aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/include/uapi/linux
diff options
context:
space:
mode:
Diffstat (limited to 'tools/include/uapi/linux')
-rw-r--r--tools/include/uapi/linux/bits.h14
-rw-r--r--tools/include/uapi/linux/bpf.h4051
-rw-r--r--tools/include/uapi/linux/bpf_perf_event.h1
-rw-r--r--tools/include/uapi/linux/btf.h77
-rw-r--r--tools/include/uapi/linux/const.h22
-rw-r--r--tools/include/uapi/linux/elf.h524
-rw-r--r--tools/include/uapi/linux/ethtool.h51
-rw-r--r--tools/include/uapi/linux/fanotify.h274
-rw-r--r--tools/include/uapi/linux/fcntl.h114
-rw-r--r--tools/include/uapi/linux/filter.h90
-rw-r--r--tools/include/uapi/linux/fs.h272
-rw-r--r--tools/include/uapi/linux/fscrypt.h25
-rw-r--r--tools/include/uapi/linux/hw_breakpoint.h10
-rw-r--r--tools/include/uapi/linux/if_link.h1000
-rw-r--r--tools/include/uapi/linux/if_tun.h2
-rw-r--r--tools/include/uapi/linux/if_xdp.h85
-rw-r--r--tools/include/uapi/linux/in.h43
-rw-r--r--tools/include/uapi/linux/io_uring.h757
-rw-r--r--tools/include/uapi/linux/kvm.h993
-rw-r--r--tools/include/uapi/linux/lirc.h229
-rw-r--r--tools/include/uapi/linux/memfd.h39
-rw-r--r--tools/include/uapi/linux/mman.h16
-rw-r--r--tools/include/uapi/linux/mount.h119
-rw-r--r--tools/include/uapi/linux/netdev.h231
-rw-r--r--tools/include/uapi/linux/nsfs.h45
-rw-r--r--tools/include/uapi/linux/openat2.h39
-rw-r--r--tools/include/uapi/linux/perf_event.h808
-rw-r--r--tools/include/uapi/linux/pkt_cls.h51
-rw-r--r--tools/include/uapi/linux/pkt_sched.h110
-rw-r--r--tools/include/uapi/linux/prctl.h135
-rw-r--r--tools/include/uapi/linux/sched.h148
-rw-r--r--tools/include/uapi/linux/seccomp.h157
-rw-r--r--tools/include/uapi/linux/seg6.h4
-rw-r--r--tools/include/uapi/linux/stat.h115
-rw-r--r--tools/include/uapi/linux/stddef.h54
-rw-r--r--tools/include/uapi/linux/tc_act/tc_bpf.h5
-rw-r--r--tools/include/uapi/linux/tcp.h357
-rw-r--r--tools/include/uapi/linux/types.h3
-rw-r--r--tools/include/uapi/linux/usbdevice_fs.h231
-rw-r--r--tools/include/uapi/linux/userfaultfd.h386
-rw-r--r--tools/include/uapi/linux/vhost.h147
41 files changed, 9412 insertions, 2422 deletions
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
new file mode 100644
index 000000000000..682b406e1067
--- /dev/null
+++ b/tools/include/uapi/linux/bits.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* bits.h: Macros for dealing with bitmasks. */
+
+#ifndef _UAPI_LINUX_BITS_H
+#define _UAPI_LINUX_BITS_H
+
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_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 8bd33050b7bb..0b4a2f124d11 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -19,7 +19,9 @@
/* ld/ldx fields */
#define BPF_DW 0x18 /* double word (64-bit) */
-#define BPF_XADD 0xc0 /* exclusive add */
+#define BPF_MEMSX 0x80 /* load with sign extension */
+#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
+#define BPF_XADD 0xc0 /* exclusive add - legacy name */
/* alu/jmp fields */
#define BPF_MOV 0xb0 /* mov reg to reg */
@@ -40,9 +42,22 @@
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
+#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */
#define BPF_CALL 0x80 /* function call */
#define BPF_EXIT 0x90 /* function return */
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */
+#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */
+#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */
+
+#define BPF_LOAD_ACQ 0x100 /* load-acquire */
+#define BPF_STORE_REL 0x110 /* store-release */
+
+enum bpf_cond_pseudo_jmp {
+ BPF_MAY_GOTO = 0,
+};
+
/* Register numbers */
enum {
BPF_REG_0 = 0,
@@ -70,18 +85,843 @@ struct bpf_insn {
__s32 imm; /* signed immediate constant */
};
-/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for
+ * byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for
+ * the trailing flexible array member) instead.
+ */
struct bpf_lpm_trie_key {
__u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
__u8 data[0]; /* Arbitrary size */
};
+/* Header for bpf_lpm_trie_key structs */
+struct bpf_lpm_trie_key_hdr {
+ __u32 prefixlen;
+};
+
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */
+struct bpf_lpm_trie_key_u8 {
+ union {
+ struct bpf_lpm_trie_key_hdr hdr;
+ __u32 prefixlen;
+ };
+ __u8 data[]; /* Arbitrary size */
+};
+
struct bpf_cgroup_storage_key {
__u64 cgroup_inode_id; /* cgroup inode id */
- __u32 attach_type; /* program attach type */
+ __u32 attach_type; /* program attach type (enum bpf_attach_type) */
+};
+
+enum bpf_cgroup_iter_order {
+ BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+ BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
+ BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
+ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
+ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
+};
+
+union bpf_iter_link_info {
+ struct {
+ __u32 map_fd;
+ } map;
+ struct {
+ enum bpf_cgroup_iter_order order;
+
+ /* At most one of cgroup_fd and cgroup_id can be non-zero. If
+ * both are zero, the walk starts from the default cgroup v2
+ * root. For walking v1 hierarchy, one should always explicitly
+ * specify cgroup_fd.
+ */
+ __u32 cgroup_fd;
+ __u64 cgroup_id;
+ } cgroup;
+ /* Parameters of task iterators. */
+ struct {
+ __u32 tid;
+ __u32 pid;
+ __u32 pid_fd;
+ } task;
};
-/* BPF syscall commands, see bpf(2) man-page for details. */
+/* BPF syscall commands, see bpf(2) man-page for more details. */
+/**
+ * DOC: eBPF Syscall Preamble
+ *
+ * The operation to be performed by the **bpf**\ () system call is determined
+ * by the *cmd* argument. Each operation takes an accompanying argument,
+ * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see
+ * below). The size argument is the size of the union pointed to by *attr*.
+ */
+/**
+ * DOC: eBPF Syscall Commands
+ *
+ * BPF_MAP_CREATE
+ * Description
+ * Create a map and return a file descriptor that refers to the
+ * map. The close-on-exec file descriptor flag (see **fcntl**\ (2))
+ * is automatically enabled for the new file descriptor.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_MAP_CREATE** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_LOOKUP_ELEM
+ * Description
+ * Look up an element with a given *key* in the map referred to
+ * by the file descriptor *map_fd*.
+ *
+ * The *flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_ELEM
+ * Description
+ * Create or update an element (key/value pair) in a specified map.
+ *
+ * The *flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create a new element or update an existing element.
+ * **BPF_NOEXIST**
+ * Create a new element only if it did not exist.
+ * **BPF_EXIST**
+ * Update an existing element.
+ * **BPF_F_LOCK**
+ * Update a spin_lock-ed map element.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**,
+ * **E2BIG**, **EEXIST**, or **ENOENT**.
+ *
+ * **E2BIG**
+ * The number of elements in the map reached the
+ * *max_entries* limit specified at map creation time.
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_ELEM
+ * Description
+ * Look up and delete an element by key in a specified map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_KEY
+ * Description
+ * Look up an element by key in a specified map and return the key
+ * of the next element. Can be used to iterate over all elements
+ * in the map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * The following cases can be used to iterate over all elements of
+ * the map:
+ *
+ * * If *key* is not found, the operation returns zero and sets
+ * the *next_key* pointer to the key of the first element.
+ * * If *key* is found, the operation returns zero and sets the
+ * *next_key* pointer to the key of the next element.
+ * * If *key* is the last element, returns -1 and *errno* is set
+ * to **ENOENT**.
+ *
+ * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or
+ * **EINVAL** on error.
+ *
+ * BPF_PROG_LOAD
+ * Description
+ * Verify and load an eBPF program, returning a new file
+ * descriptor associated with the program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES).
+ *
+ * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is
+ * automatically enabled for the new file descriptor.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_PIN
+ * Description
+ * Pin an eBPF program or map referred by the specified *bpf_fd*
+ * to the provided *pathname* on the filesystem.
+ *
+ * The *pathname* argument must not contain a dot (".").
+ *
+ * On success, *pathname* retains a reference to the eBPF object,
+ * preventing deallocation of the object when the original
+ * *bpf_fd* is closed. This allow the eBPF object to live beyond
+ * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent
+ * process.
+ *
+ * Applying **unlink**\ (2) or similar calls to the *pathname*
+ * unpins the object from the filesystem, removing the reference.
+ * If no other file descriptors or filesystem nodes refer to the
+ * same object, it will be deallocated (see NOTES).
+ *
+ * The filesystem type for the parent directory of *pathname* must
+ * be **BPF_FS_MAGIC**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_OBJ_GET
+ * Description
+ * Open a file descriptor for the eBPF object pinned to the
+ * specified *pathname*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_PROG_ATTACH
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook.
+ *
+ * The *attach_type* specifies the eBPF attachment point to
+ * attach the program to, and must be one of *bpf_attach_type*
+ * (see below).
+ *
+ * The *attach_bpf_fd* must be a valid file descriptor for a
+ * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap
+ * or sock_ops type corresponding to the specified *attach_type*.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_TYPE_SK_SKB**,
+ * **BPF_PROG_TYPE_SK_MSG**
+ *
+ * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_DETACH
+ * Description
+ * Detach the eBPF program associated with the *target_fd* at the
+ * hook specified by *attach_type*. The program must have been
+ * previously attached using **BPF_PROG_ATTACH**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_TEST_RUN
+ * Description
+ * Run the eBPF program associated with the *prog_fd* a *repeat*
+ * number of times against a provided program context *ctx_in* and
+ * data *data_in*, and return the modified program context
+ * *ctx_out*, *data_out* (for example, packet data), result of the
+ * execution *retval*, and *duration* of the test run.
+ *
+ * The sizes of the buffers provided as input and output
+ * parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
+ * be provided in the corresponding variables *ctx_size_in*,
+ * *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
+ * of these parameters are not provided (ie set to NULL), the
+ * corresponding size field must be zero.
+ *
+ * Some program types have particular requirements:
+ *
+ * **BPF_PROG_TYPE_SK_LOOKUP**
+ * *data_in* and *data_out* must be NULL.
+ *
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT**,
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
+ *
+ * *ctx_out*, *data_in* and *data_out* must be NULL.
+ * *repeat* must be zero.
+ *
+ * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * **ENOSPC**
+ * Either *data_size_out* or *ctx_size_out* is too small.
+ * **ENOTSUPP**
+ * This command is not supported by the program type of
+ * the program referred to by *prog_fd*.
+ *
+ * BPF_PROG_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF program currently loaded into the kernel.
+ *
+ * Looks for the eBPF program with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF programs
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF map currently loaded into the kernel.
+ *
+ * Looks for the eBPF map with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF maps
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_PROG_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF program corresponding to
+ * *prog_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF map corresponding to
+ * *map_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_GET_INFO_BY_FD
+ * Description
+ * Obtain information about the eBPF object corresponding to
+ * *bpf_fd*.
+ *
+ * Populates up to *info_len* bytes of *info*, which will be in
+ * one of the following formats depending on the eBPF object type
+ * of *bpf_fd*:
+ *
+ * * **struct bpf_prog_info**
+ * * **struct bpf_map_info**
+ * * **struct bpf_btf_info**
+ * * **struct bpf_link_info**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * specified *attach_type* hook.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_QUERY** always fetches the number of programs
+ * attached and the *attach_flags* which were used to attach those
+ * programs. Additionally, if *prog_ids* is nonzero and the number
+ * of attached programs is less than *prog_cnt*, populates
+ * *prog_ids* with the eBPF program ids of the programs attached
+ * at *target_fd*.
+ *
+ * The following flags may alter the result:
+ *
+ * **BPF_F_QUERY_EFFECTIVE**
+ * Only return information regarding programs which are
+ * currently effective at the specified *target_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_RAW_TRACEPOINT_OPEN
+ * Description
+ * Attach an eBPF program to a tracepoint *name* to access kernel
+ * internal arguments of the tracepoint in their raw form.
+ *
+ * The *prog_fd* must be a valid file descriptor associated with
+ * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**.
+ *
+ * No ABI guarantees are made about the content of tracepoint
+ * arguments exposed to the corresponding eBPF program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_LOAD
+ * Description
+ * Verify and load BPF Type Format (BTF) metadata into the kernel,
+ * returning a new file descriptor associated with the metadata.
+ * BTF is described in more detail at
+ * https://www.kernel.org/doc/html/latest/bpf/btf.html.
+ *
+ * The *btf* parameter must point to valid memory providing
+ * *btf_size* bytes of BTF binary metadata.
+ *
+ * The returned file descriptor can be passed to other **bpf**\ ()
+ * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to
+ * associate the BTF with those objects.
+ *
+ * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional
+ * parameters to specify a *btf_log_buf*, *btf_log_size* and
+ * *btf_log_level* which allow the kernel to return freeform log
+ * output regarding the BTF verification process.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the BPF Type Format (BTF)
+ * corresponding to *btf_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_TASK_FD_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * target process identified by *pid* and *fd*.
+ *
+ * If the *pid* and *fd* are associated with a tracepoint, kprobe
+ * or uprobe perf event, then the *prog_id* and *fd_type* will
+ * be populated with the eBPF program id and file descriptor type
+ * of type **bpf_task_fd_type**. If associated with a kprobe or
+ * uprobe, the *probe_offset* and *probe_addr* will also be
+ * populated. Optionally, if *buf* is provided, then up to
+ * *buf_len* bytes of *buf* will be populated with the name of
+ * the tracepoint, kprobe or uprobe.
+ *
+ * The resulting *prog_id* may be introspected in deeper detail
+ * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_ELEM
+ * Description
+ * Look up an element with the given *key* in the map referred to
+ * by the file descriptor *fd*, and if found, delete the element.
+ *
+ * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ * types, the *flags* argument needs to be set to 0, but for other
+ * map types, it may be specified as:
+ *
+ * **BPF_F_LOCK**
+ * Look up and delete the value of a spin-locked map
+ * without returning the lock. This must be specified if
+ * the elements contain a spinlock.
+ *
+ * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
+ * implement this command as a "pop" operation, deleting the top
+ * element rather than one corresponding to *key*.
+ * The *key* and *key_len* parameters should be zeroed when
+ * issuing this operation for these map types.
+ *
+ * This command is only valid for the following map types:
+ * * **BPF_MAP_TYPE_QUEUE**
+ * * **BPF_MAP_TYPE_STACK**
+ * * **BPF_MAP_TYPE_HASH**
+ * * **BPF_MAP_TYPE_PERCPU_HASH**
+ * * **BPF_MAP_TYPE_LRU_HASH**
+ * * **BPF_MAP_TYPE_LRU_PERCPU_HASH**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_FREEZE
+ * Description
+ * Freeze the permissions of the specified map.
+ *
+ * Write permissions may be frozen by passing zero *flags*.
+ * Upon success, no future syscall invocations may alter the
+ * map state of *map_fd*. Write operations from eBPF programs
+ * are still possible for a frozen map.
+ *
+ * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_BTF_GET_NEXT_ID
+ * Description
+ * Fetch the next BPF Type Format (BTF) object currently loaded
+ * into the kernel.
+ *
+ * Looks for the BTF object with an id greater than *start_id*
+ * and updates *next_id* on success. If no other BTF objects
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_BATCH
+ * Description
+ * Iterate and fetch multiple elements in a map.
+ *
+ * Two opaque values are used to manage batch operations,
+ * *in_batch* and *out_batch*. Initially, *in_batch* must be set
+ * to NULL to begin the batched operation. After each subsequent
+ * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
+ * *out_batch* as the *in_batch* for the next operation to
+ * continue iteration from the current point. Both *in_batch* and
+ * *out_batch* must point to memory large enough to hold a key,
+ * except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH,
+ * LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters
+ * must be at least 4 bytes wide regardless of key size.
+ *
+ * The *keys* and *values* are output parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are copied into the
+ * user buffer, with the keys copied into *keys* and the values
+ * copied into the corresponding indices in *values*.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **ENOSPC** to indicate that *keys* or
+ * *values* is too small to dump an entire bucket during
+ * iteration of a hash-based map type.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_BATCH
+ * Description
+ * Iterate and delete all elements in a map.
+ *
+ * This operation has the same behavior as
+ * **BPF_MAP_LOOKUP_BATCH** with two exceptions:
+ *
+ * * Every element that is successfully returned is also deleted
+ * from the map. This is at least *count* elements. Note that
+ * *count* is both an input and an output parameter.
