used to manage batch operations, + * *in_batch* and *out_batch*. Initially, *in_batch* must be set + * to NULL to begin the batched operation. After each subsequent + * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant + * *out_batch* as the *in_batch* for the next operation to + * continue iteration from the current point. + * + * The *keys* and *values* are output parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are copied into the + * user buffer, with the keys copied into *keys* and the values + * copied into the corresponding indices in *values*. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **ENOSPC** to indicate that *keys* or + * *values* is too small to dump an entire bucket during + * iteration of a hash-based map type. + * + * BPF_MAP_LOOKUP_AND_DELETE_BATCH + * Description + * Iterate and delete all elements in a map. + * + * This operation has the same behavior as + * **BPF_MAP_LOOKUP_BATCH** with two exceptions: + * + * * Every element that is successfully returned is also deleted + * from the map. This is at least *count* elements. Note that + * *count* is both an input and an output parameter. + * * Upon returning with *errno* set to **EFAULT**, up to + * *count* elements may be deleted without returning the keys + * and values of the deleted elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_BATCH + * Description + * Update multiple elements in a map by *key*. + * + * The *keys* and *values* are input parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * Each element specified in *keys* is sequentially updated to the + * value in the corresponding index in *values*. The *in_batch* + * and *out_batch* parameters are ignored and should be zeroed. + * + * The *elem_flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create new elements or update a existing elements. + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * **BPF_EXIST** + * Update existing elements. + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or + * **E2BIG**. **E2BIG** indicates that the number of elements in + * the map reached the *max_entries* limit specified at map + * creation time. + * + * May set *errno* to one of the following error codes under + * specific circumstances: + * + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_BATCH + * Description + * Delete multiple elements in a map by *key*. + * + * The *keys* parameter is an input parameter which must point + * to memory large enough to hold *count* items based on the key + * size of the map *map_fd*, that is, *key_size* * *count*. + * + * Each element specified in *keys* is sequentially deleted. The + * *in_batch*, *out_batch*, and *values* parameters are ignored + * and should be zeroed. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. If + * *errno* is **EFAULT**, up to *count* elements may be been + * deleted. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_CREATE + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook and return a file descriptor handle for + * managing the link. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_UPDATE + * Description + * Update the eBPF program in the specified *link_fd* to + * *new_prog_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF Link corresponding to + * *link_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_GET_NEXT_ID + * Description + * Fetch the next eBPF link currently loaded into the kernel. + * + * Looks for the eBPF link with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF links + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_ENABLE_STATS + * Description + * Enable eBPF runtime statistics gathering. + * + * Runtime statistics gathering for the eBPF runtime is disabled + * by default to minimize the corresponding performance overhead. + * This command enables statistics globally. + * + * Multiple programs may independently enable statistics. + * After gathering the desired statistics, eBPF runtime statistics + * may be disabled again by calling **close**\ (2) for the file + * descriptor returned by this function. Statistics will only be + * disabled system-wide when all outstanding file descriptors + * returned by prior calls for this subcommand are closed. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_ITER_CREATE + * Description + * Create an iterator on top of the specified *link_fd* (as + * previously created using **BPF_LINK_CREATE**) and return a + * file descriptor that can be used to trigger the iteration. + * + * If the resulting file descriptor is pinned to the filesystem + * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls + * for that path will trigger the iterator to read kernel state + * using the eBPF program attached to *link_fd*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_DETACH + * Description + * Forcefully detach the specified *link_fd* from its + * corresponding attachment point. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_BIND_MAP + * Description + * Bind a map to the lifetime of an eBPF program. + * + * The map identified by *map_fd* is bound to the program + * identified by *prog_fd* and only released when *prog_fd* is + * released. This may be used in cases where metadata should be + * associated with a program which otherwise does not contain any + * references to the map (for example, embedded in the eBPF + * program instructions). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * NOTES + * eBPF objects (maps and programs) can be shared between processes. + * + * * After **fork**\ (2), the child inherits file descriptors + * referring to the same eBPF objects. + * * File descriptors referring to eBPF objects can be transferred over + * **unix**\ (7) domain sockets. + * * File descriptors referring to eBPF objects can be duplicated in the + * usual way, using **dup**\ (2) and similar calls. + * * File descriptors referring to eBPF objects can be pinned to the + * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2). + * + * An eBPF object is deallocated only after all file descriptors referring + * to the object have been closed and no references remain pinned to the + * filesystem or attached (for example, bound to a program or device). + */ enum bpf_cmd { BPF_MAP_CREATE, BPF_MAP_LOOKUP_ELEM, @@ -100,6 +875,7 @@ enum bpf_cmd { BPF_PROG_ATTACH, BPF_PROG_DETACH, BPF_PROG_TEST_RUN, + BPF_PROG_RUN = BPF_PROG_TEST_RUN, BPF_PROG_GET_NEXT_ID, BPF_MAP_GET_NEXT_ID, BPF_PROG_GET_FD_BY_ID, @@ -147,7 +923,14 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, @@ -158,6 +941,9 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, + BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -200,6 +986,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ + BPF_PROG_TYPE_NETFILTER, }; enum bpf_attach_type { @@ -241,6 +1029,17 @@ enum bpf_attach_type { BPF_XDP_CPUMAP, BPF_SK_LOOKUP, BPF_XDP, + BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, + BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, + BPF_STRUCT_OPS, + BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -254,10 +1053,25 @@ enum bpf_link_type { BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, - + BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, + BPF_LINK_TYPE_STRUCT_OPS = 9, + BPF_LINK_TYPE_NETFILTER = 10, + BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, MAX_BPF_LINK_TYPE, }; +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -304,7 +1118,12 @@ enum bpf_link_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ #define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -313,7 +1132,7 @@ enum bpf_link_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) -/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will allow any alignment whatsoever. On platforms * with strict alignment requirements for loads ands stores (such * as sparc and mips) the