diff options
Diffstat (limited to 'tools/include/uapi')
35 files changed, 5175 insertions, 417 deletions
diff --git a/tools/include/uapi/README b/tools/include/uapi/README new file mode 100644 index 000000000000..7147b1b2cb28 --- /dev/null +++ b/tools/include/uapi/README @@ -0,0 +1,73 @@ +Why we want a copy of kernel headers in tools? +============================================== + +There used to be no copies, with tools/ code using kernel headers +directly. From time to time tools/perf/ broke due to legitimate kernel +hacking. At some point Linus complained about such direct usage. Then we +adopted the current model. + +The way these headers are used in perf are not restricted to just +including them to compile something. + +There are sometimes used in scripts that convert defines into string +tables, etc, so some change may break one of these scripts, or new MSRs +may use some different #define pattern, etc. + +E.g.: + + $ ls -1 tools/perf/trace/beauty/*.sh | head -5 + tools/perf/trace/beauty/arch_errno_names.sh + tools/perf/trace/beauty/drm_ioctl.sh + tools/perf/trace/beauty/fadvise.sh + tools/perf/trace/beauty/fsconfig.sh + tools/perf/trace/beauty/fsmount.sh + $ + $ tools/perf/trace/beauty/fadvise.sh + static const char *fadvise_advices[] = { + [0] = "NORMAL", + [1] = "RANDOM", + [2] = "SEQUENTIAL", + [3] = "WILLNEED", + [4] = "DONTNEED", + [5] = "NOREUSE", + }; + $ + +The tools/perf/check-headers.sh script, part of the tools/ build +process, points out changes in the original files. + +So its important not to touch the copies in tools/ when doing changes in +the original kernel headers, that will be done later, when +check-headers.sh inform about the change to the perf tools hackers. + +Another explanation from Ingo Molnar: +It's better than all the alternatives we tried so far: + + - Symbolic links and direct #includes: this was the original approach but + was pushed back on from the kernel side, when tooling modified the + headers and broke them accidentally for kernel builds. + + - Duplicate self-defined ABI headers like glibc: double the maintenance + burden, double the chance for mistakes, plus there's no tech-driven + notification mechanism to look at new kernel side changes. + +What we are doing now is a third option: + + - A software-enforced copy-on-write mechanism of kernel headers to + tooling, driven by non-fatal warnings on the tooling side build when + kernel headers get modified: + + Warning: Kernel ABI header differences: + diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h + diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h + diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h + ... + + The tooling policy is to always pick up the kernel side headers as-is, + and integate them into the tooling build. The warnings above serve as a + notification to tooling maintainers that there's changes on the kernel + side. + +We've been using this for many years now, and it might seem hacky, but +works surprisingly well. + diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 6ce1f1ceb432..ef1c27fa3c57 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -79,9 +79,13 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 +#define PKEY_UNRESTRICTED 0x0 #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 406f7718f9ad..51d2556af54a 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -19,4 +19,8 @@ #define MCL_FUTURE 2 /* lock all future mappings */ #define MCL_ONFAULT 4 /* lock all pages that are faulted in */ +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack marker in the shadow stack */ + + #endif /* __ASM_GENERIC_MMAN_H */ diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 54d9c8bf7c55..f333a0ac4ee4 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -119,11 +119,34 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + +#define SO_NETNS_COOKIE 71 + +#define SO_BUF_LOCK 72 + +#define SO_RESERVE_MEM 73 + +#define SO_TXREHASH 74 + #define SO_RCVMARK 75 #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80 + +#define SCM_TS_OPT_ID 81 + +#define SO_RCVPRIORITY 82 + +#define SO_PASSRIGHTS 83 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index d983c48a3b6a..04e0077fb4c9 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 @@ -776,12 +776,8 @@ __SYSCALL(__NR_fsmount, sys_fsmount) __SYSCALL(__NR_fspick, sys_fspick) #define __NR_pidfd_open 434 __SYSCALL(__NR_pidfd_open, sys_pidfd_open) - -#ifdef __ARCH_WANT_SYS_CLONE3 #define __NR_clone3 435 __SYSCALL(__NR_clone3, sys_clone3) -#endif - #define __NR_close_range 436 __SYSCALL(__NR_close_range, sys_close_range) #define __NR_openat2 437 @@ -845,8 +841,25 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) #define __NR_mseal 462 __SYSCALL(__NR_mseal, sys_mseal) +#define __NR_setxattrat 463 +__SYSCALL(__NR_setxattrat, sys_setxattrat) +#define __NR_getxattrat 464 +__SYSCALL(__NR_getxattrat, sys_getxattrat) +#define __NR_listxattrat 465 +__SYSCALL(__NR_listxattrat, sys_listxattrat) +#define __NR_removexattrat 466 +__SYSCALL(__NR_removexattrat, sys_removexattrat) +#define __NR_open_tree_attr 467 +__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) + +/* fs/inode.c */ +#define __NR_file_getattr 468 +__SYSCALL(__NR_file_getattr, sys_file_getattr) +#define __NR_file_setattr 469 +__SYSCALL(__NR_file_setattr, sys_file_setattr) + #undef __NR_syscalls -#define __NR_syscalls 463 +#define __NR_syscalls 470 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 16122819edfe..3cd5cf15e3c9 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -597,35 +597,66 @@ struct drm_set_version { int drm_dd_minor; }; -/* DRM_IOCTL_GEM_CLOSE ioctl argument type */ +/** + * struct drm_gem_close - Argument for &DRM_IOCTL_GEM_CLOSE ioctl. + * @handle: Handle of the object to be closed. + * @pad: Padding. + * + * Releases the handle to an mm object. + */ struct drm_gem_close { - /** Handle of the object to be closed. */ __u32 handle; __u32 pad; }; -/* DRM_IOCTL_GEM_FLINK ioctl argument type */ +/** + * struct drm_gem_flink - Argument for &DRM_IOCTL_GEM_FLINK ioctl. + * @handle: Handle for the object being named. + * @name: Returned global name. + * + * Create a global name for an object, returning the name. + * + * Note that the name does not hold a reference; when the object + * is freed, the name goes away. + */ struct drm_gem_flink { - /** Handle for the object being named */ __u32 handle; - - /** Returned global name */ __u32 name; }; -/* DRM_IOCTL_GEM_OPEN ioctl argument type */ +/** + * struct drm_gem_open - Argument for &DRM_IOCTL_GEM_OPEN ioctl. + * @name: Name of object being opened. + * @handle: Returned handle for the object. + * @size: Returned size of the object + * + * Open an object using the global name, returning a handle and the size. + * + * This handle (of course) holds a reference to the object, so the object + * will not go away until the handle is deleted. + */ struct drm_gem_open { - /** Name of object being opened */ __u32 name; - - /** Returned handle for the object */ __u32 handle; - - /** Returned size of the object */ __u64 size; }; /** + * struct drm_gem_change_handle - Argument for &DRM_IOCTL_GEM_CHANGE_HANDLE ioctl. + * @handle: The handle of a gem object. + * @new_handle: An available gem handle. + * + * This ioctl changes the handle of a GEM object to the specified one. + * The new handle must be unused. On success the old handle is closed + * and all further IOCTL should refer to the new handle only. + * Calls to DRM_IOCTL_PRIME_FD_TO_HANDLE will return the new handle. + */ +struct drm_gem_change_handle { + __u32 handle; + __u32 new_handle; +}; + +/** * DRM_CAP_DUMB_BUFFER * * If set to 1, the driver supports creating dumb buffers via the @@ -905,13 +936,17 @@ struct drm_syncobj_destroy { }; #define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE (1 << 1) #define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE (1 << 1) struct drm_syncobj_handle { __u32 handle; __u32 flags; __s32 fd; __u32 pad; + + __u64 point; }; struct drm_syncobj_transfer { @@ -1024,6 +1059,13 @@ struct drm_crtc_queue_sequence { __u64 user_data; /* user data passed to event */ }; +#define DRM_CLIENT_NAME_MAX_LEN 64 +struct drm_set_client_name { + __u64 name_len; + __u64 name; +}; + + #if defined(__cplusplus) } #endif @@ -1288,6 +1330,24 @@ extern "C" { */ #define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb) +/** + * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file + * + * Having a name allows for easier tracking and debugging. + * The length of the name (without null ending char) must be + * <= DRM_CLIENT_NAME_MAX_LEN. + * The call will fail if the name contains whitespaces or non-printable chars. + */ +#define DRM_IOCTL_SET_CLIENT_NAME DRM_IOWR(0xD1, struct drm_set_client_name) + +/** + * DRM_IOCTL_GEM_CHANGE_HANDLE - Move an object to a different handle + * + * Some applications (notably CRIU) need objects to have specific gem handles. + * This ioctl changes the object at one gem handle to use a new gem handle. + */ +#define DRM_IOCTL_GEM_CHANGE_HANDLE DRM_IOWR(0xD2, struct drm_gem_change_handle) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index d4d86e566e07..535cb68fdb5c 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2163,6 +2163,15 @@ struct drm_i915_gem_context_param { * supports this per context flag. */ #define I915_CONTEXT_PARAM_LOW_LATENCY 0xe + +/* + * I915_CONTEXT_PARAM_CONTEXT_IMAGE: + * + * Allows userspace to provide own context images. + * + * Note that this is a debug API not available on production kernel builds. + */ +#define I915_CONTEXT_PARAM_CONTEXT_IMAGE 0xf /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2564,6 +2573,24 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +struct i915_gem_context_param_context_image { + /** @engine: Engine class & instance to be configured. */ + struct i915_engine_class_instance engine; + + /** @flags: One of the supported flags or zero. */ + __u32 flags; +#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0) + + /** @size: Size of the image blob pointed to by @image. */ + __u32 size; + + /** @mbz: Must be zero. */ + __u32 mbz; + + /** @image: Userspace memory containing the context image. */ + __u64 image; +} __attribute__((packed)); + /** * struct drm_i915_gem_context_create_ext_setparam - Context parameter * to set or query during context creation. diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h index 3c2a101986a3..a04afef9efca 100644 --- a/tools/include/uapi/linux/bits.h +++ b/tools/include/uapi/linux/bits.h @@ -4,12 +4,11 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) \ - (((~_UL(0)) - (_UL(1) << (l)) + 1) & \ - (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) \ - (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ - (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) #endif /* _UAPI_LINUX_BITS_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 35bcf52dbc65..be7d8e060e10 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -51,6 +51,9 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, }; @@ -447,6 +450,7 @@ union bpf_iter_link_info { * * **struct bpf_map_info** * * **struct bpf_btf_info** * * **struct bpf_link_info** + * * **struct bpf_token_info** * * Return * Returns zero on success. On error, -1 is returned and *errno* @@ -903,6 +907,17 @@ union bpf_iter_link_info { * A new file descriptor (a nonnegative integer), or -1 if an * error occurred (in which case, *errno* is set appropriately). * + * BPF_PROG_STREAM_READ_BY_FD + * Description + * Read data of a program's BPF stream. The program is identified + * by *prog_fd*, and the stream is identified by the *stream_id*. + * The data is copied to a buffer pointed to by *stream_buf*, and + * filled less than or equal to *stream_buf_len* bytes. + * + * Return + * Number of bytes read from the stream on success, or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -958,6 +973,7 @@ enum bpf_cmd { BPF_LINK_DETACH, BPF_PROG_BIND_MAP, BPF_TOKEN_CREATE, + BPF_PROG_STREAM_READ_BY_FD, __MAX_BPF_CMD, }; @@ -1010,6 +1026,7 @@ enum bpf_map_type { BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, BPF_MAP_TYPE_ARENA, + BPF_MAP_TYPE_INSN_ARRAY, __MAX_BPF_MAP_TYPE }; @@ -1116,11 +1133,15 @@ enum bpf_attach_type { BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, BPF_TRACE_KPROBE_SESSION, + BPF_TRACE_UPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, @@ -1203,6 +1224,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the @@ -1409,6 +1431,9 @@ enum { /* Do not translate kernel bpf_arena pointers to user pointers */ BPF_F_NO_USER_CONV = (1U << 18), + +/* Enable BPF ringbuf overwrite mode */ + BPF_F_RB_OVERWRITE = (1U << 19), }; /* Flags for BPF_PROG_QUERY. */ @@ -1455,6 +1480,11 @@ struct bpf_stack_build_id { #define BPF_OBJ_NAME_LEN 16U +enum { + BPF_STREAM_STDOUT = 1, + BPF_STREAM_STDERR = 2, +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -1496,9 +1526,15 @@ union bpf_attr { * If provided, map_flags should have BPF_F_TOKEN_FD flag set. */ __s32 map_token_fd; + + /* Hash of the program that has exclusive access to the map. + */ + __aligned_u64 excl_prog_hash; + /* Size of the passed excl_prog_hash. */ + __u32 excl_prog_hash_size; }; - struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */ __u32 map_fd; __aligned_u64 key; union { @@ -1569,6 +1605,26 @@ union bpf_attr { * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. */ __s32 prog_token_fd; + /* The fd_array_cnt can be used to pass the length of the + * fd_array array. In this case all the [map] file descriptors + * passed in this array will be bound to the program, even if + * the maps are not referenced directly. The functionality is + * similar to the BPF_PROG_BIND_MAP syscall, but maps can be + * used by the verifier during the program load. If provided, + * then the fd_array[0,...,fd_array_cnt-1] is expected to be + * continuous. + */ + __u32 fd_array_cnt; + /* Pointer to a buffer containing the signature of the BPF + * program. + */ + __aligned_u64 signature; + /* Size of the signature buffer in bytes. */ + __u32 signature_size; + /* ID of the kernel keyring to be used for signature + * verification. + */ + __s32 keyring_id; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1634,6 +1690,7 @@ union bpf_attr { }; __u32 next_id; __u32 open_flags; + __s32 fd_by_id_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ @@ -1775,6 +1832,13 @@ union bpf_attr { }; __u64 expected_revision; } netkit; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } cgroup; }; } link_create; @@ -1823,6 +1887,13 @@ union bpf_attr { __u32 bpffs_fd; } token_create; + struct { + __aligned_u64 stream_buf; + __u32 stream_buf_len; + __u32 stream_id; + __u32 prog_fd; + } prog_stream_read; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -1970,15 +2041,21 @@ union bpf_attr { * program. * Return * The SMP id of the processor running the program. + * Attributes + * __bpf_fastcall * * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description * Store *len* bytes from address *from* into the packet - * associated to *skb*, at *offset*. *flags* are a combination of - * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the - * checksum for the packet after storing the bytes) and - * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ - * **->swhash** and *skb*\ **->l4hash** to 0). + * associated to *skb*, at *offset*. The *flags* are a combination + * of the following values: + * + * **BPF_F_RECOMPUTE_CSUM** + * Automatically update *skb*\ **->csum** after storing the + * bytes. + * **BPF_F_INVALIDATE_HASH** + * Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\ + * **->l4hash** to 0. * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers @@ -2030,7 +2107,8 @@ union bpf_attr { * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates - * the checksum is to be computed against a pseudo-header. + * that the modified header field is part of the pseudo-header. + * Flag **BPF_F_IPV6** should be set for IPv6 packets. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more @@ -2377,7 +2455,7 @@ union bpf_attr { * into it. An example is available in file * *samples/bpf/trace_output_user.c* in the Linux kernel source * tree (the eBPF program counterpart is in - * *samples/bpf/trace_output_kern.c*). + * *samples/bpf/trace_output.bpf.c*). * * **bpf_perf_event_output**\ () achieves better performance * than **bpf_trace_printk**\ () for sharing data with user @@ -2851,7 +2929,7 @@ union bpf_attr { * **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**. + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports the following *optname*\ s: * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. @@ -3101,10 +3179,6 @@ union bpf_attr { * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration * option, and in this case it only works on functions tagged with * **ALLOW_ERROR_INJECTION** in the kernel code. - * - * Also, the helper is only available for the architectures having - * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, - * x86 architecture is the only one to support this feature. * Return * 0 * @@ -4821,7 +4895,7 @@ union bpf_attr { * * **-ENOENT** if the bpf_local_storage cannot be found. * - * long bpf_d_path(struct path *path, char *buf, u32 sz) + * long bpf_d_path(const struct path *path, char *buf, u32 sz) * Description * Return full path for given **struct path** object, which * needs to be the kernel BTF *path* object. The path is @@ -4951,6 +5025,9 @@ union bpf_attr { * the netns switch takes place from ingress to ingress without * going through the CPU's backlog queue. * + * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during + * the netns switch. + * * 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 and netkit target device types. The @@ -5369,7 +5446,7 @@ union bpf_attr { * Currently, the **flags** must be 0. Currently, nr_loops is * limited to 1 << 23 (~8 million) loops. * - * long (\*callback_fn)(u32 index, void \*ctx); + * long (\*callback_fn)(u64 index, void \*ctx); * * where **index** is the current index in the loop. The index * is zero-indexed. @@ -5519,11 +5596,12 @@ union bpf_attr { * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * - * void *bpf_kptr_xchg(void *map_value, void *ptr) + * void *bpf_kptr_xchg(void *dst, 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. + * Exchange kptr at pointer *dst* with *ptr*, and return the old value. + * *dst* can be map value or local kptr. *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 @@ -5544,7 +5622,7 @@ union bpf_attr { * Return * *sk* if casting is valid, or **NULL** otherwise. * - * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * long bpf_dynptr_from_mem(void *data, u64 size, u64 flags, struct bpf_dynptr *ptr) * Description * Get a dynptr to local memory *data*. * @@ -5587,7 +5665,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr *src, u64 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5597,7 +5675,7 @@ union bpf_attr { * 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) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u64 offset, void *src, u64 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5618,7 +5696,7 @@ union bpf_attr { * 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) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u64 offset, u64 len) * Description * Get a pointer to the underlying dynptr data. * @@ -6006,7 +6084,10 @@ union bpf_attr { FN(user_ringbuf_drain, 209, ##ctx) \ FN(cgrp_storage_get, 210, ##ctx) \ FN(cgrp_storage_delete, 211, ##ctx) \ - /* */ + /* This helper list is effectively frozen. If you are trying to \ + * add a new helper, you should add a kfunc instead which has \ + * less stability guarantees. See Documentation/bpf/kfuncs.rst \ + */ /* 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 @@ -6044,11 +6125,7 @@ enum { BPF_F_PSEUDO_HDR = (1ULL << 4), BPF_F_MARK_MANGLED_0 = (1ULL << 5), BPF_F_MARK_ENFORCE = (1ULL << 6), -}; - -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), + BPF_F_IPV6 = (1ULL << 7), }; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ @@ -6158,6 +6235,7 @@ enum { BPF_RB_RING_SIZE = 1, BPF_RB_CONS_POS = 2, BPF_RB_PROD_POS = 3, + BPF_RB_OVERWRITE_POS = 4, }; /* BPF ring buffer constants */ @@ -6197,10 +6275,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ @@ -6607,6 +6687,8 @@ struct bpf_map_info { __u32 btf_value_type_id; __u32 btf_vmlinux_id; __u64 map_extra; + __aligned_u64 hash; + __u32 hash_size; } __attribute__((aligned(8))); struct bpf_btf_info { @@ -6626,11 +6708,15 @@ struct bpf_link_info { struct { __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ __u32 tp_name_len; /* in/out: tp_name buffer len */ + __u32 :32; + __u64 cookie; } 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 */ + __u32 :32; + __u64 cookie; } tracing; struct { __u64 cgroup_id; @@ -6702,6 +6788,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from file_name */ __u64 cookie; + __u64 ref_ctr_offset; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ @@ -6740,6 +6827,13 @@ struct bpf_link_info { }; } __attribute__((aligned(8))); +struct bpf_token_info { + __u64 allowed_cmds; + __u64 allowed_maps; + __u64 allowed_progs; + __u64 allowed_attachs; +} __attribute__((aligned(8))); + /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on * attach type). @@ -6903,6 +6997,12 @@ enum { BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; +enum { + SK_BPF_CB_TX_TIMESTAMPING = 1<<0, + SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING - 1) | + SK_BPF_CB_TX_TIMESTAMPING +}; + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -7015,6 +7115,29 @@ enum { * by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TSTAMP_SCHED_CB, /* Called when skb is passing + * through dev layer when + * SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_SW_CB, /* Called when skb is about to send + * to the nic when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_HW_CB, /* Called in hardware phase when + * SK_BPF_CB_TX_TIMESTAMPING feature + * is on. + */ + BPF_SOCK_OPS_TSTAMP_ACK_CB, /* Called when all the skbs in the + * same sendmsg call are acked + * when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall + * is triggered. It's used to correlate + * sendmsg timestamp with corresponding + * tskey. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -7080,6 +7203,9 @@ enum { TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ + TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ }; enum { @@ -7316,6 +7442,10 @@ struct bpf_timer { __u64 __opaque[2]; } __attribute__((aligned(8))); +struct bpf_task_work { + __u64 __opaque; +} __attribute__((aligned(8))); + struct bpf_wq { __u64 __opaque[2]; } __attribute__((aligned(8))); @@ -7512,4 +7642,33 @@ struct bpf_iter_num { __u64 __opaque[1]; } __attribute__((aligned(8))); +/* + * Flags to control BPF kfunc behaviour. + * - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective + * helper documentation for details.) + */ +enum bpf_kfunc_flags { + BPF_F_PAD_ZEROS = (1ULL << 0), +}; + +/* + * Values of a BPF_MAP_TYPE_INSN_ARRAY entry must be of this type. + * + * Before the map is used the orig_off field should point to an + * instruction inside the program being loaded. The other fields + * must be set to 0. + * + * After the program is loaded, the xlated_off will be adjusted + * by the verifier to point to the index of the original instruction + * in the xlated program. If the instruction is deleted, it will + * be set to (u32)-1. The jitted_off will be set to the corresponding + * offset in the jitted image of the program. + */ +struct bpf_insn_array_value { + __u32 orig_off; + __u32 xlated_off; + __u32 jitted_off; + __u32 :32; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index ec1798b6d3ff..266d4ffa6c07 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -36,7 +36,8 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union, enum, fwd and enum64 + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag */ __u32 info; /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index a429381e7ca5..b8f629ef135f 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __int128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/tools/include/uapi/linux/coredump.h b/tools/include/uapi/linux/coredump.h new file mode 100644 index 000000000000..dc3789b78af0 --- /dev/null +++ b/tools/include/uapi/linux/coredump.