+ * * Upon returning with *errno* set to **EFAULT**, up to
+ * *count* elements may be deleted without returning the keys
+ * and values of the deleted elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_BATCH
+ * Description
+ * Update multiple elements in a map by *key*.
+ *
+ * The *keys* and *values* are input parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially updated to the
+ * value in the corresponding index in *values*. The *in_batch*
+ * and *out_batch* parameters are ignored and should be zeroed.
+ *
+ * The *elem_flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create new elements or update a existing elements.
+ * **BPF_NOEXIST**
+ * Create new elements only if they do not exist.
+ * **BPF_EXIST**
+ * Update existing elements.
+ * **BPF_F_LOCK**
+ * Update spin_lock-ed map elements. This must be
+ * specified if the map value contains a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or
+ * **E2BIG**. **E2BIG** indicates that the number of elements in
+ * the map reached the *max_entries* limit specified at map
+ * creation time.
+ *
+ * May set *errno* to one of the following error codes under
+ * specific circumstances:
+ *
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_BATCH
+ * Description
+ * Delete multiple elements in a map by *key*.
+ *
+ * The *keys* parameter is an input parameter which must point
+ * to memory large enough to hold *count* items based on the key
+ * size of the map *map_fd*, that is, *key_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially deleted. The
+ * *in_batch*, *out_batch*, and *values* parameters are ignored
+ * and should be zeroed.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements. If
+ * *errno* is **EFAULT**, up to *count* elements may be been
+ * deleted.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_CREATE
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook and return a file descriptor handle for
+ * managing the link.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_UPDATE
+ * Description
+ * Update the eBPF program in the specified *link_fd* to
+ * *new_prog_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF Link corresponding to
+ * *link_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF link currently loaded into the kernel.
+ *
+ * Looks for the eBPF link with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF links
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_ENABLE_STATS
+ * Description
+ * Enable eBPF runtime statistics gathering.
+ *
+ * Runtime statistics gathering for the eBPF runtime is disabled
+ * by default to minimize the corresponding performance overhead.
+ * This command enables statistics globally.
+ *
+ * Multiple programs may independently enable statistics.
+ * After gathering the desired statistics, eBPF runtime statistics
+ * may be disabled again by calling **close**\ (2) for the file
+ * descriptor returned by this function. Statistics will only be
+ * disabled system-wide when all outstanding file descriptors
+ * returned by prior calls for this subcommand are closed.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_ITER_CREATE
+ * Description
+ * Create an iterator on top of the specified *link_fd* (as
+ * previously created using **BPF_LINK_CREATE**) and return a
+ * file descriptor that can be used to trigger the iteration.
+ *
+ * If the resulting file descriptor is pinned to the filesystem
+ * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls
+ * for that path will trigger the iterator to read kernel state
+ * using the eBPF program attached to *link_fd*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_DETACH
+ * Description
+ * Forcefully detach the specified *link_fd* from its
+ * corresponding attachment point.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_BIND_MAP
+ * Description
+ * Bind a map to the lifetime of an eBPF program.
+ *
+ * The map identified by *map_fd* is bound to the program
+ * identified by *prog_fd* and only released when *prog_fd* is
+ * released. This may be used in cases where metadata should be
+ * associated with a program which otherwise does not contain any
+ * references to the map (for example, embedded in the eBPF
+ * program instructions).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_TOKEN_CREATE
+ * Description
+ * Create BPF token with embedded information about what
+ * BPF-related functionality it allows:
+ * - a set of allowed bpf() syscall commands;
+ * - a set of allowed BPF map types to be created with
+ * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
+ * - a set of allowed BPF program types and BPF program attach
+ * types to be loaded with BPF_PROG_LOAD command, if
+ * BPF_PROG_LOAD itself is allowed.
+ *
+ * BPF token is created (derived) from an instance of BPF FS,
+ * assuming it has necessary delegation mount options specified.
+ * This BPF token can be passed as an extra parameter to various
+ * bpf() syscall commands to grant BPF subsystem functionality to
+ * unprivileged processes.
+ *
+ * When created, BPF token is "associated" with the owning
+ * user namespace of BPF FS instance (super block) that it was
+ * derived from, and subsequent BPF operations performed with
+ * BPF token would be performing capabilities checks (i.e.,
+ * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
+ * that user namespace. Without BPF token, such capabilities
+ * have to be granted in init user namespace, making bpf()
+ * syscall incompatible with user namespace, for the most part.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * NOTES
+ * eBPF objects (maps and programs) can be shared between processes.
+ *
+ * * After **fork**\ (2), the child inherits file descriptors
+ * referring to the same eBPF objects.
+ * * File descriptors referring to eBPF objects can be transferred over
+ * **unix**\ (7) domain sockets.
+ * * File descriptors referring to eBPF objects can be duplicated in the
+ * usual way, using **dup**\ (2) and similar calls.
+ * * File descriptors referring to eBPF objects can be pinned to the
+ * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2).
+ *
+ * An eBPF object is deallocated only after all file descriptors referring
+ * to the object have been closed and no references remain pinned to the
+ * filesystem or attached (for example, bound to a program or device).
+ */
enum bpf_cmd {
BPF_MAP_CREATE,
BPF_MAP_LOOKUP_ELEM,
@@ -94,6 +934,7 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_RUN = BPF_PROG_TEST_RUN,
BPF_PROG_GET_NEXT_ID,
BPF_MAP_GET_NEXT_ID,
BPF_PROG_GET_FD_BY_ID,
@@ -117,6 +958,10 @@ enum bpf_cmd {
BPF_LINK_GET_NEXT_ID,
BPF_ENABLE_STATS,
BPF_ITER_CREATE,
+ BPF_LINK_DETACH,
+ BPF_PROG_BIND_MAP,
+ BPF_TOKEN_CREATE,
+ __MAX_BPF_CMD,
};
enum bpf_map_type {
@@ -139,15 +984,36 @@ enum bpf_map_type {
BPF_MAP_TYPE_CPUMAP,
BPF_MAP_TYPE_XSKMAP,
BPF_MAP_TYPE_SOCKHASH,
- BPF_MAP_TYPE_CGROUP_STORAGE,
+ BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+ /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+ * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+ * both cgroup-attached and other progs and supports all functionality
+ * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+ * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+ */
+ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
- BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+ /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
+ * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
+ * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+ * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+ * deprecated.
+ */
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
BPF_MAP_TYPE_QUEUE,
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
BPF_MAP_TYPE_RINGBUF,
+ BPF_MAP_TYPE_INODE_STORAGE,
+ BPF_MAP_TYPE_TASK_STORAGE,
+ BPF_MAP_TYPE_BLOOM_FILTER,
+ BPF_MAP_TYPE_USER_RINGBUF,
+ BPF_MAP_TYPE_CGRP_STORAGE,
+ BPF_MAP_TYPE_ARENA,
+ __MAX_BPF_MAP_TYPE
};
/* Note that tracing related programs such as
@@ -189,6 +1055,10 @@ enum bpf_prog_type {
BPF_PROG_TYPE_STRUCT_OPS,
BPF_PROG_TYPE_EXT,
BPF_PROG_TYPE_LSM,
+ BPF_PROG_TYPE_SK_LOOKUP,
+ BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
+ BPF_PROG_TYPE_NETFILTER,
+ __MAX_BPF_PROG_TYPE
};
enum bpf_attach_type {
@@ -226,11 +1096,38 @@ enum bpf_attach_type {
BPF_CGROUP_INET4_GETSOCKNAME,
BPF_CGROUP_INET6_GETSOCKNAME,
BPF_XDP_DEVMAP,
+ BPF_CGROUP_INET_SOCK_RELEASE,
+ BPF_XDP_CPUMAP,
+ BPF_SK_LOOKUP,
+ BPF_XDP,
+ BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
+ BPF_PERF_EVENT,
+ BPF_TRACE_KPROBE_MULTI,
+ BPF_LSM_CGROUP,
+ BPF_STRUCT_OPS,
+ BPF_NETFILTER,
+ BPF_TCX_INGRESS,
+ BPF_TCX_EGRESS,
+ BPF_TRACE_UPROBE_MULTI,
+ BPF_CGROUP_UNIX_CONNECT,
+ BPF_CGROUP_UNIX_SENDMSG,
+ BPF_CGROUP_UNIX_RECVMSG,
+ BPF_CGROUP_UNIX_GETPEERNAME,
+ BPF_CGROUP_UNIX_GETSOCKNAME,
+ 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,
@@ -238,8 +1135,28 @@ enum bpf_link_type {
BPF_LINK_TYPE_CGROUP = 3,
BPF_LINK_TYPE_ITER = 4,
BPF_LINK_TYPE_NETNS = 5,
+ BPF_LINK_TYPE_XDP = 6,
+ BPF_LINK_TYPE_PERF_EVENT = 7,
+ BPF_LINK_TYPE_KPROBE_MULTI = 8,
+ BPF_LINK_TYPE_STRUCT_OPS = 9,
+ BPF_LINK_TYPE_NETFILTER = 10,
+ BPF_LINK_TYPE_TCX = 11,
+ BPF_LINK_TYPE_UPROBE_MULTI = 12,
+ BPF_LINK_TYPE_NETKIT = 13,
+ BPF_LINK_TYPE_SOCKMAP = 14,
+ __MAX_BPF_LINK_TYPE,
+};
+
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
- MAX_BPF_LINK_TYPE,
+enum bpf_perf_event_type {
+ BPF_PERF_EVENT_UNSPEC = 0,
+ BPF_PERF_EVENT_UPROBE = 1,
+ BPF_PERF_EVENT_URETPROBE = 2,
+ BPF_PERF_EVENT_KPROBE = 3,
+ BPF_PERF_EVENT_KRETPROBE = 4,
+ BPF_PERF_EVENT_TRACEPOINT = 5,
+ BPF_PERF_EVENT_EVENT = 6,
};
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
@@ -288,7 +1205,13 @@ enum bpf_link_type {
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
#define BPF_F_ALLOW_MULTI (1U << 1)
+/* Generic attachment flags. */
#define BPF_F_REPLACE (1U << 2)
+#define BPF_F_BEFORE (1U << 3)
+#define BPF_F_AFTER (1U << 4)
+#define BPF_F_ID (1U << 5)
+#define BPF_F_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
* verifier will perform strict alignment checking as if the kernel
@@ -297,7 +1220,7 @@ enum bpf_link_type {
*/
#define BPF_F_STRICT_ALIGNMENT (1U << 0)
-/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the
* verifier will allow any alignment whatsoever. On platforms
* with strict alignment requirements for loads ands stores (such
* as sparc and mips) the verifier validates that all loads and
@@ -332,24 +1255,103 @@ enum bpf_link_type {
/* The verifier internal test flag. Behavior is undefined */
#define BPF_F_TEST_STATE_FREQ (1U << 3)
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE (1U << 4)
+
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6)
+
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_REG_INVARIANTS (1U << 7)
+
+/* link_create.kprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
- * insn[0].imm: map fd map fd
- * insn[1].imm: 0 offset into value
- * insn[0].off: 0 0
- * insn[1].off: 0 0
- * ldimm64 rewrite: address of map address of map[0]+offset
- * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map
+ * verifier type: CONST_PTR_TO_MAP
*/
#define BPF_PSEUDO_MAP_FD 1
-#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_IDX 5
+
+/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: offset into value
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map[0]+offset
+ * verifier type: PTR_TO_MAP_VALUE
+ */
+#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_IDX_VALUE 6
+
+/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
+ * insn[0].imm: kernel btd id of VAR
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the kernel variable
+ * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ * is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID 3
+/* insn[0].src_reg: BPF_PSEUDO_FUNC
+ * insn[0].imm: insn offset to the func
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the function
+ * verifier type: PTR_TO_FUNC.
+ */
+#define BPF_PSEUDO_FUNC 4
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
*/
#define BPF_PSEUDO_CALL 1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL 2
+
+enum bpf_addr_space_cast {
+ BPF_ADDR_SPACE_CAST = 1,
+};
/* flags for BPF_MAP_UPDATE_ELEM command */
enum {
@@ -391,16 +1393,49 @@ enum {
/* Enable memory-mapping BPF map */
BPF_F_MMAPABLE = (1U << 10),
+
+/* Share perf_event among processes */
+ BPF_F_PRESERVE_ELEMS = (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+ BPF_F_INNER_MAP = (1U << 12),
+
+/* Create a map that will be registered/unregesitered by the backed bpf_link */
+ BPF_F_LINK = (1U << 13),
+
+/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
+ BPF_F_PATH_FD = (1U << 14),
+
+/* Flag for value_type_btf_obj_fd, the fd is available */
+ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15),
+
+/* BPF token FD is passed in a corresponding command's token_fd field */
+ BPF_F_TOKEN_FD = (1U << 16),
+
+/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */
+ BPF_F_SEGV_ON_FAULT = (1U << 17),
+
+/* Do not translate kernel bpf_arena pointers to user pointers */
+ BPF_F_NO_USER_CONV = (1U << 18),
};
/* Flags for BPF_PROG_QUERY. */
/* Query effective (directly attached + inherited from ancestor cgroups)
* programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU (1U << 0)
+/* If set, XDP frames will be transmitted after processing */
+#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2)
+
/* type for BPF_ENABLE_STATS */
enum bpf_stats_type {
/* enabled run_time_ns and run_cnt */
@@ -450,9 +1485,28 @@ union bpf_attr {
* struct stored as the
* map value
*/
+ /* Any per-map-type extra fields
+ *
+ * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+ * number of hash functions (if 0, the bloom filter will default
+ * to using 5 hash functions).
+ *
+ * BPF_MAP_TYPE_ARENA - contains the address where user space
+ * is going to mmap() the arena. It has to be page aligned.
+ */
+ __u64 map_extra;
+
+ __s32 value_type_btf_obj_fd; /* fd pointing to a BTF
+ * type data for
+ * btf_vmlinux_value_type_id.
+ */
+ /* BPF token FD to use with BPF_MAP_CREATE operation.
+ * If provided, map_flags should have BPF_F_TOKEN_FD flag set.
+ */
+ __s32 map_token_fd;
};
- 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 {
@@ -504,24 +1558,64 @@ union bpf_attr {
__aligned_u64 line_info; /* line info */
__u32 line_info_cnt; /* number of bpf_line_info records */
__u32 attach_btf_id; /* in-kernel BTF type id to attach to */
- __u32 attach_prog_fd; /* 0 to attach to vmlinux */
+ union {
+ /* valid prog_fd to attach to bpf prog */
+ __u32 attach_prog_fd;
+ /* or valid module BTF object fd or 0 to attach to vmlinux */
+ __u32 attach_btf_obj_fd;
+ };
+ __u32 core_relo_cnt; /* number of bpf_core_relo */
+ __aligned_u64 fd_array; /* array of FDs */
+ __aligned_u64 core_relos;
+ __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 log_true_size;
+ /* BPF token FD to use with BPF_PROG_LOAD operation.
+ * 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;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
__aligned_u64 pathname;
__u32 bpf_fd;
__u32 file_flags;
+ /* Same as dirfd in openat() syscall; see openat(2)
+ * manpage for details of path FD and pathname semantics;
+ * path_fd should accompanied by BPF_F_PATH_FD flag set in
+ * file_flags field, otherwise it should be set to zero;
+ * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed.
+ */
+ __s32 path_fd;
};
struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
- __u32 target_fd; /* container object to attach to */
- __u32 attach_bpf_fd; /* eBPF program to attach */
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_bpf_fd;
__u32 attach_type;
__u32 attach_flags;
- __u32 replace_bpf_fd; /* previously attached eBPF
- * program to replace if
- * BPF_F_REPLACE is used
- */
+ __u32 replace_bpf_fd;
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
};
struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -543,6 +1637,9 @@ union bpf_attr {
*/
__aligned_u64 ctx_in;
__aligned_u64 ctx_out;
+ __u32 flags;
+ __u32 cpu;
+ __u32 batch_size;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -555,6 +1652,7 @@ 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 */
@@ -564,17 +1662,33 @@ union bpf_attr {
} info;
struct { /* anonymous struct used by BPF_PROG_QUERY command */
- __u32 target_fd; /* container object to query */
+ union {
+ __u32 target_fd; /* target object to query or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
__u32 attach_type;
__u32 query_flags;
__u32 attach_flags;
__aligned_u64 prog_ids;
- __u32 prog_cnt;
+ union {
+ __u32 prog_cnt;
+ __u32 count;
+ };
+ __u32 :32;
+ /* output: per-program attach_flags.
+ * not allowed to be set during effective query.
+ */
+ __aligned_u64 prog_attach_flags;
+ __aligned_u64 link_ids;
+ __aligned_u64 link_attach_flags;
+ __u64 revision;
} query;
struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
- __u64 name;
- __u32 prog_fd;
+ __u64 name;
+ __u32 prog_fd;
+ __u32 :32;
+ __aligned_u64 cookie;
} raw_tracepoint;
struct { /* anonymous struct for BPF_BTF_LOAD */
@@ -583,6 +1697,16 @@ union bpf_attr {
__u32 btf_size;
__u32 btf_log_size;
__u32 btf_log_level;
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 btf_log_true_size;
+ __u32 btf_flags;
+ /* BPF token FD to use with BPF_BTF_LOAD operation.