verifier validates that all loads and @@ -356,27 +1175,60 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) -/* When BPF ldimm64's insn[0].src_reg != 0 then this can have - * the following extensions: - * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd - * insn[1].imm: 0 - * insn[0].off: 0 - * insn[1].off: 0 - * ldimm64 rewrite: address of map +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_UPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) + +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * the following extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -387,11 +1239,24 @@ enum bpf_link_type { * is struct/union. */ #define BPF_PSEUDO_BTF_ID 3 +/* insn[0].src_reg: BPF_PSEUDO_FUNC + * insn[0].imm: insn offset to the func + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the function + * verifier type: PTR_TO_FUNC. + */ +#define BPF_PSEUDO_FUNC 4 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function */ #define BPF_PSEUDO_CALL 1 +/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL, + * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel + */ +#define BPF_PSEUDO_KFUNC_CALL 2 /* flags for BPF_MAP_UPDATE_ELEM command */ enum { @@ -439,13 +1304,19 @@ enum { /* Create a map that is suitable to be an inner map with dynamic max entries */ BPF_F_INNER_MAP = (1U << 12), + +/* Create a map that will be registered/unregesitered by the backed bpf_link */ + BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* 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. + * attach_flags with this flag are always returned 0. */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -453,6 +1324,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -503,6 +1376,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -563,23 +1443,44 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 core_relo_cnt; /* number of bpf_core_relo */ + __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 log_true_size; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; __u32 attach_type; __u32 attach_flags; - __u32 replace_bpf_fd; /* previously attached eBPF - * program to replace if - * BPF_F_REPLACE is used - */ + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -603,6 +1504,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -624,12 +1526,26 @@ union bpf_attr { } info; struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __u32 target_fd; /* container object to query */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; __u32 query_flags; __u32 attach_flags; __aligned_u64 prog_ids; - __u32 prog_cnt; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; + /* output: per-program attach_flags. + * not allowed to be set during effective query. + */ + __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -643,6 +1559,11 @@ union bpf_attr { __u32 btf_size; __u32 btf_log_size; __u32 btf_log_level; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 btf_log_true_size; }; struct { @@ -662,30 +1583,89 @@ union bpf_attr { } task_fd_query; struct { /* struct used by BPF_LINK_CREATE command */ - __u32 prog_fd; /* eBPF program to attach */ union { - __u32 target_fd; /* object to attach to */ - __u32 target_ifindex; /* target ifindex */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 map_fd; /* struct_ops to attach */ + }; + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ union { - __u32 target_btf_id; /* btf_id of target to attach to */ + __u32 target_btf_id; /* btf_id of target to attach to */ struct { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ }; + struct { + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 bpf_cookie; + } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; + struct { + /* this is overlaid with the target_btf_id above. */ + __u32 target_btf_id; + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 cookie; + } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 cnt; + __u32 flags; + __u32 pid; + } uprobe_multi; }; } 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; + union { + /* new program fd to update link with */ + __u32 new_prog_fd; + /* new struct_ops map fd to update link with */ + __u32 new_map_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; + union { + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags. + */ + __u32 old_prog_fd; + /* expected link's map fd; is specified only + * if BPF_F_REPLACE flag is set. + */ + __u32 old_map_fd; + }; } link_update; struct { @@ -714,7 +1694,7 @@ union bpf_attr { * parsed and used to produce a manual page. The workflow is the following, * and requires the rst2man utility: * - * $ ./scripts/bpf_helpers_doc.py \ + * $ ./scripts/bpf_doc.py \ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 * $ man /tmp/bpf-helpers.7 @@ -779,17 +1759,17 @@ union bpf_attr { * Description * This helper is a "printk()-like" facility for debugging. It * prints a message defined by format *fmt* (of size *fmt_size*) - * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * to file *\/sys/kernel/tracing/trace* from TraceFS, if * available. It can take up to three additional **u64** * arguments (as an eBPF helpers, the total number of arguments is * limited to five). * * Each time the helper is called, it appends a line to the trace. - * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is - * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. + * Lines are discarded while *\/sys/kernel/tracing/trace* is + * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this. * The format of the trace is customizable, and the exact output * one will get depends on the options set in - * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *\/sys/kernel/tracing/trace_options* (see also the * *README* file under the same directory). However, it usually * defaults to something like: * @@ -849,7 +1829,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return @@ -956,7 +1936,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * @@ -985,6 +1965,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -992,6 +1974,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -1134,6 +2118,9 @@ union bpf_attr { * sending the packet. This flag was added for GRE * encapsulation, but might be used with other protocols * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. * * Here is a typical usage on the transmit path: * @@ -1466,6 +2453,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -1496,8 +2485,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -1529,7 +2518,8 @@ union bpf_attr { * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes * from *skb* readable and writable. If a zero value is passed for - * *len*, then the whole length of the *skb* is pulled. + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. * * This helper is only needed for reading and writing with direct * packet access. @@ -1579,6 +2569,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -1650,24 +2642,34 @@ union bpf_attr { * networking traffic statistics as it provides a global socket * identifier that can be assumed unique. * Return - * A 8-byte long non-decreasing number on success, or 0 if the - * socket field is missing inside *skb*. + * A 8-byte long unique 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** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique 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** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. + * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -1702,14 +2704,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -1728,10 +2735,12 @@ union bpf_attr { * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). + * (room space is added or removed between the layer 2 and + * layer 3 headers). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). + * (room space is added or removed between the layer 3 and + * layer 4 headers). * * The following flags are supported at this time: * @@ -1751,6 +2760,15 @@ union bpf_attr { * Use with ENCAP_L3/L4 flags to further specify the tunnel * type; *len* is the length of the inner MAC header. * + * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**: + * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the + * L2 type as Ethernet. + * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -1759,7 +2777,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -1771,8 +2789,12 @@ union bpf_attr { * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. Any higher bits in the *flags* argument must be - * unset. + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. * * See also **bpf_redirect**\ (), which only supports redirecting * to an ifindex, but doesn't require a map to do so. @@ -1891,7 +2913,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see @@ -1916,12 +2938,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * @@ -2155,8 +3175,18 @@ union bpf_attr { * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. * **BPF_F_USER_BUILD_ID** - * Collect buildid+offset instead of ips for user stack, - * only valid if **BPF_F_USER_STACK** is also specified. + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. * * **bpf_get_stack**\ () can collect up to * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject @@ -2169,8 +3199,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -2213,9 +3243,18 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -2225,6 +3264,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long 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. @@ -2431,6 +3473,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -2448,7 +3493,7 @@ union bpf_attr { * running simultaneously. * * A user should care about the synchronization by himself. - * For example, by using the **BPF_STX_XADD** instruction to alter + * For example, by using the **BPF_ATOMIC** instructions to alter * the shared data. * Return * A pointer to the local storage area. @@ -2456,7 +3501,7 @@ union bpf_attr { * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) * Description * Select a **SO_REUSEPORT** socket from a - * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. * It checks the selected socket is matching the incoming * request in the socket buffer. * Return @@ -2741,10 +3786,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -2927,10 +3973,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -2993,10 +4040,10 @@ union bpf_attr { * 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: + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: * * :: * @@ -3024,7 +4071,7 @@ union bpf_attr { * **->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, + * On success, the strictly positive length of the output string, * including the trailing NUL character. On error, a negative * value. * @@ -3177,9 +4224,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This @@ -3247,7 +4291,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -3316,12 +4360,20 @@ union bpf_attr { * of new data availability is sent. * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * An adaptive notification is a notification sent whenever the user-space + * process has caught up and consumed all available payloads. In case the user-space + * process is still processing a previous payload, then no notification is needed + * as it will process the newly added payload automatically. * Return * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * *flags* must be 0. * Return * Valid pointer with *size* bytes of memory available; NULL, * otherwise. @@ -3333,6 +4385,10 @@ union bpf_attr { * of new data availability is sent. * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. * Return * Nothing. Always succeeds. * @@ -3343,6 +4399,10 @@ union bpf_attr { * of new data availability is sent. * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. * Return * Nothing. Always succeeds. * @@ -3454,8 +4514,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description @@ -3548,7 +4608,7 @@ union bpf_attr { * * **-EEXIST** if the option already exists. * - * **-EFAULT** on failrue to parse the existing header options. + * **-EFAULT** on failure to parse the existing header options. * * **-EPERM** if the helper cannot be used under the current * *skops*\ **->op**. @@ -3623,147 +4683,943 @@ union bpf_attr { * including the trailing NUL character. On error, a negative * value. * - * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) - * Description - * Read *size* bytes from user space address *user_ptr* and store - * the data in *dst*. This is a wrapper of **copy_from_user**\ (). - * Return - * 0 on success, or a negative error in case of failure. + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of **copy_from_user**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags) + * Description + * Use BTF to store a string representation of *ptr*->ptr in *str*, + * using *ptr*->type_id. This value should specify the type + * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) + * can be used to look up vmlinux BTF type ids. Traversing the + * data structure using BTF, the type information and values are + * stored in the first *str_size* - 1 bytes of *str*. Safe copy of + * the pointer data is carried out to avoid kernel crashes during + * operation. Smaller types can use string space on the stack; + * larger programs can use map data to store the string + * representation. + * + * The string can be subsequently shared with userspace via + * bpf_perf_event_output() or ring buffer interfaces. + * bpf_trace_printk() is to be avoided as it places too small + * a limit on string size to be useful. + * + * *flags* is a combination of + * + * **BTF_F_COMPACT** + * no formatting around type information + * **BTF_F_NONAME** + * no struct/union member names/types + * **BTF_F_PTR_RAW** + * show raw (unobfuscated) pointer values; + * equivalent to printk specifier %px. + * **BTF_F_ZERO** + * show zero-valued struct/union members; they + * are not displayed by default + * + * Return + * The number of bytes that were written (or would have been + * written if output had to be truncated due to string size), + * or a negative error in cases of failure. + * + * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags) + * Description + * Use BTF to write to seq_write a string representation of + * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). + * *flags* are identical to those used for bpf_snprintf_btf. + * Return + * 0 on success or a negative error in case of failure. + * + * u64 bpf_skb_cgroup_classid(struct sk_buff *skb) + * Description + * See **bpf_get_cgroup_classid**\ () for the main description. + * This helper differs from **bpf_get_cgroup_classid**\ () in that + * the cgroup v1 net_cls class is retrieved only from the *skb*'s + * associated socket instead of the current process. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex* + * and fill in L2 addresses from neighboring subsystem. This helper + * is somewhat similar to **bpf_redirect**\ (), except that it + * populates L2 addresses as well, meaning, internally, the helper + * relies on the neighbor lookup for the L2 address of the nexthop. + * + * The helper will perform a FIB lookup based on the skb's + * networking header to get the address of the next hop, unless + * this is supplied by the caller in the *params* argument. The + * *plen* argument indicates the len of *params* and should be set + * to 0 if *params* is NULL. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types, and enabled + * for IPv4 and IPv6 protocols. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + * + * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on *cpu*. A ksym is an + * extern variable decorated with '__ksym'. For ksym, there is a + * global var (either static or global) defined of the same name + * in the kernel. The ksym is percpu if the global var is percpu. + * The returned pointer points to the global percpu var on *cpu*. + * + * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the + * kernel, except that bpf_per_cpu_ptr() may return NULL. This + * happens if *cpu* is larger than nr_cpu_ids. The caller of + * bpf_per_cpu_ptr() must check the returned value. + * Return + * A pointer pointing to the kernel percpu variable on *cpu*, or + * NULL, if *cpu* is invalid. + * + * void *bpf_this_cpu_ptr(const void *percpu_ptr) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on this cpu. See the + * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * + * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in + * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would + * never return NULL. + * Return + * A pointer pointing to the kernel percpu variable on this cpu. + * + * long bpf_redirect_peer(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device and + * the netns switch takes place from ingress to ingress without + * going through the CPU's backlog queue. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types at the ingress + * hook and for veth device types. The peer device must reside in a + * different network namespace. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + * + * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *task*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *task* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this + * helper enforces the key must be a task_struct and the map must also + * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * + * Underneath, the value is stored locally at *task* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *task*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task) + * Description + * Delete a bpf_local_storage from a *task*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * struct task_struct *bpf_get_current_task_btf(void) + * Description + * Return a BTF pointer to the "current" task. + * This pointer can also be used in helpers that accept an + * *ARG_PTR_TO_BTF_ID* of type *task_struct*. + * Return + * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's available). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + * Check packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing a *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, which is why it is not considered + * a failure. Other BPF helpers are needed for performing the + * planned size change; therefore the responsibility for catching + * a negative packet size belongs in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * On input *mtu_len* must be a valid pointer, else verifier will + * reject BPF program. If the value *mtu_len* is initialized to + * zero then the ctx packet size is use. When value *mtu_len* is + * provided as input this specify the L3 length that the MTU check + * is done against. Remember XDP and TC length operate at L2, but + * this value is L3 as this correlate to MTU and IP-header tot_len + * values which are L3 (similar behavior as bpf_fib_lookup). + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TC length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * + * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For each element in **map**, call **callback_fn** function with + * **map**, **callback_ctx** and other map-specific parameters. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. + * + * The following are a list of supported map types and their + * respective expected callback signatures: + * + * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, + * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY + * + * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx); + * + * For per_cpu maps, the map_value is the value on the cpu where the + * bpf_prog is running. + * + * If **callback_fn** return 0, the helper will continue to the next + * element. If return value is 1, the helper will skip the rest of + * elements and return. Other return values are not used now. + * + * Return + * The number of traversed map elements for success, **-EINVAL** for + * invalid **flags**. + * + * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len) + * Description + * Outputs a string into the **str** buffer of size **str_size** + * based on a format string stored in a read-only map pointed by + * **fmt**. + * + * Each format specifier in **fmt** corresponds to one u64 element + * in the **data** array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. + * + * Formats **%s** and **%p{i,I}{4,6}** require to read kernel + * memory. Reading kernel memory may fail due to either invalid + * address or valid address but requiring a major memory fault. If + * reading kernel memory fails, the string for **%s** will be an + * empty string, and the ip address for **%p{i,I}{4,6}** will be 0. + * Not returning error to bpf program is consistent with what + * **bpf_trace_printk**\ () does for now. + * + * Return + * The strictly positive length of the formatted string, including + * the trailing zero character. If the return value is greater than + * **str_size**, **str** contains a truncated string, guaranteed to + * be zero-terminated except when **str_size** is 0. + * + * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + * + * long bpf_sys_close(u32 fd) + * Description + * Execute close syscall for given FD. + * Return + * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * *flags* can be one of: + * + * **BPF_F_TIMER_ABS** + * Start the timer in absolute expire value instead of the + * default relative one. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. + * + * u64 bpf_get_func_ip(void *ctx) + * Description + * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * + * Return + * Address of the traced function for kprobe. + * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. + * + * u64 bpf_get_attach_cookie(void *ctx) + * Description + * Get bpf_cookie value provided (optionally) during the program + * attachment. It might be different for each individual + * attachment, even if BPF program itself is the same. + * Expects BPF program context *ctx* as a first argument. + * + * Supported for the following program types: + * - kprobe/uprobe; + * - tracepoint; + * - perf_event. + * Return + * Value specified by user at BPF link creation/attachment time + * or 0, if it was not specified. + * + * long bpf_task_pt_regs(struct task_struct *task) + * Description + * Get the struct pt_regs associated with **task**. + * Return + * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument register (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= argument register count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of registers of the traced function (for tracing programs) where + * function arguments are stored in these registers. + * + * Return + * The number of argument registers of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * Return + * The BPF program's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Note that there is the following corner case where the program exports an error + * via bpf_set_retval but signals success via 'return 1': + * + * bpf_set_retval(-EPERM); + * return 1; + * + * In this case, the BPF program's return value will use helper's -EPERM. This + * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case. + * + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. + * + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) + * Description + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. + * + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp + * instead. + * + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. + * + * void *bpf_kptr_xchg(void *map_value, void *ptr) + * Description + * Exchange kptr at pointer *map_value* with *ptr*, and return the + * old value. *ptr* can be NULL, otherwise it must be a referenced + * pointer which will be released when this helper is called. + * Return + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. + * + * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu) + * Description + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * Return + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. + * + * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. + * + * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * Return + * 0 on success, or a negative error in case of failure. + * + * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * Return + * Nothing. Always succeeds. + * + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) + * Description + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. + * + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * Description + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * + * *flags* must be 0 except for skb-type dynptrs. + * + * For skb-type dynptrs: + * * All data slices of the dynptr are automatically + * invalidated after **bpf_dynptr_write**\ (). This is + * because writing may pull the skb and change the + * underlying packet buffer. + * + * * For *flags*, please see the flags accepted by + * **bpf_skb_store_bytes**\ (). + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, + * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). + * + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) + * Description + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * + * skb and xdp type dynptrs may not use bpf_dynptr_data. They should + * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr. + * Return + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. * - * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags) + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) * Description - * Use BTF to store a string representation of *ptr*->ptr in *str*, - * using *ptr*->type_id. This value should specify the type - * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) - * can be used to look up vmlinux BTF type ids. Traversing the - * data structure using BTF, the type information and values are - * stored in the first *str_size* - 1 bytes of *str*. Safe copy of - * the pointer data is carried out to avoid kernel crashes during - * operation. Smaller types can use string space on the stack; - * larger programs can use map data to store the string - * representation. + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. * - * The string can be subsequently shared with userspace via - * bpf_perf_event_output() or ring buffer interfaces. - * bpf_trace_printk() is to be avoided as it places too small - * a limit on string size to be useful. + * *iph* points to the IPv4 header. * - * *flags* is a combination of + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. * - * **BTF_F_COMPACT** - * no formatting around type information - * **BTF_F_NONAME** - * no struct/union member names/types - * **BTF_F_PTR_RAW** - * show raw (unobfuscated) pointer values; - * equivalent to printk specifier %px. - * **BTF_F_ZERO** - * show zero-valued struct/union members; they - * are not displayed by default + * On failure, the returned value is one of the following: * - * Return - * The number of bytes that were written (or would have been - * written if output had to be truncated due to string size), - * or a negative error in cases of failure. + * **-EACCES** if the SYN cookie is not valid. * - * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags) + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) * Description - * Use BTF to write to seq_write a string representation of - * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). - * *flags* are identical to those used for bpf_snprintf_btf. - * Return - * 0 on success or a negative error in case of failure. + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. * - * u64 bpf_skb_cgroup_classid(struct sk_buff *skb) - * Description - * See **bpf_get_cgroup_classid**\ () for the main description. - * This helper differs from **bpf_get_cgroup_classid**\ () in that - * the cgroup v1 net_cls class is retrieved only from the *skb*'s - * associated socket instead of the current process. - * Return - * The id is returned or 0 in case the id could not be retrieved. + * *iph* points to the IPv6 header. * - * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags) - * Description - * Redirect the packet to another net device of index *ifindex* - * and fill in L2 addresses from neighboring subsystem. This helper - * is somewhat similar to **bpf_redirect**\ (), except that it - * populates L2 addresses as well, meaning, internally, the helper - * relies on the neighbor lookup for the L2 address of the nexthop. + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. * - * The helper will perform a FIB lookup based on the skb's - * networking header to get the address of the next hop, unless - * this is supplied by the caller in the *params* argument. The - * *plen* argument indicates the len of *params* and should be set - * to 0 if *params* is NULL. + * On failure, the returned value is one of the following: * - * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types, and enabled - * for IPv4 and IPv6 protocols. - * Return - * The helper returns **TC_ACT_REDIRECT** on success or - * **TC_ACT_SHOT** on error. + * **-EACCES** if the SYN cookie is not valid. * - * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu) - * Description - * Take a pointer to a percpu ksym, *percpu_ptr*, and return a - * pointer to the percpu kernel variable on *cpu*. A ksym is an - * extern variable decorated with '__ksym'. For ksym, there is a - * global var (either static or global) defined of the same name - * in the kernel. The ksym is percpu if the global var is percpu. - * The returned pointer points to the global percpu var on *cpu*. + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. * - * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the - * kernel, except that bpf_per_cpu_ptr() may return NULL. This - * happens if *cpu* is larger than nr_cpu_ids. The caller of - * bpf_per_cpu_ptr() must check the returned value. - * Return - * A pointer pointing to the kernel percpu variable on *cpu*, or - * NULL, if *cpu* is invalid. + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. * - * void *bpf_this_cpu_ptr(const void *percpu_ptr) + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * + * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags) * Description - * Take a pointer to a percpu ksym, *percpu_ptr*, and return a - * pointer to the percpu kernel variable on this cpu. See the - * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * Drain samples from the specified user ring buffer, and invoke + * the provided callback for each such sample: * - * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in - * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would - * never return NULL. + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); + * + * If **callback_fn** returns 0, the helper will continue to try + * and drain the next sample, up to a maximum of + * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, + * the helper will skip the rest of the samples and return. Other + * return values are not used now, and will be rejected by the + * verifier. * Return - * A pointer pointing to the kernel percpu variable on this cpu. + * The number of drained samples if no error was encountered while + * draining samples, or 0 if no samples were present in the ring + * buffer. If a user-space producer was epoll-waiting on this map, + * and at