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_COREDUMP_H +#define _UAPI_LINUX_COREDUMP_H + +#include <linux/types.h> + +/** + * coredump_{req,ack} flags + * @COREDUMP_KERNEL: kernel writes coredump + * @COREDUMP_USERSPACE: userspace writes coredump + * @COREDUMP_REJECT: don't generate coredump + * @COREDUMP_WAIT: wait for coredump server + */ +enum { + COREDUMP_KERNEL = (1ULL << 0), + COREDUMP_USERSPACE = (1ULL << 1), + COREDUMP_REJECT = (1ULL << 2), + COREDUMP_WAIT = (1ULL << 3), +}; + +/** + * struct coredump_req - message kernel sends to userspace + * @size: size of struct coredump_req + * @size_ack: known size of struct coredump_ack on this kernel + * @mask: supported features + * + * When a coredump happens the kernel will connect to the coredump + * socket and send a coredump request to the coredump server. The @size + * member is set to the size of struct coredump_req and provides a hint + * to userspace how much data can be read. Userspace may use MSG_PEEK to + * peek the size of struct coredump_req and then choose to consume it in + * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0 + * request. If the size the kernel sends is larger userspace simply + * discards any remaining data. + * + * The coredump_req->mask member is set to the currently know features. + * Userspace may only set coredump_ack->mask to the bits raised by the + * kernel in coredump_req->mask. + * + * The coredump_req->size_ack member is set by the kernel to the size of + * struct coredump_ack the kernel knows. Userspace may only send up to + * coredump_req->size_ack bytes to the kernel and must set + * coredump_ack->size accordingly. + */ +struct coredump_req { + __u32 size; + __u32 size_ack; + __u64 mask; +}; + +enum { + COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * struct coredump_ack - message userspace sends to kernel + * @size: size of the struct + * @spare: unused + * @mask: features kernel is supposed to use + * + * The @size member must be set to the size of struct coredump_ack. It + * may never exceed what the kernel returned in coredump_req->size_ack + * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <= + * coredump_req->size_ack). + * + * The @mask member must be set to the features the coredump server + * wants the kernel to use. Only bits the kernel returned in + * coredump_req->mask may be set. + */ +struct coredump_ack { + __u32 size; + __u32 spare; + __u64 mask; +}; + +enum { + COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * enum coredump_mark - Markers for the coredump socket + * + * The kernel will place a single byte on the coredump socket. The + * markers notify userspace whether the coredump ack succeeded or + * failed. + * + * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small + * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big + * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid + * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options + * @COREDUMP_MARK_REQACK: the coredump request and ack was successful + * @__COREDUMP_MARK_MAX: the maximum coredump mark value + */ +enum coredump_mark { + COREDUMP_MARK_REQACK = 0U, + COREDUMP_MARK_MINSIZE = 1U, + COREDUMP_MARK_MAXSIZE = 2U, + COREDUMP_MARK_UNSUPPORTED = 3U, + COREDUMP_MARK_CONFLICTING = 4U, + __COREDUMP_MARK_MAX = (1U << 31), +}; + +#endif /* _UAPI_LINUX_COREDUMP_H */ diff --git a/tools/include/uapi/linux/elf.h b/tools/include/uapi/linux/elf.h new file mode 100644 index 000000000000..5834b83d7f9a --- /dev/null +++ b/tools/include/uapi/linux/elf.h @@ -0,0 +1,524 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_ELF_H +#define _LINUX_ELF_H + +#include <linux/types.h> +#include <linux/elf-em.h> + +/* 32-bit ELF base types. */ +typedef __u32 Elf32_Addr; +typedef __u16 Elf32_Half; +typedef __u32 Elf32_Off; +typedef __s32 Elf32_Sword; +typedef __u32 Elf32_Word; +typedef __u16 Elf32_Versym; + +/* 64-bit ELF base types. */ +typedef __u64 Elf64_Addr; +typedef __u16 Elf64_Half; +typedef __s16 Elf64_SHalf; +typedef __u64 Elf64_Off; +typedef __s32 Elf64_Sword; +typedef __u32 Elf64_Word; +typedef __u64 Elf64_Xword; +typedef __s64 Elf64_Sxword; +typedef __u16 Elf64_Versym; + +/* These constants are for the segment types stored in the image headers */ +#define PT_NULL 0 +#define PT_LOAD 1 +#define PT_DYNAMIC 2 +#define PT_INTERP 3 +#define PT_NOTE 4 +#define PT_SHLIB 5 +#define PT_PHDR 6 +#define PT_TLS 7 /* Thread local storage segment */ +#define PT_LOOS 0x60000000 /* OS-specific */ +#define PT_HIOS 0x6fffffff /* OS-specific */ +#define PT_LOPROC 0x70000000 +#define PT_HIPROC 0x7fffffff +#define PT_GNU_EH_FRAME (PT_LOOS + 0x474e550) +#define PT_GNU_STACK (PT_LOOS + 0x474e551) +#define PT_GNU_RELRO (PT_LOOS + 0x474e552) +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + + +/* ARM MTE memory tag segment type */ +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) + +/* + * Extended Numbering + * + * If the real number of program header table entries is larger than + * or equal to PN_XNUM(0xffff), it is set to sh_info field of the + * section header at index 0, and PN_XNUM is set to e_phnum + * field. Otherwise, the section header at index 0 is zero + * initialized, if it exists. + * + * Specifications are available in: + * + * - Oracle: Linker and Libraries. + * Part No: 817–1984–19, August 2011. + * https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf + * + * - System V ABI AMD64 Architecture Processor Supplement + * Draft Version 0.99.4, + * January 13, 2010. + * http://www.cs.washington.edu/education/courses/cse351/12wi/supp-docs/abi.pdf + */ +#define PN_XNUM 0xffff + +/* These constants define the different elf file types */ +#define ET_NONE 0 +#define ET_REL 1 +#define ET_EXEC 2 +#define ET_DYN 3 +#define ET_CORE 4 +#define ET_LOPROC 0xff00 +#define ET_HIPROC 0xffff + +/* This is the info that is needed to parse the dynamic section of the file */ +#define DT_NULL 0 +#define DT_NEEDED 1 +#define DT_PLTRELSZ 2 +#define DT_PLTGOT 3 +#define DT_HASH 4 +#define DT_STRTAB 5 +#define DT_SYMTAB 6 +#define DT_RELA 7 +#define DT_RELASZ 8 +#define DT_RELAENT 9 +#define DT_STRSZ 10 +#define DT_SYMENT 11 +#define DT_INIT 12 +#define DT_FINI 13 +#define DT_SONAME 14 +#define DT_RPATH 15 +#define DT_SYMBOLIC 16 +#define DT_REL 17 +#define DT_RELSZ 18 +#define DT_RELENT 19 +#define DT_PLTREL 20 +#define DT_DEBUG 21 +#define DT_TEXTREL 22 +#define DT_JMPREL 23 +#define DT_ENCODING 32 +#define OLD_DT_LOOS 0x60000000 +#define DT_LOOS 0x6000000d +#define DT_HIOS 0x6ffff000 +#define DT_VALRNGLO 0x6ffffd00 +#define DT_VALRNGHI 0x6ffffdff +#define DT_ADDRRNGLO 0x6ffffe00 +#define DT_GNU_HASH 0x6ffffef5 +#define DT_ADDRRNGHI 0x6ffffeff +#define DT_VERSYM 0x6ffffff0 +#define DT_RELACOUNT 0x6ffffff9 +#define DT_RELCOUNT 0x6ffffffa +#define DT_FLAGS_1 0x6ffffffb +#define DT_VERDEF 0x6ffffffc +#define DT_VERDEFNUM 0x6ffffffd +#define DT_VERNEED 0x6ffffffe +#define DT_VERNEEDNUM 0x6fffffff +#define OLD_DT_HIOS 0x6fffffff +#define DT_LOPROC 0x70000000 +#define DT_HIPROC 0x7fffffff + +/* This info is needed when parsing the symbol table */ +#define STB_LOCAL 0 +#define STB_GLOBAL 1 +#define STB_WEAK 2 + +#define STN_UNDEF 0 + +#define STT_NOTYPE 0 +#define STT_OBJECT 1 +#define STT_FUNC 2 +#define STT_SECTION 3 +#define STT_FILE 4 +#define STT_COMMON 5 +#define STT_TLS 6 + +#define VER_FLG_BASE 0x1 +#define VER_FLG_WEAK 0x2 + +#define ELF_ST_BIND(x) ((x) >> 4) +#define ELF_ST_TYPE(x) ((x) & 0xf) +#define ELF32_ST_BIND(x) ELF_ST_BIND(x) +#define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) +#define ELF64_ST_BIND(x) ELF_ST_BIND(x) +#define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) + +typedef struct { + Elf32_Sword d_tag; + union { + Elf32_Sword d_val; + Elf32_Addr d_ptr; + } d_un; +} Elf32_Dyn; + +typedef struct { + Elf64_Sxword d_tag; /* entry tag value */ + union { + Elf64_Xword d_val; + Elf64_Addr d_ptr; + } d_un; +} Elf64_Dyn; + +/* The following are used with relocations */ +#define ELF32_R_SYM(x) ((x) >> 8) +#define ELF32_R_TYPE(x) ((x) & 0xff) + +#define ELF64_R_SYM(i) ((i) >> 32) +#define ELF64_R_TYPE(i) ((i) & 0xffffffff) + +typedef struct elf32_rel { + Elf32_Addr r_offset; + Elf32_Word r_info; +} Elf32_Rel; + +typedef struct elf64_rel { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ +} Elf64_Rel; + +typedef struct elf32_rela { + Elf32_Addr r_offset; + Elf32_Word r_info; + Elf32_Sword r_addend; +} Elf32_Rela; + +typedef struct elf64_rela { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ + Elf64_Sxword r_addend; /* Constant addend used to compute value */ +} Elf64_Rela; + +typedef struct elf32_sym { + Elf32_Word st_name; + Elf32_Addr st_value; + Elf32_Word st_size; + unsigned char st_info; + unsigned char st_other; + Elf32_Half st_shndx; +} Elf32_Sym; + +typedef struct elf64_sym { + Elf64_Word st_name; /* Symbol name, index in string tbl */ + unsigned char st_info; /* Type and binding attributes */ + unsigned char st_other; /* No defined meaning, 0 */ + Elf64_Half st_shndx; /* Associated section index */ + Elf64_Addr st_value; /* Value of the symbol */ + Elf64_Xword st_size; /* Associated symbol size */ +} Elf64_Sym; + + +#define EI_NIDENT 16 + +typedef struct elf32_hdr { + unsigned char e_ident[EI_NIDENT]; + Elf32_Half e_type; + Elf32_Half e_machine; + Elf32_Word e_version; + Elf32_Addr e_entry; /* Entry point */ + Elf32_Off e_phoff; + Elf32_Off e_shoff; + Elf32_Word e_flags; + Elf32_Half e_ehsize; + Elf32_Half e_phentsize; + Elf32_Half e_phnum; + Elf32_Half e_shentsize; + Elf32_Half e_shnum; + Elf32_Half e_shstrndx; +} Elf32_Ehdr; + +typedef struct elf64_hdr { + unsigned char e_ident[EI_NIDENT]; /* ELF "magic number" */ + Elf64_Half e_type; + Elf64_Half e_machine; + Elf64_Word e_version; + Elf64_Addr e_entry; /* Entry point virtual address */ + Elf64_Off e_phoff; /* Program header table file offset */ + Elf64_Off e_shoff; /* Section header table file offset */ + Elf64_Word e_flags; + Elf64_Half e_ehsize; + Elf64_Half e_phentsize; + Elf64_Half e_phnum; + Elf64_Half e_shentsize; + Elf64_Half e_shnum; + Elf64_Half e_shstrndx; +} Elf64_Ehdr; + +/* These constants define the permissions on sections in the program + header, p_flags. */ +#define PF_R 0x4 +#define PF_W 0x2 +#define PF_X 0x1 + +typedef struct elf32_phdr { + Elf32_Word p_type; + Elf32_Off p_offset; + Elf32_Addr p_vaddr; + Elf32_Addr p_paddr; + Elf32_Word p_filesz; + Elf32_Word p_memsz; + Elf32_Word p_flags; + Elf32_Word p_align; +} Elf32_Phdr; + +typedef struct elf64_phdr { + Elf64_Word p_type; + Elf64_Word p_flags; + Elf64_Off p_offset; /* Segment file offset */ + Elf64_Addr p_vaddr; /* Segment virtual address */ + Elf64_Addr p_paddr; /* Segment physical address */ + Elf64_Xword p_filesz; /* Segment size in file */ + Elf64_Xword p_memsz; /* Segment size in memory */ + Elf64_Xword p_align; /* Segment alignment, file & memory */ +} Elf64_Phdr; + +/* sh_type */ +#define SHT_NULL 0 +#define SHT_PROGBITS 1 +#define SHT_SYMTAB 2 +#define SHT_STRTAB 3 +#define SHT_RELA 4 +#define SHT_HASH 5 +#define SHT_DYNAMIC 6 +#define SHT_NOTE 7 +#define SHT_NOBITS 8 +#define SHT_REL 9 +#define SHT_SHLIB 10 +#define SHT_DYNSYM 11 +#define SHT_NUM 12 +#define SHT_LOPROC 0x70000000 +#define SHT_HIPROC 0x7fffffff +#define SHT_LOUSER 0x80000000 +#define SHT_HIUSER 0xffffffff + +/* sh_flags */ +#define SHF_WRITE 0x1 +#define SHF_ALLOC 0x2 +#define SHF_EXECINSTR 0x4 +#define SHF_RELA_LIVEPATCH 0x00100000 +#define SHF_RO_AFTER_INIT 0x00200000 +#define SHF_MASKPROC 0xf0000000 + +/* special section indexes */ +#define SHN_UNDEF 0 +#define SHN_LORESERVE 0xff00 +#define SHN_LOPROC 0xff00 +#define SHN_HIPROC 0xff1f +#define SHN_LIVEPATCH 0xff20 +#define SHN_ABS 0xfff1 +#define SHN_COMMON 0xfff2 +#define SHN_HIRESERVE 0xffff + +typedef struct elf32_shdr { + Elf32_Word sh_name; + Elf32_Word sh_type; + Elf32_Word sh_flags; + Elf32_Addr sh_addr; + Elf32_Off sh_offset; + Elf32_Word sh_size; + Elf32_Word sh_link; + Elf32_Word sh_info; + Elf32_Word sh_addralign; + Elf32_Word sh_entsize; +} Elf32_Shdr; + +typedef struct elf64_shdr { + Elf64_Word sh_name; /* Section name, index in string tbl */ + Elf64_Word sh_type; /* Type of section */ + Elf64_Xword sh_flags; /* Miscellaneous section attributes */ + Elf64_Addr sh_addr; /* Section virtual addr at execution */ + Elf64_Off sh_offset; /* Section file offset */ + Elf64_Xword sh_size; /* Size of section in bytes */ + Elf64_Word sh_link; /* Index of another section */ + Elf64_Word sh_info; /* Additional section information */ + Elf64_Xword sh_addralign; /* Section alignment */ + Elf64_Xword sh_entsize; /* Entry size if section holds table */ +} Elf64_Shdr; + +#define EI_MAG0 0 /* e_ident[] indexes */ +#define EI_MAG1 1 +#define EI_MAG2 2 +#define EI_MAG3 3 +#define EI_CLASS 4 +#define EI_DATA 5 +#define EI_VERSION 6 +#define EI_OSABI 7 +#define EI_PAD 8 + +#define ELFMAG0 0x7f /* EI_MAG */ +#define ELFMAG1 'E' +#define ELFMAG2 'L' +#define ELFMAG3 'F' +#define ELFMAG "\177ELF" +#define SELFMAG 4 + +#define ELFCLASSNONE 0 /* EI_CLASS */ +#define ELFCLASS32 1 +#define ELFCLASS64 2 +#define ELFCLASSNUM 3 + +#define ELFDATANONE 0 /* e_ident[EI_DATA] */ +#define ELFDATA2LSB 1 +#define ELFDATA2MSB 2 + +#define EV_NONE 0 /* e_version, EI_VERSION */ +#define EV_CURRENT 1 +#define EV_NUM 2 + +#define ELFOSABI_NONE 0 +#define ELFOSABI_LINUX 3 + +#ifndef ELF_OSABI +#define ELF_OSABI ELFOSABI_NONE +#endif + +/* + * Notes used in ET_CORE. Architectures export some of the arch register sets + * using the corresponding note types via the PTRACE_GETREGSET and + * PTRACE_SETREGSET requests. + * The note name for these types is "LINUX", except NT_PRFPREG that is named + * "CORE". + */ +#define NT_PRSTATUS 1 +#define NT_PRFPREG 2 +#define NT_PRPSINFO 3 +#define NT_TASKSTRUCT 4 +#define NT_AUXV 6 +/* + * Note to userspace developers: size of NT_SIGINFO note may increase + * in the future to accomodate more fields, don't assume it is fixed! + */ +#define NT_SIGINFO 0x53494749 +#define NT_FILE 0x46494c45 +#define NT_PRXFPREG 0x46e62b7f /* copied from gdb5.1/include/elf/common.h */ +#define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ +#define NT_PPC_SPE 0x101 /* PowerPC SPE/EVR registers */ +#define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ +#define NT_PPC_TAR 0x103 /* Target Address Register */ +#define NT_PPC_PPR 0x104 /* Program Priority Register */ +#define NT_PPC_DSCR 0x105 /* Data Stream Control Register */ +#define NT_PPC_EBB 0x106 /* Event Based Branch Registers */ +#define NT_PPC_PMU 0x107 /* Performance Monitor Registers */ +#define NT_PPC_TM_CGPR 0x108 /* TM checkpointed GPR Registers */ +#define NT_PPC_TM_CFPR 0x109 /* TM checkpointed FPR Registers */ +#define NT_PPC_TM_CVMX 0x10a /* TM checkpointed VMX Registers */ +#define NT_PPC_TM_CVSX 0x10b /* TM checkpointed VSX Registers */ +#define NT_PPC_TM_SPR 0x10c /* TM Special Purpose Registers */ +#define NT_PPC_TM_CTAR 0x10d /* TM checkpointed Target Address Register */ +#define NT_PPC_TM_CPPR 0x10e /* TM checkpointed Program Priority Register */ +#define NT_PPC_TM_CDSCR 0x10f /* TM checkpointed Data Stream Control Register */ +#define NT_PPC_PKEY 0x110 /* Memory Protection Keys registers */ +#define NT_PPC_DEXCR 0x111 /* PowerPC DEXCR registers */ +#define NT_PPC_HASHKEYR 0x112 /* PowerPC HASHKEYR register */ +#define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ +#define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ +#define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ +/* Old binutils treats 0x203 as a CET state */ +#define NT_X86_SHSTK 0x204 /* x86 SHSTK state */ +#define NT_X86_XSAVE_LAYOUT 0x205 /* XSAVE layout description */ +#define NT_S390_HIGH_GPRS 0x300 /* s390 upper register halves */ +#define NT_S390_TIMER 0x301 /* s390 timer register */ +#define NT_S390_TODCMP 0x302 /* s390 TOD clock comparator register */ +#define NT_S390_TODPREG 0x303 /* s390 TOD programmable register */ +#define NT_S390_CTRS 0x304 /* s390 control registers */ +#define NT_S390_PREFIX 0x305 /* s390 prefix register */ +#define NT_S390_LAST_BREAK 0x306 /* s390 breaking event address */ +#define NT_S390_SYSTEM_CALL 0x307 /* s390 system call restart data */ +#define NT_S390_TDB 0x308 /* s390 transaction diagnostic block */ +#define NT_S390_VXRS_LOW 0x309 /* s390 vector registers 0-15 upper half */ +#define NT_S390_VXRS_HIGH 0x30a /* s390 vector registers 16-31 */ +#define NT_S390_GS_CB 0x30b /* s390 guarded storage registers */ +#define NT_S390_GS_BC 0x30c /* s390 guarded storage broadcast control block */ +#define NT_S390_RI_CB 0x30d /* s390 runtime instrumentation */ +#define NT_S390_PV_CPU_DATA 0x30e /* s390 protvirt cpu dump data */ +#define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ +#define NT_ARM_TLS 0x401 /* ARM TLS register */ +#define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ +#define NT_ARM_HW_WATCH 0x403 /* ARM hardware watchpoint registers */ +#define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ +#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ +#define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ +#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ +#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ +#define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ +#define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ +#define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ +#define NT_ARM_POE 0x40f /* ARM POE registers */ +#define NT_ARM_GCS 0x410 /* ARM GCS state */ +#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ +#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ +#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ +#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ +#define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ +#define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ +#define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ +#define NT_LOONGARCH_HW_BREAK 0xa05 /* LoongArch hardware breakpoint registers */ +#define NT_LOONGARCH_HW_WATCH 0xa06 /* LoongArch hardware watchpoint registers */ + +/* Note types with note name "GNU" */ +#define NT_GNU_PROPERTY_TYPE_0 5 + +/* Note header in a PT_NOTE section */ +typedef struct elf32_note { + Elf32_Word n_namesz; /* Name size */ + Elf32_Word n_descsz; /* Content size */ + Elf32_Word n_type; /* Content type */ +} Elf32_Nhdr; + +/* Note header in a PT_NOTE section */ +typedef struct elf64_note { + Elf64_Word n_namesz; /* Name size */ + Elf64_Word n_descsz; /* Content size */ + Elf64_Word n_type; /* Content type */ +} Elf64_Nhdr; + +/* .note.gnu.property types for EM_AARCH64: */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) + +typedef struct { + Elf32_Half vd_version; + Elf32_Half vd_flags; + Elf32_Half vd_ndx; + Elf32_Half vd_cnt; + Elf32_Word vd_hash; + Elf32_Word vd_aux; + Elf32_Word vd_next; +} Elf32_Verdef; + +typedef struct { + Elf64_Half vd_version; + Elf64_Half vd_flags; + Elf64_Half vd_ndx; + Elf64_Half vd_cnt; + Elf64_Word vd_hash; + Elf64_Word vd_aux; + Elf64_Word vd_next; +} Elf64_Verdef; + +typedef struct { + Elf32_Word vda_name; + Elf32_Word vda_next; +} Elf32_Verdaux; + +typedef struct { + Elf64_Word vda_name; + Elf64_Word vda_next; +} Elf64_Verdaux; + +#endif /* _LINUX_ELF_H */ diff --git a/tools/include/uapi/linux/fanotify.h b/tools/include/uapi/linux/fanotify.h new file mode 100644 index 000000000000..e710967c7c26 --- /dev/null +++ b/tools/include/uapi/linux/fanotify.h @@ -0,0 +1,274 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_FANOTIFY_H +#define _UAPI_LINUX_FANOTIFY_H + +#include <linux/types.h> + +/* the following events that user-space can register for */ +#define FAN_ACCESS 0x00000001 /* File was accessed */ +#define FAN_MODIFY 0x00000002 /* File was modified */ +#define FAN_ATTRIB 0x00000004 /* Metadata changed */ +#define FAN_CLOSE_WRITE 0x00000008 /* Writable file closed */ +#define FAN_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ +#define FAN_OPEN 0x00000020 /* File was opened */ +#define FAN_MOVED_FROM 0x00000040 /* File was moved from X */ +#define FAN_MOVED_TO 0x00000080 /* File was moved to Y */ +#define FAN_CREATE 0x00000100 /* Subfile was created */ +#define FAN_DELETE 0x00000200 /* Subfile was deleted */ +#define FAN_DELETE_SELF 0x00000400 /* Self was deleted */ +#define FAN_MOVE_SELF 0x00000800 /* Self was moved */ +#define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ + +#define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ + +#define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ +#define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ +#define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ +/* #define FAN_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FAN_PRE_ACCESS 0x00100000 /* Pre-content access hook */ +#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */ +#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */ + +#define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ + +#define FAN_RENAME 0x10000000 /* File was renamed */ + +#define FAN_ONDIR 0x40000000 /* Event occurred against dir */ + +/* helper events */ +#define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ +#define FAN_MOVE (FAN_MOVED_FROM | FAN_MOVED_TO) /* moves */ + +/* flags used for fanotify_init() */ +#define FAN_CLOEXEC 0x00000001 +#define FAN_NONBLOCK 0x00000002 + +/* These are NOT bitwise flags. Both bits are used together. */ +#define FAN_CLASS_NOTIF 0x00000000 +#define FAN_CLASS_CONTENT 0x00000004 +#define FAN_CLASS_PRE_CONTENT 0x00000008 + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ + FAN_CLASS_PRE_CONTENT) + +#define FAN_UNLIMITED_QUEUE 0x00000010 +#define FAN_UNLIMITED_MARKS 0x00000020 +#define FAN_ENABLE_AUDIT 0x00000040 + +/* Flags to determine fanotify event format */ +#define FAN_REPORT_PIDFD 0x00000080 /* Report pidfd for event->pid */ +#define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ +#define FAN_REPORT_FID 0x00000200 /* Report unique file id */ +#define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ +#define FAN_REPORT_NAME 0x00000800 /* Report events with name */ +#define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ +#define FAN_REPORT_FD_ERROR 0x00002000 /* event->fd can report error */ +#define FAN_REPORT_MNT 0x00004000 /* Report mount events */ + +/* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ +#define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) +/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */ +#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \ + FAN_REPORT_FID | FAN_REPORT_TARGET_FID) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ + FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\ + FAN_UNLIMITED_MARKS) + +/* flags used for fanotify_modify_mark() */ +#define FAN_MARK_ADD 