+ * If provided, btf_flags should have BPF_F_TOKEN_FD flag set.
+ */
+ __s32 btf_token_fd;
};
struct {
@@ -602,22 +1726,102 @@ union bpf_attr {
} task_fd_query;
struct { /* struct used by BPF_LINK_CREATE command */
- __u32 prog_fd; /* eBPF program to attach */
- __u32 target_fd; /* object to attach to */
+ union {
+ __u32 prog_fd; /* eBPF program to attach */
+ __u32 map_fd; /* struct_ops to attach */
+ };
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
__u32 attach_type; /* attach type */
__u32 flags; /* extra flags */
+ union {
+ __u32 target_btf_id; /* btf_id of target to attach to */
+ struct {
+ __aligned_u64 iter_info; /* extra bpf_iter_link_info */
+ __u32 iter_info_len; /* iter_info length */
+ };
+ struct {
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 bpf_cookie;
+ } perf_event;
+ struct {
+ __u32 flags;
+ __u32 cnt;
+ __aligned_u64 syms;
+ __aligned_u64 addrs;
+ __aligned_u64 cookies;
+ } kprobe_multi;
+ struct {
+ /* this is overlaid with the target_btf_id above. */
+ __u32 target_btf_id;
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 cookie;
+ } tracing;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } tcx;
+ struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 cnt;
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } netkit;
+ };
} link_create;
struct { /* struct used by BPF_LINK_UPDATE command */
__u32 link_fd; /* link fd */
- /* new program fd to update link with */
- __u32 new_prog_fd;
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
__u32 flags; /* extra flags */
- /* expected link's program fd; is specified only if
- * BPF_F_REPLACE flag is set in flags */
- __u32 old_prog_fd;
+ union {
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags.
+ */
+ __u32 old_prog_fd;
+ /* expected link's map fd; is specified only
+ * if BPF_F_REPLACE flag is set.
+ */
+ __u32 old_map_fd;
+ };
} link_update;
+ struct {
+ __u32 link_fd;
+ } link_detach;
+
struct { /* struct used by BPF_ENABLE_STATS command */
__u32 type;
} enable_stats;
@@ -627,6 +1831,17 @@ union bpf_attr {
__u32 flags;
} iter_create;
+ struct { /* struct used by BPF_PROG_BIND_MAP command */
+ __u32 prog_fd;
+ __u32 map_fd;
+ __u32 flags; /* extra flags */
+ } prog_bind_map;
+
+ struct { /* struct used by BPF_TOKEN_CREATE command */
+ __u32 flags;
+ __u32 bpffs_fd;
+ } token_create;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -634,7 +1849,7 @@ union bpf_attr {
* parsed and used to produce a manual page. The workflow is the following,
* and requires the rst2man utility:
*
- * $ ./scripts/bpf_helpers_doc.py \
+ * $ ./scripts/bpf_doc.py \
* --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
* $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
* $ man /tmp/bpf-helpers.7
@@ -653,7 +1868,7 @@ union bpf_attr {
* Map value associated to *key*, or **NULL** if no entry was
* found.
*
- * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+ * long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
* Description
* Add or update the value of the entry associated to *key* in
* *map* with *value*. *flags* is one of:
@@ -671,13 +1886,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_delete_elem(struct bpf_map *map, const void *key)
+ * long bpf_map_delete_elem(struct bpf_map *map, const void *key)
* Description
* Delete entry with *key* from *map*.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
* kernel space address *unsafe_ptr* and store the data in *dst*.
@@ -695,21 +1910,21 @@ union bpf_attr {
* Return
* Current *ktime*.
*
- * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
+ * long bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
* Description
* This helper is a "printk()-like" facility for debugging. It
* prints a message defined by format *fmt* (of size *fmt_size*)
- * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if
+ * to file *\/sys/kernel/tracing/trace* from TraceFS, if
* available. It can take up to three additional **u64**
* arguments (as an eBPF helpers, the total number of arguments is
* limited to five).
*
* Each time the helper is called, it appends a line to the trace.
- * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is
- * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this.
+ * Lines are discarded while *\/sys/kernel/tracing/trace* is
+ * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this.
* The format of the trace is customizable, and the exact output
* one will get depends on the options set in
- * *\/sys/kernel/debug/tracing/trace_options* (see also the
+ * *\/sys/kernel/tracing/trace_options* (see also the
* *README* file under the same directory). However, it usually
* defaults to something like:
*
@@ -745,7 +1960,7 @@ union bpf_attr {
*
* Also, note that **bpf_trace_printk**\ () is slow, and should
* only be used for debugging purposes. For this reason, a notice
- * bloc (spanning several lines) is printed to kernel logs and
+ * block (spanning several lines) is printed to kernel logs and
* states that the helper should not be used "for production use"
* the first time this helper is used (or more precisely, when
* **trace_printk**\ () buffers are allocated). For passing values
@@ -769,20 +1984,26 @@ union bpf_attr {
* u32 bpf_get_smp_processor_id(void)
* Description
* Get the SMP (symmetric multiprocessing) processor id. Note that
- * all programs run with preemption disabled, which means that the
+ * all programs run with migration disabled, which means that the
* SMP processor id is stable during all the execution of the
* program.
* Return
* The SMP id of the processor running the program.
+ * Attributes
+ * __bpf_fastcall
*
- * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
+ * 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
@@ -792,7 +2013,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
+ * long bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
* Description
* Recompute the layer 3 (e.g. IP) checksum for the packet
* associated to *skb*. Computation is incremental, so the helper
@@ -817,7 +2038,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
+ * long bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
* Description
* Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
* packet associated to *skb*. Computation is incremental, so the
@@ -834,7 +2055,8 @@ 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
@@ -849,7 +2071,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
+ * long bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
* Description
* This special helper is used to trigger a "tail call", or in
* other words, to jump into another eBPF program. The same stack
@@ -876,11 +2098,11 @@ union bpf_attr {
* if the maximum number of tail calls has been reached for this
* chain of programs. This limit is defined in the kernel by the
* macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
- * which is currently set to 32.
+ * which is currently set to 33.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
+ * long bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
* Description
* Clone and redirect the packet associated to *skb* to another
* net device of index *ifindex*. Both ingress and egress
@@ -902,9 +2124,13 @@ union bpf_attr {
* performed again, if the helper is used in combination with
* direct packet access.
* Return
- * 0 on success, or a negative error in case of failure.
+ * 0 on success, or a negative error in case of failure. Positive
+ * error indicates a potential drop or congestion in the target
+ * device. The particular positive error codes are not defined.
*
* u64 bpf_get_current_pid_tgid(void)
+ * Description
+ * Get the current pid and tgid.
* Return
* A 64-bit integer containing the current tgid and pid, and
* created as such:
@@ -912,11 +2138,13 @@ union bpf_attr {
* *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
+ * Description
+ * Get the current uid and gid.
* Return
* A 64-bit integer containing the current GID and UID, and
* created as such: *current_gid* **<< 32 \|** *current_uid*.
*
- * int bpf_get_current_comm(void *buf, u32 size_of_buf)
+ * long bpf_get_current_comm(void *buf, u32 size_of_buf)
* Description
* Copy the **comm** attribute of the current task into *buf* of
* *size_of_buf*. The **comm** attribute contains the name of
@@ -953,7 +2181,7 @@ union bpf_attr {
* Return
* The classid, or 0 for the default unconfigured classid.
*
- * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+ * long bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
* Description
* Push a *vlan_tci* (VLAN tag control information) of protocol
* *vlan_proto* to the packet associated to *skb*, then update
@@ -969,7 +2197,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_vlan_pop(struct sk_buff *skb)
+ * long bpf_skb_vlan_pop(struct sk_buff *skb)
* Description
* Pop a VLAN header from the packet associated to *skb*.
*
@@ -981,7 +2209,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * long bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
* Description
* Get tunnel metadata. This helper takes a pointer *key* to an
* empty **struct bpf_tunnel_key** of **size**, that will be
@@ -1011,14 +2239,14 @@ union bpf_attr {
*
* int ret;
* struct bpf_tunnel_key key = {};
- *
+ *
* ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
* if (ret < 0)
* return TC_ACT_SHOT; // drop packet
- *
+ *
* if (key.remote_ipv4 != 0x0a000001)
* return TC_ACT_SHOT; // drop packet
- *
+ *
* return TC_ACT_OK; // accept packet
*
* This interface can also be used with all encapsulation devices
@@ -1032,7 +2260,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * long bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
* Description
* Populate tunnel metadata for packet associated to *skb.* The
* tunnel metadata is set to the contents of *key*, of *size*. The
@@ -1054,6 +2282,9 @@ union bpf_attr {
* sending the packet. This flag was added for GRE
* encapsulation, but might be used with other protocols
* as well in the future.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
*
* Here is a typical usage on the transmit path:
*
@@ -1098,7 +2329,7 @@ union bpf_attr {
* The value of the perf event counter read from the map, or a
* negative error code in case of failure.
*
- * int bpf_redirect(u32 ifindex, u64 flags)
+ * long bpf_redirect(u32 ifindex, u64 flags)
* Description
* Redirect the packet to another net device of index *ifindex*.
* This helper is somewhat similar to **bpf_clone_redirect**\
@@ -1125,7 +2356,7 @@ union bpf_attr {
* Description
* Retrieve the realm or the route, that is to say the
* **tclassid** field of the destination for the *skb*. The
- * indentifier retrieved is a user-provided tag, similar to the
+ * identifier retrieved is a user-provided tag, similar to the
* one used with the net_cls cgroup (see description for
* **bpf_get_cgroup_classid**\ () helper), but here this tag is
* held by a route (a destination entry), not by a task.
@@ -1145,7 +2376,7 @@ union bpf_attr {
* The realm of the route for the packet associated to *skb*, or 0
* if none was found.
*
- * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * long bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
* Description
* Write raw *data* blob into a special BPF perf event held by
* *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -1190,7 +2421,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
+ * long bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
* Description
* This helper was provided as an easy way to load data from a
* packet. It can be used to load *len* bytes from *offset* from
@@ -1207,7 +2438,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
+ * long bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
* Description
* Walk a user or a kernel stack and return its id. To achieve
* this, the helper needs *ctx*, which is a pointer to the context
@@ -1276,7 +2507,7 @@ union bpf_attr {
* The checksum result, or a negative error code in case of
* failure.
*
- * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
+ * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
* Description
* Retrieve tunnel options metadata for the packet associated to
* *skb*, and store the raw tunnel option data to the buffer *opt*
@@ -1294,7 +2525,7 @@ union bpf_attr {
* Return
* The size of the option data retrieved.
*
- * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
+ * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
* Description
* Set tunnel options metadata for the packet associated to *skb*
* to the option data contained in the raw buffer *opt* of *size*.
@@ -1304,7 +2535,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
+ * long bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
* Description
* Change the protocol of the *skb* to *proto*. Currently
* supported are transition from IPv4 to IPv6, and from IPv6 to
@@ -1331,7 +2562,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_change_type(struct sk_buff *skb, u32 type)
+ * long bpf_skb_change_type(struct sk_buff *skb, u32 type)
* Description
* Change the packet type for the packet associated to *skb*. This
* comes down to setting *skb*\ **->pkt_type** to *type*, except
@@ -1358,7 +2589,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
+ * long bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
* Description
* Check whether *skb* is a descendant of the cgroup2 held by
* *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
@@ -1386,10 +2617,12 @@ union bpf_attr {
* The 32-bit hash.
*
* u64 bpf_get_current_task(void)
+ * Description
+ * Get the current task.
* Return
* A pointer to the current task struct.
*
- * int bpf_probe_write_user(void *dst, const void *src, u32 len)
+ * long bpf_probe_write_user(void *dst, const void *src, u32 len)
* Description
* Attempt in a safe way to write *len* bytes from the buffer
* *src* to *dst* in memory. It only works for threads that are in
@@ -1408,7 +2641,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
+ * long bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
* Description
* Check whether the probe is being run is the context of a given
* subset of the cgroup2 hierarchy. The cgroup2 to test is held by
@@ -1416,11 +2649,11 @@ union bpf_attr {
* Return
* The return value depends on the result of the test, and can be:
*
- * * 0, if the *skb* task belongs to the cgroup2.
- * * 1, if the *skb* task does not belong to the cgroup2.
+ * * 1, if current task belongs to the cgroup2.
+ * * 0, if current task does not belong to the cgroup2.
* * A negative error code, if an error occurred.
*
- * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
+ * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
* Description
* Resize (trim or grow) the packet associated to *skb* to the
* new *len*. The *flags* are reserved for future usage, and must
@@ -1444,12 +2677,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_pull_data(struct sk_buff *skb, u32 len)
+ * long bpf_skb_pull_data(struct sk_buff *skb, u32 len)
* Description
* Pull in non-linear data in case the *skb* is non-linear and not
* all of *len* are part of the linear section. Make *len* bytes
* from *skb* readable and writable. If a zero value is passed for
- * *len*, then the whole length of the *skb* is pulled.
+ * *len*, then all bytes in the linear part of *skb* will be made
+ * readable and writable.
*
* This helper is only needed for reading and writing with direct
* packet access.
@@ -1499,8 +2733,10 @@ union bpf_attr {
* indicate that the hash is outdated and to trigger a
* recalculation the next time the kernel tries to access this
* hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * Return
+ * void.
*
- * int bpf_get_numa_node_id(void)
+ * long bpf_get_numa_node_id(void)
* Description
* Return the id of the current NUMA node. The primary use case
* for this helper is the selection of sockets for the local NUMA
@@ -1511,7 +2747,7 @@ union bpf_attr {
* Return
* The id of current NUMA node.
*
- * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
+ * long bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
* Description
* Grows headroom of packet associated to *skb* and adjusts the
* offset of the MAC header accordingly, adding *len* bytes of
@@ -1532,7 +2768,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
+ * long bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
* Description
* Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that
* it is possible to use a negative value for *delta*. This helper
@@ -1547,7 +2783,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address
* *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
@@ -1570,24 +2806,34 @@ union bpf_attr {
* networking traffic statistics as it provides a global socket
* identifier that can be assumed unique.
* Return
- * A 8-byte long non-decreasing number on success, or 0 if the
- * socket field is missing inside *skb*.
+ * A 8-byte long unique number on success, or 0 if the socket
+ * field is missing inside *skb*.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
* *skb*, but gets socket from **struct bpf_sock_addr** context.
* Return
- * A 8-byte long non-decreasing number.
+ * A 8-byte long unique number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
* *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
- * A 8-byte long non-decreasing number.
+ * A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * Description
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * *sk*, but gets socket from a BTF **struct sock**. This helper
+ * also works for sleepable programs.
+ * Return
+ * A 8-byte long unique number or 0 if *sk* is NULL.
*
* u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Description
+ * Get the owner UID of the socked associated to *skb*.
* Return
* The owner UID of the socket associated to *skb*. If the socket
* is **NULL**, or if it is not a full socket (i.e. if it is a
@@ -1595,14 +2841,14 @@ union bpf_attr {
* is returned (note that **overflowuid** might also be the actual
* UID value for the socket).
*
- * u32 bpf_set_hash(struct sk_buff *skb, u32 hash)
+ * long bpf_set_hash(struct sk_buff *skb, u32 hash)
* Description
* Set the full hash for *skb* (set the field *skb*\ **->hash**)
* to value *hash*.
* Return
* 0
*
- * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
+ * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **setsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1613,24 +2859,32 @@ union bpf_attr {
* *bpf_socket* should be one of the following:
*
* * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * and **BPF_CGROUP_INET6_CONNECT**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
*
* This helper actually implements a subset of **setsockopt()**.
* It supports the following *level*\ s:
*
* * **SOL_SOCKET**, which supports the following *optname*\ s:
* **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
- * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**.
+ * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**,
+ * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
* * **IPPROTO_TCP**, which supports the following *optname*\ s:
* **TCP_CONGESTION**, **TCP_BPF_IW**,
- * **TCP_BPF_SNDCWND_CLAMP**.
+ * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
+ * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
+ * **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_SOCK_OPS_CB_FLAGS**.
* * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * * **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
+ * long bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
* Description
* Grow or shrink the room for data in the packet associated to
* *skb* by *len_diff*, and according to the selected *mode*.
@@ -1645,10 +2899,12 @@ union bpf_attr {
* There are two supported modes at this time:
*
* * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- * (room space is added or removed below the layer 2 header).
+ * (room space is added or removed between the layer 2 and
+ * layer 3 headers).
*
* * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * (room space is added or removed below the layer 3 header).
+ * (room space is added or removed between the layer 3 and
+ * layer 4 headers).
*
* The following flags are supported at this time:
*
@@ -1668,6 +2924,15 @@ union bpf_attr {
* Use with ENCAP_L3/L4 flags to further specify the tunnel
* type; *len* is the length of the inner MAC header.