least one sample was drained, they will receive an event + * notification notifying them of available space in the ring + * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this + * function, no wakeup notification will be sent. If the + * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will + * be sent even if no sample was drained. * - * long bpf_redirect_peer(u32 ifindex, u64 flags) - * Description - * Redirect the packet to another net device of index *ifindex*. - * This helper is somewhat similar to **bpf_redirect**\ (), except - * that the redirection happens to the *ifindex*' peer device and - * the netns switch takes place from ingress to ingress without - * going through the CPU's backlog queue. + * On failure, the returned value is one of the following: * - * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types at the ingress - * hook and for veth device types. The peer device must reside in a - * different network namespace. - * Return - * The helper returns **TC_ACT_REDIRECT** on success or - * **TC_ACT_SHOT** on error. + * **-EBUSY** if the ring buffer is contended, and another calling + * context was concurrently draining the ring buffer. * - * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags) + * **-EINVAL** if user-space is not properly tracking the ring + * buffer due to the producer position not being aligned to 8 + * bytes, a sample not being aligned to 8 bytes, or the producer + * position not matching the advertised length of a sample. + * + * **-E2BIG** if user-space has tried to publish a sample which is + * larger than the size of the ring buffer, or which cannot fit + * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) * Description - * Get a bpf_local_storage from the *task*. + * Get a bpf_local_storage from the *cgroup*. * * Logically, it could be thought of as getting the value from - * a *map* with *task* as the **key**. From this + * a *map* with *cgroup* as the **key**. From this * perspective, the usage is not much different from - * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this - * helper enforces the key must be an task_struct and the map must also - * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. * - * Underneath, the value is stored locally at *task* instead of - * the *map*. The *map* is used as the bpf-local-storage - * "type". The bpf-local-storage "type" (i.e. the *map*) is - * searched against all bpf_local_storage residing at *task*. + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. * * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be * used such that a new bpf_local_storage will be @@ -3777,232 +5633,241 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf_local_storage. * - * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task) + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) * Description - * Delete a bpf_local_storage from a *task*. + * Delete a bpf_local_storage from a *cgroup*. * Return * 0 on success. * * **-ENOENT** if the bpf_local_storage cannot be found. - * - * struct task_struct *bpf_get_current_task_btf(void) - * Description - * Return a BTF pointer to the "current" task. - * This pointer can also be used in helpers that accept an - * *ARG_PTR_TO_BTF_ID* of type *task_struct*. - * Return - * Pointer to the current task. - * - * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) - * Description - * Set or clear certain options on *bprm*: - * - * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit - * which sets the **AT_SECURE** auxv for glibc. The bit - * is cleared if the flag is not specified. - * Return - * **-EINVAL** if invalid *flags* are passed, zero otherwise. - * - * u64 bpf_ktime_get_coarse_ns(void) - * Description - * Return a coarse-grained version of the time elapsed since - * system boot, in nanoseconds. Does not include time the system - * was suspended. - * - * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) - * Return - * Current *ktime*. - * - * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) - * Description - * Returns the stored IMA hash of the *inode* (if it's avaialable). - * If the hash is larger than *size*, then only *size* - * bytes will be copied to *dst* - * Return - * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if - * invalid arguments are passed. - * - * struct socket *bpf_sock_from_file(struct file *file) - * Description - * If the given file represents a socket, returns the associated - * socket. - * Return - * A pointer to a struct socket on success or NULL if the file is - * not a socket. */ -#define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - FN(redirect_map), \ - FN(sk_redirect_map), \ - FN(sock_map_update), \ - FN(xdp_adjust_meta), \ - FN(perf_event_read_value), \ - FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), \ - FN(sock_ops_cb_flags_set), \ - FN(msg_redirect_map), \ - FN(msg_apply_bytes), \ - FN(msg_cork_bytes), \ - FN(msg_pull_data), \ - FN(bind), \ - FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), \ - FN(get_stack), \ - FN(skb_load_bytes_relative), \ - FN(fib_lookup), \ - FN(sock_hash_update), \ - FN(msg_redirect_hash), \ - FN(sk_redirect_hash), \ - FN(lwt_push_encap), \ - FN(lwt_seg6_store_bytes), \ - FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), \ - FN(rc_repeat), \ - 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), \ - 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), \ - FN(msg_pop_data), \ - FN(rc_pointer_rel), \ - FN(spin_lock), \ - FN(spin_unlock), \ - FN(sk_fullsock), \ - FN(tcp_sock), \ - FN(skb_ecn_set_ce), \ - FN(get_listener_sock), \ - FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), \ - FN(sysctl_get_name), \ - FN(sysctl_get_current_value), \ - FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), \ - FN(strtol), \ - FN(strtoul), \ - FN(sk_storage_get), \ - FN(sk_storage_delete), \ - FN(send_signal), \ - 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), \ - FN(ktime_get_boot_ns), \ - FN(seq_printf), \ - FN(seq_write), \ - FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), \ - FN(ringbuf_output), \ - FN(ringbuf_reserve), \ - FN(ringbuf_submit), \ - FN(ringbuf_discard), \ - FN(ringbuf_query), \ - FN(csum_level), \ - FN(skc_to_tcp6_sock), \ - FN(skc_to_tcp_sock), \ - FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), \ - FN(get_task_stack), \ - FN(load_hdr_opt), \ - FN(store_hdr_opt), \ - FN(reserve_hdr_opt), \ - FN(inode_storage_get), \ - FN(inode_storage_delete), \ - FN(d_path), \ - FN(copy_from_user), \ - FN(snprintf_btf), \ - FN(seq_printf_btf), \ - FN(skb_cgroup_classid), \ - FN(redirect_neigh), \ - FN(per_cpu_ptr), \ - FN(this_cpu_ptr), \ - FN(redirect_peer), \ - FN(task_storage_get), \ - FN(task_storage_delete), \ - FN(get_current_task_btf), \ - FN(bprm_opts_set), \ - FN(ktime_get_coarse_ns), \ - FN(ima_inode_hash), \ - FN(sock_from_file), \ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ -#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN @@ -4055,6 +5920,12 @@ enum { BPF_F_ZERO_CSUM_TX = (1ULL << 1), BPF_F_DONT_FRAGMENT = (1ULL << 2), BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), +}; + +/* BPF_FUNC_skb_get_tunnel_key flags. */ +enum { + BPF_F_TUNINFO_FLAGS = (1ULL << 4), }; /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and @@ -4088,6 +5959,9 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), + BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { @@ -4171,12 +6045,27 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; +/* Flags for bpf_redirect_map helper */ +enum { + BPF_F_BROADCAST = (1ULL << 3), + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -4217,6 +6106,9 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u8 tstamp_type; + __u32 :24; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { @@ -4227,8 +6119,15 