0x00000001 +#define FAN_MARK_REMOVE 0x00000002 +#define FAN_MARK_DONT_FOLLOW 0x00000004 +#define FAN_MARK_ONLYDIR 0x00000008 +/* FAN_MARK_MOUNT is 0x00000010 */ +#define FAN_MARK_IGNORED_MASK 0x00000020 +#define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 +#define FAN_MARK_FLUSH 0x00000080 +/* FAN_MARK_FILESYSTEM is 0x00000100 */ +#define FAN_MARK_EVICTABLE 0x00000200 +/* This bit is mutually exclusive with FAN_MARK_IGNORED_MASK bit */ +#define FAN_MARK_IGNORE 0x00000400 + +/* These are NOT bitwise flags. Both bits can be used togther. */ +#define FAN_MARK_INODE 0x00000000 +#define FAN_MARK_MOUNT 0x00000010 +#define FAN_MARK_FILESYSTEM 0x00000100 +#define FAN_MARK_MNTNS 0x00000110 + +/* + * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY + * for non-inode mark types. + */ +#define FAN_MARK_IGNORE_SURV (FAN_MARK_IGNORE | FAN_MARK_IGNORED_SURV_MODIFY) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ + FAN_MARK_REMOVE |\ + FAN_MARK_DONT_FOLLOW |\ + FAN_MARK_ONLYDIR |\ + FAN_MARK_MOUNT |\ + FAN_MARK_IGNORED_MASK |\ + FAN_MARK_IGNORED_SURV_MODIFY |\ + FAN_MARK_FLUSH) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_EVENTS (FAN_ACCESS |\ + FAN_MODIFY |\ + FAN_CLOSE |\ + FAN_OPEN) + +/* + * All events which require a permission response from userspace + */ +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\ + FAN_ACCESS_PERM) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ + FAN_ALL_PERM_EVENTS |\ + FAN_Q_OVERFLOW) + +#define FANOTIFY_METADATA_VERSION 3 + +struct fanotify_event_metadata { + __u32 event_len; + __u8 vers; + __u8 reserved; + __u16 metadata_len; + __aligned_u64 mask; + __s32 fd; + __s32 pid; +}; + +#define FAN_EVENT_INFO_TYPE_FID 1 +#define FAN_EVENT_INFO_TYPE_DFID_NAME 2 +#define FAN_EVENT_INFO_TYPE_DFID 3 +#define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 +#define FAN_EVENT_INFO_TYPE_RANGE 6 +#define FAN_EVENT_INFO_TYPE_MNT 7 + +/* Special info types for FAN_RENAME */ +#define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 +/* Reserved for FAN_EVENT_INFO_TYPE_OLD_DFID 11 */ +#define FAN_EVENT_INFO_TYPE_NEW_DFID_NAME 12 +/* Reserved for FAN_EVENT_INFO_TYPE_NEW_DFID 13 */ + +/* Variable length info record following event metadata */ +struct fanotify_event_info_header { + __u8 info_type; + __u8 pad; + __u16 len; +}; + +/* + * Unique file identifier info record. + * This structure is used for records of types FAN_EVENT_INFO_TYPE_FID, + * FAN_EVENT_INFO_TYPE_DFID and FAN_EVENT_INFO_TYPE_DFID_NAME. + * For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null terminated + * name immediately after the file handle. + */ +struct fanotify_event_info_fid { + struct fanotify_event_info_header hdr; + __kernel_fsid_t fsid; + /* + * Following is an opaque struct file_handle that can be passed as + * an argument to open_by_handle_at(2). + */ + unsigned char handle[]; +}; + +/* + * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD. + * It holds a pidfd for the pid that was responsible for generating an event. + */ +struct fanotify_event_info_pidfd { + struct fanotify_event_info_header hdr; + __s32 pidfd; +}; + +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + +struct fanotify_event_info_range { + struct fanotify_event_info_header hdr; + __u32 pad; + __u64 offset; + __u64 count; +}; + +struct fanotify_event_info_mnt { + struct fanotify_event_info_header hdr; + __u64 mnt_id; +}; + +/* + * User space may need to record additional information about its decision. + * The extra information type records what kind of information is included. + * The default is none. We also define an extra information buffer whose + * size is determined by the extra information type. + * + * If the information type is Audit Rule, then the information following + * is the rule number that triggered the user space decision that + * requires auditing. + */ + +#define FAN_RESPONSE_INFO_NONE 0 +#define FAN_RESPONSE_INFO_AUDIT_RULE 1 + +struct fanotify_response { + __s32 fd; + __u32 response; +}; + +struct fanotify_response_info_header { + __u8 type; + __u8 pad; + __u16 len; +}; + +struct fanotify_response_info_audit_rule { + struct fanotify_response_info_header hdr; + __u32 rule_number; + __u32 subj_trust; + __u32 obj_trust; +}; + +/* Legit userspace responses to a _PERM event */ +#define FAN_ALLOW 0x01 +#define FAN_DENY 0x02 +/* errno other than EPERM can specified in upper byte of deny response */ +#define FAN_ERRNO_BITS 8 +#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS) +#define FAN_ERRNO_MASK ((1 << FAN_ERRNO_BITS) - 1) +#define FAN_DENY_ERRNO(err) \ + (FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT)) + +#define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ +#define FAN_INFO 0x20 /* Bitmask to indicate additional information */ + +/* No fd set in event */ +#define FAN_NOFD -1 +#define FAN_NOPIDFD FAN_NOFD +#define FAN_EPIDFD -2 + +/* Helper functions to deal with fanotify_event_metadata buffers */ +#define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) + +#define FAN_EVENT_NEXT(meta, len) ((len) -= (meta)->event_len, \ + (struct fanotify_event_metadata*)(((char *)(meta)) + \ + (meta)->event_len)) + +#define FAN_EVENT_OK(meta, len) ((long)(len) >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len <= (long)(len)) + +#endif /* _UAPI_LINUX_FANOTIFY_H */ diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h new file mode 100644 index 000000000000..24ddf7bc4f25 --- /dev/null +++ b/tools/include/uapi/linux/fs.h @@ -0,0 +1,569 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_FS_H +#define _UAPI_LINUX_FS_H + +/* + * This file has definitions for some important file table structures + * and constants and structures used by various generic file system + * ioctl's. Please do not make any changes in this file before + * sending patches for review to linux-fsdevel@vger.kernel.org and + * linux-api@vger.kernel.org. + */ + +#include <linux/limits.h> +#include <linux/ioctl.h> +#include <linux/types.h> +#ifndef __KERNEL__ +#include <linux/fscrypt.h> +#endif + +/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#if !defined(__KERNEL__) +#include <linux/mount.h> +#endif + +/* + * It's silly to have NR_OPEN bigger than NR_FILE, but you can change + * the file limit at runtime and only root can increase the per-process + * nr_file rlimit, so it's safe to set up a ridiculously high absolute + * upper limit on files-per-process. + * + * Some programs (notably those using select()) may have to be + * recompiled to take full advantage of the new limits.. + */ + +/* Fixed constants first: */ +#undef NR_OPEN +#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ +#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ + +#define BLOCK_SIZE_BITS 10 +#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS) + +/* flags for integrity meta */ +#define IO_INTEGRITY_CHK_GUARD (1U << 0) /* enforce guard check */ +#define IO_INTEGRITY_CHK_REFTAG (1U << 1) /* enforce ref check */ +#define IO_INTEGRITY_CHK_APPTAG (1U << 2) /* enforce app check */ + +#define IO_INTEGRITY_VALID_FLAGS (IO_INTEGRITY_CHK_GUARD | \ + IO_INTEGRITY_CHK_REFTAG | \ + IO_INTEGRITY_CHK_APPTAG) + +#define SEEK_SET 0 /* seek relative to beginning of file */ +#define SEEK_CUR 1 /* seek relative to current file position */ +#define SEEK_END 2 /* seek relative to end of file */ +#define SEEK_DATA 3 /* seek to the next data */ +#define SEEK_HOLE 4 /* seek to the next hole */ +#define SEEK_MAX SEEK_HOLE + +#define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */ +#define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ +#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ + +struct file_clone_range { + __s64 src_fd; + __u64 src_offset; + __u64 src_length; + __u64 dest_offset; +}; + +struct fstrim_range { + __u64 start; + __u64 len; + __u64 minlen; +}; + +/* + * We include a length field because some filesystems (vfat) have an identifier + * that we do want to expose as a UUID, but doesn't have the standard length. + * + * We use a fixed size buffer beacuse this interface will, by fiat, never + * support "UUIDs" longer than 16 bytes; we don't want to force all downstream + * users to have to deal with that. + */ +struct fsuuid2 { + __u8 len; + __u8 uuid[16]; +}; + +struct fs_sysfs_path { + __u8 len; + __u8 name[128]; +}; + +/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ +#define FILE_DEDUPE_RANGE_SAME 0 +#define FILE_DEDUPE_RANGE_DIFFERS 1 + +/* from struct btrfs_ioctl_file_extent_same_info */ +struct file_dedupe_range_info { + __s64 dest_fd; /* in - destination file */ + __u64 dest_offset; /* in - start of extent in destination */ + __u64 bytes_deduped; /* out - total # of bytes we were able + * to dedupe from this file. */ + /* status of this dedupe operation: + * < 0 for error + * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds + * == FILE_DEDUPE_RANGE_DIFFERS if data differs + */ + __s32 status; /* out - see above description */ + __u32 reserved; /* must be zero */ +}; + +/* from struct btrfs_ioctl_file_extent_same_args */ +struct file_dedupe_range { + __u64 src_offset; /* in - start of extent in source */ + __u64 src_length; /* in - length of extent */ + __u16 dest_count; /* in - total elements in info array */ + __u16 reserved1; /* must be zero */ + __u32 reserved2; /* must be zero */ + struct file_dedupe_range_info info[]; +}; + +/* And dynamically-tunable limits and defaults: */ +struct files_stat_struct { + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ +}; + +struct inodes_stat_t { + long nr_inodes; + long nr_unused; + long dummy[5]; /* padding for sysctl ABI compatibility */ +}; + + +#define NR_FILE 8192 /* this can well be larger on a larger system */ + +/* + * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR. + */ +struct fsxattr { + __u32 fsx_xflags; /* xflags field value (get/set) */ + __u32 fsx_extsize; /* extsize field value (get/set)*/ + __u32 fsx_nextents; /* nextents field value (get) */ + __u32 fsx_projid; /* project identifier (get/set) */ + __u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ + unsigned char fsx_pad[8]; +}; + +/* + * Flags for the fsx_xflags field + */ +#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ +#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ +#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ +#define FS_XFLAG_APPEND 0x00000010 /* all writes append */ +#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ +#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */ +#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ +#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ +#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ +#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ +#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ +#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ +#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ +#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ +#define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ +#define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ +#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ + +/* the read-only stuff doesn't really belong here, but any other place is + probably as bad and I don't want to create yet another include file. */ + +#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */ +#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */ +#define BLKRRPART _IO(0x12,95) /* re-read partition table */ +#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */ +#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */ +#define BLKRASET _IO(0x12,98) /* set read ahead for block device */ +#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */ +#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */ +#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */ +#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */ +#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */ +#define BLKSSZGET _IO(0x12,104)/* get block device sector size */ +#if 0 +#define BLKPG _IO(0x12,105)/* See blkpg.h */ + +/* Some people are morons. Do not use sizeof! */ + +#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */ +#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */ +/* This was here just to show that the number is taken - + probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */ +#endif +/* A jump here: 108-111 have been used for various private purposes. */ +#define BLKBSZGET _IOR(0x12,112,size_t) +#define BLKBSZSET _IOW(0x12,113,size_t) +#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ +#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) +#define BLKTRACESTART _IO(0x12,116) +#define BLKTRACESTOP _IO(0x12,117) +#define BLKTRACETEARDOWN _IO(0x12,118) +#define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) +#define BLKDISCARDZEROES _IO(0x12,124) +#define BLKSECDISCARD _IO(0x12,125) +#define BLKROTATIONAL _IO(0x12,126) +#define BLKZEROOUT _IO(0x12,127) +#define BLKGETDISKSEQ _IOR(0x12,128,__u64) +/* + * A jump here: 130-136 are reserved for zoned block devices + * (see uapi/linux/blkzoned.h) + */ + +#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ +#define FIBMAP _IO(0x00,1) /* bmap access */ +#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ +#define FIFREEZE _IOWR('X', 119, int) /* Freeze */ +#define FITHAW _IOWR('X', 120, int) /* Thaw */ +#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */ +#define FICLONE _IOW(0x94, 9, int) +#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range) +#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range) + +#define FSLABEL_MAX 256 /* Max chars for the interface; each fs may differ */ + +#define FS_IOC_GETFLAGS _IOR('f', 1, long) +#define FS_IOC_SETFLAGS _IOW('f', 2, long) +#define FS_IOC_GETVERSION _IOR('v', 1, long) +#define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap) +#define FS_IOC32_GETFLAGS _IOR('f', 1, int) +#define FS_IOC32_SETFLAGS _IOW('f', 2, int) +#define FS_IOC32_GETVERSION _IOR('v', 1, int) +#define FS_IOC32_SETVERSION _IOW('v', 2, int) +#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr) +#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) +#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) +#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +/* Returns the external filesystem UUID, the same one blkid returns */ +#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) +/* + * Returns the path component under /sys/fs/ that refers to this filesystem; + * also /sys/kernel/debug/ for filesystems with debugfs exports + */ +#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) + +/* + * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) + * + * Note: for historical reasons, these flags were originally used and + * defined for use by ext2/ext3, and then other file systems started + * using these flags so they wouldn't need to write their own version + * of chattr/lsattr (which was shipped as part of e2fsprogs). You + * should think twice before trying to use these flags in new + * contexts, or trying to assign these flags, since they are used both + * as the UAPI and the on-disk encoding for ext2/3/4. Also, we are + * almost out of 32-bit flags. :-) + * + * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from + * XFS to the generic FS level interface. This uses a structure that + * has padding and hence has more room to grow, so it may be more + * appropriate for many new use cases. + * + * Please do not change these flags or interfaces before checking with + * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org. + */ +#define FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define FS_UNRM_FL 0x00000002 /* Undelete */ +#define FS_COMPR_FL 0x00000004 /* Compress file */ +#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define FS_DIRTY_FL 0x00000100 +#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ +/* End compression flags --- maybe not all used */ +#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */ +#define FS_BTREE_FL 0x00001000 /* btree format dir */ +#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ +#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_HUGE_FILE_FL 0x00040000 /* Reserved for ext4 */ +#define FS_EXTENT_FL 0x00080000 /* Extents */ +#define FS_VERITY_FL 0x00100000 /* Verity protected inode */ +#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ +#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */ +#define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_DAX_FL 0x02000000 /* Inode is DAX */ +#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ +#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ +#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */ +#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ + +#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + + +#define SYNC_FILE_RANGE_WAIT_BEFORE 1 +#define SYNC_FILE_RANGE_WRITE 2 +#define SYNC_FILE_RANGE_WAIT_AFTER 4 +#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \ + SYNC_FILE_RANGE_WAIT_BEFORE | \ + SYNC_FILE_RANGE_WAIT_AFTER) + +/* + * Flags for preadv2/pwritev2: + */ + +typedef int __bitwise __kernel_rwf_t; + +/* high priority request, poll if possible */ +#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001) + +/* per-IO O_DSYNC */ +#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002) + +/* per-IO O_SYNC */ +#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004) + +/* per-IO, return -EAGAIN if operation would block */ +#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008) + +/* per-IO O_APPEND */ +#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) + +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + +/* buffered IO that drops the cache after reading or writing data */ +#define RWF_DONTCACHE ((__force __kernel_rwf_t)0x00000080) + +/* mask of flags supported by the kernel */ +#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\ + RWF_DONTCACHE) + +#define PROCFS_IOCTL_MAGIC 'f' + +/* Pagemap ioctl */ +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) + +/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ +#define PAGE_IS_WPALLOWED (1 << 0) +#define PAGE_IS_WRITTEN (1 << 1) +#define PAGE_IS_FILE (1 << 2) +#define PAGE_IS_PRESENT (1 << 3) +#define PAGE_IS_SWAPPED (1 << 4) +#define PAGE_IS_PFNZERO (1 << 5) +#define PAGE_IS_HUGE (1 << 6) +#define PAGE_IS_SOFT_DIRTY (1 << 7) +#define PAGE_IS_GUARD (1 << 8) + +/* + * struct page_region - Page region with flags + * @start: Start of the region + * @end: End of the region (exclusive) + * @categories: PAGE_IS_* category bitmask for the region + */ +struct page_region { + __u64 start; + __u64 end; + __u64 categories; +}; + +/* Flags for PAGEMAP_SCAN ioctl */ +#define PM_SCAN_WP_MATCHING (1 << 0) /* Write protect the pages matched. */ +#define PM_SCAN_CHECK_WPASYNC (1 << 1) /* Abort the scan when a non-WP-enabled page is found. */ + +/* + * struct pm_scan_arg - Pagemap ioctl argument + * @size: Size of the structure + * @flags: Flags for the IOCTL + * @start: Starting address of the region + * @end: Ending address of the region + * @walk_end Address where the scan stopped (written by kernel). + * walk_end == end (address tags cleared) informs that the scan completed on entire range. + * @vec: Address of page_region struct array for output + * @vec_len: Length of the page_region struct array + * @max_pages: Optional limit for number of returned pages (0 = disabled) + * @category_inverted: PAGE_IS_* categories which values match if 0 instead of 1 + * @category_mask: Skip pages for which any category doesn't match + * @category_anyof_mask: Skip pages for which no category matches + * @return_mask: PAGE_IS_* categories that are to be reported in `page_region`s returned + */ +struct pm_scan_arg { + __u64 size; + __u64 flags; + __u64 start; + __u64 end; + __u64 walk_end; + __u64 vec; + __u64 vec_len; + __u64 max_pages; + __u64 category_inverted; + __u64 category_mask; + __u64 category_anyof_mask; + __u64 return_mask; +}; + +/* /proc/<pid>/maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc/<pid>/maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + +#endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 7a8f4c290187..3aff99f2696a 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -119,7 +119,7 @@ struct fscrypt_key_specifier { */ struct fscrypt_provisioning_key_payload { __u32 type; - __u32 __reserved; + __u32 flags; __u8 raw[]; }; @@ -128,7 +128,9 @@ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; __u32 key_id; - __u32 __reserved[8]; +#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; __u8 raw[]; }; diff --git a/tools/include/uapi/linux/genetlink.h b/tools/include/uapi/linux/genetlink.h new file mode 100644 index 000000000000..ddba3ca01e39 --- /dev/null +++ b/tools/include/uapi/linux/genetlink.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_GENERIC_NETLINK_H +#define _UAPI__LINUX_GENERIC_NETLINK_H + +#include <linux/types.h> +#include <linux/netlink.h> + +#define GENL_NAMSIZ 16 /* length of family name */ + +#define GENL_MIN_ID NLMSG_MIN_TYPE +#define GENL_MAX_ID 1023 + +struct genlmsghdr { + __u8 cmd; + __u8 version; + __u16 reserved; +}; + +#define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr)) + +#define GENL_ADMIN_PERM 0x01 +#define GENL_CMD_CAP_DO 0x02 +#define GENL_CMD_CAP_DUMP 0x04 +#define GENL_CMD_CAP_HASPOL 0x08 +#define GENL_UNS_ADMIN_PERM 0x10 + +/* + * List of reserved static generic netlink identifiers: + */ +#define GENL_ID_CTRL NLMSG_MIN_TYPE +#define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1) +#define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2) +/* must be last reserved + 1 */ +#define GENL_START_ALLOC (NLMSG_MIN_TYPE + 3) + +/************************************************************************** + * Controller + **************************************************************************/ + +enum { + CTRL_CMD_UNSPEC, + CTRL_CMD_NEWFAMILY, + CTRL_CMD_DELFAMILY, + CTRL_CMD_GETFAMILY, + CTRL_CMD_NEWOPS, + CTRL_CMD_DELOPS, + CTRL_CMD_GETOPS, + CTRL_CMD_NEWMCAST_GRP, + CTRL_CMD_DELMCAST_GRP, + CTRL_CMD_GETMCAST_GRP, /* unused */ + CTRL_CMD_GETPOLICY, + __CTRL_CMD_MAX, +}; + +#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1) + +enum { + CTRL_ATTR_UNSPEC, + CTRL_ATTR_FAMILY_ID, + CTRL_ATTR_FAMILY_NAME, + CTRL_ATTR_VERSION, + CTRL_ATTR_HDRSIZE, + CTRL_ATTR_MAXATTR, + CTRL_ATTR_OPS, + CTRL_ATTR_MCAST_GROUPS, + CTRL_ATTR_POLICY, + CTRL_ATTR_OP_POLICY, + CTRL_ATTR_OP, + __CTRL_ATTR_MAX, +}; + +#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1) + +enum { + CTRL_ATTR_OP_UNSPEC, + CTRL_ATTR_OP_ID, + CTRL_ATTR_OP_FLAGS, + __CTRL_ATTR_OP_MAX, +}; + +#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1) + +enum { + CTRL_ATTR_MCAST_GRP_UNSPEC, + CTRL_ATTR_MCAST_GRP_NAME, + CTRL_ATTR_MCAST_GRP_ID, + __CTRL_ATTR_MCAST_GRP_MAX, +}; + +#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) + +enum { + CTRL_ATTR_POLICY_UNSPEC, + CTRL_ATTR_POLICY_DO, + CTRL_ATTR_POLICY_DUMP, + + __CTRL_ATTR_POLICY_DUMP_MAX, + CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1 +}; + +#define CTRL_ATTR_POLICY_MAX (__CTRL_ATTR_POLICY_DUMP_MAX - 1) + +#endif /* _UAPI__LINUX_GENERIC_NETLINK_H */ diff --git a/tools/include/uapi/linux/if_addr.h b/tools/include/uapi/linux/if_addr.h new file mode 100644 index 000000000000..aa7958b4e41d --- /dev/null +++ b/tools/include/uapi/linux/if_addr.