*
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:
+ * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
+ * L2 type as Ethernet.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ * Indicate the new IP header version after decapsulating the outer
+ * IP header. Used when the inner and outer IP versions are different.
+ *
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
@@ -1676,7 +2941,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags)
* Description
* Redirect the packet to the endpoint referenced by *map* at
* index *key*. Depending on its type, this *map* can contain
@@ -1688,8 +2953,12 @@ union bpf_attr {
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
* one of the XDP program return codes up to **XDP_TX**, as chosen
- * by the caller. Any higher bits in the *flags* argument must be
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -1697,7 +2966,7 @@ union bpf_attr {
* **XDP_REDIRECT** on success, or the value of the two lower bits
* of the *flags* argument on error.
*
- * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
+ * long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
* Description
* Redirect the packet to the socket referenced by *map* (of type
* **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
@@ -1708,7 +2977,7 @@ union bpf_attr {
* Return
* **SK_PASS** on success, or **SK_DROP** on error.
*
- * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
* Description
* Add an entry to, or update a *map* referencing sockets. The
* *skops* is used as a new value for the entry associated to
@@ -1727,7 +2996,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
+ * long bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
* Description
* Adjust the address pointed by *xdp_md*\ **->data_meta** by
* *delta* (which can be positive or negative). Note that this
@@ -1756,7 +3025,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
+ * long bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
* Description
* Read the value of a perf event counter, and store it into *buf*
* of size *buf_size*. This helper relies on a *map* of type
@@ -1806,9 +3075,9 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
* Description
- * For en eBPF program attached to a perf event, retrieve the
+ * For an eBPF program attached to a perf event, retrieve the
* value of the event counter associated to *ctx* and store it in
* the structure pointed by *buf* and of size *buf_size*. Enabled
* and running times are also stored in the structure (see
@@ -1817,7 +3086,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
+ * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **getsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1829,20 +3098,18 @@ union bpf_attr {
* *bpf_socket* should be one of the following:
*
* * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * and **BPF_CGROUP_INET6_CONNECT**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
*
* This helper actually implements a subset of **getsockopt()**.
- * It supports the following *level*\ s:
- *
- * * **IPPROTO_TCP**, which supports *optname*
- * **TCP_CONGESTION**.
- * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * It supports the same set of *optname*\ s that is supported by
+ * the **bpf_setsockopt**\ () helper. The exceptions are
+ * **TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_override_return(struct pt_regs *regs, u64 rc)
+ * long bpf_override_return(struct pt_regs *regs, u64 rc)
* Description
* Used for error injection, this helper uses kprobes to override
* the return value of the probed function, and to set it to *rc*.
@@ -1860,14 +3127,10 @@ 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
*
- * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
+ * long bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
* Description
* Attempt to set the value of the **bpf_sock_ops_cb_flags** field
* for the full TCP socket associated to *bpf_sock_ops* to
@@ -1911,7 +3174,7 @@ union bpf_attr {
* be set is returned (which comes down to 0 if all bits were set
* as required).
*
- * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+ * long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
* Description
* This helper is used in programs implementing policies at the
* socket level. If the message *msg* is allowed to pass (i.e. if
@@ -1925,7 +3188,7 @@ union bpf_attr {
* Return
* **SK_PASS** on success, or **SK_DROP** on error.
*
- * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
* Description
* For socket policies, apply the verdict of the eBPF program to
* the next *bytes* (number of bytes) of message *msg*.
@@ -1959,7 +3222,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
* Description
* For socket policies, prevent the execution of the verdict eBPF
* program for message *msg* until *bytes* (byte number) have been
@@ -1977,7 +3240,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+ * long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
* Description
* For socket policies, pull in non-linear data from user space
* for *msg* and set pointers *msg*\ **->data** and *msg*\
@@ -2008,7 +3271,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
+ * long bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
* Description
* Bind the socket associated to *ctx* to the address pointed by
* *addr*, of length *addr_len*. This allows for making outgoing
@@ -2026,7 +3289,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
* Description
* Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
* possible to both shrink and grow the packet tail.
@@ -2040,7 +3303,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
+ * long bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
* Description
* Retrieve the XFRM state (IP transform framework, see also
* **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*.
@@ -2056,7 +3319,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
+ * long bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
* Description
* Return a user or a kernel stack in bpf program provided buffer.
* To achieve this, the helper needs *ctx*, which is a pointer
@@ -2072,8 +3335,18 @@ union bpf_attr {
* **BPF_F_USER_STACK**
* Collect a user space stack instead of a kernel stack.
* **BPF_F_USER_BUILD_ID**
- * Collect buildid+offset instead of ips for user stack,
- * only valid if **BPF_F_USER_STACK** is also specified.
+ * Collect (build_id, file_offset) instead of ips for user
+ * stack, only valid if **BPF_F_USER_STACK** is also
+ * specified.
+ *
+ * *file_offset* is an offset relative to the beginning
+ * of the executable or shared object file backing the vma
+ * which the *ip* falls in. It is *not* an offset relative
+ * to that object's base address. Accordingly, it must be
+ * adjusted by adding (sh_addr - sh_offset), where
+ * sh_{addr,offset} correspond to the executable section
+ * containing *file_offset* in the object, for comparisons
+ * to symbols' st_value to be valid.
*
* **bpf_get_stack**\ () can collect up to
* **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -2086,10 +3359,10 @@ union bpf_attr {
*
* # sysctl kernel.perf_event_max_stack=<new value>
* Return
- * A non-negative value equal to or less than *size* on success,
- * or a negative error in case of failure.
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
*
- * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
* Description
* This helper is similar to **bpf_skb_load_bytes**\ () in that
* it provides an easy way to load *len* bytes from *offset*
@@ -2111,7 +3384,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ * long bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
* Description
* Do FIB lookup in kernel tables using parameters in *params*.
* If lookup is successful and result shows packet is to be
@@ -2130,9 +3403,27 @@ union bpf_attr {
* **BPF_FIB_LOOKUP_DIRECT**
* Do a direct table lookup vs full lookup using FIB
* rules.
+ * **BPF_FIB_LOOKUP_TBID**
+ * Used with BPF_FIB_LOOKUP_DIRECT.
+ * Use the routing table ID present in *params*->tbid
+ * for the fib lookup.
* **BPF_FIB_LOOKUP_OUTPUT**
* Perform lookup from an egress perspective (default is
* ingress).
+ * **BPF_FIB_LOOKUP_SKIP_NEIGH**
+ * Skip the neighbour table lookup. *params*->dmac
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
+ * **BPF_FIB_LOOKUP_SRC**
+ * Derive and set source IP addr in *params*->ipv{4,6}_src
+ * for the nexthop. If the src addr cannot be derived,
+ * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
+ * case, *params*->dmac and *params*->smac are not set either.
+ * **BPF_FIB_LOOKUP_MARK**
+ * Use the mark present in *params*->mark for the fib lookup.
+ * This option should not be used with BPF_FIB_LOOKUP_DIRECT,
+ * as it only has meaning for full lookups.
*
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
@@ -2142,7 +3433,10 @@ union bpf_attr {
* * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
* packet is not forwarded or needs assist from full stack
*
- * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ * was exceeded and output params->mtu_result contains the MTU.
+ *
+ * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
* Description
* Add an entry to, or update a sockhash *map* referencing sockets.
* The *skops* is used as a new value for the entry associated to
@@ -2161,7 +3455,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ * long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
* Description
* This helper is used in programs implementing policies at the
* socket level. If the message *msg* is allowed to pass (i.e. if
@@ -2175,11 +3469,11 @@ union bpf_attr {
* Return
* **SK_PASS** on success, or **SK_DROP** on error.
*
- * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ * long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
* Description
* This helper is used in programs implementing policies at the
* skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
- * if the verdeict eBPF program returns **SK_PASS**), redirect it
+ * if the verdict eBPF program returns **SK_PASS**), redirect it
* to the socket referenced by *map* (of type
* **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
* egress interfaces can be used for redirection. The
@@ -2189,7 +3483,7 @@ union bpf_attr {
* Return
* **SK_PASS** on success, or **SK_DROP** on error.
*
- * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
+ * long bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
* Description
* Encapsulate the packet associated to *skb* within a Layer 3
* protocol header. This header is provided in the buffer at
@@ -2226,7 +3520,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len)
+ * long bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len)
* Description
* Store *len* bytes from address *from* into the packet
* associated to *skb*, at *offset*. Only the flags, tag and TLVs
@@ -2241,7 +3535,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta)
+ * long bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta)
* Description
* Adjust the size allocated to TLVs in the outermost IPv6
* Segment Routing Header contained in the packet associated to
@@ -2257,7 +3551,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len)
+ * long bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len)
* Description
* Apply an IPv6 Segment Routing action of type *action* to the
* packet associated to *skb*. Each action takes a parameter
@@ -2286,7 +3580,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_rc_repeat(void *ctx)
+ * long bpf_rc_repeat(void *ctx)
* Description
* This helper is used in programs implementing IR decoding, to
* report a successfully decoded repeat key message. This delays
@@ -2305,7 +3599,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * long bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
* Description
* This helper is used in programs implementing IR decoding, to
* report a successfully decoded key press with *scancode*,
@@ -2348,6 +3642,9 @@ union bpf_attr {
* The id is returned or 0 in case the id could not be retrieved.
*
* u64 bpf_get_current_cgroup_id(void)
+ * Description
+ * Get the current cgroup id based on the cgroup within which
+ * the current task is running.
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
@@ -2365,15 +3662,15 @@ union bpf_attr {
* running simultaneously.
*
* A user should care about the synchronization by himself.
- * For example, by using the **BPF_STX_XADD** instruction to alter
+ * For example, by using the **BPF_ATOMIC** instructions to alter
* the shared data.
* Return
* A pointer to the local storage area.
*
- * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
* Description
* Select a **SO_REUSEPORT** socket from a
- * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*.
* It checks the selected socket is matching the incoming
* request in the socket buffer.
* Return
@@ -2415,7 +3712,7 @@ union bpf_attr {
* Look for an IPv6 socket.
*
* If the *netns* is a negative signed 32-bit integer, then the
- * socket lookup table in the netns associated with the *ctx* will
+ * socket lookup table in the netns associated with the *ctx*
* will be used. For the TC hooks, this is the netns of the device
* in the skb. For socket hooks, this is the netns of the socket.
* If *netns* is any other signed 32-bit value greater than or
@@ -2452,7 +3749,7 @@ union bpf_attr {
* Look for an IPv6 socket.
*
* If the *netns* is a negative signed 32-bit integer, then the
- * socket lookup table in the netns associated with the *ctx* will
+ * socket lookup table in the netns associated with the *ctx*
* will be used. For the TC hooks, this is the netns of the device
* in the skb. For socket hooks, this is the netns of the socket.
* If *netns* is any other signed 32-bit value greater than or
@@ -2471,7 +3768,7 @@ union bpf_attr {
* result is from *reuse*\ **->socks**\ [] using the hash of the
* tuple.
*
- * int bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
* Description
* Release the reference held by *sock*. *sock* must be a
* non-**NULL** pointer that was returned from
@@ -2479,7 +3776,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
* Description
* Push an element *value* in *map*. *flags* is one of:
*
@@ -2489,19 +3786,19 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * long bpf_map_pop_elem(struct bpf_map *map, void *value)
* Description
* Pop an element from *map*.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * long bpf_map_peek_elem(struct bpf_map *map, void *value)
* Description
* Get an element from *map* without removing it.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
* Description
* For socket policies, insert *len* bytes into *msg* at offset
* *start*.
@@ -2517,7 +3814,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
* Description
* Will remove *len* bytes from a *msg* starting at byte *start*.
* This may result in **ENOMEM** errors under certain situations if
@@ -2529,7 +3826,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
* Description
* This helper is used in programs implementing IR decoding, to
* report a successfully decoded pointer movement.
@@ -2543,7 +3840,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ * long bpf_spin_lock(struct bpf_spin_lock *lock)
* Description
* Acquire a spinlock represented by the pointer *lock*, which is
* stored as part of a value of a map. Taking the lock allows to
@@ -2591,7 +3888,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * long bpf_spin_unlock(struct bpf_spin_lock *lock)
* Description
* Release the *lock* previously locked by a call to
* **bpf_spin_lock**\ (\ *lock*\ ).
@@ -2614,7 +3911,7 @@ union bpf_attr {
* A **struct bpf_tcp_sock** pointer on success, or **NULL** in
* case of failure.
*
- * int bpf_skb_ecn_set_ce(struct sk_buff *skb)
+ * long bpf_skb_ecn_set_ce(struct sk_buff *skb)
* Description
* Set ECN (Explicit Congestion Notification) field of IP header
* to **CE** (Congestion Encountered) if current value is **ECT**
@@ -2651,22 +3948,23 @@ union bpf_attr {
* result is from *reuse*\ **->socks**\ [] using the hash of the
* tuple.
*
- * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
* Description
* Check whether *iph* and *th* contain a valid SYN cookie ACK for
* the listening socket in *sk*.
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains **sizeof**\ (**struct tcphdr**).
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
* error otherwise.
*
- * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
* Description
* Get name of sysctl in /proc/sys/ and copy it into provided by
* program buffer *buf* of size *buf_len*.
@@ -2682,7 +3980,7 @@ union bpf_attr {
* **-E2BIG** if the buffer wasn't big enough (*buf* will contain
* truncated name in this case).
*
- * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
* Description
* Get current value of sysctl as it is presented in /proc/sys
* (incl. newline, etc), and copy it as a string into provided
@@ -2701,7 +3999,7 @@ union bpf_attr {
* **-EINVAL** if current value was unavailable, e.g. because
* sysctl is uninitialized and read returns -EIO for it.
*
- * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
* Description
* Get new value being written by user space to sysctl (before
* the actual write happens) and copy it as a string into
@@ -2718,7 +4016,7 @@ union bpf_attr {
*
* **-EINVAL** if sysctl is being read.
*
- * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
* Description
* Override new value being written by user space to sysctl with
* value provided by program in buffer *buf* of size *buf_len*.
@@ -2735,7 +4033,7 @@ union bpf_attr {
*
* **-EINVAL** if sysctl is being read.
*
- * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
* Description
* Convert the initial part of the string from buffer *buf* of
* size *buf_len* to a long integer according to the given base
@@ -2759,7 +4057,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
* Description
* Convert the initial part of the string from buffer *buf* of
* size *buf_len* to an unsigned long integer according to the
@@ -2782,7 +4080,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
* Description
* Get a bpf-local-storage from a *sk*.
*
@@ -2798,6 +4096,9 @@ union bpf_attr {
* "type". The bpf-local-storage "type" (i.e. the *map*) is
* searched against all bpf-local-storages residing at *sk*.
*
+ * *sk* is a kernel **struct sock** pointer for LSM program.
+ * *sk* is a **struct bpf_sock** pointer for other program types.
+ *
* An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
* used such that a new bpf-local-storage will be
* created if one does not exist. *value* can be used
@@ -2810,15 +4111,16 @@ union bpf_attr {
* **NULL** if not found or there was an error in adding
* a new bpf-local-storage.
*
- * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
* Description
* Delete a bpf-local-storage from a *sk*.
* Return
* 0 on success.
*
* **-ENOENT** if the bpf-local-storage cannot be found.
+ * **-EINVAL** if sk is not a fullsock (e.g. a request_sock).
*
- * int bpf_send_signal(u32 sig)
+ * long bpf_send_signal(u32 sig)
* Description
* Send signal *sig* to the process of the current task.
* The signal may be delivered to any of this process's threads.
@@ -2833,17 +4135,18 @@ union bpf_attr {
*
* **-EAGAIN** if bpf program can try again.
*
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
* Description
* Try to issue a SYN cookie for the packet with corresponding
* IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
*
* *iph* points to the start of the IPv4 or IPv6 header, while
* *iph_len* contains **sizeof**\ (**struct iphdr**) or
- * **sizeof**\ (**struct ip6hdr**).
+ * **sizeof**\ (**struct ipv6hdr**).
*
* *th* points to the start of the TCP header, while *th_len*
- * contains the length of the TCP header.
+ * contains the length of the TCP header with options (at least
+ * **sizeof**\ (**struct tcphdr**)).
* Return
* On success, lower 32 bits hold the generated SYN cookie in
* followed by 16 bits which hold the MSS value for that cookie,
@@ -2859,7 +4162,7 @@ union bpf_attr {
*
* **-EPROTONOSUPPORT** IP packet version is not 4 or 6
*
- * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * long bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
* Description
* Write raw *data* blob into a special BPF perf event held by
* *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -2883,21 +4186,21 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Safely attempt to read *size* bytes from user space address
* *unsafe_ptr* and store the data in *dst*.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Safely attempt to read *size* bytes from kernel space address
* *unsafe_ptr* and store the data in *dst*.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe user address
* *unsafe_ptr* to *dst*. The *size* should include the
@@ -2906,10 +4209,10 @@ union bpf_attr {
* string length is larger than *size*, just *size*-1 bytes are
* copied and the last byte is set to NUL.
