From 254a7d66c6d92193c5f2473c76f4a67a9d22d0a4 Mon Sep 17 00:00:00 2001 From: Yu Watanabe Date: Fri, 24 Dec 2021 11:23:11 +0900 Subject: shared/linux: update linux headers from v5.16-rc6 --- src/shared/linux/bpf.h | 1340 ++++++++++++++++++++++++++++++++++++++++++- src/shared/linux/bpf_insn.h | 28 +- src/shared/linux/dm-ioctl.h | 22 +- src/shared/linux/ethtool.h | 146 +++-- 4 files changed, 1464 insertions(+), 72 deletions(-) diff --git a/src/shared/linux/bpf.h b/src/shared/linux/bpf.h index e6ceac3f7d..ba5af15e25 100644 --- a/src/shared/linux/bpf.h +++ b/src/shared/linux/bpf.h @@ -19,7 +19,8 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#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 +44,11 @@ #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, @@ -78,7 +84,7 @@ 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) */ }; union bpf_iter_link_info { @@ -87,7 +93,748 @@ union bpf_iter_link_info { } map; }; -/* 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. + * + * 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 +847,7 @@ 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, @@ -157,6 +905,8 @@ enum bpf_map_type { BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, + BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -199,6 +949,7 @@ 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 */ }; enum bpf_attach_type { @@ -240,6 +991,10 @@ 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, __MAX_BPF_ATTACH_TYPE }; @@ -253,6 +1008,7 @@ 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, MAX_BPF_LINK_TYPE, }; @@ -358,8 +1114,8 @@ enum bpf_link_type { /* 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[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 @@ -367,15 +1123,19 @@ enum bpf_link_type { * 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 @@ -386,11 +1146,24 @@ 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 { @@ -502,6 +1275,13 @@ 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 */ @@ -556,7 +1336,14 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -669,6 +1456,13 @@ union bpf_attr { __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; }; } link_create; @@ -708,7 +1502,7 @@ 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 @@ -843,7 +1637,7 @@ 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 @@ -1644,22 +2438,30 @@ 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) * Return @@ -1745,6 +2547,10 @@ 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. + * * 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 @@ -1765,8 +2571,12 @@ 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. @@ -2219,6 +3029,9 @@ 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. @@ -2442,7 +3255,7 @@ 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. @@ -2450,7 +3263,7 @@ 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 @@ -2987,10 +3800,10 @@ 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: * * :: * @@ -3018,7 +3831,7 @@ 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. * @@ -3241,7 +4054,7 @@ 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 @@ -3310,12 +4123,20 @@ 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. @@ -3327,6 +4148,10 @@ 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. * @@ -3337,6 +4162,10 @@ 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. * @@ -3742,6 +4571,373 @@ union bpf_attr { * 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 an 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 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. + * + * 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 an *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, why it is not considered a + * failure. Other BPF-helpers are needed for performing the + * planned size change, why the responsability for catch a negative + * packet size belong 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. + * + * 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). + * Return + * Address of the traced function. + * + * 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. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3897,9 +5093,33 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + 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), \ + FN(check_mtu), \ + FN(for_each_map_elem), \ + FN(snprintf), \ + FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ + FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ + FN(get_func_ip), \ + FN(get_attach_cookie), \ + FN(task_pt_regs), \ + FN(get_branch_snapshot), \ + FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -3993,6 +5213,7 @@ 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), }; enum { @@ -4071,6 +5292,17 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +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; \ @@ -4117,6 +5349,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { @@ -4355,6 +5589,20 @@ 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 @@ -4395,6 +5643,8 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { @@ -4412,12 +5662,17 @@ 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 { __aligned_u64 btf; __u32 btf_size; __u32 id; + __aligned_u64 name; + __u32 name_len; + __u32 kernel_btf; } __attribute__((aligned(8))); struct bpf_link_info { @@ -4431,6 +5686,8 @@ 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; @@ -4872,9 +6129,13 @@ 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 */ @@ -4920,6 +6181,17 @@ 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 */ @@ -4979,6 +6251,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. @@ -5006,7 +6283,10 @@ 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) */ diff --git a/src/shared/linux/bpf_insn.h b/src/shared/linux/bpf_insn.h index c459c03c51..92ec06b0e6 100644 --- a/src/shared/linux/bpf_insn.h +++ b/src/shared/linux/bpf_insn.h @@ -134,15 +134,31 @@ struct bpf_insn; .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ - -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_AND *(uint *) (dst_reg + off16) &= src_reg + * BPF_OR *(uint *) (dst_reg + off16) |= src_reg + * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); + * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); + * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/src/shared/linux/dm-ioctl.h b/src/shared/linux/dm-ioctl.h index ab312e13fb..a6cc1cc40f 100644 --- a/src/shared/linux/dm-ioctl.h +++ b/src/shared/linux/dm-ioctl.h @@ -193,8 +193,22 @@ struct dm_name_list { __u32 next; /* offset to the next record from the _start_ of this */ char name[0]; + + /* + * The following members can be accessed by taking a pointer that + * points immediately after the terminating zero character in "name" + * and aligning this pointer to next 8-byte boundary. + * Uuid is present if the flag DM_NAME_LIST_FLAG_HAS_UUID is set. + * + * __u32 event_nr; + * __u32 flags; + * char uuid[0]; + */ }; +#define DM_NAME_LIST_FLAG_HAS_UUID 1 +#define DM_NAME_LIST_FLAG_DOESNT_HAVE_UUID 2 + /* * Used to retrieve the target versions */ @@ -274,7 +288,7 @@ enum { #define DM_VERSION_MAJOR 4 #define DM_VERSION_MINOR 27 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2020-10-01)" +#define DM_VERSION_EXTRA "-ioctl (2021-03-22)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ @@ -362,4 +376,10 @@ enum { */ #define DM_INTERNAL_SUSPEND_FLAG (1 << 18) /* Out */ +/* + * If set, returns in the in buffer passed by UM, the raw table information + * that would be measured by IMA subsystem on device state change. + */ +#define DM_IMA_MEASUREMENT_FLAG (1 << 19) /* In */ + #endif /* _LINUX_DM_IOCTL_H */ diff --git a/src/shared/linux/ethtool.h b/src/shared/linux/ethtool.h index 974d4292e7..cf20b6dba5 100644 --- a/src/shared/linux/ethtool.h +++ b/src/shared/linux/ethtool.h @@ -14,7 +14,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H -#include +#include #include #include @@ -30,6 +30,14 @@ * have the same layout for 32-bit and 64-bit userland. */ +/* Note on reserved space. + * Reserved fields must not be accessed directly by user space because + * they may be replaced by a different field in the future. They must + * be initialized to zero before making the request, e.g. via memset + * of the entire structure or implicitly by not being set in a structure + * initializer. + */ + /** * struct ethtool_cmd - DEPRECATED, link control and status * This structure is DEPRECATED, please use struct ethtool_link_settings. @@ -71,6 +79,7 @@ * and other link features that the link partner advertised * through autonegotiation; 0 if unknown or not applicable. * Read-only. + * @reserved: Reserved for future use; see the note on reserved space. * * The link speed in Mbps is split between @speed and @speed_hi. Use * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to @@ -159,6 +168,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * @bus_info: Device bus address. This should match the dev_name() * string for the underlying bus device, if there is one. May be * an empty string. + * @reserved2: Reserved for future use; see the note on reserved space. * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and * %ETHTOOL_SPFLAGS commands; also the number of strings in the * %ETH_SS_PRIV_FLAGS set @@ -227,7 +237,7 @@ enum tunable_id { ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* * Add your fresh new tunable attribute above and remember to update - * tunable_strings[] in net/core/ethtool.c + * tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_TUNABLE_COUNT, }; @@ -291,7 +301,7 @@ enum phy_tunable_id { ETHTOOL_PHY_EDPD, /* * Add your fresh new phy tunable attribute above and remember to update - * phy_tunable_strings[] in net/core/ethtool.c + * phy_tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_PHY_TUNABLE_COUNT, }; @@ -360,6 +370,7 @@ struct ethtool_eeprom { * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting * its tx lpi (after reaching 'idle' state). Effective only when eee * was negotiated and tx_lpi_enabled was set. + * @reserved: Reserved for future use; see the note on reserved space. */ struct ethtool_eee { __u32 cmd; @@ -378,6 +389,7 @@ struct ethtool_eee { * @cmd: %ETHTOOL_GMODULEINFO * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx * @eeprom_len: Length of the eeprom + * @reserved: Reserved for future use; see the note on reserved space. * * This structure is used to return the information to * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM. @@ -583,9 +595,7 @@ struct ethtool_pauseparam { __u32 tx_pause; }; -/** - * enum ethtool_link_ext_state - link extended state - */ +/* Link extended state */ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_AUTONEG, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE, @@ -597,12 +607,10 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, + ETHTOOL_LINK_EXT_STATE_MODULE, }; -/** - * enum ethtool_link_ext_substate_autoneg - more information in addition to - * ETHTOOL_LINK_EXT_STATE_AUTONEG. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1, ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED, @@ -612,9 +620,7 @@ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD, }; -/** - * enum ethtool_link_ext_substate_link_training - more information in addition to - * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. */ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1, @@ -623,9 +629,7 @@ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT, }; -/** - * enum ethtool_link_ext_substate_logical_mismatch - more information in addition - * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. */ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1, @@ -635,24 +639,26 @@ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED, }; -/** - * enum ethtool_link_ext_substate_bad_signal_integrity - more information in - * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. */ enum ethtool_link_ext_substate_bad_signal_integrity { ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS, }; -/** - * enum ethtool_link_ext_substate_cable_issue - more information in - * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1, ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, }; +/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ +enum ethtool_link_ext_substate_module { + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, +}; + #define ETH_GSTRING_LEN 32 /** @@ -665,6 +671,7 @@ enum ethtool_link_ext_substate_cable_issue { * now deprecated * @ETH_SS_FEATURES: Device feature names * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names + * @ETH_SS_TUNABLES: tunable names * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS * @ETH_SS_PHY_TUNABLES: PHY tunable names * @ETH_SS_LINK_MODES: link mode names @@ -674,6 +681,13 @@ enum ethtool_link_ext_substate_cable_issue { * @ETH_SS_TS_TX_TYPES: timestamping Tx types * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types + * @ETH_SS_STATS_STD: standardized stats + * @ETH_SS_STATS_ETH_PHY: names of IEEE 802.3 PHY statistics + * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics + * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics + * @ETH_SS_STATS_RMON: names of RMON statistics + * + * @ETH_SS_COUNT: number of defined string sets */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -692,11 +706,39 @@ enum ethtool_stringset { ETH_SS_TS_TX_TYPES, ETH_SS_TS_RX_FILTERS, ETH_SS_UDP_TUNNEL_TYPES, + ETH_SS_STATS_STD, + ETH_SS_STATS_ETH_PHY, + ETH_SS_STATS_ETH_MAC, + ETH_SS_STATS_ETH_CTRL, + ETH_SS_STATS_RMON, /* add new constants above here */ ETH_SS_COUNT }; +/** + * enum ethtool_module_power_mode_policy - plug-in module power mode policy + * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. + * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host + * to high power mode when the first port using it is put administratively + * up and to low power mode when the last port using it is put + * administratively down. + */ +enum ethtool_module_power_mode_policy { + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, +}; + +/** + * enum ethtool_module_power_mode - plug-in module power mode + * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. + * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. + */ +enum ethtool_module_power_mode { + ETHTOOL_MODULE_POWER_MODE_LOW = 1, + ETHTOOL_MODULE_POWER_MODE_HIGH, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS @@ -719,6 +761,7 @@ struct ethtool_gstrings { /** * struct ethtool_sset_info - string set information * @cmd: Command number = %ETHTOOL_GSSET_INFO + * @reserved: Reserved for future use; see the note on reserved space. * @sset_mask: On entry, a bitmask of string sets to query, with bits * numbered according to &enum ethtool_stringset. On return, a * bitmask of those string sets queried that are supported. @@ -763,6 +806,7 @@ enum ethtool_test_flags { * @flags: A bitmask of flags from &enum ethtool_test_flags. Some * flags may be set by the user on entry; others may be set by * the driver on return. + * @reserved: Reserved for future use; see the note on reserved space. * @len: On return, the number of test results * @data: Array of test results * @@ -963,6 +1007,7 @@ union ethtool_flow_union { * @vlan_etype: VLAN EtherType * @vlan_tci: VLAN tag control information * @data: user defined data + * @padding: Reserved for future use; see the note on reserved space. * * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT * is set in &struct ethtool_rx_flow_spec @flow_type. @@ -1138,7 +1183,8 @@ struct ethtool_rxfh_indir { * hardware hash key. * @hfunc: Defines the current RSS hash function used by HW (or to be set to). * Valid values are one of the %ETH_RSS_HASH_*. - * @rsvd: Reserved for future extensions. + * @rsvd8: Reserved for future use; see the note on reserved space. + * @rsvd32: Reserved for future use; see the note on reserved space. * @rss_config: RX ring/queue index for each hash value i.e., indirection table * of @indir_size __u32 elements, followed by hash key of @key_size * bytes. @@ -1306,7 +1352,9 @@ struct ethtool_sfeatures { * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @tx_reserved: Reserved for future use; see the note on reserved space. * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + * @rx_reserved: Reserved for future use; see the note on reserved space. * * The bits in the 'tx_types' and 'rx_filters' fields correspond to * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, @@ -1380,15 +1428,33 @@ struct ethtool_per_queue_op { }; /** - * struct ethtool_fecparam - Ethernet forward error correction(fec) parameters + * struct ethtool_fecparam - Ethernet Forward Error Correction parameters * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM - * @active_fec: FEC mode which is active on porte - * @fec: Bitmask of supported/configured FEC modes - * @rsvd: Reserved for future extensions. i.e FEC bypass feature. + * @active_fec: FEC mode which is active on the port, single bit set, GET only. + * @fec: Bitmask of configured FEC modes. + * @reserved: Reserved for future extensions, ignore on GET, write 0 for SET. * - * Drivers should reject a non-zero setting of @autoneg when - * autoneogotiation is disabled (or not supported) for the link. + * Note that @reserved was never validated on input and ethtool user space + * left it uninitialized when calling SET. Hence going forward it can only be + * used to return a value to userspace with GET. + * + * FEC modes supported by the device can be read via %ETHTOOL_GLINKSETTINGS. + * FEC settings are configured by link autonegotiation whenever it's enabled. + * With autoneg on %ETHTOOL_GFECPARAM can be used to read the current mode. + * + * When autoneg is disabled %ETHTOOL_SFECPARAM controls the FEC settings. + * It is recommended that drivers only accept a single bit set in @fec. + * When multiple bits are set in @fec drivers may pick mode in an implementation + * dependent way. Drivers should reject mixing %ETHTOOL_FEC_AUTO_BIT with other + * FEC modes, because it's unclear whether in this case other modes constrain + * AUTO or are independent choices. + * Drivers must reject SET requests if they support none of the requested modes. + * + * If device does not support FEC drivers may use %ETHTOOL_FEC_NONE instead + * of returning %EOPNOTSUPP from %ETHTOOL_GFECPARAM. * + * See enum ethtool_fec_config_bits for definition of valid bits for both + * @fec and @active_fec. */ struct ethtool_fecparam { __u32 cmd; @@ -1400,11 +1466,16 @@ struct ethtool_fecparam { /** * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration - * @ETHTOOL_FEC_NONE: FEC mode configuration is not supported - * @ETHTOOL_FEC_AUTO: Default/Best FEC mode provided by driver - * @ETHTOOL_FEC_OFF: No FEC Mode - * @ETHTOOL_FEC_RS: Reed-Solomon Forward Error Detection mode - * @ETHTOOL_FEC_BASER: Base-R/Reed-Solomon Forward Error Detection mode + * @ETHTOOL_FEC_NONE_BIT: FEC mode configuration is not supported. Should not + * be used together with other bits. GET only. + * @ETHTOOL_FEC_AUTO_BIT: Select default/best FEC mode automatically, usually + * based link mode and SFP parameters read from module's + * EEPROM. This bit does _not_ mean autonegotiation. + * @ETHTOOL_FEC_OFF_BIT: No FEC Mode + * @ETHTOOL_FEC_RS_BIT: Reed-Solomon FEC Mode + * @ETHTOOL_FEC_BASER_BIT: Base-R/Reed-Solomon FEC Mode + * @ETHTOOL_FEC_LLRS_BIT: Low Latency Reed Solomon FEC Mode (25G/50G Ethernet + * Consortium) */ enum ethtool_fec_config_bits { ETHTOOL_FEC_NONE_BIT, @@ -1962,6 +2033,11 @@ enum ethtool_reset_flags { * autonegotiation; 0 if unknown or not applicable. Read-only. * @transceiver: Used to distinguish different possible PHY types, * reported consistently by PHYLIB. Read-only. + * @master_slave_cfg: Master/slave port mode. + * @master_slave_state: Master/slave port state. + * @reserved: Reserved for future use; see the note on reserved space. + * @reserved1: Reserved for future use; see the note on reserved space. + * @link_mode_masks: Variable length bitmaps. * * If autonegotiation is disabled, the speed and @duplex represent the * fixed link mode and are writable if the driver supports multiple -- cgit v1.2.1