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_IF_ADDR_H +#define _UAPI__LINUX_IF_ADDR_H + +#include <linux/types.h> +#include <linux/netlink.h> + +struct ifaddrmsg { + __u8 ifa_family; + __u8 ifa_prefixlen; /* The prefix length */ + __u8 ifa_flags; /* Flags */ + __u8 ifa_scope; /* Address scope */ + __u32 ifa_index; /* Link index */ +}; + +/* + * Important comment: + * IFA_ADDRESS is prefix address, rather than local interface address. + * It makes no difference for normally configured broadcast interfaces, + * but for point-to-point IFA_ADDRESS is DESTINATION address, + * local address is supplied in IFA_LOCAL attribute. + * + * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags. + * If present, the value from struct ifaddrmsg will be ignored. + */ +enum { + IFA_UNSPEC, + IFA_ADDRESS, + IFA_LOCAL, + IFA_LABEL, + IFA_BROADCAST, + IFA_ANYCAST, + IFA_CACHEINFO, + IFA_MULTICAST, + IFA_FLAGS, + IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_TARGET_NETNSID, + IFA_PROTO, /* u8, address protocol */ + __IFA_MAX, +}; + +#define IFA_MAX (__IFA_MAX - 1) + +/* ifa_flags */ +#define IFA_F_SECONDARY 0x01 +#define IFA_F_TEMPORARY IFA_F_SECONDARY + +#define IFA_F_NODAD 0x02 +#define IFA_F_OPTIMISTIC 0x04 +#define IFA_F_DADFAILED 0x08 +#define IFA_F_HOMEADDRESS 0x10 +#define IFA_F_DEPRECATED 0x20 +#define IFA_F_TENTATIVE 0x40 +#define IFA_F_PERMANENT 0x80 +#define IFA_F_MANAGETEMPADDR 0x100 +#define IFA_F_NOPREFIXROUTE 0x200 +#define IFA_F_MCAUTOJOIN 0x400 +#define IFA_F_STABLE_PRIVACY 0x800 + +struct ifa_cacheinfo { + __u32 ifa_prefered; + __u32 ifa_valid; + __u32 cstamp; /* created timestamp, hundredths of seconds */ + __u32 tstamp; /* updated timestamp, hundredths of seconds */ +}; + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)))) +#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) +#endif + +/* ifa_proto */ +#define IFAPROT_UNSPEC 0 +#define IFAPROT_KERNEL_LO 1 /* loopback */ +#define IFAPROT_KERNEL_RA 2 /* set by kernel from router announcement */ +#define IFAPROT_KERNEL_LL 3 /* link-local set by kernel */ + +#endif diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index f0d71b2a3f1e..7e46ca4cd31b 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -377,6 +377,7 @@ enum { IFLA_GSO_IPV4_MAX_SIZE, IFLA_GRO_IPV4_MAX_SIZE, IFLA_DPLL_PIN, + IFLA_MAX_PACING_OFFLOAD_HORIZON, __IFLA_MAX }; @@ -461,6 +462,286 @@ enum in6_addr_gen_mode { /* Bridge section */ +/** + * DOC: Bridge enum definition + * + * Please *note* that the timer values in the following section are expected + * in clock_t format, which is seconds multiplied by USER_HZ (generally + * defined as 100). + * + * @IFLA_BR_FORWARD_DELAY + * The bridge forwarding delay is the time spent in LISTENING state + * (before moving to LEARNING) and in LEARNING state (before moving + * to FORWARDING). Only relevant if STP is enabled. + * + * The valid values are between (2 * USER_HZ) and (30 * USER_HZ). + * The default value is (15 * USER_HZ). + * + * @IFLA_BR_HELLO_TIME + * The time between hello packets sent by the bridge, when it is a root + * bridge or a designated bridge. Only relevant if STP is enabled. + * + * The valid values are between (1 * USER_HZ) and (10 * USER_HZ). + * The default value is (2 * USER_HZ). + * + * @IFLA_BR_MAX_AGE + * The hello packet timeout is the time until another bridge in the + * spanning tree is assumed to be dead, after reception of its last hello + * message. Only relevant if STP is enabled. + * + * The valid values are between (6 * USER_HZ) and (40 * USER_HZ). + * The default value is (20 * USER_HZ). + * + * @IFLA_BR_AGEING_TIME + * Configure the bridge's FDB entries aging time. It is the time a MAC + * address will be kept in the FDB after a packet has been received from + * that address. After this time has passed, entries are cleaned up. + * Allow values outside the 802.1 standard specification for special cases: + * + * * 0 - entry never ages (all permanent) + * * 1 - entry disappears (no persistence) + * + * The default value is (300 * USER_HZ). + * + * @IFLA_BR_STP_STATE + * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off + * (*IFLA_BR_STP_STATE* == 0) for this bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_PRIORITY + * Set this bridge's spanning tree priority, used during STP root bridge + * election. + * + * The valid values are between 0 and 65535. + * + * @IFLA_BR_VLAN_FILTERING + * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off + * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not + * consider the VLAN tag when handling packets. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_PROTOCOL + * Set the protocol used for VLAN filtering. + * + * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value + * is 0x8100(802.1Q). + * + * @IFLA_BR_GROUP_FWD_MASK + * The group forwarding mask. This is the bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses (of the form 01:80:C2:00:00:0X). + * + * The default value is 0, which means the bridge does not forward any + * link-local frames coming on this port. + * + * @IFLA_BR_ROOT_ID + * The bridge root id, read only. + * + * @IFLA_BR_BRIDGE_ID + * The bridge id, read only. + * + * @IFLA_BR_ROOT_PORT + * The bridge root port, read only. + * + * @IFLA_BR_ROOT_PATH_COST + * The bridge root path cost, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE + * The bridge topology change, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED + * The bridge topology change detected, read only. + * + * @IFLA_BR_HELLO_TIMER + * The bridge hello timer, read only. + * + * @IFLA_BR_TCN_TIMER + * The bridge tcn timer, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_TIMER + * The bridge topology change timer, read only. + * + * @IFLA_BR_GC_TIMER + * The bridge gc timer, read only. + * + * @IFLA_BR_GROUP_ADDR + * Set the MAC address of the multicast group this bridge uses for STP. + * The address must be a link-local address in standard Ethernet MAC address + * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f]. + * + * The default value is 0. + * + * @IFLA_BR_FDB_FLUSH + * Flush bridge's fdb dynamic entries. + * + * @IFLA_BR_MCAST_ROUTER + * Set bridge's multicast router if IGMP snooping is enabled. + * The valid values are: + * + * * 0 - disabled. + * * 1 - automatic (queried). + * * 2 - permanently enabled. + * + * The default value is 1. + * + * @IFLA_BR_MCAST_SNOOPING + * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off + * (*IFLA_BR_MCAST_SNOOPING* == 0). + * + * The default value is 1. + * + * @IFLA_BR_MCAST_QUERY_USE_IFADDR + * If enabled use the bridge's own IP address as source address for IGMP + * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0 + * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0). + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_QUERIER + * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable + * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast + * queries by the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_HASH_ELASTICITY + * Set multicast database hash elasticity, It is the maximum chain length in + * the multicast hash table. This attribute is *deprecated* and the value + * is always 16. + * + * @IFLA_BR_MCAST_HASH_MAX + * Set maximum size of the multicast hash table + * + * The default value is 4096, the value must be a power of 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_CNT + * The Last Member Query Count is the number of Group-Specific Queries + * sent before the router assumes there are no local members. The Last + * Member Query Count is also the number of Group-and-Source-Specific + * Queries sent before the router assumes there are no listeners for a + * particular source. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_STARTUP_QUERY_CNT + * The Startup Query Count is the number of Queries sent out on startup, + * separated by the Startup Query Interval. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_INTVL + * The Last Member Query Interval is the Max Response Time inserted into + * Group-Specific Queries sent in response to Leave Group messages, and + * is also the amount of time between Group-Specific Query messages. + * + * The default value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_MEMBERSHIP_INTVL + * The interval after which the bridge will leave a group, if no membership + * reports for this group are received. + * + * The default value is (260 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERIER_INTVL + * The interval between queries sent by other routers. if no queries are + * seen after this delay has passed, the bridge will start to send its own + * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled). + * + * The default value is (255 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_INTVL + * The Query Interval is the interval between General Queries sent by + * the Querier. + * + * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL + * The Max Response Time used to calculate the Max Resp Code inserted + * into the periodic General Queries. + * + * The default value is (10 * USER_HZ). + * + * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL + * The interval between queries in the startup phase. + * + * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_NF_CALL_IPTABLES + * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0) + * iptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_IP6TABLES + * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0) + * ip6tables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_ARPTABLES + * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0) + * arptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_DEFAULT_PVID + * VLAN ID applied to untagged and priority-tagged incoming packets. + * + * The default value is 1. Setting to the special value 0 makes all ports of + * this bridge not have a PVID by default, which means that they will + * not accept VLAN-untagged traffic. + * + * @IFLA_BR_PAD + * Bridge attribute padding type for netlink message. + * + * @IFLA_BR_VLAN_STATS_ENABLED + * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable + * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_STATS_ENABLED + * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable + * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats + * accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_IGMP_VERSION + * Set the IGMP version. + * + * The valid values are 2 and 3. The default value is 2. + * + * @IFLA_BR_MCAST_MLD_VERSION + * Set the MLD version. + * + * The valid values are 1 and 2. The default value is 1. + * + * @IFLA_BR_VLAN_STATS_PER_PORT + * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable + * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting. + * Can be changed only when there are no port VLANs configured. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MULTI_BOOLOPT + * The multi_boolopt is used to control new boolean options to avoid adding + * new netlink attributes. You can look at ``enum br_boolopt_id`` for those + * options. + * + * @IFLA_BR_MCAST_QUERIER_STATE + * Bridge mcast querier states, read only. + * + * @IFLA_BR_FDB_N_LEARNED + * The number of dynamically learned FDB entries for the current bridge, + * read only. + * + * @IFLA_BR_FDB_MAX_LEARNED + * Set the number of max dynamically learned FDB entries for the current + * bridge. + */ enum { IFLA_BR_UNSPEC, IFLA_BR_FORWARD_DELAY, @@ -510,6 +791,8 @@ enum { IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, IFLA_BR_MCAST_QUERIER_STATE, + IFLA_BR_FDB_N_LEARNED, + IFLA_BR_FDB_MAX_LEARNED, __IFLA_BR_MAX, }; @@ -520,11 +803,252 @@ struct ifla_bridge_id { __u8 addr[6]; /* ETH_ALEN */ }; +/** + * DOC: Bridge mode enum definition + * + * @BRIDGE_MODE_HAIRPIN + * Controls whether traffic may be sent back out of the port on which it + * was received. This option is also called reflective relay mode, and is + * used to support basic VEPA (Virtual Ethernet Port Aggregator) + * capabilities. By default, this flag is turned off and the bridge will + * not forward traffic back out of the receiving port. + */ enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, }; +/** + * DOC: Bridge port enum definition + * + * @IFLA_BRPORT_STATE + * The operation state of the port. Here are the valid values. + * + * * 0 - port is in STP *DISABLED* state. Make this port completely + * inactive for STP. This is also called BPDU filter and could be used + * to disable STP on an untrusted port, like a leaf virtual device. + * The traffic forwarding is also stopped on this port. + * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled + * on the bridge. In this state the port listens for STP BPDUs and + * drops all other traffic frames. + * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on + * the bridge. In this state the port will accept traffic only for the + * purpose of updating MAC address tables. + * * 3 - port is in STP *FORWARDING* state. Port is fully active. + * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on + * the bridge. This state is used during the STP election process. + * In this state, port will only process STP BPDUs. + * + * @IFLA_BRPORT_PRIORITY + * The STP port priority. The valid values are between 0 and 255. + * + * @IFLA_BRPORT_COST + * The STP path cost of the port. The valid values are between 1 and 65535. + * + * @IFLA_BRPORT_MODE + * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details. + * + * @IFLA_BRPORT_GUARD + * Controls whether STP BPDUs will be processed by the bridge port. By + * default, the flag is turned off to allow BPDU processing. Turning this + * flag on will disable the bridge port if a STP BPDU packet is received. + * + * If the bridge has Spanning Tree enabled, hostile devices on the network + * may send BPDU on a port and cause network failure. Setting *guard on* + * will detect and stop this by disabling the port. The port will be + * restarted if the link is brought down, or removed and reattached. + * + * @IFLA_BRPORT_PROTECT + * Controls whether a given port is allowed to become a root port or not. + * Only used when STP is enabled on the bridge. By default the flag is off. + * + * This feature is also called root port guard. If BPDU is received from a + * leaf (edge) port, it should not be elected as root port. This could + * be used if using STP on a bridge and the downstream bridges are not fully + * trusted; this prevents a hostile guest from rerouting traffic. + * + * @IFLA_BRPORT_FAST_LEAVE + * This flag allows the bridge to immediately stop multicast traffic + * forwarding on a port that receives an IGMP Leave message. It is only used + * when IGMP snooping is enabled on the bridge. By default the flag is off. + * + * @IFLA_BRPORT_LEARNING + * Controls whether a given port will learn *source* MAC addresses from + * received traffic or not. Also controls whether dynamic FDB entries + * (which can also be added by software) will be refreshed by incoming + * traffic. By default this flag is on. + * + * @IFLA_BRPORT_UNICAST_FLOOD + * Controls whether unicast traffic for which there is no FDB entry will + * be flooded towards this port. By default this flag is on. + * + * @IFLA_BRPORT_PROXYARP + * Enable proxy ARP on this port. + * + * @IFLA_BRPORT_LEARNING_SYNC + * Controls whether a given port will sync MAC addresses learned on device + * port to bridge FDB. + * + * @IFLA_BRPORT_PROXYARP_WIFI + * Enable proxy ARP on this port which meets extended requirements by + * IEEE 802.11 and Hotspot 2.0 specifications. + * + * @IFLA_BRPORT_ROOT_ID + * + * @IFLA_BRPORT_BRIDGE_ID + * + * @IFLA_BRPORT_DESIGNATED_PORT + * + * @IFLA_BRPORT_DESIGNATED_COST + * + * @IFLA_BRPORT_ID + * + * @IFLA_BRPORT_NO + * + * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK + * + * @IFLA_BRPORT_CONFIG_PENDING + * + * @IFLA_BRPORT_MESSAGE_AGE_TIMER + * + * @IFLA_BRPORT_FORWARD_DELAY_TIMER + * + * @IFLA_BRPORT_HOLD_TIMER + * + * @IFLA_BRPORT_FLUSH + * Flush bridge ports' fdb dynamic entries. + * + * @IFLA_BRPORT_MULTICAST_ROUTER + * Configure the port's multicast router presence. A port with + * a multicast router will receive all multicast traffic. + * The valid values are: + * + * * 0 disable multicast routers on this port + * * 1 let the system detect the presence of routers (default) + * * 2 permanently enable multicast traffic forwarding on this port + * * 3 enable multicast routers temporarily on this port, not depending + * on incoming queries. + * + * @IFLA_BRPORT_PAD + * + * @IFLA_BRPORT_MCAST_FLOOD + * Controls whether a given port will flood multicast traffic for which + * there is no MDB entry. By default this flag is on. + * + * @IFLA_BRPORT_MCAST_TO_UCAST + * Controls whether a given port will replicate packets using unicast + * instead of multicast. By default this flag is off. + * + * This is done by copying the packet per host and changing the multicast + * destination MAC to a unicast one accordingly. + * + * *mcast_to_unicast* works on top of the multicast snooping feature of the + * bridge. Which means unicast copies are only delivered to hosts which + * are interested in unicast and signaled this via IGMP/MLD reports previously. + * + * This feature is intended for interface types which have a more reliable + * and/or efficient way to deliver unicast packets than broadcast ones + * (e.g. WiFi). + * + * However, it should only be enabled on interfaces where no IGMPv2/MLDv1 + * report suppression takes place. IGMP/MLD report suppression issue is + * usually overcome by the network daemon (supplicant) enabling AP isolation + * and by that separating all STAs. + * + * Delivery of STA-to-STA IP multicast is made possible again by enabling + * and utilizing the bridge hairpin mode, which considers the incoming port + * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option). + * Hairpin mode is performed after multicast snooping, therefore leading + * to only deliver reports to STAs running a multicast router. + * + * @IFLA_BRPORT_VLAN_TUNNEL + * Controls whether vlan to tunnel mapping is enabled on the port. + * By default this flag is off. + * + * @IFLA_BRPORT_BCAST_FLOOD + * Controls flooding of broadcast traffic on the given port. By default + * this flag is on. + * + * @IFLA_BRPORT_GROUP_FWD_MASK + * Set the group forward mask. This is a bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults + * to 0, which means the bridge does not forward any link-local frames + * coming on this port). + * + * @IFLA_BRPORT_NEIGH_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression + * is enabled on the port. By default this flag is off. + * + * @IFLA_BRPORT_ISOLATED + * Controls whether a given port will be isolated, which means it will be + * able to communicate with non-isolated ports only. By default this + * flag is off. + * + * @IFLA_BRPORT_BACKUP_PORT + * Set a backup port. If the port loses carrier all traffic will be + * redirected to the configured backup port. Set the value to 0 to disable + * it. + * + * @IFLA_BRPORT_MRP_RING_OPEN + * + * @IFLA_BRPORT_MRP_IN_OPEN + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + * The number of per-port EHT hosts limit. The default value is 512. + * Setting to 0 is not allowed. + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT + * The current number of tracked hosts, read only. + * + * @IFLA_BRPORT_LOCKED + * Controls whether a port will be locked, meaning that hosts behind the + * port will not be able to communicate through the port unless an FDB + * entry with the unit's MAC address is in the FDB. The common use case is + * that hosts are allowed access through authentication with the IEEE 802.1X + * protocol or based on whitelists. By default this flag is off. + * + * Please note that secure 802.1X deployments should always use the + * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its + * FDB based on link-local (EAPOL) traffic received on the port. + * + * @IFLA_BRPORT_MAB + * Controls whether a port will use MAC Authentication Bypass (MAB), a + * technique through which select MAC addresses may be allowed on a locked + * port, without using 802.1X authentication. Packets with an unknown source + * MAC address generates a "locked" FDB entry on the incoming bridge port. + * The common use case is for user space to react to these bridge FDB + * notifications and optionally replace the locked FDB entry with a normal + * one, allowing traffic to pass for whitelisted MAC addresses. + * + * Setting this flag also requires *IFLA_BRPORT_LOCKED* and + * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized + * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic + * FDB entries installed by user space (as replacements for the locked FDB + * entries) to be refreshed and/or aged out. + * + * @IFLA_BRPORT_MCAST_N_GROUPS + * + * @IFLA_BRPORT_MCAST_MAX_GROUPS + * Sets the maximum number of MDB entries that can be registered for a + * given port. Attempts to register more MDB entries at the port than this + * limit allows will be rejected, whether they are done through netlink + * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a + * limit of 0 disables the limit. The default value is 0. + * + * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression is + * enabled for a given port. By default this flag is off. + * + * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* + * is enabled for a given port. + * + * @IFLA_BRPORT_BACKUP_NHID + * The FDB nexthop object ID to attach to packets being redirected to a + * backup port that has VLAN tunnel mapping enabled (via the + * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has + * the effect of not attaching any ID. + */ enum { IFLA_BRPORT_UNSPEC, IFLA_BRPORT_STATE, /* Spanning tree state */ @@ -769,6 +1293,19 @@ enum netkit_mode { NETKIT_L3, }; +/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to + * the BPF program if attached. This also means the latter can + * consume the two fields if they were populated earlier. + * + * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before + * invoking the attached BPF program when the peer device resides + * in a different network namespace. This is the default behavior. + */ +enum netkit_scrub { + NETKIT_SCRUB_NONE, + NETKIT_SCRUB_DEFAULT, +}; + enum { IFLA_NETKIT_UNSPEC, IFLA_NETKIT_PEER_INFO, @@ -776,6 +1313,10 @@ enum { IFLA_NETKIT_POLICY, IFLA_NETKIT_PEER_POLICY, IFLA_NETKIT_MODE, + IFLA_NETKIT_SCRUB, + IFLA_NETKIT_PEER_SCRUB, + IFLA_NETKIT_HEADROOM, + IFLA_NETKIT_TAILROOM, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) @@ -854,6 +1395,7 @@ enum { IFLA_VXLAN_DF, IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ IFLA_VXLAN_LOCALBYPASS, + IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -871,6 +1413,13 @@ enum ifla_vxlan_df { VXLAN_DF_MAX = __VXLAN_DF_END - 1, }; +enum ifla_vxlan_label_policy { + VXLAN_LABEL_FIXED = 0, + VXLAN_LABEL_INHERIT = 1, + __VXLAN_LABEL_END, + VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1, +}; + /* GENEVE section */ enum { IFLA_GENEVE_UNSPEC, @@ -935,6 +1484,8 @@ enum { IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, IFLA_GTP_RESTART_COUNT, + IFLA_GTP_LOCAL, + IFLA_GTP_LOCAL6, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) @@ -1240,6 +1791,7 @@ enum { IFLA_HSR_PROTOCOL, /* Indicate different protocol than * HSR. For example PRP. */ + IFLA_HSR_INTERLINK, /* HSR interlink network device */ __IFLA_HSR_MAX, }; @@ -1417,7 +1969,9 @@ enum { enum { IFLA_DSA_UNSPEC, - IFLA_DSA_MASTER, + IFLA_DSA_CONDUIT, + /* Deprecated, use IFLA_DSA_CONDUIT instead */ + IFLA_DSA_MASTER = IFLA_DSA_CONDUIT, __IFLA_DSA_MAX, }; diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 638c606dfa74..23a062781468 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -7,8 +7,8 @@ * Magnus Karlsson <magnus.karlsson@intel.com> */ -#ifndef _LINUX_IF_XDP_H -#define _LINUX_IF_XDP_H +#ifndef _UAPI_LINUX_IF_XDP_H +#define _UAPI_LINUX_IF_XDP_H #include <linux/types.h> @@ -41,6 +41,10 @@ */ #define XDP_UMEM_TX_SW_CSUM (1 << 1) +/* Request to reserve tx_metadata_len bytes of per-chunk metadata. + */ +#define XDP_UMEM_TX_METADATA_LEN (1 << 2) + struct sockaddr_xdp { __u16 sxdp_family; __u16 sxdp_flags; @@ -75,6 +79,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 #define XDP_OPTIONS 8 +#define XDP_MAX_TX_SKB_BUDGET 9 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -113,16 +118,22 @@ struct xdp_options { ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) /* Request transmit timestamp. Upon completion, put it into tx_timestamp - * field of union xsk_tx_metadata. + * field of struct xsk_tx_metadata. */ #define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) /* Request transmit checksum offload. Checksum start position and offset - * are communicated via csum_start and csum_offset fields of union + * are communicated via csum_start and csum_offset fields of struct * xsk_tx_metadata. */ #define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) +/* Request launch time hardware offload. The device will schedule the packet for + * transmission at a pre-determined time called launch time. The value of + * launch time is communicated via launch_time field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_LAUNCH_TIME (1 << 2) + /* AF_XDP offloads request. 