*
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
+ * On success, returns the number of bytes that were written,
+ * including the terminal NUL. This makes this helper useful in
+ * tracing programs for reading strings, and more importantly to
+ * get its length at runtime. See the following snippet:
*
* ::
*
@@ -2937,11 +4240,11 @@ union bpf_attr {
* **->mm->env_start**: using this helper and the return value,
* one can quickly iterate at the right offset of the memory area.
* Return
- * On success, the strictly positive length of the string,
+ * On success, the strictly positive length of the output string,
* including the trailing NUL character. On error, a negative
* value.
*
- * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
* to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
@@ -2949,14 +4252,14 @@ union bpf_attr {
* On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
*
- * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
* Description
* Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
* *rcv_nxt* is the ack_seq to be sent out.
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_send_signal_thread(u32 sig)
+ * long bpf_send_signal_thread(u32 sig)
* Description
* Send signal *sig* to the thread corresponding to the current task.
* Return
@@ -2976,7 +4279,7 @@ union bpf_attr {
* Return
* The 64 bit jiffies
*
- * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
* Description
* For an eBPF program attached to a perf event, retrieve the
* branch records (**struct perf_branch_entry**) associated to *ctx*
@@ -2995,7 +4298,7 @@ union bpf_attr {
*
* **-ENOENT** if architecture does not support branch records.
*
- * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
* Description
* Returns 0 on success, values for *pid* and *tgid* as seen from the current
* *namespace* will be returned in *nsdata*.
@@ -3007,7 +4310,7 @@ union bpf_attr {
*
* **-ENOENT** if pidns does not exists for the current task.
*
- * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * long bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
* Description
* Write raw *data* blob into a special BPF perf event held by
* *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -3062,8 +4365,12 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
* Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SCHED_CLS** and
+ * **BPF_PROG_TYPE_SCHED_ACT** programs.
+ *
* Assign the *sk* to the *skb*. When combined with appropriate
* routing configuration to receive the packet towards the socket,
* will cause *skb* to be delivered to the specified socket.
@@ -3086,8 +4393,55 @@ union bpf_attr {
* **-EOPNOTSUPP** if the operation is not supported, for example
* a call from outside of TC ingress.
*
- * **-ESOCKTNOSUPPORT** if the socket type is not supported
- * (reuseport).
+ * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
+ * Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
+ *
+ * Select the *sk* as a result of a socket lookup.
+ *
+ * For the operation to succeed passed socket must be compatible
+ * with the packet description provided by the *ctx* object.
+ *
+ * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must
+ * be an exact match. While IP family (**AF_INET** or
+ * **AF_INET6**) must be compatible, that is IPv6 sockets
+ * that are not v6-only can be selected for IPv4 packets.
+ *
+ * Only TCP listeners and UDP unconnected sockets can be
+ * selected. *sk* can also be NULL to reset any previous
+ * selection.
+ *
+ * *flags* argument can combination of following values:
+ *
+ * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous
+ * socket selection, potentially done by a BPF program
+ * that ran before us.
+ *
+ * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip
+ * load-balancing within reuseport group for the socket
+ * being selected.
+ *
+ * On success *ctx->sk* will point to the selected socket.
+ *
+ * Return
+ * 0 on success, or a negative errno in case of failure.
+ *
+ * * **-EAFNOSUPPORT** if socket family (*sk->family*) is
+ * not compatible with packet family (*ctx->family*).
+ *
+ * * **-EEXIST** if socket has been already selected,
+ * potentially by another program, and
+ * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified.
+ *
+ * * **-EINVAL** if unsupported flags were specified.
+ *
+ * * **-EPROTOTYPE** if socket L4 protocol
+ * (*sk->protocol*) doesn't match packet protocol
+ * (*ctx->protocol*).
+ *
+ * * **-ESOCKTNOSUPPORT** if socket is not in allowed
+ * state (TCP listening or UDP unconnected).
*
* u64 bpf_ktime_get_boot_ns(void)
* Description
@@ -3097,7 +4451,7 @@ union bpf_attr {
* Return
* Current *ktime*.
*
- * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
* Description
* **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
* out the format string.
@@ -3106,7 +4460,7 @@ union bpf_attr {
* arguments. The *data* are a **u64** array and corresponding format string
* values are stored in the array. For strings and pointers where pointees
* are accessed, only the pointer values are stored in the *data* array.
- * The *data_len* is the size of *data* in bytes.
+ * The *data_len* is the size of *data* in bytes - must be a multiple of 8.
*
* Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
* Reading kernel memory may fail due to either invalid address or
@@ -3126,7 +4480,7 @@ union bpf_attr {
*
* **-EOVERFLOW** if an overflow happened: The same object will be tried again.
*
- * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * long bpf_seq_write(struct seq_file *m, const void *data, u32 len)
* Description
* **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
* The *m* represents the seq_file. The *data* and *len* represent the
@@ -3136,11 +4490,11 @@ union bpf_attr {
*
* **-EOVERFLOW** if an overflow happened: The same object will be tried again.
*
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *sk)
* Description
* Return the cgroup v2 id of the socket *sk*.
*
- * *sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ * *sk* must be a non-**NULL** pointer to a socket, e.g. one
* returned from **bpf_sk_lookup_xxx**\ (),
* **bpf_sk_fullsock**\ (), etc. The format of returned id is
* same as in **bpf_skb_cgroup_id**\ ().
@@ -3150,7 +4504,7 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
* Description
* Return id of cgroup v2 that is ancestor of cgroup associated
* with the *sk* at the *ancestor_level*. The root cgroup is at
@@ -3168,19 +4522,27 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
* Description
* Copy *size* bytes from *data* into a ring buffer *ringbuf*.
* If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * An adaptive notification is a notification sent whenever the user-space
+ * process has caught up and consumed all available payloads. In case the user-space
+ * process is still processing a previous payload, then no notification is needed
+ * as it will process the newly added payload automatically.
* Return
* 0 on success, or a negative error in case of failure.
*
* void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
* Description
* Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * *flags* must be 0.
* Return
* Valid pointer with *size* bytes of memory available; NULL,
* otherwise.
@@ -3192,6 +4554,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@@ -3202,6 +4568,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@@ -3222,7 +4592,7 @@ union bpf_attr {
* Return
* Requested value, or 0, if *flags* are not recognized.
*
- * int bpf_csum_level(struct sk_buff *skb, u64 level)
+ * long bpf_csum_level(struct sk_buff *skb, u64 level)
* Description
* Change the skbs checksum level by one layer up or down, or
* reset it entirely to none in order to have the stack perform
@@ -3253,151 +4623,1432 @@ union bpf_attr {
* case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
* is returned or the error code -EACCES in case the skb is not
* subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * Note: the user stack will only be populated if the *task* is
+ * the current task; all other tasks will return -EOPNOTSUPP.
+ * To achieve this, the helper needs *task*, which is a valid
+ * pointer to **struct task_struct**. To store the stacktrace, the
+ * bpf program provides *buf* with a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * The *task* must be the current task.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect buildid+offset instead of ips for user stack,
+ * only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * **bpf_get_task_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
+ *
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ * Description
+ * Load header option. Support reading a particular TCP header
+ * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
+ *
+ * If *flags* is 0, it will search the option from the
+ * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops**
+ * has details on what skb_data contains under different
+ * *skops*\ **->op**.
+ *
+ * The first byte of the *searchby_res* specifies the
+ * kind that it wants to search.
+ *
+ * If the searching kind is an experimental kind
+ * (i.e. 253 or 254 according to RFC6994). It also
+ * needs to specify the "magic" which is either
+ * 2 bytes or 4 bytes. It then also needs to
+ * specify the size of the magic by using
+ * the 2nd byte which is "kind-length" of a TCP
+ * header option and the "kind-length" also
+ * includes the first 2 bytes "kind" and "kind-length"
+ * itself as a normal TCP header option also does.
+ *
+ * For example, to search experimental kind 254 with
+ * 2 byte magic 0xeB9F, the searchby_res should be
+ * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ * To search for the standard window scale option (3),
+ * the *searchby_res* should be [ 3, 0, 0, .... 0 ].
+ * Note, kind-length must be 0 for regular option.
+ *
+ * Searching for No-Op (0) and End-of-Option-List (1) are
+ * not supported.
+ *
+ * *len* must be at least 2 bytes which is the minimal size
+ * of a header option.
+ *
+ * Supported flags:
+ *
+ * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ * saved_syn packet or the just-received syn packet.
+ *
+ * Return
+ * > 0 when found, the header option is copied to *searchby_res*.
+ * The return value is the total length copied. On failure, a
+ * negative error code is returned:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOMSG** if the option is not found.
+ *
+ * **-ENOENT** if no syn packet is available when
+ * **BPF_LOAD_HDR_OPT_TCP_SYN** is used.
+ *
+ * **-ENOSPC** if there is not enough space. Only *len* number of
+ * bytes are copied.
+ *
+ * **-EFAULT** on failure to parse the header options in the
+ * packet.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ * Description
+ * Store header option. The data will be copied
+ * from buffer *from* with length *len* to the TCP header.
+ *
+ * The buffer *from* should have the whole option that
+ * includes the kind, kind-length, and the actual
+ * option data. The *len* must be at least kind-length
+ * long. The kind-length does not have to be 4 byte
+ * aligned. The kernel will take care of the padding
+ * and setting the 4 bytes aligned value to th->doff.
+ *
+ * This helper will check for duplicated option
+ * by searching the same option in the outgoing skb.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** If param is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ * Nothing has been written
+ *
+ * **-EEXIST** if the option already exists.
+ *
+ * **-EFAULT** on failure to parse the existing header options.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ * Description
+ * Reserve *len* bytes for the bpf header option. The
+ * space will be used by **bpf_store_hdr_opt**\ () later in
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * If **bpf_reserve_hdr_opt**\ () is called multiple times,
+ * the total number of bytes will be reserved.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from an *inode*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *inode* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ * helper enforces the key must be an inode and the map must also
+ * be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *inode* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *inode*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ * Description
+ * Delete a bpf_local_storage from an *inode*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(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
+ * returned in the provided buffer *buf* of size *sz* and
+ * is zero terminated.
+ *
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* and store
+ * the data in *dst*. This is a wrapper of **copy_from_user**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ * Description
+ * Use BTF to store a string representation of *ptr*->ptr in *str*,
+ * using *ptr*->type_id. This value should specify the type
+ * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ * can be used to look up vmlinux BTF type ids. Traversing the
+ * data structure using BTF, the type information and values are
+ * stored in the first *str_size* - 1 bytes of *str*. Safe copy of
+ * the pointer data is carried out to avoid kernel crashes during
+ * operation. Smaller types can use string space on the stack;
+ * larger programs can use map data to store the string
+ * representation.
+ *
+ * The string can be subsequently shared with userspace via
+ * bpf_perf_event_output() or ring buffer interfaces.
+ * bpf_trace_printk() is to be avoided as it places too small
+ * a limit on string size to be useful.
+ *
+ * *flags* is a combination of
+ *
+ * **BTF_F_COMPACT**
+ * no formatting around type information
+ * **BTF_F_NONAME**
+ * no struct/union member names/types
+ * **BTF_F_PTR_RAW**
+ * show raw (unobfuscated) pointer values;
+ * equivalent to printk specifier %px.
+ * **BTF_F_ZERO**
+ * show zero-valued struct/union members; they
+ * are not displayed by default
+ *
+ * Return
+ * The number of bytes that were written (or would have been
+ * written if output had to be truncated due to string size),
+ * or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ * Description
+ * Use BTF to write to seq_write a string representation of
+ * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ * *flags* are identical to those used for bpf_snprintf_btf.
+ * Return
+ * 0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * See **bpf_get_cgroup_classid**\ () for the main description.
+ * This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * associated socket instead of the current process.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*
+ * and fill in L2 addresses from neighboring subsystem. This helper
+ * is somewhat similar to **bpf_redirect**\ (), except that it
+ * populates L2 addresses as well, meaning, internally, the helper
+ * relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * The helper will perform a FIB lookup based on the skb's
+ * networking header to get the address of the next hop, unless
+ * this is supplied by the caller in the *params* argument. The
+ * *plen* argument indicates the len of *params* and should be set
+ * to 0 if *params* is NULL.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types, and enabled
+ * for IPv4 and IPv6 protocols.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on *cpu*. A ksym is an
+ * extern variable decorated with '__ksym'. For ksym, there is a
+ * global var (either static or global) defined of the same name
+ * in the kernel. The ksym is percpu if the global var is percpu.
+ * The returned pointer points to the global percpu var on *cpu*.
+ *
+ * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ * kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ * happens if *cpu* is larger than nr_cpu_ids. The caller of
+ * bpf_per_cpu_ptr() must check the returned value.
+ * Return
+ * A pointer pointing to the kernel percpu variable on *cpu*, or
+ * NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on this cpu. See the
+ * description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ * never return NULL.
+ * Return
+ * A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * *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
+ * peer device must reside in a different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *task*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *task* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ * helper enforces the key must be a task_struct and the map must also
+ * be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *task* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *task*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ * Description
+ * Delete a bpf_local_storage from a *task*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ * Description
+ * Return a BTF pointer to the "current" task.
+ * This pointer can also be used in helpers that accept an
+ * *ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ * Return
+ * Pointer to the current task.
+ *
+ * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags)
+ * Description
+ * Set or clear certain options on *bprm*:
+ *
+ * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit
+ * which sets the **AT_SECURE** auxv for glibc. The bit
+ * is cleared if the flag is not specified.
+ * Return
+ * **-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * Description
+ * Return a coarse-grained version of the time elapsed since
+ * system boot, in nanoseconds. Does not include time the system
+ * was suspended.
+ *
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
+ * Description
+ * Returns the stored IMA hash of the *inode* (if it's available).
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * struct socket *bpf_sock_from_file(struct file *file)
+ * Description
+ * If the given file represents a socket, returns the associated
+ * socket.
+ * Return
+ * A pointer to a struct socket on success or NULL if the file is
+ * not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+ * Check packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing a *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, which is why it is not considered
+ * a failure. Other BPF helpers are needed for performing the
+ * planned size change; therefore the responsibility for catching
+ * a negative packet size belongs in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * On input *mtu_len* must be a valid pointer, else verifier will
+ * reject BPF program. If the value *mtu_len* is initialized to
+ * zero then the ctx packet size is use. When value *mtu_len* is
+ * provided as input this specify the L3 length that the MTU check
+ * is done against. Remember XDP and TC length operate at L2, but
+ * this value is L3 as this correlate to MTU and IP-header tot_len
+ * values which are L3 (similar behavior as bpf_fib_lookup).
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TC length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
+ * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For each element in **map**, call **callback_fn** function with
+ * **map**, **callback_ctx** and other map-specific parameters.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0.
+ *
+ * The following are a list of supported map types and their
+ * respective expected callback signatures:
+ *
+ * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH,
+ * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY
+ *
+ * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx);
+ *
+ * For per_cpu maps, the map_value is the value on the cpu where the
+ * bpf_prog is running.
+ *
+ * If **callback_fn** return 0, the helper will continue to the next
+ * element. If return value is 1, the helper will skip the rest of
+ * elements and return. Other return values are not used now.
+ *
+ * Return
+ * The number of traversed map elements for success, **-EINVAL** for
+ * invalid **flags**.
+ *
+ * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
+ * Description
+ * Outputs a string into the **str** buffer of size **str_size**
+ * based on a format string stored in a read-only map pointed by
+ * **fmt**.
+ *
+ * Each format specifier in **fmt** corresponds to one u64 element
+ * in the **data** array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data*
+ * array. The *data_len* is the size of *data* in bytes - must be
+ * a multiple of 8.
+ *
+ * Formats **%s** and **%p{i,I}{4,6}** require to read kernel
+ * memory. Reading kernel memory may fail due to either invalid
+ * address or valid address but requiring a major memory fault. If
+ * reading kernel memory fails, the string for **%s** will be an
+ * empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
+ * Not returning error to bpf program is consistent with what
+ * **bpf_trace_printk**\ () does for now.
+ *
+ * Return
+ * The strictly positive length of the formatted string, including
+ * the trailing zero character. If the return value is greater than
+ * **str_size**, **str** contains a truncated string, guaranteed to
+ * be zero-terminated except when **str_size** is 0.
+ *
+ * Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * Description
+ * Execute bpf syscall with given arguments.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * Description
+ * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * Return
+ * Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * Description
+ * Execute close syscall for given FD.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags)
+ * Description
+ * Initialize the timer.
+ * First 4 bits of *flags* specify clockid.
+ * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
+ * All other bits of *flags* are reserved.
+ * The verifier will reject the program if *timer* is not from
+ * the same *map*.
+ * Return
+ * 0 on success.
+ * **-EBUSY** if *timer* is already initialized.
+ * **-EINVAL** if invalid *flags* are passed.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn)
+ * Description
+ * Configure the timer to call *callback_fn* static function.
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags)
+ * Description
+ * Set timer expiration N nanoseconds from the current time. The
+ * configured callback will be invoked in soft irq context on some cpu
+ * and will not repeat unless another bpf_timer_start() is made.