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; /* Padding, future use. */ + union { + __u16 tunnel_ext; /* compat */ + __be16 tunnel_flags; + }; __u32 tunnel_label; + union { + __u32 local_ipv4; + __u32 local_ipv6[4]; + }; }; /* user accessible mirror of in-kernel xfrm_state. @@ -4267,6 +6166,11 @@ enum bpf_ret_code { * represented by BPF_REDIRECT above). */ BPF_LWT_REROUTE = 128, + /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR + * to indicate that no custom dissection was performed, and + * fallback to standard dissector is requested. + */ + BPF_FLOW_DISSECTOR_CONTINUE = 129, }; struct bpf_sock { @@ -4280,7 +6184,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; @@ -4349,6 +6254,19 @@ struct bpf_sock_tuple { }; }; +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + struct bpf_xdp_sock { __u32 queue_id; }; @@ -4455,6 +6373,20 @@ struct sk_reuseport_md { __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 */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); }; #define BPF_TAG_SIZE 8 @@ -4495,6 +6427,10 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; + __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; } __attribute__((aligned(8))); struct bpf_map_info { @@ -4512,6 +6448,8 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { @@ -4534,6 +6472,8 @@ struct bpf_link_info { } raw_tracepoint; struct { __u32 attach_type; + __u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */ + __u32 target_btf_id; /* BTF type id inside the object */ } tracing; struct { __u64 cgroup_id; @@ -4542,11 +6482,26 @@ struct bpf_link_info { struct { __aligned_u64 target_name; /* in/out: target_name buffer ptr */ __u32 target_name_len; /* in/out: target_name buffer len */ + + /* If the iter specific field is 32 bits, it can be put + * in the first or second union. Otherwise it should be + * put in the second union. + */ union { struct { __u32 map_id; } map; }; + union { + struct { + __u64 cgroup_id; + __u32 order; + } cgroup; + struct { + __u32 tid; + __u32 pid; + } task; + }; } iter; struct { __u32 netns_ino; @@ -4555,6 +6510,49 @@ struct bpf_link_info { struct { __u32 ifindex; } xdp; + struct { + __u32 map_id; + } struct_ops; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + } kprobe_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; }; } __attribute__((aligned(8))); @@ -4665,6 +6663,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4950,6 +6949,8 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), }; enum { @@ -4975,9 +6976,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ @@ -5006,9 +7011,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; @@ -5023,6 +7038,17 @@ struct bpf_redir_neigh { }; }; +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ @@ -5082,6 +7108,43 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_dynptr { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_root { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 :64; + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_refcount { + __u32 :32; +} __attribute__((aligned(4))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. @@ -5109,16 +7172,21 @@ struct bpf_pidns_info { /* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ struct bpf_sk_lookup { - __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + union { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */ + }; __u32 family; /* Protocol family (AF_INET, AF_INET6) */ __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* @@ -5151,4 +7219,96 @@ enum { BTF_F_ZERO = (1ULL << 3), }; -#endif /* __LINUX_BPF_H__ */ +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + +/* + * Flags to control bpf_timer_start() behaviour. + * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is + * relative to current time. + */ +enum { + BPF_F_TIMER_ABS = (1ULL << 0), +}; + +/* BPF numbers iterator state */ +struct bpf_iter_num { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/headers/vmlinux/vmlinux_net.h b/headers/vmlinux/vmlinux_net.h index 1afcc5d7..db998501 100644 --- a/headers/vmlinux/vmlinux_net.h +++ b/headers/vmlinux/vmlinux_net.h @@ -16,6 +16,9 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif */ +struct llist_node { + struct llist_node *next; +}; struct sk_buff { union { @@ -29,6 +32,7 @@ struct sk_buff { }; struct rb_node rbnode; struct list_head list; + struct llist_node ll_node; }; union { struct sock *sk; @@ -45,6 +49,7 @@ struct sk_buff { void (*destructor)(struct sk_buff *); }; struct list_head tcp_tsorted_anchor; + long unsigned int _sk_redir; }; long unsigned int _nfct; unsigned int len; @@ -59,73 +64,152 @@ struct sk_buff { __u8 peeked: 1; __u8 head_frag: 1; __u8 pfmemalloc: 1; + __u8 pp_recycle: 1; __u8 active_extensions; - __u32 headers_start[0]; - __u8 __pkt_type_offset[0]; - __u8 pkt_type: 3; - __u8 ignore_df: 1; - __u8 nf_trace: 1; - __u8 ip_summed: 2; - __u8 ooo_okay: 1; - __u8 l4_hash: 1; - __u8 sw_hash: 1; - __u8 wifi_acked_valid: 1; - __u8 wifi_acked: 1; - __u8 no_fcs: 1; - __u8 encapsulation: 1; - __u8 encap_hdr_csum: 1; - __u8 csum_valid: 1; - __u8 __pkt_vlan_present_offset[0]; - __u8 vlan_present: 1; - __u8 csum_complete_sw: 1; - __u8 csum_level: 2; - __u8 csum_not_inet: 1; - __u8 dst_pending_confirm: 1; - __u8 ndisc_nodetype: 2; - __u8 ipvs_property: 1; - __u8 inner_protocol_type: 1; - __u8 remcsum_offload: 1; - __u8 offload_fwd_mark: 1; - __u8 offload_l3_fwd_mark: 1; - __u8 tc_skip_classify: 1; - __u8 tc_at_ingress: 1; - __u8 redirected: 1; - __u8 from_ingress: 1; - __u8 decrypted: 1; - __u16 tc_index; union { - __wsum csum; struct { - __u16 csum_start; - __u16 csum_offset; + __u8 __pkt_type_offset[0]; + __u8 pkt_type: 3; + __u8 ignore_df: 1; + __u8 dst_pending_confirm: 1; + __u8 ip_summed: 2; + __u8 ooo_okay: 1; + __u8 __mono_tc_offset[0]; + __u8 mono_delivery_time: 1; + __u8 tc_at_ingress: 1; + __u8 tc_skip_classify: 1; + __u8 remcsum_offload: 1; + __u8 csum_complete_sw: 1; + __u8 csum_level: 2; + __u8 inner_protocol_type: 1; + __u8 l4_hash: 1; + __u8 sw_hash: 1; + __u8 wifi_acked_valid: 1; + __u8 wifi_acked: 1; + __u8 no_fcs: 1; + __u8 encapsulation: 1; + __u8 encap_hdr_csum: 1; + __u8 csum_valid: 1; + __u8 ndisc_nodetype: 2; + __u8 ipvs_property: 1; + __u8 nf_trace: 1; + __u8 redirected: 1; + __u8 from_ingress: 1; + __u8 nf_skip_egress: 1; + __u8 slow_gro: 1; + __u8 csum_not_inet: 1; + __u16 tc_index; + u16 alloc_cpu; + union { + __wsum csum; + struct { + __u16 csum_start; + __u16 csum_offset; + }; + }; + __u32 priority; + int skb_iif; + __u32 hash; + union { + u32 vlan_all; + struct { + __be16 vlan_proto; + __u16 vlan_tci; + }; + }; + union { + unsigned int napi_id; + unsigned int sender_cpu; + }; + __u32 secmark; + union { + __u32 mark; + __u32 reserved_tailroom; + }; + union { + __be16 inner_protocol; + __u8 inner_ipproto; + }; + __u16 inner_transport_header; + __u16 inner_network_header; + __u16 inner_mac_header; + __be16 protocol; + __u16 transport_header; + __u16 network_header; + __u16 mac_header; }; + struct { + __u8 __pkt_type_offset[0]; + __u8 pkt_type: 3; + __u8 ignore_df: 1; + __u8 dst_pending_confirm: 1; + __u8 ip_summed: 2; + __u8 ooo_okay: 1; + __u8 __mono_tc_offset[0]; + __u8 mono_delivery_time: 1; + __u8 tc_at_ingress: 1; + __u8 tc_skip_classify: 1; + __u8 remcsum_offload: 1; + __u8 csum_complete_sw: 1; + __u8 csum_level: 2; + __u8 inner_protocol_type: 1; + __u8 l4_hash: 1; + __u8 sw_hash: 1; + __u8 wifi_acked_valid: 1; + __u8 wifi_acked: 1; + __u8 no_fcs: 1; + __u8 encapsulation: 1; + __u8 encap_hdr_csum: 1; + __u8 csum_valid: 1; + __u8 ndisc_nodetype: 2; + __u8 ipvs_property: 1; + __u8 nf_trace: 1; + __u8 redirected: 1; + __u8 from_ingress: 1; + __u8 nf_skip_egress: 1; + __u8 slow_gro: 1; + __u8 csum_not_inet: 1; + __u16 tc_index; + u16 alloc_cpu; + union { + __wsum csum; + struct { + __u16 csum_start; + __u16 csum_offset; + }; + }; + __u32 priority; + int