'request' union member is consumed by the driver * when the packet is being transmitted. 'completion' union member is * filled by the driver when the transmit completion arrives. @@ -138,6 +149,10 @@ struct xsk_tx_metadata { __u16 csum_start; /* Offset from csum_start where checksum should be stored. */ __u16 csum_offset; + + /* XDP_TXMD_FLAGS_LAUNCH_TIME */ + /* Launch time in nanosecond against the PTP HW Clock */ + __u64 launch_time; } request; struct { @@ -166,4 +181,4 @@ struct xdp_desc { /* TX packet carries valid metadata. */ #define XDP_TX_METADATA (1 << 1) -#endif /* _LINUX_IF_XDP_H */ +#endif /* _UAPI_LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e682ab628dfa..ced0fc3c3aa5 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -79,8 +79,12 @@ enum { #define IPPROTO_MPLS IPPROTO_MPLS IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */ #define IPPROTO_ETHERNET IPPROTO_ETHERNET + IPPROTO_AGGFRAG = 144, /* AGGFRAG in ESP (RFC 9347) */ +#define IPPROTO_AGGFRAG IPPROTO_AGGFRAG IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX @@ -139,7 +143,7 @@ struct in_addr { */ #define IP_PMTUDISC_INTERFACE 4 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get - * fragmented if they exeed the interface mtu + * fragmented if they exceed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d03842abae57..52f6000ab020 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -178,6 +178,7 @@ struct kvm_xen_exit { #define KVM_EXIT_NOTIFY 37 #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 +#define KVM_EXIT_TDX 40 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -192,11 +193,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -362,6 +376,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_WAKEUP 4 #define KVM_SYSTEM_EVENT_SUSPEND 5 #define KVM_SYSTEM_EVENT_SEV_TERM 6 +#define KVM_SYSTEM_EVENT_TDX_FATAL 7 __u32 type; __u32 ndata; union { @@ -433,6 +448,31 @@ struct kvm_run { __u64 gpa; __u64 size; } memory_fault; + /* KVM_EXIT_TDX */ + struct { + __u64 flags; + __u64 nr; + union { + struct { + __u64 ret; + __u64 data[5]; + } unknown; + struct { + __u64 ret; + __u64 gpa; + __u64 size; + } get_quote; + struct { + __u64 ret; + __u64 leaf; + __u64 r11, r12, r13, r14; + } get_tdvmcall_info; + struct { + __u64 ret; + __u64 vector; + } setup_event_notify; + }; + } tdx; /* Fix the size of the union. */ char padding[256]; }; @@ -604,10 +644,7 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) -#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ - KVM_X86_DISABLE_EXITS_HLT | \ - KVM_X86_DISABLE_EXITS_PAUSE | \ - KVM_X86_DISABLE_EXITS_CSTATE) +#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { @@ -917,6 +954,15 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 +#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_ARM_EL2 240 +#define KVM_CAP_ARM_EL2_E2H0 241 +#define KVM_CAP_RISCV_MP_STATE_RESET 242 +#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 +#define KVM_CAP_GUEST_MEMFD_FLAGS 244 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1054,6 +1100,10 @@ struct kvm_dirty_tlb { #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL + +#define KVM_REG_SIZE(id) \ + (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) + #define KVM_REG_SIZE_U8 0x0000000000000000ULL #define KVM_REG_SIZE_U16 0x0010000000000000ULL #define KVM_REG_SIZE_U32 0x0020000000000000ULL @@ -1142,7 +1192,15 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_RISCV_AIA, #define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA + KVM_DEV_TYPE_LOONGARCH_IPI, +#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI + KVM_DEV_TYPE_LOONGARCH_EIOINTC, +#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC + KVM_DEV_TYPE_LOONGARCH_PCHPIC, +#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC + KVM_DEV_TYPE_MAX, + }; struct kvm_vfio_spapr_tce { @@ -1541,6 +1599,8 @@ struct kvm_memory_attributes { #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) +#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) struct kvm_create_guest_memfd { __u64 size; @@ -1548,4 +1608,13 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h new file mode 100644 index 000000000000..7fa67c2031a5 --- /dev/null +++ b/tools/include/uapi/linux/mount.h @@ -0,0 +1,235 @@ +#ifndef _UAPI_LINUX_MOUNT_H +#define _UAPI_LINUX_MOUNT_H + +#include <linux/types.h> + +/* + * These are the fs-independent mount-flags: up to 32 flags are supported + * + * Usage of these is restricted within the kernel to core mount(2) code and + * callers of sys_mount() only. Filesystems should be using the SB_* + * equivalent instead. + */ +#define MS_RDONLY 1 /* Mount read-only */ +#define MS_NOSUID 2 /* Ignore suid and sgid bits */ +#define MS_NODEV 4 /* Disallow access to device special files */ +#define MS_NOEXEC 8 /* Disallow program execution */ +#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ +#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ +#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ +#define MS_NOATIME 1024 /* Do not update access times. */ +#define MS_NODIRATIME 2048 /* Do not update directory access times */ +#define MS_BIND 4096 +#define MS_MOVE 8192 +#define MS_REC 16384 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 +#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ +#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ +#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define MS_I_VERSION (1<<23) /* Update inode I_version field */ +#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define MS_SUBMOUNT (1<<26) +#define MS_NOREMOTELOCK (1<<27) +#define MS_NOSEC (1<<28) +#define MS_BORN (1<<29) +#define MS_ACTIVE (1<<30) +#define MS_NOUSER (1<<31) + +/* + * Superblock flags that can be altered by MS_REMOUNT + */ +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ + MS_LAZYTIME) + +/* + * Old magic mount flag and mask + */ +#define MS_MGC_VAL 0xC0ED0000 +#define MS_MGC_MSK 0xffff0000 + +/* + * open_tree() flags. + */ +#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ +#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ + +/* + * move_mount() flags. + */ +#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */ +#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */ +#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ +#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ +#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ +#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ +#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 + +/* + * fsopen() flags. + */ +#define FSOPEN_CLOEXEC 0x00000001 + +/* + * fspick() flags. + */ +#define FSPICK_CLOEXEC 0x00000001 +#define FSPICK_SYMLINK_NOFOLLOW 0x00000002 +#define FSPICK_NO_AUTOMOUNT 0x00000004 +#define FSPICK_EMPTY_PATH 0x00000008 + +/* + * The type of fsconfig() call made. + */ +enum fsconfig_command { + FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */ + FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */ + FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */ + FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */ + FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */ + FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */ + FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */ + FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */ + FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */ +}; + +/* + * fsmount() flags. + */ +#define FSMOUNT_CLOEXEC 0x00000001 + +/* + * Mount attributes. + */ +#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ +#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ +#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ +#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ +#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ +#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ +#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ +#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ +#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ +#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */ + +/* + * mount_setattr() + */ +struct mount_attr { + __u64 attr_set; + __u64 attr_clr; + __u64 propagation; + __u64 userns_fd; +}; + +/* List of all mount_attr versions. */ +#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + + +/* + * Structure for getting mount/superblock/filesystem info with statmount(2). + * + * The interface is similar to statx(2): individual fields or groups can be + * selected with the @mask argument of statmount(). Kernel will set the @mask + * field according to the supported fields. + * + * If string fields are selected, then the caller needs to pass a buffer that + * has space after the fixed part of the structure. Nul terminated strings are + * copied there and offsets relative to @str are stored in the relevant fields. + * If the buffer is too small, then EOVERFLOW is returned. The actually used + * size is returned in @size. + */ +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 mnt_opts; /* [str] Options (comma separated, escaped) */ + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */ + __u32 sb_source; /* [str] Source string of the mount */ + __u32 opt_num; /* Number of fs options */ + __u32 opt_array; /* [str] Array of nul terminated fs options */ + __u32 opt_sec_num; /* Number of security options */ + __u32 opt_sec_array; /* [str] Array of nul terminated security options */ + __u64 supported_mask; /* Mask flags that this kernel supports */ + __u32 mnt_uidmap_num; /* Number of uid mappings */ + __u32 mnt_uidmap; /* [str] Array of uid mappings (as seen from callers namespace) */ + __u32 mnt_gidmap_num; /* Number of gid mappings */ + __u32 mnt_gidmap; /* [str] Array of gid mappings (as seen from callers namespace) */ + __u64 __spare2[43]; + char str[]; /* Variable size part containing strings */ +}; + +/* + * Structure for passing mount ID and miscellaneous parameters to statmount(2) + * and listmount(2). + * + * For statmount(2) @param represents the request mask. + * For listmount(2) @param represents the last listed mount id (or zero). + */ +struct mnt_id_req { + __u32 size; + __u32 spare; + __u64 mnt_id; + __u64 param; + __u64 mnt_ns_id; +}; + +/* List of all mnt_id_req versions. */ +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ + +/* + * @mask bits for statmount(2) + */ +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ +#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */ +#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */ +#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */ +#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */ +#define STATMOUNT_SUPPORTED_MASK 0x00001000U /* Want/got supported mask flags */ +#define STATMOUNT_MNT_UIDMAP 0x00002000U /* Want/got uidmap... */ +#define STATMOUNT_MNT_GIDMAP 0x00004000U /* Want/got gidmap... */ + +/* + * Special @mnt_id values that can be passed to listmount + */ +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ + +#endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/linux/neighbour.h b/tools/include/uapi/linux/neighbour.h new file mode 100644 index 000000000000..c34a81245f87 --- /dev/null +++ b/tools/include/uapi/linux/neighbour.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NEIGHBOUR_H +#define _UAPI__LINUX_NEIGHBOUR_H + +#include <linux/types.h> +#include <linux/netlink.h> + +struct ndmsg { + __u8 ndm_family; + __u8 ndm_pad1; + __u16 ndm_pad2; + __s32 ndm_ifindex; + __u16 ndm_state; + __u8 ndm_flags; + __u8 ndm_type; +}; + +enum { + NDA_UNSPEC, + NDA_DST, + NDA_LLADDR, + NDA_CACHEINFO, + NDA_PROBES, + NDA_VLAN, + NDA_PORT, + NDA_VNI, + NDA_IFINDEX, + NDA_MASTER, + NDA_LINK_NETNSID, + NDA_SRC_VNI, + NDA_PROTOCOL, /* Originator of entry */ + NDA_NH_ID, + NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, + NDA_NDM_STATE_MASK, + NDA_NDM_FLAGS_MASK, + __NDA_MAX +}; + +#define NDA_MAX (__NDA_MAX - 1) + +/* + * Neighbor Cache Entry Flags + */ + +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_LOCKED (1 << 1) +#define NTF_EXT_EXT_VALIDATED (1 << 2) + +/* + * Neighbor Cache Entry States. + */ + +#define NUD_INCOMPLETE 0x01 +#define NUD_REACHABLE 0x02 +#define NUD_STALE 0x04 +#define NUD_DELAY 0x08 +#define NUD_PROBE 0x10 +#define NUD_FAILED 0x20 + +/* Dummy states */ +#define NUD_NOARP 0x40 +#define NUD_PERMANENT 0x80 +#define NUD_NONE 0x00 + +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * + * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry + * states don't make sense and thus are ignored. Such entries don't age and + * can roam. + * + * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf + * of a user space control plane, and automatically refreshed so that (if + * possible) they remain in NUD_REACHABLE state. + * + * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the + * bridge in response to a host trying to communicate via a locked bridge port + * with MAB enabled. Their purpose is to notify user space that a host requires + * authentication. + * + * NTF_EXT_EXT_VALIDATED flagged neighbor entries were externally validated by + * a user space control plane. The kernel will not remove or invalidate them, + * but it can probe them and notify user space when they become reachable. + */ + +struct nda_cacheinfo { + __u32 ndm_confirmed; + __u32 ndm_used; + __u32 ndm_updated; + __u32 ndm_refcnt; +}; + +/***************************************************************** + * Neighbour tables specific messages. + * + * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the + * NLM_F_DUMP flag set. Every neighbour table configuration is + * spread over multiple messages to avoid running into message + * size limits on systems with many interfaces. The first message + * in the sequence transports all not device specific data such as + * statistics, configuration, and the default parameter set. + * This message is followed by 0..n messages carrying device + * specific parameter sets. + * Although the ordering should be sufficient, NDTA_NAME can be + * used to identify sequences. The initial message can be identified + * by checking for NDTA_CONFIG. The device specific messages do + * not contain this TLV but have NDTPA_IFINDEX set to the + * corresponding interface index. + * + * To change neighbour table attributes, send RTM_SETNEIGHTBL + * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], + * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked + * otherwise. Device specific parameter sets can be changed by + * setting NDTPA_IFINDEX to the interface index of the corresponding + * device. + ****/ + +struct ndt_stats { + __u64 ndts_allocs; + __u64 ndts_destroys; + __u64 ndts_hash_grows; + __u64 ndts_res_failed; + __u64 ndts_lookups; + __u64 ndts_hits; + __u64 ndts_rcv_probes_mcast; + __u64 ndts_rcv_probes_ucast; + __u64 ndts_periodic_gc_runs; + __u64 ndts_forced_gc_runs; + __u64 ndts_table_fulls; +}; + +enum { + NDTPA_UNSPEC, + NDTPA_IFINDEX, /* u32, unchangeable */ + NDTPA_REFCNT, /* u32, read-only */ + NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ + NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ + NDTPA_RETRANS_TIME, /* u64, msecs */ + NDTPA_GC_STALETIME, /* u64, msecs */ + NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ + NDTPA_QUEUE_LEN, /* u32 */ + NDTPA_APP_PROBES, /* u32 */ + NDTPA_UCAST_PROBES, /* u32 */ + NDTPA_MCAST_PROBES, /* u32 */ + NDTPA_ANYCAST_DELAY, /* u64, msecs */ + NDTPA_PROXY_DELAY, /* u64, msecs */ + NDTPA_PROXY_QLEN, /* u32 */ + NDTPA_LOCKTIME, /* u64, msecs */ + NDTPA_QUEUE_LENBYTES, /* u32 */ + NDTPA_MCAST_REPROBES, /* u32 */ + NDTPA_PAD, + NDTPA_INTERVAL_PROBE_TIME_MS, /* u64, msecs */ + __NDTPA_MAX +}; +#define NDTPA_MAX (__NDTPA_MAX - 1) + +struct ndtmsg { + __u8 ndtm_family; + __u8 ndtm_pad1; + __u16 ndtm_pad2; +}; + +struct ndt_config { + __u16 ndtc_key_len; + __u16 ndtc_entry_size; + __u32 ndtc_entries; + __u32 ndtc_last_flush; /* delta to now in msecs */ + __u32 ndtc_last_rand; /* delta to now in msecs */ + __u32 ndtc_hash_rnd; + __u32 ndtc_hash_mask; + __u32 ndtc_hash_chain_gc; + __u32 ndtc_proxy_qlen; +}; + +enum { + NDTA_UNSPEC, + NDTA_NAME, /* char *, unchangeable */ + NDTA_THRESH1, /* u32 */ + NDTA_THRESH2, /* u32 */ + NDTA_THRESH3, /* u32 */ + NDTA_CONFIG, /* struct ndt_config, read-only */ + NDTA_PARMS, /* nested TLV NDTPA_* */ + NDTA_STATS, /* struct ndt_stats, read-only */ + NDTA_GC_INTERVAL, /* u64, msecs */ + NDTA_PAD, + __NDTA_MAX +}; +#define NDTA_MAX (__NDTA_MAX - 1) + + /* FDB activity notification bits used in NFEA_ACTIVITY_NOTIFY: + * - FDB_NOTIFY_BIT - notify on activity/expire for any entry + * - FDB_NOTIFY_INACTIVE_BIT - mark as inactive to avoid multiple notifications + */ +enum { + FDB_NOTIFY_BIT = (1 << 0), + FDB_NOTIFY_INACTIVE_BIT = (1 << 1) +}; + +/* embedded into NDA_FDB_EXT_ATTRS: + * [NDA_FDB_EXT_ATTRS] = { + * [NFEA_ACTIVITY_NOTIFY] + * ... + * } + */ +enum { + NFEA_UNSPEC, + NFEA_ACTIVITY_NOTIFY, + NFEA_DONT_REFRESH, + __NFEA_MAX +}; +#define NFEA_MAX (__NFEA_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 43742ac5b00d..e0b579a1df4f 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NETDEV_H #define _UAPI_LINUX_NETDEV_H @@ -59,10 +60,13 @@ enum netdev_xdp_rx_metadata { * by the driver. * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the * driver. + * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported + * by the driver. */ enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4, }; enum netdev_queue_type { @@ -74,6 +78,12 @@ enum netdev_qstats_scope { NETDEV_QSTATS_SCOPE_QUEUE = 1, }; +enum netdev_napi_threaded { + NETDEV_NAPI_THREADED_DISABLED, + NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -87,12 +97,19 @@ enum { }; enum { + __NETDEV_A_IO_URING_PROVIDER_INFO_MAX, + NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1) +}; + +enum { NETDEV_A_PAGE_POOL_ID = 1, NETDEV_A_PAGE_POOL_IFINDEX, NETDEV_A_PAGE_POOL_NAPI_ID, NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, + NETDEV_A_PAGE_POOL_IO_URING, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -121,16 +138,28 @@ enum { NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, + NETDEV_A_NAPI_DEFER_HARD_IRQS, + NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, + NETDEV_A_NAPI_THREADED, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) }; enum { + __NETDEV_A_XSK_INFO_MAX, + NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) +}; + +enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, + NETDEV_A_QUEUE_IO_URING, + NETDEV_A_QUEUE_XSK, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) @@ -174,6 +203,16 @@ enum { }; enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -186,6 +225,9 @@ enum { NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, + NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/include/uapi/linux/netfilter.h b/tools/include/uapi/linux/netfilter.h new file mode 100644 index 000000000000..5a79ccb76701 --- /dev/null +++ b/tools/include/uapi/linux/netfilter.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETFILTER_H +#define _UAPI__LINUX_NETFILTER_H + +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/in.h> +#include <linux/in6.h> + +/* Responses from hook functions. */ +#define NF_DROP 0 +#define NF_ACCEPT 1 +#define NF_STOLEN 2 +#define NF_QUEUE 3 +#define NF_REPEAT 4 +#define NF_STOP 5 /* Deprecated, for userspace nf_queue compatibility. */ +#define NF_MAX_VERDICT NF_STOP + +/* we overload the higher bits for encoding auxiliary data such as the queue + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 + +/* queue number (NF_QUEUE) or errno (NF_DROP) */ +#define NF_VERDICT_QMASK 0xffff0000 +#define NF_VERDICT_QBITS 16 + +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) + +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) + +/* only for userspace compatibility */ +#ifndef __KERNEL__ + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 +#endif + +enum nf_inet_hooks { + NF_INET_PRE_ROUTING, + NF_INET_LOCAL_IN, + NF_INET_FORWARD, + NF_INET_LOCAL_OUT, + NF_INET_POST_ROUTING, + NF_INET_NUMHOOKS, + NF_INET_INGRESS = NF_INET_NUMHOOKS, +}; + +enum nf_dev_hooks { + NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, + NF_NETDEV_NUMHOOKS +}; + +enum { + NFPROTO_UNSPEC = 0, + NFPROTO_INET = 1, + NFPROTO_IPV4 = 2, + NFPROTO_ARP = 3, + NFPROTO_NETDEV = 5, + NFPROTO_BRIDGE = 7, + NFPROTO_IPV6 = 10, +#ifndef __KERNEL__ /* no longer supported by kernel */ + NFPROTO_DECNET = 12, +#endif + NFPROTO_NUMPROTO, +}; + +union nf_inet_addr { + __u32 all[4]; + __be32 ip; + __be32 ip6[4]; + struct in_addr in; + struct in6_addr in6; +}; + +#endif /* _UAPI__LINUX_NETFILTER_H */ diff --git a/tools/include/uapi/linux/netfilter_arp.h b/tools/include/uapi/linux/netfilter_arp.h new file mode 100644 index 000000000000..791dfc5ae907 --- /dev/null +++ b/tools/include/uapi/linux/netfilter_arp.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ +#ifndef __LINUX_ARP_NETFILTER_H +#define __LINUX_ARP_NETFILTER_H + +/* ARP-specific defines for netfilter. + * (C)2002 Rusty Russell IBM -- This code is GPL. + */ + +#include <linux/netfilter.h> + +/* There is no PF_ARP. */ +#define NF_ARP 0 + +/* ARP Hooks */ +#define NF_ARP_IN 0 +#define NF_ARP_OUT 1 +#define NF_ARP_FORWARD 2 + +#ifndef __KERNEL__ +#define NF_ARP_NUMHOOKS 3 +#endif + +#endif /* __LINUX_ARP_NETFILTER_H */ diff --git a/tools/include/uapi/linux/nsfs.h b/tools/include/uapi/linux/nsfs.h new file mode 100644 index 000000000000..a25e38d1c874 --- /dev/null +++ b/tools/include/uapi/linux/nsfs.