+ * In such case the next invocation can migrate to a different cpu.
+ * Since struct bpf_timer is a field inside map element the map
+ * owns the timer. The bpf_timer_set_callback() will increment refcnt
+ * of BPF program to make sure that callback_fn code stays valid.
+ * When user space reference to a map reaches zero all timers
+ * in a map are cancelled and corresponding program's refcnts are
+ * decremented. This is done to make sure that Ctrl-C of a user
+ * process doesn't leave any timers running. If map is pinned in
+ * bpffs the callback_fn can re-arm itself indefinitely.
+ * bpf_map_update/delete_elem() helpers and user space sys_bpf commands
+ * cancel and free the timer in the given map element.
+ * The map can contain timers that invoke callback_fn-s from different
+ * programs. The same callback_fn can serve different timers from
+ * different maps if key/value layout matches across maps.
+ * Every bpf_timer_set_callback() can have different callback_fn.
+ *
+ * *flags* can be one of:
+ *
+ * **BPF_F_TIMER_ABS**
+ * Start the timer in absolute expire value instead of the
+ * default relative one.
+ * **BPF_F_TIMER_CPU_PIN**
+ * Timer will be pinned to the CPU of the caller.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
+ * or invalid *flags* are passed.
+ *
+ * long bpf_timer_cancel(struct bpf_timer *timer)
+ * Description
+ * Cancel the timer and wait for callback_fn to finish if it was running.
+ * Return
+ * 0 if the timer was not active.
+ * 1 if the timer was active.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
+ * own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * Description
+ * Get address of the traced function (for tracing and kprobe programs).
+ *
+ * When called for kprobe program attached as uprobe it returns
+ * probe address for both entry and return uprobe.
+ *
+ * Return
+ * Address of the traced function for kprobe.
+ * 0 for kprobes placed within the function (not at the entry).
+ * Address of the probe for uprobe and return uprobe.
+ *
+ * u64 bpf_get_attach_cookie(void *ctx)
+ * Description
+ * Get bpf_cookie value provided (optionally) during the program
+ * attachment. It might be different for each individual
+ * attachment, even if BPF program itself is the same.
+ * Expects BPF program context *ctx* as a first argument.
+ *
+ * Supported for the following program types:
+ * - kprobe/uprobe;
+ * - tracepoint;
+ * - perf_event.
+ * Return
+ * Value specified by user at BPF link creation/attachment time
+ * or 0, if it was not specified.
+ *
+ * long bpf_task_pt_regs(struct task_struct *task)
+ * Description
+ * Get the struct pt_regs associated with **task**.
+ * Return
+ * A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ * Description
+ * Get branch trace from hardware engines like Intel LBR. The
+ * hardware engine is stopped shortly after the helper is
+ * called. Therefore, the user need to filter branch entries
+ * based on the actual use case. To capture branch trace
+ * before the trigger point of the BPF program, the helper
+ * should be called at the beginning of the BPF program.
+ *
+ * The data is stored as struct perf_branch_entry into output
+ * buffer *entries*. *size* is the size of *entries* in bytes.
+ * *flags* is reserved for now and must be zero.
+ *
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ * to format and can handle more format args as a result.
+ *
+ * Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * struct unix_sock *bpf_skc_to_unix_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *unix_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res)
+ * Description
+ * Get the address of a kernel symbol, returned in *res*. *res* is
+ * set to 0 if the symbol is not found.
+ * Return
+ * On success, zero. On error, a negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-EINVAL** if string *name* is not the same size as *name_sz*.
+ *
+ * **-ENOENT** if symbol is not found.
+ *
+ * **-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * Find vma of *task* that contains *addr*, call *callback_fn*
+ * function with *task*, *vma*, and *callback_ctx*.
+ * The *callback_fn* should be a static function and
+ * the *callback_ctx* should be a pointer to the stack.
+ * The *flags* is used to control certain aspects of the helper.
+ * Currently, the *flags* must be 0.
+ *
+ * The expected callback signature is
+ *
+ * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ * Return
+ * 0 on success.
+ * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ * **-EBUSY** if failed to try lock mmap_lock.
+ * **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For **nr_loops**, call **callback_fn** function
+ * with **callback_ctx** as the context parameter.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0. Currently, nr_loops is
+ * limited to 1 << 23 (~8 million) loops.
+ *
+ * long (\*callback_fn)(u64 index, void \*ctx);
+ *
+ * where **index** is the current index in the loop. The index
+ * is zero-indexed.
+ *
+ * If **callback_fn** returns 0, the helper will continue to the next
+ * loop. If return value is 1, the helper will skip the rest of
+ * the loops and return. Other return values are not used now,
+ * and will be rejected by the verifier.
+ *
+ * Return
+ * The number of loops performed, **-EINVAL** for invalid **flags**,
+ * **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument register (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= argument register count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of registers of the traced function (for tracing programs) where
+ * function arguments are stored in these registers.
+ *
+ * Return
+ * The number of argument registers of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ * Return
+ * The BPF program's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ *
+ * Note that there is the following corner case where the program exports an error
+ * via bpf_set_retval but signals success via 'return 1':
+ *
+ * bpf_set_retval(-EPERM);
+ * return 1;
+ *
+ * In this case, the BPF program's return value will use helper's -EPERM. This
+ * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
+ *
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ * Description
+ * Get the total size of a given xdp buff (linear and paged area)
+ * Return
+ * The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * This helper is provided as an easy way to load data from a
+ * xdp buffer. It can be used to load *len* bytes from *offset* from
+ * the frame associated to *xdp_md*, into the buffer pointed by
+ * *buf*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * Store *len* bytes from buffer *buf* into the frame
+ * associated to *xdp_md*, at *offset*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ * address space, and stores the data in *dst*. *flags* is not
+ * used yet and is provided for future extensibility. This helper
+ * can only be used by sleepable programs.
+ * Return
+ * 0 on success, or a negative error in case of failure. On error
+ * *dst* buffer is zeroed out.
+ *
+ * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type)
+ * Description
+ * Change the __sk_buff->tstamp_type to *tstamp_type*
+ * and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ * If there is no need to change the __sk_buff->tstamp_type,
+ * the tstamp value can be directly written to __sk_buff->tstamp
+ * instead.
+ *
+ * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ * will be kept during bpf_redirect_*(). A non zero
+ * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ * *tstamp_type*.
+ *
+ * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ * with a zero *tstamp*.
+ *
+ * Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ * This function is most useful when it needs to set a
+ * mono delivery time to __sk_buff->tstamp and then
+ * bpf_redirect_*() to the egress of an iface. For example,
+ * changing the (rcv) timestamp in __sk_buff->tstamp at
+ * ingress to a mono delivery time and then bpf_redirect_*()
+ * to sch_fq@phy-dev.
+ * Return
+ * 0 on success.
+ * **-EINVAL** for invalid input
+ * **-EOPNOTSUPP** for unsupported protocol
+ *
+ * long bpf_ima_file_hash(struct file *file, void *dst, u32 size)
+ * Description
+ * Returns a calculated IMA hash of the *file*.
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *dst, void *ptr)
+ * Description
+ * 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
+ * corresponding release function, or moved into a BPF map before
+ * program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * Description
+ * Perform a lookup in *percpu map* for an entry associated to
+ * *key* on *cpu*.
+ * Return
+ * Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Get a dynptr to local memory *data*.
+ *
+ * *data* must be a ptr to a map value.
+ * The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * -EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * through the dynptr interface. *flags* must be 0.
+ *
+ * Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * reservation fails. This is enforced by the verifier.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*,
+ * through the dynptr interface. This is a no-op if the dynptr is
+ * invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_submit'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample through the dynptr
+ * interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_discard'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
+ * Description
+ * Read *len* bytes from *src* into *dst*, starting from *offset*
+ * into *src*.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * *flags* is not 0.
+ *
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * Description
+ * Write *len* bytes from *src* into *dst*, starting from *offset*
+ * into *dst*.
+ *
+ * *flags* must be 0 except for skb-type dynptrs.
+ *
+ * For skb-type dynptrs:
+ * * All data slices of the dynptr are automatically
+ * invalidated after **bpf_dynptr_write**\ (). This is
+ * because writing may pull the skb and change the
+ * underlying packet buffer.
+ *
+ * * For *flags*, please see the flags accepted by
+ * **bpf_skb_store_bytes**\ ().
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
+ * other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
+ *
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * Description
+ * Get a pointer to the underlying dynptr data.
+ *
+ * *len* must be a statically known value. The returned data slice
+ * is invalidated whenever the dynptr is invalidated.
+ *
+ * skb and xdp type dynptrs may not use bpf_dynptr_data. They should
+ * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
+ * Return
+ * Pointer to the underlying dynptr data, NULL if the dynptr is
+ * read-only, if the dynptr is invalid, or if the offset and length
+ * is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv4/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv6/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ * Description
+ * A nonsettable system-wide clock derived from wall-clock time but
+ * ignoring leap seconds. This clock does not experience
+ * discontinuities and backwards jumps caused by NTP inserting leap
+ * seconds as CLOCK_REALTIME does.
+ *
+ * See: **clock_gettime**\ (**CLOCK_TAI**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ * Description
+ * Drain samples from the specified user ring buffer, and invoke
+ * the provided callback for each such sample:
+ *
+ * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * If **callback_fn** returns 0, the helper will continue to try
+ * and drain the next sample, up to a maximum of
+ * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * the helper will skip the rest of the samples and return. Other
+ * return values are not used now, and will be rejected by the
+ * verifier.
+ * Return
+ * The number of drained samples if no error was encountered while
+ * draining samples, or 0 if no samples were present in the ring
+ * buffer. If a user-space producer was epoll-waiting on this map,
+ * and at least one sample was drained, they will receive an event
+ * notification notifying them of available space in the ring
+ * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * function, no wakeup notification will be sent. If the
+ * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * be sent even if no sample was drained.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EBUSY** if the ring buffer is contended, and another calling
+ * context was concurrently draining the ring buffer.
+ *
+ * **-EINVAL** if user-space is not properly tracking the ring
+ * buffer due to the producer position not being aligned to 8
+ * bytes, a sample not being aligned to 8 bytes, or the producer
+ * position not matching the advertised length of a sample.
+ *
+ * **-E2BIG** if user-space has tried to publish a sample which is
+ * larger than the size of the ring buffer, or which cannot fit
+ * within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *cgroup*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *cgroup* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ * helper enforces the key must be a cgroup struct and the map must also
+ * be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ * In reality, the local-storage value is embedded directly inside of the
+ * *cgroup* object itself, rather than being located in the
+ * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ * queried for some *map* on a *cgroup* object, the kernel will perform an
+ * O(n) iteration over all of the live local-storage values for that
+ * *cgroup* object until the local-storage value for the *map* is found.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ * Description
+ * Delete a bpf_local_storage from a *cgroup*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
*/
-#define __BPF_FUNC_MAPPER(FN) \
- FN(unspec), \
- FN(map_lookup_elem), \
- FN(map_update_elem), \
- FN(map_delete_elem), \
- FN(probe_read), \
- FN(ktime_get_ns), \
- FN(trace_printk), \
- FN(get_prandom_u32), \
- FN(get_smp_processor_id), \
- FN(skb_store_bytes), \
- FN(l3_csum_replace), \
- FN(l4_csum_replace), \
- FN(tail_call), \
- FN(clone_redirect), \
- FN(get_current_pid_tgid), \
- FN(get_current_uid_gid), \
- FN(get_current_comm), \
- FN(get_cgroup_classid), \
- FN(skb_vlan_push), \
- FN(skb_vlan_pop), \
- FN(skb_get_tunnel_key), \
- FN(skb_set_tunnel_key), \
- FN(perf_event_read), \
- FN(redirect), \
- FN(get_route_realm), \
- FN(perf_event_output), \
- FN(skb_load_bytes), \
- FN(get_stackid), \
- FN(csum_diff), \
- FN(skb_get_tunnel_opt), \
- FN(skb_set_tunnel_opt), \
- FN(skb_change_proto), \
- FN(skb_change_type), \
- FN(skb_under_cgroup), \
- FN(get_hash_recalc), \
- FN(get_current_task), \
- FN(probe_write_user), \
- FN(current_task_under_cgroup), \
- FN(skb_change_tail), \
- FN(skb_pull_data), \
- FN(csum_update), \
- FN(set_hash_invalid), \
- FN(get_numa_node_id), \
- FN(skb_change_head), \
- FN(xdp_adjust_head), \
- FN(probe_read_str), \
- FN(get_socket_cookie), \
- FN(get_socket_uid), \
- FN(set_hash), \
- FN(setsockopt), \