skb_iif; + __u32 hash; + union { + u32 vlan_all; + struct { + __be16 vlan_proto; + __u16 vlan_tci; + }; + }; + union { + unsigned int napi_id; + unsigned int sender_cpu; + }; + __u32 secmark; + union { + __u32 mark; + __u32 reserved_tailroom; + }; + union { + __be16 inner_protocol; + __u8 inner_ipproto; + }; + __u16 inner_transport_header; + __u16 inner_network_header; + __u16 inner_mac_header; + __be16 protocol; + __u16 transport_header; + __u16 network_header; + __u16 mac_header; + } headers; }; - __u32 priority; - int skb_iif; - __u32 hash; - __be16 vlan_proto; - __u16 vlan_tci; - union { - unsigned int napi_id; - unsigned int sender_cpu; - }; - __u32 secmark; - union { - __u32 mark; - __u32 reserved_tailroom; - }; - union { - __be16 inner_protocol; - __u8 inner_ipproto; - }; - __u16 inner_transport_header; - __u16 inner_network_header; - __u16 inner_mac_header; - __be16 protocol; - __u16 transport_header; - __u16 network_header; - __u16 mac_header; - __u32 headers_end[0]; sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head; @@ -135,4 +219,34 @@ struct sk_buff { struct skb_ext *extensions; }; + + +struct iphdr { + __u8 ihl: 4; + __u8 version: 4; + __u8 tos; + __be16 tot_len; + __be16 id; + __be16 frag_off; + __u8 ttl; + __u8 protocol; + __sum16 check; + union { + struct { + __be32 saddr; + __be32 daddr; + }; + struct { + __be32 saddr; + __be32 daddr; + } addrs; + }; +}; + +struct bpf_nf_ctx { + const struct nf_hook_state *state; + struct sk_buff *skb; +}; + + #endif /* __VMLINUX_NET_H__ */ diff --git a/headers/vmlinux/vmlinux_types.h b/headers/vmlinux/vmlinux_types.h index d7b3bed0..f2010415 100644 --- a/headers/vmlinux/vmlinux_types.h +++ b/headers/vmlinux/vmlinux_types.h @@ -11,4 +11,7 @@ typedef __u64 u64; typedef s64 ktime_t; +typedef u32 uint32_t; + + #endif /* __VMLINUX_TYPES_H__ */ diff --git a/lib/libbpf b/lib/libbpf index a6d7530c..5fc06771 160000 --- a/lib/libbpf +++ b/lib/libbpf @@ -1 +1 @@ -Subproject commit a6d7530cb7dff87ac1e64a540e63b67ddde2e0f9 +Subproject commit 5fc0677111c66a98d76736a1850b8aca1a16a049 diff --git a/netfilter-bpf/Makefile b/netfilter-bpf/Makefile new file mode 100644 index 00000000..48a05475 --- /dev/null +++ b/netfilter-bpf/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) + +USER_TARGETS := netfilter_ip4_blocklist +BPF_TARGETS := netfilter_ip4_blocklist.bpf + + +LIB_DIR = ../lib + +include $(LIB_DIR)/common.mk diff --git a/netfilter-bpf/README.md b/netfilter-bpf/README.md new file mode 100644 index 00000000..b5f6b775 --- /dev/null +++ b/netfilter-bpf/README.md @@ -0,0 +1,20 @@ +# Introduction + +BPF_PROG_TYPE_NETFILTER was introduced in 6.4, now with a new kernel, a bpf program could attach to netfilter hooks and handles package in a similiar way as iptables/nftables. By now, 6.5.0, there is no bpf kfunc implemented yet for DNAT/SNAT, and the only thing a bpf program can do is to decide whether to DROP the package or not. + +* netfilter_ip4_blocklist.c/netfilter_ip4_blocklist.bpf.c + +This sample code implements a simple ipv4 blocklist. +The bpf program drops package if destination ip address hits a match in the map of type BPF_MAP_TYPE_LPM_TRIE, +The userspace code would load the bpf program, attach it to netfilter's FORWARD/OUTPUT hook, and then write ip patterns into the bpf map. + + +# TODO + +This sample hard-codes ip address to be blocked, just for demonstration. +It would be better to break the userspace program into two parts: +* init program +Loads bpf program and pin bpf program and map into somewhere under /sys/fs/bpf +* interactive program +add/delete/query ip blocklist via bpf map under /sys/fs/bpf + diff --git a/netfilter-bpf/netfilter_ip4_blocklist.bpf.c b/netfilter-bpf/netfilter_ip4_blocklist.bpf.c new file mode 100644 index 00000000..fa3655a5 --- /dev/null +++ b/netfilter-bpf/netfilter_ip4_blocklist.bpf.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux_local.h" +#include "linux/bpf.h" +#include + + +#define NF_DROP 0 +#define NF_ACCEPT 1 + +int bpf_dynptr_from_skb(struct sk_buff *skb, + __u64 flags, struct bpf_dynptr *ptr__uninit) __ksym; +void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, + uint32_t offset, void *buffer, uint32_t buffer__sz) __ksym; + + +struct ipv4_lpm_key { + __u32 prefixlen; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct ipv4_lpm_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 200); +} ipv4_lpm_map SEC(".maps"); + + +SEC("netfilter") +int netfilter_ip4block(struct bpf_nf_ctx *ctx) +{ + struct sk_buff *skb = ctx->skb; + struct bpf_dynptr ptr; + struct iphdr *p, iph = {}; + struct ipv4_lpm_key key; + __u32 *pvalue; + + if (skb->len <= 20 || bpf_dynptr_from_skb(skb, 0, &ptr)) + return NF_ACCEPT; + p = bpf_dynptr_slice(&ptr, 0, &iph, sizeof(iph)); + if (!p) + return NF_ACCEPT; + + /* ip4 only */ + if (p->version != 4) + return NF_ACCEPT; + + /* search p->daddr in trie */ + key.prefixlen = 32; + key.data = p->daddr; + pvalue = bpf_map_lookup_elem(&ipv4_lpm_map, &key); + if (pvalue) { + /* cat /sys/kernel/debug/tracing/trace_pipe */ + bpf_printk("rule matched with %d...\n", *pvalue); + return NF_DROP; + } + return NF_ACCEPT; +} + +char _license[] SEC("license") = "GPL"; + diff --git a/netfilter-bpf/netfilter_ip4_blocklist.c b/netfilter-bpf/netfilter_ip4_blocklist.c new file mode 100644 index 00000000..6ef4a0f6 --- /dev/null +++ b/netfilter-bpf/netfilter_ip4_blocklist.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include + + +static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +struct ipv4_lpm_key { + __u32 prefixlen; + __u32 data; +}; + + +int main(int argc, char **argv) +{ + int prog_fd, map_fd; + int err; + struct bpf_object *obj; + struct bpf_program *prog; + union bpf_attr attr = { }; + + obj = bpf_object__open_file("./netfilter_ip4_blocklist.bpf.o", NULL); + if (libbpf_get_error(obj)) { + printf("fail to open bpf file\n"); + return 1; + } + prog = bpf_object__find_program_by_name(obj, "netfilter_ip4block"); + if (!prog) { + printf("fail to find bpf program\n"); + return 1; + } + bpf_program__set_type(prog, BPF_PROG_TYPE_NETFILTER); + if (bpf_object__load(obj)) { + printf("loading BPF object file failed\n"); + return 1; + } + map_fd = bpf_object__find_map_fd_by_name(obj, "ipv4_lpm_map"); + if (map_fd < 0) { + printf("Fail to locate trie ipv4_lpm_map\n"); + return 1; + } + /* attach to netfilter forward handler */ + prog_fd = bpf_program__fd(prog); + attr.link_create.prog_fd = prog_fd; + attr.link_create.attach_type = BPF_NETFILTER; + attr.link_create.netfilter.pf = NFPROTO_IPV4; + attr.link_create.netfilter.hooknum = NF_INET_FORWARD; + attr.link_create.netfilter.priority = -128; + err = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); + if (err < 0) { + perror("Fail to link bpf program to netfilter forward hook\n"); + return 1; + } + /* attach to netfilter output handler */ + attr.link_create.netfilter.hooknum = NF_INET_LOCAL_OUT; + err = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); + if (err < 0) { + perror("Fail to link bpf program to netfilter output hook\n"); + return 1; + } + printf("bpf program/map loaded....\n"); + /* add rules */ + { + struct ipv4_lpm_key key; + __u32 value = 0; + __u8 *p = (__u8 *) &key.data; + /* block 192.168.11.107/32 */ + key.prefixlen = 27; + /* same as key.data = 0x6B0BA8C0; on a little-endian machine */ + p[0] = 192; + p[1] = 168; + p[2] = 11; + p[3] = 107; + bpf_map_update_elem(map_fd, &key, &value, BPF_ANY); + /* block 192.168.11.107/24 */ + key.prefixlen = 24; + value++; + bpf_map_update_elem(map_fd, &key, &value, BPF_ANY); + /* block 192.168.11.107/27 */ + key.prefixlen = 32; + value++; + bpf_map_update_elem(map_fd, &key, &value, BPF_ANY); + /* remove rule */ + /* bpf_map_delete_elem(map_fd, &key); */ + printf("rules inserted, ready to work\n"); + } + while (1) + sleep(600); + return 0; +}