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_NSFS_H +#define __LINUX_NSFS_H + +#include <linux/ioctl.h> +#include <linux/types.h> + +#define NSIO 0xb7 + +/* Returns a file descriptor that refers to an owning user namespace */ +#define NS_GET_USERNS _IO(NSIO, 0x1) +/* Returns a file descriptor that refers to a parent namespace */ +#define NS_GET_PARENT _IO(NSIO, 0x2) +/* Returns the type of namespace (CLONE_NEW* value) referred to by + file descriptor */ +#define NS_GET_NSTYPE _IO(NSIO, 0x3) +/* Get owner UID (in the caller's user namespace) for a user namespace */ +#define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Translate pid from target pid namespace into the caller's pid namespace. */ +#define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) +/* Return thread-group leader id of pid in the callers pid namespace. */ +#define NS_GET_TGID_FROM_PIDNS _IOR(NSIO, 0x7, int) +/* Translate pid from caller's pid namespace into a target pid namespace. */ +#define NS_GET_PID_IN_PIDNS _IOR(NSIO, 0x8, int) +/* Return thread-group leader id of pid in the target pid namespace. */ +#define NS_GET_TGID_IN_PIDNS _IOR(NSIO, 0x9, int) + +struct mnt_ns_info { + __u32 size; + __u32 nr_mounts; + __u64 mnt_ns_id; +}; + +#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */ + +/* Get information about namespace. */ +#define NS_MNT_GET_INFO _IOR(NSIO, 10, struct mnt_ns_info) +/* Get next namespace. */ +#define NS_MNT_GET_NEXT _IOR(NSIO, 11, struct mnt_ns_info) +/* Get previous namespace. */ +#define NS_MNT_GET_PREV _IOR(NSIO, 12, struct mnt_ns_info) + +/* Retrieve namespace identifiers. */ +#define NS_GET_MNTNS_ID _IOR(NSIO, 5, __u64) +#define NS_GET_ID _IOR(NSIO, 13, __u64) + +enum init_ns_ino { + IPC_NS_INIT_INO = 0xEFFFFFFFU, + UTS_NS_INIT_INO = 0xEFFFFFFEU, + USER_NS_INIT_INO = 0xEFFFFFFDU, + PID_NS_INIT_INO = 0xEFFFFFFCU, + CGROUP_NS_INIT_INO = 0xEFFFFFFBU, + TIME_NS_INIT_INO = 0xEFFFFFFAU, + NET_NS_INIT_INO = 0xEFFFFFF9U, + MNT_NS_INIT_INO = 0xEFFFFFF8U, +#ifdef __KERNEL__ + MNT_NS_ANON_INO = 0xEFFFFFF7U, +#endif +}; + +struct nsfs_file_handle { + __u64 ns_id; + __u32 ns_type; + __u32 ns_inum; +}; + +#define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ +#define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ + +enum init_ns_id { + IPC_NS_INIT_ID = 1ULL, + UTS_NS_INIT_ID = 2ULL, + USER_NS_INIT_ID = 3ULL, + PID_NS_INIT_ID = 4ULL, + CGROUP_NS_INIT_ID = 5ULL, + TIME_NS_INIT_ID = 6ULL, + NET_NS_INIT_ID = 7ULL, + MNT_NS_INIT_ID = 8ULL, +#ifdef __KERNEL__ + NS_LAST_INIT_ID = MNT_NS_INIT_ID, +#endif +}; + +enum ns_type { + TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */ + MNT_NS = (1ULL << 17), /* CLONE_NEWNS */ + CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */ + UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */ + IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */ + USER_NS = (1ULL << 28), /* CLONE_NEWUSER */ + PID_NS = (1ULL << 29), /* CLONE_NEWPID */ + NET_NS = (1ULL << 30), /* CLONE_NEWNET */ +}; + +/** + * struct ns_id_req - namespace ID request structure + * @size: size of this structure + * @spare: reserved for future use + * @filter: filter mask + * @ns_id: last namespace id + * @user_ns_id: owning user namespace ID + * + * Structure for passing namespace ID and miscellaneous parameters to + * statns(2) and listns(2). + * + * For statns(2) @param represents the request mask. + * For listns(2) @param represents the last listed mount id (or zero). + */ +struct ns_id_req { + __u32 size; + __u32 spare; + __u64 ns_id; + struct /* listns */ { + __u32 ns_type; + __u32 spare2; + __u64 user_ns_id; + }; +}; + +/* + * Special @user_ns_id value that can be passed to listns() + */ +#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */ + +/* List of all ns_id_req versions. */ +#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */ + +#endif /* __LINUX_NSFS_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3a64499b0f5d..c44a8fb3e418 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -39,18 +39,21 @@ enum perf_type_id { /* * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA * AA: hardware event ID * EEEEEEEE: PMU type ID + * * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB * BB: hardware cache ID * CC: hardware cache op ID * DD: hardware cache op result ID * EEEEEEEE: PMU type ID - * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + * + * If the PMU type ID is 0, PERF_TYPE_RAW will be applied. */ -#define PERF_PMU_TYPE_SHIFT 32 -#define PERF_HW_EVENT_MASK 0xffffffff +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff /* * Generalized performance event event_id types, used by the @@ -112,7 +115,7 @@ enum perf_hw_cache_op_result_id { /* * Special "software" events provided by the kernel, even if the hardware * does not support performance events. These events measure various - * physical and sw events of the kernel (and allow the profiling of them as + * physical and SW events of the kernel (and allow the profiling of them as * well): */ enum perf_sw_ids { @@ -167,8 +170,9 @@ enum perf_event_sample_format { }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) + /* - * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * Values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set. * * If the user does not pass priv level information via branch_sample_type, * the kernel uses the event's priv level. Branch and event priv levels do @@ -178,20 +182,20 @@ enum perf_event_sample_format { * of branches and therefore it supersedes all the other types. */ enum perf_branch_sample_type_shift { - PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ - PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ - PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ - - PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ - PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ - PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ - PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ - PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ - PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ - PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ - PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* CALL/RET stack */ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ @@ -210,96 +214,95 @@ enum perf_branch_sample_type_shift { }; enum perf_branch_sample_type { - PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, - PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, - PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, - PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, - PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, - PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, - PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, - PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, - PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, - PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, - PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, - PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, - PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, - PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, - PERF_SAMPLE_BRANCH_TYPE_SAVE = - 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, - PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, - PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; /* - * Common flow change classification + * Common control flow change classifications: */ enum { - PERF_BR_UNKNOWN = 0, /* unknown */ - PERF_BR_COND = 1, /* conditional */ - PERF_BR_UNCOND = 2, /* unconditional */ - PERF_BR_IND = 3, /* indirect */ - PERF_BR_CALL = 4, /* function call */ - PERF_BR_IND_CALL = 5, /* indirect function call */ - PERF_BR_RET = 6, /* function return */ - PERF_BR_SYSCALL = 7, /* syscall */ - PERF_BR_SYSRET = 8, /* syscall return */ - PERF_BR_COND_CALL = 9, /* conditional function call */ - PERF_BR_COND_RET = 10, /* conditional function return */ - PERF_BR_ERET = 11, /* exception return */ - PERF_BR_IRQ = 12, /* irq */ - PERF_BR_SERROR = 13, /* system error */ - PERF_BR_NO_TX = 14, /* not in transaction */ - PERF_BR_EXTEND_ABI = 15, /* extend ABI */ + PERF_BR_UNKNOWN = 0, /* Unknown */ + PERF_BR_COND = 1, /* Conditional */ + PERF_BR_UNCOND = 2, /* Unconditional */ + PERF_BR_IND = 3, /* Indirect */ + PERF_BR_CALL = 4, /* Function call */ + PERF_BR_IND_CALL = 5, /* Indirect function call */ + PERF_BR_RET = 6, /* Function return */ + PERF_BR_SYSCALL = 7, /* Syscall */ + PERF_BR_SYSRET = 8, /* Syscall return */ + PERF_BR_COND_CALL = 9, /* Conditional function call */ + PERF_BR_COND_RET = 10, /* Conditional function return */ + PERF_BR_ERET = 11, /* Exception return */ + PERF_BR_IRQ = 12, /* IRQ */ + PERF_BR_SERROR = 13, /* System error */ + PERF_BR_NO_TX = 14, /* Not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* Extend ABI */ PERF_BR_MAX, }; /* - * Common branch speculation outcome classification + * Common branch speculation outcome classifications: */ enum { - PERF_BR_SPEC_NA = 0, /* Not available */ - PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ - PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ - PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ PERF_BR_SPEC_MAX, }; enum { - PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ - PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ - PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ - PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ - PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ - PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ - PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ - PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ PERF_BR_NEW_MAX, }; enum { - PERF_BR_PRIV_UNKNOWN = 0, - PERF_BR_PRIV_USER = 1, - PERF_BR_PRIV_KERNEL = 2, - PERF_BR_PRIV_HV = 3, + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, }; -#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 -#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 -#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 -#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 -#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ @@ -310,9 +313,9 @@ enum { * Values to determine ABI of the registers dump. */ enum perf_sample_regs_abi { - PERF_SAMPLE_REGS_ABI_NONE = 0, - PERF_SAMPLE_REGS_ABI_32 = 1, - PERF_SAMPLE_REGS_ABI_64 = 2, + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, }; /* @@ -320,21 +323,21 @@ enum perf_sample_regs_abi { * abort events. Multiple bits can be set. */ enum { - PERF_TXN_ELISION = (1 << 0), /* From elision */ - PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ - PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ - PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ - PERF_TXN_RETRY = (1 << 4), /* Retry possible */ - PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ - PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ - PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction is not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ - PERF_TXN_MAX = (1 << 8), /* non-ABI */ + PERF_TXN_MAX = (1 << 8), /* non-ABI */ - /* bits 32..63 are reserved for the abort code */ + /* Bits 32..63 are reserved for the abort code */ - PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), - PERF_TXN_ABORT_SHIFT = 32, + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, }; /* @@ -369,22 +372,23 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; -#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ -#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ -#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ -#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ - /* add: sample_stack_user */ -#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ -#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ -#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ -#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ -#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ +#define PERF_ATTR_SIZE_VER0 64 /* Size of first published 'struct perf_event_attr' */ +#define PERF_ATTR_SIZE_VER1 72 /* Add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* Add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* Add: sample_regs_user */ + /* Add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* Add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* Add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ +#define PERF_ATTR_SIZE_VER9 144 /* add: config4 */ /* - * Hardware event_id to monitor via a performance monitoring event: - * - * @sample_max_stack: Max number of frame pointers in a callchain, - * should be < /proc/sys/kernel/perf_event_max_stack + * 'struct perf_event_attr' contains various attributes that define + * a performance event - most of them hardware related configuration + * details, but also a lot of behavioral switches and values implemented + * by the kernel. */ struct perf_event_attr { @@ -394,7 +398,7 @@ struct perf_event_attr { __u32 type; /* - * Size of the attr structure, for fwd/bwd compat. + * Size of the attr structure, for forward/backwards compatibility. */ __u32 size; @@ -449,21 +453,23 @@ struct perf_event_attr { comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ - write_backward : 1, /* Write ring buffer from end to beginning */ + write_backward : 1, /* write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - bpf_event : 1, /* include bpf events */ + bpf_event : 1, /* include BPF events */ aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - build_id : 1, /* use build id in mmap2 events */ + build_id : 1, /* use build ID in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + defer_callchain: 1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */ + defer_output : 1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */ + __reserved_1 : 24; union { - __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_events; /* wake up every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; @@ -472,13 +478,13 @@ struct perf_event_attr { __u64 bp_addr; __u64 kprobe_func; /* for perf_kprobe */ __u64 uprobe_path; /* for perf_uprobe */ - __u64 config1; /* extension of config */ + __u64 config1; /* extension of config */ }; union { __u64 bp_len; - __u64 kprobe_addr; /* when kprobe_func == NULL */ + __u64 kprobe_addr; /* when kprobe_func == NULL */ __u64 probe_offset; /* for perf_[k,u]probe */ - __u64 config2; /* extension of config1 */ + __u64 config2; /* extension of config1 */ }; __u64 branch_sample_type; /* enum perf_branch_sample_type */ @@ -508,10 +514,28 @@ struct perf_event_attr { * Wakeup watermark for AUX area */ __u32 aux_watermark; + + /* + * Max number of frame pointers in a callchain, should be + * lower than /proc/sys/kernel/perf_event_max_stack. + * + * Max number of entries of branch stack should be lower + * than the hardware limit. + */ __u16 sample_max_stack; + __u16 __reserved_2; __u32 aux_sample_size; - __u32 __reserved_3; + + union { + __u32 aux_action; + struct { + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 29; + }; + }; /* * User provided data if sigtrap=1, passed back to user via @@ -522,11 +546,12 @@ struct perf_event_attr { __u64 sig_data; __u64 config3; /* extension of config2 */ + __u64 config4; /* extension of config3 */ }; /* * Structure used by below PERF_EVENT_IOC_QUERY_BPF command - * to query bpf programs attached to the same perf tracepoint + * to query BPF programs attached to the same perf tracepoint * as the given perf event. */ struct perf_event_query_bpf { @@ -548,21 +573,21 @@ struct perf_event_query_bpf { /* * Ioctls that can be done on a perf event fd: */ -#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) -#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) -#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) -#define PERF_EVENT_IOC_RESET _IO ('$', 3) -#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) -#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) -#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) -#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) -#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) -#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW ('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW ('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR ('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW ('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW ('$', 9, __u32) #define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) -#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *) +#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW ('$', 11, struct perf_event_attr *) enum perf_event_ioc_flags { - PERF_IOC_FLAG_GROUP = 1U << 0, + PERF_IOC_FLAG_GROUP = 1U << 0, }; /* @@ -573,7 +598,7 @@ struct perf_event_mmap_page { __u32 compat_version; /* lowest version this is compat with */ /* - * Bits needed to read the hw events in user-space. + * Bits needed to read the HW events in user-space. * * u32 seq, time_mult, time_shift, index, width; * u64 count, enabled, running; @@ -611,7 +636,7 @@ struct perf_event_mmap_page { __u32 index; /* hardware event identifier */ __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ - __u64 time_running; /* time event on cpu */ + __u64 time_running; /* time event on CPU */ union { __u64 capabilities; struct { @@ -639,7 +664,7 @@ struct perf_event_mmap_page { /* * If cap_usr_time the below fields can be used to compute the time - * delta since time_enabled (in ns) using rdtsc or similar. + * delta since time_enabled (in ns) using RDTSC or similar. * * u64 quot, rem; * u64 delta; @@ -712,7 +737,7 @@ struct perf_event_mmap_page { * after reading this value. * * When the mapping is PROT_WRITE the @data_tail value should be - * written by userspace to reflect the last read data, after issueing + * written by user-space to reflect the last read data, after issuing * an smp_mb() to separate the data read from the ->data_tail store. * In this case the kernel will not over-write unread data. * @@ -728,7 +753,7 @@ struct perf_event_mmap_page { /* * AUX area is defined by aux_{offset,size} fields that should be set - * by the userspace, so that + * by the user-space, so that * * aux_offset >= data_offset + data_size * @@ -802,7 +827,7 @@ struct perf_event_mmap_page { * Indicates that thread was preempted in TASK_RUNNING state. * * PERF_RECORD_MISC_MMAP_BUILD_ID: - * Indicates that mmap2 event carries build id data. + * Indicates that mmap2 event carries build ID data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) @@ -813,26 +838,26 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) struct perf_event_header { - __u32 type; - __u16 misc; - __u16 size; + __u32 type; + __u16 misc; + __u16 size; }; struct perf_ns_link_info { - __u64 dev; - __u64 ino; + __u64 dev; + __u64 ino; }; enum { - NET_NS_INDEX = 0, - UTS_NS_INDEX = 1, - IPC_NS_INDEX = 2, - PID_NS_INDEX = 3, - USER_NS_INDEX = 4, - MNT_NS_INDEX = 5, - CGROUP_NS_INDEX = 6, - - NR_NAMESPACES, /* number of available namespaces */ + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ }; enum perf_event_type { @@ -848,11 +873,11 @@ enum perf_event_type { * optional fields being ignored. * * struct sample_id { - * { u32 pid, tid; } && PERF_SAMPLE_TID - * { u64 time; } && PERF_SAMPLE_TIME - * { u64 id; } && PERF_SAMPLE_ID - * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID - * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 id; } && PERF_SAMPLE_IDENTIFIER * } && perf_event_attr::sample_id_all * @@ -863,7 +888,7 @@ enum perf_event_type { /* * The MMAP events record the PROT_EXEC mappings so that we can - * correlate userspace IPs to code. They have the following structure: + * correlate user-space IPs to code. They have the following structure: * * struct { * struct perf_event_header header; @@ -873,7 +898,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -883,7 +908,7 @@ enum perf_event_type { * struct perf_event_header header; * u64 id; * u64 lost; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_LOST = 2, @@ -894,7 +919,7 @@ enum perf_event_type { * * u32 pid, tid; * char comm[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_COMM = 3, @@ -905,7 +930,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_EXIT = 4, @@ -916,7 +941,7 @@ enum perf_event_type { * u64 time; * u64 id; * u64 stream_id; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_THROTTLE = 5, @@ -928,7 +953,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_FORK = 7, @@ -939,7 +964,7 @@ enum perf_event_type { * u32 pid, tid; * * struct read_format values; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_READ = 8, @@ -994,12 +1019,12 @@ enum perf_event_type { * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * - * { u64 abi; # enum perf_sample_regs_abi - * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER * - * { u64 size; - * char data[size]; - * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * * { union perf_sample_weight * { @@ -1024,10 +1049,11 @@ enum perf_event_type { * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR - * { u64 size; - * char data[size]; } && PERF_SAMPLE_AUX + * { u64 cgroup;} && PERF_SAMPLE_CGROUP * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX * }; */ PERF_RECORD_SAMPLE = 9, @@ -1059,7 +1085,7 @@ enum perf_event_type { * }; * u32 prot, flags; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP2 = 10, @@ -1068,12 +1094,12 @@ enum perf_event_type { * Records that new data landed in the AUX buffer part. * * struct { - * struct perf_event_header header; + * struct perf_event_header header; * - * u64 aux_offset; - * u64 aux_size; + * u64 aux_offset; + * u64 aux_size; * u64 flags; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_AUX = 11, @@ -1156,7 +1182,7 @@ enum perf_event_type { PERF_RECORD_KSYMBOL = 17, /* - * Record bpf events: + * Record BPF events: * enum perf_bpf_event_type { * PERF_BPF_EVENT_UNKNOWN = 0, * PERF_BPF_EVENT_PROG_LOAD = 1, @@ -1217,6 +1243,22 @@ enum perf_event_type { */ PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + /* + * This user callchain capture was deferred until shortly before + * returning to user space. Previous samples would have kernel + * callchains only and they need to be stitched with this to make full + * callchains. + * + * struct { + * struct perf_event_header header; + * u64 cookie; + * u64 nr; + * u64 ips[nr]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CALLCHAIN_DEFERRED = 22, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -1234,179 +1276,182 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) enum perf_bpf_event_type { - PERF_BPF_EVENT_UNKNOWN = 0, - PERF_BPF_EVENT_PROG_LOAD = 1, - PERF_BPF_EVENT_PROG_UNLOAD = 2, - PERF_BPF_EVENT_MAX, /* non-ABI */ + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ }; -#define PERF_MAX_STACK_DEPTH 127 -#define PERF_MAX_CONTEXTS_PER_STACK 8 +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 enum perf_callchain_context { - PERF_CONTEXT_HV = (__u64)-32, - PERF_CONTEXT_KERNEL = (__u64)-128, - PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_USER_DEFERRED = (__u64)-640, - PERF_CONTEXT_GUEST = (__u64)-2048, - PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, - PERF_CONTEXT_GUEST_USER = (__u64)-2560, + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, - PERF_CONTEXT_MAX = (__u64)-4095, + PERF_CONTEXT_MAX = (__u64)-4095, }; /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x0001 /* Record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x0002 /* Snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x0004 /* Record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x0008 /* Sample collided with another */ #define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ /* CoreSight PMU AUX buffer formats */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ -#define PERF_FLAG_FD_NO_GROUP (1UL << 0) -#define PERF_FLAG_FD_OUTPUT (1UL << 1) -#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup ID, per-CPU mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ #if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_op:5, /* type of opcode */ - mem_lvl:14, /* memory hierarchy