- FN(skb_adjust_room), \
- FN(redirect_map), \
- FN(sk_redirect_map), \
- FN(sock_map_update), \
- FN(xdp_adjust_meta), \
- FN(perf_event_read_value), \
- FN(perf_prog_read_value), \
- FN(getsockopt), \
- FN(override_return), \
- FN(sock_ops_cb_flags_set), \
- FN(msg_redirect_map), \
- FN(msg_apply_bytes), \
- FN(msg_cork_bytes), \
- FN(msg_pull_data), \
- FN(bind), \
- FN(xdp_adjust_tail), \
- FN(skb_get_xfrm_state), \
- FN(get_stack), \
- FN(skb_load_bytes_relative), \
- FN(fib_lookup), \
- FN(sock_hash_update), \
- FN(msg_redirect_hash), \
- FN(sk_redirect_hash), \
- FN(lwt_push_encap), \
- FN(lwt_seg6_store_bytes), \
- FN(lwt_seg6_adjust_srh), \
- FN(lwt_seg6_action), \
- FN(rc_repeat), \
- FN(rc_keydown), \
- FN(skb_cgroup_id), \
- FN(get_current_cgroup_id), \
- FN(get_local_storage), \
- FN(sk_select_reuseport), \
- FN(skb_ancestor_cgroup_id), \
- FN(sk_lookup_tcp), \
- FN(sk_lookup_udp), \
- FN(sk_release), \
- FN(map_push_elem), \
- FN(map_pop_elem), \
- FN(map_peek_elem), \
- FN(msg_push_data), \
- FN(msg_pop_data), \
- FN(rc_pointer_rel), \
- FN(spin_lock), \
- FN(spin_unlock), \
- FN(sk_fullsock), \
- FN(tcp_sock), \
- FN(skb_ecn_set_ce), \
- FN(get_listener_sock), \
- FN(skc_lookup_tcp), \
- FN(tcp_check_syncookie), \
- FN(sysctl_get_name), \
- FN(sysctl_get_current_value), \
- FN(sysctl_get_new_value), \
- FN(sysctl_set_new_value), \
- FN(strtol), \
- FN(strtoul), \
- FN(sk_storage_get), \
- FN(sk_storage_delete), \
- FN(send_signal), \
- FN(tcp_gen_syncookie), \
- FN(skb_output), \
- FN(probe_read_user), \
- FN(probe_read_kernel), \
- FN(probe_read_user_str), \
- FN(probe_read_kernel_str), \
- FN(tcp_send_ack), \
- FN(send_signal_thread), \
- FN(jiffies64), \
- FN(read_branch_records), \
- FN(get_ns_current_pid_tgid), \
- FN(xdp_output), \
- FN(get_netns_cookie), \
- FN(get_current_ancestor_cgroup_id), \
- FN(sk_assign), \
- FN(ktime_get_boot_ns), \
- FN(seq_printf), \
- FN(seq_write), \
- FN(sk_cgroup_id), \
- FN(sk_ancestor_cgroup_id), \
- FN(ringbuf_output), \
- FN(ringbuf_reserve), \
- FN(ringbuf_submit), \
- FN(ringbuf_discard), \
- FN(ringbuf_query), \
- FN(csum_level),
+#define ___BPF_FUNC_MAPPER(FN, ctx...) \
+ FN(unspec, 0, ##ctx) \
+ FN(map_lookup_elem, 1, ##ctx) \
+ FN(map_update_elem, 2, ##ctx) \
+ FN(map_delete_elem, 3, ##ctx) \
+ FN(probe_read, 4, ##ctx) \
+ FN(ktime_get_ns, 5, ##ctx) \
+ FN(trace_printk, 6, ##ctx) \
+ FN(get_prandom_u32, 7, ##ctx) \
+ FN(get_smp_processor_id, 8, ##ctx) \
+ FN(skb_store_bytes, 9, ##ctx) \
+ FN(l3_csum_replace, 10, ##ctx) \
+ FN(l4_csum_replace, 11, ##ctx) \
+ FN(tail_call, 12, ##ctx) \
+ FN(clone_redirect, 13, ##ctx) \
+ FN(get_current_pid_tgid, 14, ##ctx) \
+ FN(get_current_uid_gid, 15, ##ctx) \
+ FN(get_current_comm, 16, ##ctx) \
+ FN(get_cgroup_classid, 17, ##ctx) \
+ FN(skb_vlan_push, 18, ##ctx) \
+ FN(skb_vlan_pop, 19, ##ctx) \
+ FN(skb_get_tunnel_key, 20, ##ctx) \
+ FN(skb_set_tunnel_key, 21, ##ctx) \
+ FN(perf_event_read, 22, ##ctx) \
+ FN(redirect, 23, ##ctx) \
+ FN(get_route_realm, 24, ##ctx) \
+ FN(perf_event_output, 25, ##ctx) \
+ FN(skb_load_bytes, 26, ##ctx) \
+ FN(get_stackid, 27, ##ctx) \
+ FN(csum_diff, 28, ##ctx) \
+ FN(skb_get_tunnel_opt, 29, ##ctx) \
+ FN(skb_set_tunnel_opt, 30, ##ctx) \
+ FN(skb_change_proto, 31, ##ctx) \
+ FN(skb_change_type, 32, ##ctx) \
+ FN(skb_under_cgroup, 33, ##ctx) \
+ FN(get_hash_recalc, 34, ##ctx) \
+ FN(get_current_task, 35, ##ctx) \
+ FN(probe_write_user, 36, ##ctx) \
+ FN(current_task_under_cgroup, 37, ##ctx) \
+ FN(skb_change_tail, 38, ##ctx) \
+ FN(skb_pull_data, 39, ##ctx) \
+ FN(csum_update, 40, ##ctx) \
+ FN(set_hash_invalid, 41, ##ctx) \
+ FN(get_numa_node_id, 42, ##ctx) \
+ FN(skb_change_head, 43, ##ctx) \
+ FN(xdp_adjust_head, 44, ##ctx) \
+ FN(probe_read_str, 45, ##ctx) \
+ FN(get_socket_cookie, 46, ##ctx) \
+ FN(get_socket_uid, 47, ##ctx) \
+ FN(set_hash, 48, ##ctx) \
+ FN(setsockopt, 49, ##ctx) \
+ FN(skb_adjust_room, 50, ##ctx) \
+ FN(redirect_map, 51, ##ctx) \
+ FN(sk_redirect_map, 52, ##ctx) \
+ FN(sock_map_update, 53, ##ctx) \
+ FN(xdp_adjust_meta, 54, ##ctx) \
+ FN(perf_event_read_value, 55, ##ctx) \
+ FN(perf_prog_read_value, 56, ##ctx) \
+ FN(getsockopt, 57, ##ctx) \
+ FN(override_return, 58, ##ctx) \
+ FN(sock_ops_cb_flags_set, 59, ##ctx) \
+ FN(msg_redirect_map, 60, ##ctx) \
+ FN(msg_apply_bytes, 61, ##ctx) \
+ FN(msg_cork_bytes, 62, ##ctx) \
+ FN(msg_pull_data, 63, ##ctx) \
+ FN(bind, 64, ##ctx) \
+ FN(xdp_adjust_tail, 65, ##ctx) \
+ FN(skb_get_xfrm_state, 66, ##ctx) \
+ FN(get_stack, 67, ##ctx) \
+ FN(skb_load_bytes_relative, 68, ##ctx) \
+ FN(fib_lookup, 69, ##ctx) \
+ FN(sock_hash_update, 70, ##ctx) \
+ FN(msg_redirect_hash, 71, ##ctx) \
+ FN(sk_redirect_hash, 72, ##ctx) \
+ FN(lwt_push_encap, 73, ##ctx) \
+ FN(lwt_seg6_store_bytes, 74, ##ctx) \
+ FN(lwt_seg6_adjust_srh, 75, ##ctx) \
+ FN(lwt_seg6_action, 76, ##ctx) \
+ FN(rc_repeat, 77, ##ctx) \
+ FN(rc_keydown, 78, ##ctx) \
+ FN(skb_cgroup_id, 79, ##ctx) \
+ FN(get_current_cgroup_id, 80, ##ctx) \
+ FN(get_local_storage, 81, ##ctx) \
+ FN(sk_select_reuseport, 82, ##ctx) \
+ FN(skb_ancestor_cgroup_id, 83, ##ctx) \
+ FN(sk_lookup_tcp, 84, ##ctx) \
+ FN(sk_lookup_udp, 85, ##ctx) \
+ FN(sk_release, 86, ##ctx) \
+ FN(map_push_elem, 87, ##ctx) \
+ FN(map_pop_elem, 88, ##ctx) \
+ FN(map_peek_elem, 89, ##ctx) \
+ FN(msg_push_data, 90, ##ctx) \
+ FN(msg_pop_data, 91, ##ctx) \
+ FN(rc_pointer_rel, 92, ##ctx) \
+ FN(spin_lock, 93, ##ctx) \
+ FN(spin_unlock, 94, ##ctx) \
+ FN(sk_fullsock, 95, ##ctx) \
+ FN(tcp_sock, 96, ##ctx) \
+ FN(skb_ecn_set_ce, 97, ##ctx) \
+ FN(get_listener_sock, 98, ##ctx) \
+ FN(skc_lookup_tcp, 99, ##ctx) \
+ FN(tcp_check_syncookie, 100, ##ctx) \
+ FN(sysctl_get_name, 101, ##ctx) \
+ FN(sysctl_get_current_value, 102, ##ctx) \
+ FN(sysctl_get_new_value, 103, ##ctx) \
+ FN(sysctl_set_new_value, 104, ##ctx) \
+ FN(strtol, 105, ##ctx) \
+ FN(strtoul, 106, ##ctx) \
+ FN(sk_storage_get, 107, ##ctx) \
+ FN(sk_storage_delete, 108, ##ctx) \
+ FN(send_signal, 109, ##ctx) \
+ FN(tcp_gen_syncookie, 110, ##ctx) \
+ FN(skb_output, 111, ##ctx) \
+ FN(probe_read_user, 112, ##ctx) \
+ FN(probe_read_kernel, 113, ##ctx) \
+ FN(probe_read_user_str, 114, ##ctx) \
+ FN(probe_read_kernel_str, 115, ##ctx) \
+ FN(tcp_send_ack, 116, ##ctx) \
+ FN(send_signal_thread, 117, ##ctx) \
+ FN(jiffies64, 118, ##ctx) \
+ FN(read_branch_records, 119, ##ctx) \
+ FN(get_ns_current_pid_tgid, 120, ##ctx) \
+ FN(xdp_output, 121, ##ctx) \
+ FN(get_netns_cookie, 122, ##ctx) \
+ FN(get_current_ancestor_cgroup_id, 123, ##ctx) \
+ FN(sk_assign, 124, ##ctx) \
+ FN(ktime_get_boot_ns, 125, ##ctx) \
+ FN(seq_printf, 126, ##ctx) \
+ FN(seq_write, 127, ##ctx) \
+ FN(sk_cgroup_id, 128, ##ctx) \
+ FN(sk_ancestor_cgroup_id, 129, ##ctx) \
+ FN(ringbuf_output, 130, ##ctx) \
+ FN(ringbuf_reserve, 131, ##ctx) \
+ FN(ringbuf_submit, 132, ##ctx) \
+ FN(ringbuf_discard, 133, ##ctx) \
+ FN(ringbuf_query, 134, ##ctx) \
+ FN(csum_level, 135, ##ctx) \
+ FN(skc_to_tcp6_sock, 136, ##ctx) \
+ FN(skc_to_tcp_sock, 137, ##ctx) \
+ FN(skc_to_tcp_timewait_sock, 138, ##ctx) \
+ FN(skc_to_tcp_request_sock, 139, ##ctx) \
+ FN(skc_to_udp6_sock, 140, ##ctx) \
+ FN(get_task_stack, 141, ##ctx) \
+ FN(load_hdr_opt, 142, ##ctx) \
+ FN(store_hdr_opt, 143, ##ctx) \
+ FN(reserve_hdr_opt, 144, ##ctx) \
+ FN(inode_storage_get, 145, ##ctx) \
+ FN(inode_storage_delete, 146, ##ctx) \
+ FN(d_path, 147, ##ctx) \
+ FN(copy_from_user, 148, ##ctx) \
+ FN(snprintf_btf, 149, ##ctx) \
+ FN(seq_printf_btf, 150, ##ctx) \
+ FN(skb_cgroup_classid, 151, ##ctx) \
+ FN(redirect_neigh, 152, ##ctx) \
+ FN(per_cpu_ptr, 153, ##ctx) \
+ FN(this_cpu_ptr, 154, ##ctx) \
+ FN(redirect_peer, 155, ##ctx) \
+ FN(task_storage_get, 156, ##ctx) \
+ FN(task_storage_delete, 157, ##ctx) \
+ FN(get_current_task_btf, 158, ##ctx) \
+ FN(bprm_opts_set, 159, ##ctx) \
+ FN(ktime_get_coarse_ns, 160, ##ctx) \
+ FN(ima_inode_hash, 161, ##ctx) \
+ FN(sock_from_file, 162, ##ctx) \
+ FN(check_mtu, 163, ##ctx) \
+ FN(for_each_map_elem, 164, ##ctx) \
+ FN(snprintf, 165, ##ctx) \
+ FN(sys_bpf, 166, ##ctx) \
+ FN(btf_find_by_name_kind, 167, ##ctx) \
+ FN(sys_close, 168, ##ctx) \
+ FN(timer_init, 169, ##ctx) \
+ FN(timer_set_callback, 170, ##ctx) \
+ FN(timer_start, 171, ##ctx) \
+ FN(timer_cancel, 172, ##ctx) \
+ FN(get_func_ip, 173, ##ctx) \
+ FN(get_attach_cookie, 174, ##ctx) \
+ FN(task_pt_regs, 175, ##ctx) \
+ FN(get_branch_snapshot, 176, ##ctx) \
+ FN(trace_vprintk, 177, ##ctx) \
+ FN(skc_to_unix_sock, 178, ##ctx) \
+ FN(kallsyms_lookup_name, 179, ##ctx) \
+ FN(find_vma, 180, ##ctx) \
+ FN(loop, 181, ##ctx) \
+ FN(strncmp, 182, ##ctx) \
+ FN(get_func_arg, 183, ##ctx) \
+ FN(get_func_ret, 184, ##ctx) \
+ FN(get_func_arg_cnt, 185, ##ctx) \
+ FN(get_retval, 186, ##ctx) \
+ FN(set_retval, 187, ##ctx) \
+ FN(xdp_get_buff_len, 188, ##ctx) \
+ FN(xdp_load_bytes, 189, ##ctx) \
+ FN(xdp_store_bytes, 190, ##ctx) \
+ FN(copy_from_user_task, 191, ##ctx) \
+ FN(skb_set_tstamp, 192, ##ctx) \
+ FN(ima_file_hash, 193, ##ctx) \
+ FN(kptr_xchg, 194, ##ctx) \
+ FN(map_lookup_percpu_elem, 195, ##ctx) \
+ FN(skc_to_mptcp_sock, 196, ##ctx) \
+ FN(dynptr_from_mem, 197, ##ctx) \
+ FN(ringbuf_reserve_dynptr, 198, ##ctx) \
+ FN(ringbuf_submit_dynptr, 199, ##ctx) \
+ FN(ringbuf_discard_dynptr, 200, ##ctx) \
+ FN(dynptr_read, 201, ##ctx) \
+ FN(dynptr_write, 202, ##ctx) \
+ FN(dynptr_data, 203, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \
+ FN(ktime_get_tai_ns, 208, ##ctx) \
+ FN(user_ringbuf_drain, 209, ##ctx) \
+ FN(cgrp_storage_get, 210, ##ctx) \
+ FN(cgrp_storage_delete, 211, ##ctx) \
+ /* 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
+ */
+#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name),
+#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN)
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
*/
-#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
+#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y,
enum bpf_func_id {
- __BPF_FUNC_MAPPER(__BPF_ENUM_FN)
+ ___BPF_FUNC_MAPPER(__BPF_ENUM_FN)
__BPF_FUNC_MAX_ID,
};
#undef __BPF_ENUM_FN
@@ -3422,11 +6073,7 @@ 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. */
@@ -3450,6 +6097,12 @@ enum {
BPF_F_ZERO_CSUM_TX = (1ULL << 1),
BPF_F_DONT_FRAGMENT = (1ULL << 2),
BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
+};
+
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_FLAGS = (1ULL << 4),
};
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
@@ -3483,6 +6136,9 @@ enum {
BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
+ BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8),
};
enum {
@@ -3499,9 +6155,13 @@ enum {
BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
};
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
enum {
- BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
};
/* BPF_FUNC_read_branch_records flags. */
@@ -3532,6 +6192,12 @@ enum {
BPF_RINGBUF_HDR_SZ = 8,
};
+/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */
+enum {
+ BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0),
+ BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1),
+};
+
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
BPF_ADJ_ROOM_NET,
@@ -3551,12 +6217,39 @@ enum bpf_lwt_encap_mode {
BPF_LWT_ENCAP_IP,
};
+/* Flags for bpf_bprm_opts_set helper */
+enum {
+ BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
+};
+
+/* Flags for bpf_redirect and bpf_redirect_map helpers */
+enum {
+ 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) \
union { \
type name; \
__u64 :64; \
} __attribute__((aligned(8)))
+/* The enum used in skb->tstamp_type. It specifies the clock type
+ * of the time stored in the skb->tstamp.
+ */
+enum {
+ BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */
+ BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */
+ BPF_SKB_CLOCK_REALTIME = 0,
+ BPF_SKB_CLOCK_MONOTONIC = 1,
+ BPF_SKB_CLOCK_TAI = 2,
+ /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
+ * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
+ */
+};
+
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
*/
@@ -3597,6 +6290,9 @@ struct __sk_buff {
__u32 gso_segs;
__bpf_md_ptr(struct bpf_sock *, sk);
__u32 gso_size;
+ __u8 tstamp_type;
+ __u32 :24; /* Padding, future use. */
+ __u64 hwtstamp;
};
struct bpf_tunnel_key {
@@ -3607,8 +6303,15 @@ struct bpf_tunnel_key {
};
__u8 tunnel_tos;
__u8 tunnel_ttl;
- __u16 tunnel_ext; /* Padding, future use. */
+ union {
+ __u16 tunnel_ext; /* compat */
+ __be16 tunnel_flags;
+ };
__u32 tunnel_label;
+ union {
+ __u32 local_ipv4;
+ __u32 local_ipv6[4];
+ };
};
/* user accessible mirror of in-kernel xfrm_state.
@@ -3647,6 +6350,11 @@ enum bpf_ret_code {
* represented by BPF_REDIRECT above).
*/
BPF_LWT_REROUTE = 128,
+ /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+ * to indicate that no custom dissection was performed, and
+ * fallback to standard dissector is requested.
+ */
+ BPF_FLOW_DISSECTOR_CONTINUE = 129,
};
struct bpf_sock {
@@ -3660,7 +6368,8 @@ struct bpf_sock {
__u32 src_ip4;
__u32 src_ip6[4];
__u32 src_port; /* host byte order */
- __u32 dst_port; /* network byte order */
+ __be16 dst_port; /* network byte order */
+ __u16 :16; /* zero padding */
__u32 dst_ip4;
__u32 dst_ip6[4];
__u32 state;
@@ -3729,6 +6438,19 @@ struct bpf_sock_tuple {
};
};
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+ TCX_NEXT = -1,
+ TCX_PASS = 0,
+ TCX_DROP = 2,
+ TCX_REDIRECT = 7,
+};
+
struct bpf_xdp_sock {
__u32 queue_id;
};
@@ -3775,6 +6497,19 @@ struct bpf_devmap_val {
} bpf_prog;
};
+/* CPUMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_cpumap_val {
+ __u32 qsize; /* queue size to remote target CPU */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
enum sk_action {
SK_DROP = 0,
SK_PASS,
@@ -3822,6 +6557,20 @@ struct sk_reuseport_md {
__u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
__u32 bind_inany; /* Is sock bound to an INANY address? */
__u32 hash; /* A hash of the packet 4 tuples */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
};
#define BPF_TAG_SIZE 8
@@ -3862,6 +6611,10 @@ struct bpf_prog_info {
__aligned_u64 prog_tags;
__u64 run_time_ns;
__u64 run_cnt;
+ __u64 recursion_misses;
+ __u32 verified_insns;
+ __u32 attach_btf_obj_id;
+ __u32 attach_btf_id;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -3879,12 +6632,17 @@ struct bpf_map_info {
__u32 btf_id;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u32 btf_vmlinux_id;
+ __u64 map_extra;
} __attribute__((aligned(8)));
struct bpf_btf_info {
__aligned_u64 btf;
__u32 btf_size;
__u32 id;
+ __aligned_u64 name;
+ __u32 name_len;
+ __u32 kernel_btf;
} __attribute__((aligned(8)));
struct bpf_link_info {
@@ -3898,21 +6656,121 @@ struct bpf_link_info {
} raw_tracepoint;
struct {
__u32 attach_type;
+ __u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
+ __u32 target_btf_id; /* BTF type id inside the object */
} tracing;
struct {
__u64 cgroup_id;
__u32 attach_type;
} cgroup;
+ struct {
+ __aligned_u64 target_name; /* in/out: target_name buffer ptr */
+ __u32 target_name_len; /* in/out: target_name buffer len */
+
+ /* If the iter specific field is 32 bits, it can be put
+ * in the first or second union. Otherwise it should be
+ * put in the second union.