level */ - mem_snoop:5, /* snoop mode */ - mem_lock:2, /* lock instr */ - mem_dtlb:7, /* tlb access */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_remote:1, /* remote */ - mem_snoopx:2, /* snoop mode, ext */ - mem_blk:3, /* access blocked */ - mem_hops:3, /* hop level */ - mem_rsvd:18; + __u64 mem_op : 5, /* Type of opcode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_snoop : 5, /* Snoop mode */ + mem_lock : 2, /* Lock instr */ + mem_dtlb : 7, /* TLB access */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_remote : 1, /* Remote */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_blk : 3, /* Access blocked */ + mem_hops : 3, /* Hop level */ + mem_rsvd : 18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:18, - mem_hops:3, /* hop level */ - mem_blk:3, /* access blocked */ - mem_snoopx:2, /* snoop mode, ext */ - mem_remote:1, /* remote */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_dtlb:7, /* tlb access */ - mem_lock:2, /* lock instr */ - mem_snoop:5, /* snoop mode */ - mem_lvl:14, /* memory hierarchy level */ - mem_op:5; /* type of opcode */ + __u64 mem_rsvd : 18, + mem_hops : 3, /* Hop level */ + mem_blk : 3, /* Access blocked */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_remote : 1, /* Remote */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_dtlb : 7, /* TLB access */ + mem_lock : 2, /* Lock instr */ + mem_snoop : 5, /* Snoop mode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_op : 5; /* Type of opcode */ }; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif -/* type of opcode (load/store/prefetch,code) */ -#define PERF_MEM_OP_NA 0x01 /* not available */ -#define PERF_MEM_OP_LOAD 0x02 /* load instruction */ -#define PERF_MEM_OP_STORE 0x04 /* store instruction */ -#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */ -#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ -#define PERF_MEM_OP_SHIFT 0 +/* Type of memory opcode: */ +#define PERF_MEM_OP_NA 0x0001 /* Not available */ +#define PERF_MEM_OP_LOAD 0x0002 /* Load instruction */ +#define PERF_MEM_OP_STORE 0x0004 /* Store instruction */ +#define PERF_MEM_OP_PFETCH 0x0008 /* Prefetch */ +#define PERF_MEM_OP_EXEC 0x0010 /* Code (execution) */ +#define PERF_MEM_OP_SHIFT 0 /* - * PERF_MEM_LVL_* namespace being depricated to some extent in the + * The PERF_MEM_LVL_* namespace is being deprecated to some extent in * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. - * Supporting this namespace inorder to not break defined ABIs. + * We support this namespace in order to not break defined ABIs. * - * memory hierarchy (memory level, hit or miss) + * Memory hierarchy (memory level, hit or miss) */ -#define PERF_MEM_LVL_NA 0x01 /* not available */ -#define PERF_MEM_LVL_HIT 0x02 /* hit level */ -#define PERF_MEM_LVL_MISS 0x04 /* miss level */ -#define PERF_MEM_LVL_L1 0x08 /* L1 */ -#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ -#define PERF_MEM_LVL_L2 0x20 /* L2 */ -#define PERF_MEM_LVL_L3 0x40 /* L3 */ -#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ -#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ -#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ -#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ -#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ -#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ -#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ -#define PERF_MEM_LVL_SHIFT 5 - -#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ -#define PERF_MEM_REMOTE_SHIFT 37 - -#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ -#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ -#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ -#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ -#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ -#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ -#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ -#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ -#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ -#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ -#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ - -#define PERF_MEM_LVLNUM_SHIFT 33 - -/* snoop mode */ -#define PERF_MEM_SNOOP_NA 0x01 /* not available */ -#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ -#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */ -#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */ -#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ -#define PERF_MEM_SNOOP_SHIFT 19 - -#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ -#define PERF_MEM_SNOOPX_SHIFT 38 - -/* locked instruction */ -#define PERF_MEM_LOCK_NA 0x01 /* not available */ -#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ -#define PERF_MEM_LOCK_SHIFT 24 +#define PERF_MEM_LVL_NA 0x0001 /* Not available */ +#define PERF_MEM_LVL_HIT 0x0002 /* Hit level */ +#define PERF_MEM_LVL_MISS 0x0004 /* Miss level */ +#define PERF_MEM_LVL_L1 0x0008 /* L1 */ +#define PERF_MEM_LVL_LFB 0x0010 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x0020 /* L2 */ +#define PERF_MEM_LVL_L3 0x0040 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x0080 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x0100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x0200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x0400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x0800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +#define PERF_MEM_REMOTE_REMOTE 0x0001 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x0001 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x0002 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x0003 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ +#define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ +/* 0x007 available */ +#define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x000b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x000c /* LFB / L1 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_RAM 0x000d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x000e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x000f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + +/* Snoop mode */ +#define PERF_MEM_SNOOP_NA 0x0001 /* Not available */ +#define PERF_MEM_SNOOP_NONE 0x0002 /* No snoop */ +#define PERF_MEM_SNOOP_HIT 0x0004 /* Snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x0008 /* Snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x0010 /* Snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +#define PERF_MEM_SNOOPX_FWD 0x0001 /* Forward */ +#define PERF_MEM_SNOOPX_PEER 0x0002 /* Transfer from peer */ +#define PERF_MEM_SNOOPX_SHIFT 38 + +/* Locked instruction */ +#define PERF_MEM_LOCK_NA 0x0001 /* Not available */ +#define PERF_MEM_LOCK_LOCKED 0x0002 /* Locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 /* TLB access */ -#define PERF_MEM_TLB_NA 0x01 /* not available */ -#define PERF_MEM_TLB_HIT 0x02 /* hit level */ -#define PERF_MEM_TLB_MISS 0x04 /* miss level */ -#define PERF_MEM_TLB_L1 0x08 /* L1 */ -#define PERF_MEM_TLB_L2 0x10 /* L2 */ -#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/ -#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ -#define PERF_MEM_TLB_SHIFT 26 +#define PERF_MEM_TLB_NA 0x0001 /* Not available */ +#define PERF_MEM_TLB_HIT 0x0002 /* Hit level */ +#define PERF_MEM_TLB_MISS 0x0004 /* Miss level */ +#define PERF_MEM_TLB_L1 0x0008 /* L1 */ +#define PERF_MEM_TLB_L2 0x0010 /* L2 */ +#define PERF_MEM_TLB_WK 0x0020 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x0040 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 /* Access blocked */ -#define PERF_MEM_BLK_NA 0x01 /* not available */ -#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ -#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ -#define PERF_MEM_BLK_SHIFT 40 - -/* hop level */ -#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_BLK_NA 0x0001 /* Not available */ +#define PERF_MEM_BLK_DATA 0x0002 /* Data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x0004 /* Address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + +/* Hop level */ +#define PERF_MEM_HOPS_0 0x0001 /* Remote core, same node */ +#define PERF_MEM_HOPS_1 0x0002 /* Remote node, same socket */ +#define PERF_MEM_HOPS_2 0x0003 /* Remote socket, same board */ +#define PERF_MEM_HOPS_3 0x0004 /* Remote board */ /* 5-7 available */ -#define PERF_MEM_HOPS_SHIFT 43 +#define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) /* - * single taken branch record layout: + * Layout of single taken branch records: * * from: source instruction (may not always be a branch insn) * to: branch target @@ -1425,37 +1470,37 @@ union perf_mem_data_src { struct perf_branch_entry { __u64 from; __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - cycles:16, /* cycle count to last branch */ - type:4, /* branch type */ - spec:2, /* branch speculation info */ - new_type:4, /* additional branch type */ - priv:3, /* privilege level */ - reserved:31; + __u64 mispred : 1, /* target mispredicted */ + predicted : 1, /* target predicted */ + in_tx : 1, /* in transaction */ + abort : 1, /* transaction abort */ + cycles : 16, /* cycle count to last branch */ + type : 4, /* branch type */ + spec : 2, /* branch speculation info */ + new_type : 4, /* additional branch type */ + priv : 3, /* privilege level */ + reserved : 31; }; /* Size of used info bits in struct perf_branch_entry */ #define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 union perf_sample_weight { - __u64 full; + __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) struct { - __u32 var1_dw; - __u16 var2_w; - __u16 var3_w; + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; }; #elif defined(__BIG_ENDIAN_BITFIELD) struct { - __u16 var3_w; - __u16 var2_w; - __u32 var1_dw; + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif }; diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h new file mode 100644 index 000000000000..475fc8ca4403 --- /dev/null +++ b/tools/include/uapi/linux/prctl.h @@ -0,0 +1,377 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_PRCTL_H +#define _LINUX_PRCTL_H + +#include <linux/types.h> + +/* Values to pass as first argument to prctl() */ + +#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */ +#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */ + +/* Get/set current->mm->dumpable */ +#define PR_GET_DUMPABLE 3 +#define PR_SET_DUMPABLE 4 + +/* Get/set unaligned access control bits (if meaningful) */ +#define PR_GET_UNALIGN 5 +#define PR_SET_UNALIGN 6 +# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */ +# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */ + +/* Get/set whether or not to drop capabilities on setuid() away from + * uid 0 (as per security/commoncap.c) */ +#define PR_GET_KEEPCAPS 7 +#define PR_SET_KEEPCAPS 8 + +/* Get/set floating-point emulation control bits (if meaningful) */ +#define PR_GET_FPEMU 9 +#define PR_SET_FPEMU 10 +# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */ +# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */ + +/* Get/set floating-point exception mode (if meaningful) */ +#define PR_GET_FPEXC 11 +#define PR_SET_FPEXC 12 +# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */ +# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */ +# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */ +# define PR_FP_EXC_UND 0x040000 /* floating point underflow */ +# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */ +# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */ +# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */ +# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */ +# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */ +# define PR_FP_EXC_PRECISE 3 /* precise exception mode */ + +/* Get/set whether we use statistical process timing or accurate timestamp + * based process timing */ +#define PR_GET_TIMING 13 +#define PR_SET_TIMING 14 +# define PR_TIMING_STATISTICAL 0 /* Normal, traditional, + statistical process timing */ +# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based + process timing */ + +#define PR_SET_NAME 15 /* Set process name */ +#define PR_GET_NAME 16 /* Get process name */ + +/* Get/set process endian */ +#define PR_GET_ENDIAN 19 +#define PR_SET_ENDIAN 20 +# define PR_ENDIAN_BIG 0 +# define PR_ENDIAN_LITTLE 1 /* True little endian mode */ +# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */ + +/* Get/set process seccomp mode */ +#define PR_GET_SECCOMP 21 +#define PR_SET_SECCOMP 22 + +/* Get/set the capability bounding set (as per security/commoncap.c) */ +#define PR_CAPBSET_READ 23 +#define PR_CAPBSET_DROP 24 + +/* Get/set the process' ability to use the timestamp counter instruction */ +#define PR_GET_TSC 25 +#define PR_SET_TSC 26 +# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */ +# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */ + +/* Get/set securebits (as per security/commoncap.c) */ +#define PR_GET_SECUREBITS 27 +#define PR_SET_SECUREBITS 28 + +/* + * Get/set the timerslack as used by poll/select/nanosleep + * A value of 0 means "use default" + */ +#define PR_SET_TIMERSLACK 29 +#define PR_GET_TIMERSLACK 30 + +#define PR_TASK_PERF_EVENTS_DISABLE 31 +#define PR_TASK_PERF_EVENTS_ENABLE 32 + +/* + * Set early/late kill mode for hwpoison memory corruption. + * This influences when the process gets killed on a memory corruption. + */ +#define PR_MCE_KILL 33 +# define PR_MCE_KILL_CLEAR 0 +# define PR_MCE_KILL_SET 1 + +# define PR_MCE_KILL_LATE 0 +# define PR_MCE_KILL_EARLY 1 +# define PR_MCE_KILL_DEFAULT 2 + +#define PR_MCE_KILL_GET 34 + +/* + * Tune up process memory map specifics. + */ +#define PR_SET_MM 35 +# define PR_SET_MM_START_CODE 1 +# define PR_SET_MM_END_CODE 2 +# define PR_SET_MM_START_DATA 3 +# define PR_SET_MM_END_DATA 4 +# define PR_SET_MM_START_STACK 5 +# define PR_SET_MM_START_BRK 6 +# define PR_SET_MM_BRK 7 +# define PR_SET_MM_ARG_START 8 +# define PR_SET_MM_ARG_END 9 +# define PR_SET_MM_ENV_START 10 +# define PR_SET_MM_ENV_END 11 +# define PR_SET_MM_AUXV 12 +# define PR_SET_MM_EXE_FILE 13 +# define PR_SET_MM_MAP 14 +# define PR_SET_MM_MAP_SIZE 15 + +/* + * This structure provides new memory descriptor + * map which mostly modifies /proc/pid/stat[m] + * output for a task. This mostly done in a + * sake of checkpoint/restore functionality. + */ +struct prctl_mm_map { + __u64 start_code; /* code section bounds */ + __u64 end_code; + __u64 start_data; /* data section bounds */ + __u64 end_data; + __u64 start_brk; /* heap for brk() syscall */ + __u64 brk; + __u64 start_stack; /* stack starts at */ + __u64 arg_start; /* command line arguments bounds */ + __u64 arg_end; + __u64 env_start; /* environment variables bounds */ + __u64 env_end; + __u64 *auxv; /* auxiliary vector */ + __u32 auxv_size; /* vector size */ + __u32 exe_fd; /* /proc/$pid/exe link file */ +}; + +/* + * Set specific pid that is allowed to ptrace the current task. + * A value of 0 mean "no process". + */ +#define PR_SET_PTRACER 0x59616d61 +# define PR_SET_PTRACER_ANY ((unsigned long)-1) + +#define PR_SET_CHILD_SUBREAPER 36 +#define PR_GET_CHILD_SUBREAPER 37 + +/* + * If no_new_privs is set, then operations that grant new privileges (i.e. + * execve) will either fail or not grant them. This affects suid/sgid, + * file capabilities, and LSMs. + * + * Operations that merely manipulate or drop existing privileges (setresuid, + * capset, etc.) will still work. Drop those privileges if you want them gone. + * + * Changing LSM security domain is considered a new privilege. So, for example, + * asking selinux for a specific new context (e.g. with runcon) will result + * in execve returning -EPERM. + * + * See Documentation/userspace-api/no_new_privs.rst for more details. + */ +#define PR_SET_NO_NEW_PRIVS 38 +#define PR_GET_NO_NEW_PRIVS 39 + +#define PR_GET_TID_ADDRESS 40 + +#define PR_SET_THP_DISABLE 41 +#define PR_GET_THP_DISABLE 42 + +/* + * No longer implemented, but left here to ensure the numbers stay reserved: + */ +#define PR_MPX_ENABLE_MANAGEMENT 43 +#define PR_MPX_DISABLE_MANAGEMENT 44 + +#define PR_SET_FP_MODE 45 +#define PR_GET_FP_MODE 46 +# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */ +# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */ + +/* Control the ambient capability set */ +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 + +/* arm64 Scalable Vector Extension controls */ +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ +#define PR_SVE_SET_VL 50 /* set task vector length */ +# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SVE_GET_VL 51 /* get task vector length */ +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ +# define PR_SVE_VL_LEN_MASK 0xffff +# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 +# define PR_SPEC_L1D_FLUSH 2 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) + +/* Reset arm64 pointer authentication keys */ +#define PR_PAC_RESET_KEYS 54 +# define PR_PAC_APIAKEY (1UL << 0) +# define PR_PAC_APIBKEY (1UL << 1) +# define PR_PAC_APDAKEY (1UL << 2) +# define PR_PAC_APDBKEY (1UL << 3) +# define PR_PAC_APGAKEY (1UL << 4) + +/* Tagged user address controls for arm64 and RISC-V */ +#define PR_SET_TAGGED_ADDR_CTRL 55 +#define PR_GET_TAGGED_ADDR_CTRL 56 +# define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* MTE tag check fault modes */ +# define PR_MTE_TCF_NONE 0UL +# define PR_MTE_TCF_SYNC (1UL << 1) +# define PR_MTE_TCF_ASYNC (1UL << 2) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) +/* MTE tag inclusion mask */ +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) +/* Unused; kept only for source compatibility */ +# define PR_MTE_TCF_SHIFT 1 +/* RISC-V pointer masking tag length */ +# define PR_PMLEN_SHIFT 24 +# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT) + +/* Control reclaim behavior when allocating memory */ +#define PR_SET_IO_FLUSHER 57 +#define PR_GET_IO_FLUSHER 58 + +/* Dispatch syscalls to a userspace handler */ +#define PR_SET_SYSCALL_USER_DISPATCH 59 +# define PR_SYS_DISPATCH_OFF 0 +/* Enable dispatch except for the specified range */ +# define PR_SYS_DISPATCH_EXCLUSIVE_ON 1 +/* Enable dispatch for the specified range */ +# define PR_SYS_DISPATCH_INCLUSIVE_ON 2 +/* Legacy name for backwards compatibility */ +# define PR_SYS_DISPATCH_ON PR_SYS_DISPATCH_EXCLUSIVE_ON +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 + +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + +/* Request the scheduler to share a core */ +#define PR_SCHED_CORE 62 +# define PR_SCHED_CORE_GET 0 +# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */ +# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ +# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ +# define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 + +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) + +#define PR_GET_MDWE 66 + +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + +#define PR_GET_AUXV 0x41555856 + +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 + +#define PR_RISCV_V_SET_CONTROL 69 +#define PR_RISCV_V_GET_CONTROL 70 +# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0 +# define PR_RISCV_V_VSTATE_CTRL_OFF 1 +# define PR_RISCV_V_VSTATE_CTRL_ON 2 +# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4) +# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3 +# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc +# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f + +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + +/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 74 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 76 + +/* + * Controls the mode of timer_create() for CRIU restore operations. + * Enabling this allows CRIU to restore timers with explicit IDs. + * + * Don't use for normal operations as the result might be undefined. + */ +#define PR_TIMER_CREATE_RESTORE_IDS 77 +# define PR_TIMER_CREATE_RESTORE_IDS_OFF 0 +# define PR_TIMER_CREATE_RESTORE_IDS_ON 1 +# define PR_TIMER_CREATE_RESTORE_IDS_GET 2 + +/* FUTEX hash management */ +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define PR_FUTEX_HASH_GET_SLOTS 2 + +#endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/rtnetlink.h b/tools/include/uapi/linux/rtnetlink.h new file mode 100644 index 000000000000..dab9493c791b --- /dev/null +++ b/tools/include/uapi/linux/rtnetlink.h @@ -0,0 +1,848 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_RTNETLINK_H +#define _UAPI__LINUX_RTNETLINK_H + +#include <linux/types.h> +#include <linux/netlink.h> +#include <linux/if_link.h> +#include <linux/if_addr.h> +#include <linux/neighbour.h> + +/* rtnetlink families. Values up to 127 are reserved for real address + * families, values above 128 may be used arbitrarily. + */ +#define RTNL_FAMILY_IPMR 128 +#define RTNL_FAMILY_IP6MR 129 +#define RTNL_FAMILY_MAX 129 + +/**** + * Routing/neighbour discovery messages. + ****/ + +/* Types of messages */ + +enum { + RTM_BASE = 16, +#define RTM_BASE RTM_BASE + + RTM_NEWLINK = 16, +#define RTM_NEWLINK RTM_NEWLINK + RTM_DELLINK, +#define RTM_DELLINK RTM_DELLINK + RTM_GETLINK, +#define RTM_GETLINK RTM_GETLINK + RTM_SETLINK, +#define RTM_SETLINK RTM_SETLINK + + RTM_NEWADDR = 20, +#define RTM_NEWADDR RTM_NEWADDR + RTM_DELADDR, +#define RTM_DELADDR RTM_DELADDR + RTM_GETADDR, +#define RTM_GETADDR RTM_GETADDR + + RTM_NEWROUTE = 24, +#define RTM_NEWROUTE RTM_NEWROUTE + RTM_DELROUTE, +#define RTM_DELROUTE RTM_DELROUTE + RTM_GETROUTE, +#define RTM_GETROUTE RTM_GETROUTE + + RTM_NEWNEIGH = 28, +#define RTM_NEWNEIGH RTM_NEWNEIGH + RTM_DELNEIGH, +#define RTM_DELNEIGH RTM_DELNEIGH + RTM_GETNEIGH, +#define RTM_GETNEIGH RTM_GETNEIGH + + RTM_NEWRULE = 32, +#define RTM_NEWRULE RTM_NEWRULE + RTM_DELRULE, +#define RTM_DELRULE RTM_DELRULE + RTM_GETRULE, +#define RTM_GETRULE RTM_GETRULE + + RTM_NEWQDISC = 36, +#define RTM_NEWQDISC RTM_NEWQDISC + RTM_DELQDISC, +#define RTM_DELQDISC RTM_DELQDISC + RTM_GETQDISC, +#define RTM_GETQDISC RTM_GETQDISC + + RTM_NEWTCLASS = 40, +#define RTM_NEWTCLASS RTM_NEWTCLASS + RTM_DELTCLASS, +#define RTM_DELTCLASS RTM_DELTCLASS + RTM_GETTCLASS, +#define RTM_GETTCLASS RTM_GETTCLASS + + RTM_NEWTFILTER = 44, +#define RTM_NEWTFILTER RTM_NEWTFILTER + RTM_DELTFILTER, +#define RTM_DELTFILTER RTM_DELTFILTER + RTM_GETTFILTER, +#define RTM_GETTFILTER RTM_GETTFILTER + + RTM_NEWACTION = 48, +#define RTM_NEWACTION RTM_NEWACTION + RTM_DELACTION, +#define RTM_DELACTION RTM_DELACTION + RTM_GETACTION, +#define RTM_GETACTION RTM_GETACTION + + RTM_NEWPREFIX = 52, +#define RTM_NEWPREFIX RTM_NEWPREFIX + + RTM_NEWMULTICAST = 56, +#define RTM_NEWMULTICAST RTM_NEWMULTICAST + RTM_DELMULTICAST, +#define RTM_DELMULTICAST RTM_DELMULTICAST + RTM_GETMULTICAST, +#define RTM_GETMULTICAST RTM_GETMULTICAST + + RTM_NEWANYCAST = 60, +#define RTM_NEWANYCAST RTM_NEWANYCAST + RTM_DELANYCAST, +#define RTM_DELANYCAST RTM_DELANYCAST + RTM_GETANYCAST, +#define RTM_GETANYCAST RTM_GETANYCAST + + RTM_NEWNEIGHTBL = 64, +#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL + RTM_GETNEIGHTBL = 66, +#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL + RTM_SETNEIGHTBL, +#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL + + RTM_NEWNDUSEROPT = 68, +#define RTM_NEWNDUSEROPT RTM_NEWNDUSEROPT + + RTM_NEWADDRLABEL = 72, +#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL + RTM_DELADDRLABEL, +#define RTM_DELADDRLABEL RTM_DELADDRLABEL + RTM_GETADDRLABEL, +#define RTM_GETADDRLABEL RTM_GETADDRLABEL + + RTM_GETDCB = 78, +#define RTM_GETDCB RTM_GETDCB + RTM_SETDCB, +#define RTM_SETDCB RTM_SETDCB + + RTM_NEWNETCONF = 80, +#define RTM_NEWNETCONF RTM_NEWNETCONF + RTM_DELNETCONF, +#define RTM_DELNETCONF RTM_DELNETCONF + RTM_GETNETCONF = 82, +#define RTM_GETNETCONF RTM_GETNETCONF + + RTM_NEWMDB = 84, +#define RTM_NEWMDB RTM_NEWMDB + RTM_DELMDB = 85, +#define RTM_DELMDB RTM_DELMDB + RTM_GETMDB = 86, +#define RTM_GETMDB RTM_GETMDB + + RTM_NEWNSID = 88, +#define RTM_NEWNSID RTM_NEWNSID + RTM_DELNSID = 89, +#define RTM_DELNSID RTM_DELNSID + RTM_GETNSID = 90, +#define RTM_GETNSID RTM_GETNSID + + RTM_NEWSTATS = 92, +#define RTM_NEWSTATS RTM_NEWSTATS + RTM_GETSTATS = 94, +#define RTM_GETSTATS RTM_GETSTATS + RTM_SETSTATS, +#define RTM_SETSTATS RTM_SETSTATS + + RTM_NEWCACHEREPORT = 96, +#define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT + + RTM_NEWCHAIN = 100, +#define RTM_NEWCHAIN RTM_NEWCHAIN + RTM_DELCHAIN, +#define RTM_DELCHAIN RTM_DELCHAIN + RTM_GETCHAIN, +#define RTM_GETCHAIN RTM_GETCHAIN + + RTM_NEWNEXTHOP = 104, +#define RTM_NEWNEXTHOP RTM_NEWNEXTHOP + RTM_DELNEXTHOP, +#define RTM_DELNEXTHOP RTM_DELNEXTHOP + RTM_GETNEXTHOP, +#define RTM_GETNEXTHOP RTM_GETNEXTHOP + + RTM_NEWLINKPROP = 108, +#define RTM_NEWLINKPROP RTM_NEWLINKPROP + RTM_DELLINKPROP, +#define RTM_DELLINKPROP RTM_DELLINKPROP + RTM_GETLINKPROP, +#define RTM_GETLINKPROP RTM_GETLINKPROP + + RTM_NEWVLAN = 112, +#define RTM_NEWVLAN RTM_NEWVLAN + RTM_DELVLAN, +#define RTM_DELVLAN RTM_DELVLAN + RTM_GETVLAN, +#define RTM_GETVLAN RTM_GETVLAN + + RTM_NEWNEXTHOPBUCKET = 116, +#define RTM_NEWNEXTHOPBUCKET RTM_NEWNEXTHOPBUCKET + RTM_DELNEXTHOPBUCKET, +#define RTM_DELNEXTHOPBUCKET RTM_DELNEXTHOPBUCKET + RTM_GETNEXTHOPBUCKET, +#define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET + + RTM_NEWTUNNEL = 120, +#define RTM_NEWTUNNEL RTM_NEWTUNNEL + RTM_DELTUNNEL, +#define RTM_DELTUNNEL RTM_DELTUNNEL + RTM_GETTUNNEL, +#define RTM_GETTUNNEL RTM_GETTUNNEL + + __RTM_MAX, +#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) +}; + +#define RTM_NR_MSGTYPES (RTM_MAX + 1 - RTM_BASE) +#define RTM_NR_FAMILIES (RTM_NR_MSGTYPES >> 2) +#define RTM_FAM(cmd) (((cmd) - RTM_BASE) >> 2) + +/* + Generic structure for encapsulation of optional route information. + It is reminiscent of sockaddr, but with sa_family replaced + with attribute type. + */ + +struct rtattr { + unsigned short rta_len; + unsigned short rta_type; +}; + +/* Macros to handle rtattributes */ + +#define RTA_ALIGNTO 4U +#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) ) +#define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \ + (rta)->rta_len >= sizeof(struct rtattr) && \ + (rta)->rta_len <= (len)) +#define RTA_NEXT(rta,attrlen) ((attrlen) -= RTA_ALIGN((rta)->rta_len), \ + (struct rtattr*)(((char*)(rta)) + RTA_ALIGN((rta)->rta_len))) +#define RTA_LENGTH(len) (RTA_ALIGN(sizeof(struct rtattr)) + (len)) +#define RTA_SPACE(len) RTA_ALIGN(RTA_LENGTH(len)) +#define RTA_DATA(rta) ((void*)(((char*)(rta)) + RTA_LENGTH(0))) +#define RTA_PAYLOAD(rta) ((int)((rta)->rta_len) - RTA_LENGTH(0)) + + + + +/****************************************************************************** + * Definitions used in routing table administration. + ****/ + +struct rtmsg { + unsigned char rtm_family; + unsigned char rtm_dst_len; + unsigned char rtm_src_len; + unsigned char rtm_tos; + + unsigned char rtm_table; /* Routing table id */ + unsigned char rtm_protocol; /* Routing protocol; see below */ + unsigned char rtm_scope; /* See below */ + unsigned char rtm_type; /* See below */ + + unsigned rtm_flags; +}; + +/* rtm_type */ + +enum { + RTN_UNSPEC, + RTN_UNICAST, /* Gateway or direct route */ + RTN_LOCAL, /* Accept locally */ + RTN_BROADCAST, /* Accept locally as broadcast, + send as broadcast */ + RTN_ANYCAST, /* Accept locally as broadcast, + but send as unicast */ + RTN_MULTICAST, /* Multicast route */ + RTN_BLACKHOLE, /* Drop */ + RTN_UNREACHABLE, /* Destination is unreachable */ + RTN_PROHIBIT, /* Administratively prohibited */ + RTN_THROW, /* Not in this table */ + RTN_NAT, /* Translate this address */ + RTN_XRESOLVE, /* Use external resolver */ + __RTN_MAX +}; + +#define RTN_MAX (__RTN_MAX - 1) + + +/* rtm_protocol */ + +#define RTPROT_UNSPEC 0 +#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects; + not used by current IPv4 */ +#define RTPROT_KERNEL 2 /* Route installed by kernel */ +#define RTPROT_BOOT 3 /* Route installed during boot */ +#define RTPROT_STATIC 4 /* Route installed by administrator */ + +/* Values of protocol >= RTPROT_STATIC are not interpreted by kernel; + they are just passed from user and back as is. + It will be used by hypothetical multiple routing daemons. + Note that protocol values should be standardized in order to + avoid conflicts. + */ + +#define RTPROT_GATED 8 /* Apparently, GateD */ +#define RTPROT_RA 9 /* RDISC/ND router advertisements */ +#define RTPROT_MRT 10 /* Merit MRT */ +#define RTPROT_ZEBRA 11 /* Zebra */ +#define RTPROT_BIRD 12 /* BIRD */ +#define RTPROT_DNROUTED 13 /* DECnet routing daemon */ +#define RTPROT_XORP 14 /* XORP */ +#define RTPROT_NTK 15 /* Netsukuku */ +#define RTPROT_DHCP 16 /* DHCP client */ +#define RTPROT_MROUTED 17 /* Multicast daemon */ +#define RTPROT_KEEPALIVED 18 /* Keepalived daemon */ +#define RTPROT_BABEL 42 /* Babel daemon */ +#define RTPROT_OVN 84 /* OVN daemon */ +#define RTPROT_OPENR 99 /* Open Routing (Open/R) Routes */ +#define RTPROT_BGP 186 /* BGP Routes */ +#define RTPROT_ISIS 187 /* ISIS Routes */ +#define RTPROT_OSPF 188 /* OSPF Routes */ +#define RTPROT_RIP 189 /* RIP Routes */ +#define RTPROT_EIGRP 192 /* EIGRP Routes */ + +/* rtm_scope + + Really it is not scope, but sort of distance to the destination. + NOWHERE are reserved for not existing destinations, HOST is our + local addresses, LINK are destinations, located on directly attached + link and UNIVERSE is everywhere in the Universe. + + Intermediate values are also possible f.e. interior routes + could be assigned a value between UNIVERSE and LINK. +*/ + +enum rt_scope_t { + RT_SCOPE_UNIVERSE=0, +/* User defined values */ + RT_SCOPE_SITE=200, + RT_SCOPE_LINK=253, + RT_SCOPE_HOST=254, + RT_SCOPE_NOWHERE=255 +}; + +/* rtm_flags */ + +#define RTM_F_NOTIFY 0x100 /* Notify user of route change */ +#define RTM_F_CLONED 0x200 /* This route is cloned */ +#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */ +#define RTM_F_PREFIX 0x800 /* Prefix addresses */ +#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */ +#define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */ +#define RTM_F_OFFLOAD 0x4000 /* route is offloaded */ +#define RTM_F_TRAP 0x8000 /* route is trapping packets */ +#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value + * is chosen to avoid conflicts with + * other flags defined in + * include/uapi/linux/ipv6_route.h + */ + +/* Reserved table identifiers */ + +enum rt_class_t { + RT_TABLE_UNSPEC=0, +/* User defined values */ + RT_TABLE_COMPAT=252, + RT_TABLE_DEFAULT=253, + RT_TABLE_MAIN=254, + RT_TABLE_LOCAL=255, + RT_TABLE_MAX=0xFFFFFFFF +}; + + +/* Routing message attributes */ + +enum rtattr_type_t { + RTA_UNSPEC, + RTA_DST, + RTA_SRC, + RTA_IIF, + RTA_OIF, + RTA_GATEWAY, + RTA_PRIORITY, + RTA_PREFSRC, + RTA_METRICS, + RTA_MULTIPATH, + RTA_PROTOINFO, /* no longer used */ + RTA_FLOW, + RTA_CACHEINFO, + RTA_SESSION, /* no longer used */ + RTA_MP_ALGO, /* no longer used */ + RTA_TABLE, + RTA_MARK, + RTA_MFC_STATS, + RTA_VIA, + RTA_NEWDST, + RTA_PREF, + RTA_ENCAP_TYPE, + RTA_ENCAP, + RTA_EXPIRES, + RTA_PAD, + RTA_UID, + RTA_TTL_PROPAGATE, + RTA_IP_PROTO, + RTA_SPORT, + RTA_DPORT, + RTA_NH_ID, + RTA_FLOWLABEL, + __RTA_MAX +}; + +#define RTA_MAX (__RTA_MAX - 1) + +#define RTM_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtmsg)))) +#define RTM_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtmsg)) + +/* RTM_MULTIPATH --- array of struct rtnexthop. + * + * "struct rtnexthop" describes all necessary nexthop information, + * i.e. parameters of path to a destination via this nexthop. + * + * At the moment it is impossible to set different prefsrc, mtu, window + * and rtt for different paths from multipath. + */ + +struct rtnexthop { + unsigned short rtnh_len; + unsigned char rtnh_flags; + unsigned char rtnh_hops; + int rtnh_ifindex; +}; + +/* rtnh_flags */ + +#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ +#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ +#define RTNH_F_ONLINK 4 /* Gateway is forced on link */ +#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */ +#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ +#define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */ +#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */ + +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \ + RTNH_F_OFFLOAD | RTNH_F_TRAP) + +/* Macros to handle hexthops */ + +#define RTNH_ALIGNTO 4 +#define RTNH_ALIGN(len) ( ((len)+RTNH_ALIGNTO-1) & ~(RTNH_ALIGNTO-1) ) +#define RTNH_OK(rtnh,len) ((rtnh)->rtnh_len >= sizeof(struct rtnexthop) && \ + ((int)(rtnh)->rtnh_len) <= (len)) +#define RTNH_NEXT(rtnh) ((struct rtnexthop*)(((char*)(rtnh)) + RTNH_ALIGN((rtnh)->rtnh_len))) +#define RTNH_LENGTH(len) (RTNH_ALIGN(sizeof(struct rtnexthop)) + (len)) +#define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len)) +#define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0))) + +/* RTA_VIA */ +struct rtvia { + __kernel_sa_family_t rtvia_family; + __u8 rtvia_addr[]; +}; + +/* RTM_CACHEINFO */ + +struct rta_cacheinfo { + __u32 rta_clntref; + __u32 rta_lastuse; + __s32 rta_expires; + __u32 rta_error; + __u32 rta_used; + +#define RTNETLINK_HAVE_PEERINFO 1 + __u32 rta_id; + __u32 rta_ts; + __u32 rta_tsage; +}; + +/* RTM_METRICS --- array of struct rtattr with types of RTAX_* */ + +enum { + RTAX_UNSPEC, +#define RTAX_UNSPEC RTAX_UNSPEC + RTAX_LOCK, +#define RTAX_LOCK RTAX_LOCK + RTAX_MTU, +#define RTAX_MTU RTAX_MTU + RTAX_WINDOW, +#define RTAX_WINDOW RTAX_WINDOW + RTAX_RTT, +#define RTAX_RTT RTAX_RTT + RTAX_RTTVAR, +#define RTAX_RTTVAR RTAX_RTTVAR + RTAX_SSTHRESH, +#define RTAX_SSTHRESH RTAX_SSTHRESH + RTAX_CWND, +#define RTAX_CWND RTAX_CWND + RTAX_ADVMSS, +#define RTAX_ADVMSS RTAX_ADVMSS + RTAX_REORDERING, +#define RTAX_REORDERING RTAX_REORDERING + RTAX_HOPLIMIT, +#define RTAX_HOPLIMIT RTAX_HOPLIMIT + RTAX_INITCWND, +#define RTAX_INITCWND RTAX_INITCWND + RTAX_FEATURES, +#define RTAX_FEATURES RTAX_FEATURES + RTAX_RTO_MIN, +#define RTAX_RTO_MIN RTAX_RTO_MIN + RTAX_INITRWND, +#define RTAX_INITRWND RTAX_INITRWND + RTAX_QUICKACK, +#define RTAX_QUICKACK RTAX_QUICKACK + RTAX_CC_ALGO, +#define RTAX_CC_ALGO RTAX_CC_ALGO + RTAX_FASTOPEN_NO_COOKIE, +#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE + __RTAX_MAX +}; + +#define RTAX_MAX (__RTAX_MAX - 1) + +#define RTAX_FEATURE_ECN (1 << 0) +#define RTAX_FEATURE_SACK (1 << 1) /* unused */ +#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */ +#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */ +#define RTAX_FEATURE_TCP_USEC_TS (1 << 4) + +#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \ + RTAX_FEATURE_SACK | \ + RTAX_FEATURE_TIMESTAMP | \ + RTAX_FEATURE_ALLFRAG | \ + RTAX_FEATURE_TCP_USEC_TS) + +struct rta_session { + __u8 proto; + __u8 pad1; + __u16 pad2; + + union { + struct { + __u16 sport; + __u16 dport; + } ports; + + struct { + __u8 type; + __u8 code; + __u16 ident; + } icmpt; + + __u32 spi; + } u; +}; + +struct rta_mfc_stats { + __u64 mfcs_packets; + __u64 mfcs_bytes; + __u64 mfcs_wrong_if; +}; + +/**** + * General form of address family dependent message. + ****/ + +struct rtgenmsg { + unsigned char rtgen_family; +}; + +/***************************************************************** + * Link layer specific messages. + ****/ + +/* struct ifinfomsg + * passes link level specific information, not dependent + * on network protocol. + */ + +struct ifinfomsg { + unsigned char ifi_family; + unsigned char __ifi_pad; + unsigned short ifi_type; /* ARPHRD_* */ + int ifi_index; /* Link index */ + unsigned ifi_flags; /* IFF_* flags */ + unsigned ifi_change; /* IFF_* change mask */ +}; + +/******************************************************************** + * prefix information + ****/ + +struct prefixmsg { + unsigned char prefix_family; + unsigned char prefix_pad1; + unsigned short prefix_pad2; + int prefix_ifindex; + unsigned char prefix_type; + unsigned char prefix_len; + unsigned char prefix_flags; + unsigned char prefix_pad3; +}; + +enum +{ + PREFIX_UNSPEC, + PREFIX_ADDRESS, + PREFIX_CACHEINFO, + __PREFIX_MAX +}; + +#define PREFIX_MAX (__PREFIX_MAX - 1) + +struct prefix_cacheinfo { + __u32 preferred_time; + __u32 valid_time; +}; + + +/***************************************************************** + * Traffic control messages. + ****/ + +struct tcmsg { + unsigned char tcm_family; + unsigned char tcm__pad1; + unsigned short tcm__pad2; + int tcm_ifindex; + __u32 tcm_handle; + __u32 tcm_parent; +/* tcm_block_index is used instead of tcm_parent + * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK + */ +#define tcm_block_index tcm_parent + __u32 tcm_info; +}; + +/* For manipulation of filters in shared block, tcm_ifindex is set to + * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index + * which is the block index. + */ +#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU) + +enum { + TCA_UNSPEC, + TCA_KIND, + TCA_OPTIONS, + TCA_STATS, + TCA_XSTATS, + TCA_RATE, + TCA_FCNT, + TCA_STATS2, + TCA_STAB, + TCA_PAD, + TCA_DUMP_INVISIBLE, + TCA_CHAIN, + TCA_HW_OFFLOAD, + TCA_INGRESS_BLOCK, + TCA_EGRESS_BLOCK, + TCA_DUMP_FLAGS, + TCA_EXT_WARN_MSG, + __TCA_MAX +}; + +#define TCA_MAX (__TCA_MAX - 1) + +#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic + * data necessary to identify the objects + * (handle, cookie, etc.) and stats. + */ + +#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg)))) +#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg)) + +/******************************************************************** + * Neighbor Discovery userland options + ****/ + +struct nduseroptmsg { + unsigned char nduseropt_family; + unsigned char nduseropt_pad1; + unsigned short nduseropt_opts_len; /* Total length of options */ + int nduseropt_ifindex; + __u8 nduseropt_icmp_type; + __u8 nduseropt_icmp_code; + unsigned short nduseropt_pad2; + unsigned int nduseropt_pad3; + /* Followed by one or more ND options */ +}; + +enum { + NDUSEROPT_UNSPEC, + NDUSEROPT_SRCADDR, + __NDUSEROPT_MAX +}; + +#define NDUSEROPT_MAX (__NDUSEROPT_MAX - 1) + +#ifndef __KERNEL__ +/* RTnetlink multicast groups - backwards compatibility for userspace */ +#define RTMGRP_LINK 1 +#define RTMGRP_NOTIFY 2 +#define RTMGRP_NEIGH 4 +#define RTMGRP_TC 8 + +#define RTMGRP_IPV4_IFADDR 0x10 +#define RTMGRP_IPV4_MROUTE 0x20 +#define RTMGRP_IPV4_ROUTE 0x40 +#define RTMGRP_IPV4_RULE 0x80 + +#define RTMGRP_IPV6_IFADDR 0x100 +#define RTMGRP_IPV6_MROUTE 0x200 +#define RTMGRP_IPV6_ROUTE 0x400 +#define RTMGRP_IPV6_IFINFO 0x800 + +#define RTMGRP_DECnet_IFADDR 0x1000 +#define RTMGRP_DECnet_ROUTE 0x4000 + +#define RTMGRP_IPV6_PREFIX 0x20000 +#endif + +/* RTnetlink multicast groups */ +enum rtnetlink_groups { + RTNLGRP_NONE, +#define RTNLGRP_NONE RTNLGRP_NONE + RTNLGRP_LINK, +#define RTNLGRP_LINK RTNLGRP_LINK + RTNLGRP_NOTIFY, +#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY + RTNLGRP_NEIGH, +#define RTNLGRP_NEIGH RTNLGRP_NEIGH + RTNLGRP_TC, +#define RTNLGRP_TC RTNLGRP_TC + RTNLGRP_IPV4_IFADDR, +#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR + RTNLGRP_IPV4_MROUTE, +#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE + RTNLGRP_IPV4_ROUTE, +#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE + RTNLGRP_IPV4_RULE, +#define RTNLGRP_IPV4_RULE RTNLGRP_IPV4_RULE + RTNLGRP_IPV6_IFADDR, +#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR + RTNLGRP_IPV6_MROUTE, +#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE + RTNLGRP_IPV6_ROUTE, +#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE + RTNLGRP_IPV6_IFINFO, +#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO + RTNLGRP_DECnet_IFADDR, +#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR + RTNLGRP_NOP2, + RTNLGRP_DECnet_ROUTE, +#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE + RTNLGRP_DECnet_RULE, +#define RTNLGRP_DECnet_RULE RTNLGRP_DECnet_RULE + RTNLGRP_NOP4, + RTNLGRP_IPV6_PREFIX, +#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + RTNLGRP_IPV6_RULE, +#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE + RTNLGRP_ND_USEROPT, +#define RTNLGRP_ND_USEROPT RTNLGRP_ND_USEROPT + RTNLGRP_PHONET_IFADDR, +#define RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_IFADDR + RTNLGRP_PHONET_ROUTE, +#define RTNLGRP_PHONET_ROUTE RTNLGRP_PHONET_ROUTE + RTNLGRP_DCB, +#define RTNLGRP_DCB RTNLGRP_DCB + RTNLGRP_IPV4_NETCONF, +#define RTNLGRP_IPV4_NETCONF RTNLGRP_IPV4_NETCONF + RTNLGRP_IPV6_NETCONF, +#define RTNLGRP_IPV6_NETCONF RTNLGRP_IPV6_NETCONF + RTNLGRP_MDB, +#define RTNLGRP_MDB RTNLGRP_MDB + RTNLGRP_MPLS_ROUTE, +#define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE + RTNLGRP_NSID, +#define RTNLGRP_NSID RTNLGRP_NSID + RTNLGRP_MPLS_NETCONF, +#define RTNLGRP_MPLS_NETCONF RTNLGRP_MPLS_NETCONF + RTNLGRP_IPV4_MROUTE_R, +#define RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV4_MROUTE_R + RTNLGRP_IPV6_MROUTE_R, +#define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R + RTNLGRP_NEXTHOP, +#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP + RTNLGRP_BRVLAN, +#define RTNLGRP_BRVLAN RTNLGRP_BRVLAN + RTNLGRP_MCTP_IFADDR, +#define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR + RTNLGRP_TUNNEL, +#define RTNLGRP_TUNNEL RTNLGRP_TUNNEL + RTNLGRP_STATS, +#define RTNLGRP_STATS RTNLGRP_STATS + RTNLGRP_IPV4_MCADDR, +#define RTNLGRP_IPV4_MCADDR RTNLGRP_IPV4_MCADDR + RTNLGRP_IPV6_MCADDR, +#define RTNLGRP_IPV6_MCADDR RTNLGRP_IPV6_MCADDR + RTNLGRP_IPV6_ACADDR, +#define RTNLGRP_IPV6_ACADDR RTNLGRP_IPV6_ACADDR + __RTNLGRP_MAX +}; +#define RTNLGRP_MAX (__RTNLGRP_MAX - 1) + +/* TC action piece */ +struct tcamsg { + unsigned char tca_family; + unsigned char tca__pad1; + unsigned short tca__pad2; +}; + +enum { + TCA_ROOT_UNSPEC, + TCA_ROOT_TAB, +#define TCA_ACT_TAB TCA_ROOT_TAB +#define TCAA_MAX TCA_ROOT_TAB + TCA_ROOT_FLAGS, + TCA_ROOT_COUNT, + TCA_ROOT_TIME_DELTA, /* in msecs */ + TCA_ROOT_EXT_WARN_MSG, + __TCA_ROOT_MAX, +#define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) +}; + +#define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg)))) +#define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg)) +/* tcamsg flags stored in attribute TCA_ROOT_FLAGS + * + * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than + * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the + * number of actions being dumped stored in for user app's consumption in + * TCA_ROOT_COUNT + * + * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only + * includes essential action info (kind, index, etc.) + * + */ +#define TCA_FLAG_LARGE_DUMP_ON (1 << 0) +#define TCA_ACT_FLAG_LARGE_DUMP_ON TCA_FLAG_LARGE_DUMP_ON +#define TCA_ACT_FLAG_TERSE_DUMP (1 << 1) + +/* New extended info filters for IFLA_EXT_MASK */ +#define RTEXT_FILTER_VF (1 << 0) +#define RTEXT_FILTER_BRVLAN (1 << 1) +#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) +#define RTEXT_FILTER_SKIP_STATS (1 << 3) +#define RTEXT_FILTER_MRP (1 << 4) +#define RTEXT_FILTER_CFM_CONFIG (1 << 5) +#define RTEXT_FILTER_CFM_STATUS (1 << 6) +#define RTEXT_FILTER_MST (1 << 7) + +/* End of information exported to user level */ + + + +#endif /* _UAPI__LINUX_RTNETLINK_H */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 67626d535316..1686861aae20 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -98,37 +98,97 @@ struct statx_timestamp { */ struct statx { /* 0x00 */ - __u32 stx_mask; /* What results were written [uncond] */ - __u32 stx_blksize; /* Preferred general I/O size [uncond] */ - __u64 stx_attributes; /* Flags conveying information about the file [uncond] */ + /* What results were written [uncond] */ + __u32 stx_mask; + + /* Preferred general I/O size [uncond] */ + __u32 stx_blksize; + + /* Flags conveying information about the file [uncond] */ + __u64 stx_attributes; + /* 0x10 */ - __u32 stx_nlink; /* Number of hard links */ - __u32 stx_uid; /* User ID of owner */ - __u32 stx_gid; /* Group ID of owner */ - __u16 stx_mode; /* File mode */ + /* Number of hard links */ + __u32 stx_nlink; + + /* User ID of owner */ + __u32 stx_uid; + + /* Group ID of owner */ + __u32 stx_gid; + + /* File mode */ + __u16 stx_mode; __u16 __spare0[1]; + /* 0x20 */ - __u64 stx_ino; /* Inode number */ - __u64 stx_size; /* File size */ - __u64 stx_blocks; /* Number of 512-byte blocks allocated */ - __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */ + /* Inode number */ + __u64 stx_ino; + + /* File size */ + __u64 stx_size; + + /* Number of 512-byte blocks allocated */ + __u64 stx_blocks; + + /* Mask to show what's supported in stx_attributes */ + __u64 stx_attributes_mask; + /* 0x40 */ - struct statx_timestamp stx_atime; /* Last access time */ - struct statx_timestamp stx_btime; /* File creation time */ - struct statx_timestamp stx_ctime; /* Last attribute change time */ - struct statx_timestamp stx_mtime; /* Last data modification time */ + /* Last access time */ + struct statx_timestamp stx_atime; + + /* File creation time */ + struct statx_timestamp stx_btime; + + /* Last attribute change time */ + struct statx_timestamp stx_ctime; + + /* Last data modification time */ + struct statx_timestamp stx_mtime; + /* 0x80 */ - __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */ + /* Device ID of special file [if bdev/cdev] */ + __u32 stx_rdev_major; __u32 stx_rdev_minor; - __u32 stx_dev_major; /* ID of device containing file [uncond] */ + + /* ID of device containing file [uncond] */ + __u32 stx_dev_major; __u32 stx_dev_minor; + /* 0x90 */ __u64 stx_mnt_id; - __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ - __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ + + /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_mem_align; + + /* File offset alignment for direct I/O */ + __u32 stx_dio_offset_align; + /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + /* Subvolume identifier */ + __u64 stx_subvol; + + /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_min; + + /* Max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; + + /* 0xb0 */ + /* Max atomic write segment count */ + __u32 stx_atomic_write_segments_max; + + /* File offset alignment for direct I/O reads */ + __u32 stx_dio_read_offset_align; + + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ + /* 0x100 */ }; @@ -157,6 +217,8 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ +#define STATX_DIO_READ_ALIGN 0x00020000U /* Want/got dio read alignment info */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +254,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index bb6ea517efb5..c53cde425406 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline __inline__ #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,14 +27,14 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ - } + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union diff --git a/tools/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h index 91fa51a9c31d..85aa327245c6 100644 --- a/tools/include/uapi/linux/types.h +++ b/tools/include/uapi/linux/types.h @@ -4,6 +4,8 @@ #include <asm-generic/int-ll64.h> +#ifndef __ASSEMBLER__ + /* copied from linux:include/uapi/linux/types.h */ #define __bitwise typedef __u16 __bitwise __le16; @@ -20,4 +22,5 @@ typedef __u32 __bitwise __wsum; #define __aligned_be64 __be64 __attribute__((aligned(8))) #define __aligned_le64 __le64 __attribute__((aligned(8))) +#endif /* __ASSEMBLER__ */ #endif /* _UAPI_LINUX_TYPES_H */ |