+ */
+ union {
+ struct {
+ __u32 map_id;
+ } map;
+ };
+ union {
+ struct {
+ __u64 cgroup_id;
+ __u32 order;
+ } cgroup;
+ struct {
+ __u32 tid;
+ __u32 pid;
+ } task;
+ };
+ } iter;
struct {
__u32 netns_ino;
__u32 attach_type;
} netns;
+ struct {
+ __u32 ifindex;
+ } xdp;
+ struct {
+ __u32 map_id;
+ } struct_ops;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ __aligned_u64 addrs;
+ __u32 count; /* in/out: kprobe_multi function count */
+ __u32 flags;
+ __u64 missed;
+ __aligned_u64 cookies;
+ } kprobe_multi;
+ struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 path_size; /* in/out: real path size on success, including zero byte */
+ __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ struct {
+ __u32 type; /* enum bpf_perf_event_type */
+ __u32 :32;
+ union {
+ struct {
+ __aligned_u64 file_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from file_name */
+ __u64 cookie;
+ __u64 ref_ctr_offset;
+ } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+ struct {
+ __aligned_u64 func_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from func_name */
+ __u64 addr;
+ __u64 missed;
+ __u64 cookie;
+ } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+ struct {
+ __aligned_u64 tp_name; /* in/out */
+ __u32 name_len;
+ __u32 :32;
+ __u64 cookie;
+ } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+ struct {
+ __u64 config;
+ __u32 type;
+ __u32 :32;
+ __u64 cookie;
+ } event; /* BPF_PERF_EVENT_EVENT */
+ };
+ } perf_event;
+ struct {
+ __u32 ifindex;
+ __u32 attach_type;
+ } tcx;
+ struct {
+ __u32 ifindex;
+ __u32 attach_type;
+ } netkit;
+ struct {
+ __u32 map_id;
+ __u32 attach_type;
+ } sockmap;
};
} __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 attach type).
+ * attach type).
*/
struct bpf_sock_addr {
__u32 user_family; /* Allows 4-byte read, but no write. */
@@ -3987,6 +6845,37 @@ struct bpf_sock_ops {
__u64 bytes_received;
__u64 bytes_acked;
__bpf_md_ptr(struct bpf_sock *, sk);
+ /* [skb_data, skb_data_end) covers the whole TCP header.
+ *
+ * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the
+ * header has not been written.
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+ * been written so far.
+ * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes
+ * the 3WHS.
+ * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+ * the 3WHS.
+ *
+ * bpf_load_hdr_opt() can also be used to read a particular option.
+ */
+ __bpf_md_ptr(void *, skb_data);
+ __bpf_md_ptr(void *, skb_data_end);
+ __u32 skb_len; /* The total length of a packet.
+ * It includes the header, options,
+ * and payload.
+ */
+ __u32 skb_tcp_flags; /* tcp_flags of the header. It provides
+ * an easy way to check for tcp_flags
+ * without parsing skb_data.
+ *
+ * In particular, the skb_tcp_flags
+ * will still be available in
+ * BPF_SOCK_OPS_HDR_OPT_LEN even though
+ * the outgoing header has not
+ * been written yet.
+ */
+ __u64 skb_hwtstamp;
};
/* Definitions for bpf_sock_ops_cb_flags */
@@ -3995,8 +6884,57 @@ enum {
BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+ /* Call bpf for all received TCP headers. The bpf prog will be
+ * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ *
+ * It could be used at the client/active side (i.e. connect() side)
+ * when the server told it that the server was in syncookie
+ * mode and required the active side to resend the bpf-written
+ * options. The active side can keep writing the bpf-options until
+ * it received a valid packet from the server side to confirm
+ * the earlier packet (and options) has been received. The later
+ * example patch is using it like this at the active side when the
+ * server is in syncookie mode.
+ *
+ * The bpf prog will usually turn this off in the common cases.
+ */
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4),
+ /* Call bpf when kernel has received a header option that
+ * the kernel cannot handle. The bpf prog will be called under
+ * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ */
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+ /* Call bpf when the kernel is writing header options for the
+ * outgoing packet. The bpf prog will first be called
+ * to reserve space in a skb under
+ * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then
+ * the bpf prog will be called to write the header option(s)
+ * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+ * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+ * related helpers that will be useful to the bpf programs.
+ *
+ * The kernel gets its chance to reserve space and write
+ * options first before the BPF program does.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
/* Mask of all currently supported cb flags */
- BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF,
+ 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.
@@ -4051,6 +6989,88 @@ enum {
* socket transition to LISTEN state.
*/
BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
+ * Arg1: measured RTT input (mrtt)
+ * Arg2: updated srtt
+ */
+ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option.
+ * It will be called to handle
+ * the packets received at
+ * an already established
+ * connection.
+ *
+ * sock_ops->skb_data:
+ * Referring to the received skb.
+ * It covers the TCP header only.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option.
+ */
+ BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the
+ * header option later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Not available because no header has
+ * been written yet.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the
+ * outgoing skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_reserve_hdr_opt() should
+ * be used to reserve space.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Referring to the outgoing skb.
+ * It covers the TCP header
+ * that has already been written
+ * by the kernel and the
+ * earlier bpf-progs.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the outgoing
+ * skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_store_hdr_opt() should
+ * be used to write the
+ * option.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option that
+ * has already been written
+ * 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.
*/
};
@@ -4072,6 +7092,7 @@ enum {
BPF_TCP_LISTEN,
BPF_TCP_CLOSING, /* Now a valid state */
BPF_TCP_NEW_SYN_RECV,
+ BPF_TCP_BOUND_INACTIVE,
BPF_TCP_MAX_STATES /* Leave at the end! */
};
@@ -4079,6 +7100,65 @@ enum {
enum {
TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */
+ /* Copy the SYN pkt to optval
+ *
+ * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the
+ * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+ * to only getting from the saved_syn. It can either get the
+ * syn packet from:
+ *
+ * 1. the just-received SYN packet (only available when writing the
+ * SYNACK). It will be useful when it is not necessary to
+ * save the SYN packet for latter use. It is also the only way
+ * to get the SYN during syncookie mode because the syn
+ * packet cannot be saved during syncookie.
+ *
+ * OR
+ *
+ * 2. the earlier saved syn which was done by
+ * bpf_setsockopt(TCP_SAVE_SYN).
+ *
+ * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+ * SYN packet is obtained.
+ *
+ * If the bpf-prog does not need the IP[46] header, the
+ * bpf-prog can avoid parsing the IP header by using
+ * TCP_BPF_SYN. Otherwise, the bpf-prog can get both
+ * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+ *
+ * >0: Total number of bytes copied
+ * -ENOSPC: Not enough space in optval. Only optlen number of
+ * bytes is copied.
+ * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+ * is not saved by setsockopt(TCP_SAVE_SYN).
+ */
+ 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 */
+};
+
+enum {
+ BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+ BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the
+ * total option spaces
+ * required for an established
+ * sk in order to calculate the
+ * MSS. No skb is actually
+ * sent.
+ */
+ BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode
+ * when sending a SYN.
+ */
};
struct bpf_perf_event_value {
@@ -4115,6 +7195,10 @@ struct bpf_raw_tracepoint_args {
enum {
BPF_FIB_LOOKUP_DIRECT = (1U << 0),
BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
+ BPF_FIB_LOOKUP_SRC = (1U << 4),
+ BPF_FIB_LOOKUP_MARK = (1U << 5),
};
enum {
@@ -4127,6 +7211,7 @@ enum {
BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */
};
struct bpf_fib_lookup {
@@ -4140,9 +7225,13 @@ struct bpf_fib_lookup {
__be16 sport;
__be16 dport;
- /* total length of packet from network header - used for MTU check */
- __u16 tot_len;
+ union { /* used for MTU check */
+ /* input to lookup */
+ __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */
+ /* output: MTU value */
+ __u16 mtu_result;
+ } __attribute__((packed, aligned(2)));
/* input: L3 device index for lookup
* output: device index from FIB lookup
*/
@@ -4157,6 +7246,9 @@ struct bpf_fib_lookup {
__u32 rt_metric;
};
+ /* input: source address to consider for lookup
+ * output: source address result from lookup
+ */
union {
__be32 ipv4_src;
__u32 ipv6_src[4]; /* in6_addr; network order */
@@ -4171,11 +7263,53 @@ struct bpf_fib_lookup {
__u32 ipv6_dst[4]; /* in6_addr; network order */
};
- /* output */
- __be16 h_vlan_proto;
- __be16 h_vlan_TCI;
- __u8 smac[6]; /* ETH_ALEN */
- __u8 dmac[6]; /* ETH_ALEN */
+ union {
+ struct {
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ };
+ /* input: when accompanied with the
+ * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
+ * specific routing table to use for the fib lookup.
+ */
+ __u32 tbid;
+ };
+
+ union {
+ /* input */
+ struct {
+ __u32 mark; /* policy routing */
+ /* 2 4-byte holes for input */
+ };
+
+ /* output: source and dest mac */
+ struct {
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+ };
+ };
+};
+
+struct bpf_redir_neigh {
+ /* network family for lookup (AF_INET, AF_INET6) */
+ __u32 nh_family;
+ /* network address of nexthop; skips fib lookup to find gateway */
+ union {
+ __be32 ipv4_nh;
+ __u32 ipv6_nh[4]; /* in6_addr; network order */
+ };
+};
+
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
};
enum bpf_task_fd_type {
@@ -4237,6 +7371,38 @@ struct bpf_spin_lock {
__u32 val;
};
+struct bpf_timer {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_wq {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_dynptr {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_list_head {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_rb_root {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+ __u64 __opaque[4];
+} __attribute__((aligned(8)));
+
+struct bpf_refcount {
+ __u32 __opaque[1];
+} __attribute__((aligned(4)));
+
struct bpf_sysctl {
__u32 write; /* Sysctl is being read (= 0) or written (= 1).
* Allows 1,2,4-byte read, but no write.
@@ -4261,4 +7427,157 @@ struct bpf_pidns_info {
__u32 pid;
__u32 tgid;
};
+
+/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
+struct bpf_sk_lookup {
+ union {
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+ __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */
+ };
+
+ __u32 family; /* Protocol family (AF_INET, AF_INET6) */
+ __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
+ __u32 remote_ip4; /* Network byte order */
+ __u32 remote_ip6[4]; /* Network byte order */
+ __be16 remote_port; /* Network byte order */
+ __u16 :16; /* Zero padding */
+ __u32 local_ip4; /* Network byte order */
+ __u32 local_ip6[4]; /* Network byte order */
+ __u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
+};
+
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above. A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+ void *ptr;
+ __u32 type_id;
+ __u32 flags; /* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ * - BTF_F_COMPACT: no formatting around type information
+ * - BTF_F_NONAME: no struct/union member names/types
+ * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ * equivalent to %px.
+ * - BTF_F_ZERO: show zero-valued struct/union members; they
+ * are not displayed by default
+ */
+enum {
+ BTF_F_COMPACT = (1ULL << 0),
+ BTF_F_NONAME = (1ULL << 1),
+ BTF_F_PTR_RAW = (1ULL << 2),
+ BTF_F_ZERO = (1ULL << 3),
+};
+
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+ BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */
+ BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */
+ BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */
+ BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */
+ BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * interpretation depends on specific relocation kind:
+ * - for field-based relocations, string encodes an accessed field using
+ * a sequence of field and array indices, separated by colon (:). It's
+ * conceptually very close to LLVM's getelementptr ([0]) instruction's
+ * arguments for identifying offset to a field.
+ * - for type-based relocations, strings is expected to be just "0";
+ * - for enum value-based relocations, string contains an index of enum
+ * value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int *x = &s->a; // encoded as "0:0" (a is field #0)
+ * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+ enum bpf_core_relo_kind kind;
+};
+
+/*
+ * Flags to control bpf_timer_start() behaviour.
+ * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
+ * relative to current time.
+ * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
+ */
+enum {
+ BPF_F_TIMER_ABS = (1ULL << 0),
+ BPF_F_TIMER_CPU_PIN = (1ULL << 1),
+};
+
+/* BPF numbers iterator state */
+struct bpf_iter_num {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+/*
+ * 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),
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
index 8f95303f9d80..eb1b9d21250c 100644
--- a/tools/include/uapi/linux/bpf_perf_event.h
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -13,6 +13,7 @@
struct bpf_perf_event_data {
bpf_user_pt_regs_t regs;
__u64 sample_period;
+ __u64 addr;
};
#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 5a667107ad2c..266d4ffa6c07 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -33,17 +33,18 @@ struct btf_type {
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
- * bits 24-27: kind (e.g. int, ptr, array...etc)
- * bits 28-30: unused
+ * bits 24-28: kind (e.g. int, ptr, array...etc)
+ * bits 29-30: unused
* bit 31: kind_flag, currently used by
- * struct, union and fwd
+ * struct, union, enum, fwd, enum64,
+ * decl_tag and type_tag
*/
__u32 info;
- /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
+ /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
- * FUNC, FUNC_PROTO and VAR.
+ * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
* "type" is a type_id referring to another type.
*/
union {
@@ -52,28 +53,35 @@ struct btf_type {
};
};
-#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f)
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
#define BTF_INFO_VLEN(info) ((info) & 0xffff)
#define BTF_INFO_KFLAG(info) ((info) >> 31)
-#define BTF_KIND_UNKN 0 /* Unknown */
-#define BTF_KIND_INT 1 /* Integer */
-#define BTF_KIND_PTR 2 /* Pointer */
-#define BTF_KIND_ARRAY 3 /* Array */
-#define BTF_KIND_STRUCT 4 /* Struct */
-#define BTF_KIND_UNION 5 /* Union */
-#define BTF_KIND_ENUM 6 /* Enumeration */
-#define BTF_KIND_FWD 7 /* Forward */
-#define BTF_KIND_TYPEDEF 8 /* Typedef */
-#define BTF_KIND_VOLATILE 9 /* Volatile */
-#define BTF_KIND_CONST 10 /* Const */
-#define BTF_KIND_RESTRICT 11 /* Restrict */
-#define BTF_KIND_FUNC 12 /* Function */
-#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
-#define BTF_KIND_VAR 14 /* Variable */
-#define BTF_KIND_DATASEC 15 /* Section */
-#define BTF_KIND_MAX BTF_KIND_DATASEC
-#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
+enum {
+ BTF_KIND_UNKN = 0, /* Unknown */
+ BTF_KIND_INT = 1, /* Integer */
+ BTF_KIND_PTR = 2, /* Pointer */
+ BTF_KIND_ARRAY = 3, /* Array */
+ BTF_KIND_STRUCT = 4, /* Struct */
+ BTF_KIND_UNION = 5, /* Union */
+ BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */
+ BTF_KIND_FWD = 7, /* Forward */
+ BTF_KIND_TYPEDEF = 8, /* Typedef */
+ BTF_KIND_VOLATILE = 9, /* Volatile */
+ BTF_KIND_CONST = 10, /* Const */
+ BTF_KIND_RESTRICT = 11, /* Restrict */
+ BTF_KIND_FUNC = 12, /* Function */
+ BTF_KIND_FUNC_PROTO = 13, /* Function Proto */
+ BTF_KIND_VAR = 14, /* Variable */
+ BTF_KIND_DATASEC = 15, /* Section */
+ BTF_KIND_FLOAT = 16, /* Floating point */
+ BTF_KIND_DECL_TAG = 17, /* Decl Tag */
+ BTF_KIND_TYPE_TAG = 18, /* Type Tag */
+ BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */
+
+ NR_BTF_KINDS,
+ BTF_KIND_MAX = NR_BTF_KINDS - 1,
+};
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
@@ -169,4 +177,25 @@ struct btf_var_secinfo {
__u32 size;
};
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+ __s32 component_idx;
+};
+
+/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64".
+ * The exact number of btf_enum64 is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum64 {
+ __u32 name_off;
+ __u32 val_lo32;
+ __u32 val_hi32;
+};
+
#endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index 5ed721ad5b19..b8f629ef135f 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,4 +28,26 @@
#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))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
#endif /* _UAPI_LINUX_CONST_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/ethtool.h b/tools/include/uapi/linux/ethtool.h
deleted file mode 100644
index c86c3e942df9..000000000000
--- a/tools/include/uapi/linux/ethtool.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * ethtool.h: Defines for Linux ethtool.
- *
- * Copyright (C) 1998 David S. Miller (davem@redhat.com)
- * Copyright 2001 Jeff Garzik <jgarzik@pobox.com>
- * Portions Copyright 2001 Sun Microsystems (thockin@sun.com)
- * Portions Copyright 2002 Intel (eli.kupermann@intel.com,
- * christopher.leech@intel.com,
- * scott.feldman@intel.com)
- * Portions Copyright (C) Sun Microsystems 2008
- */
-
-#ifndef _UAPI_LINUX_ETHTOOL_H
-#define _UAPI_LINUX_ETHTOOL_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */
-
-/**
- * struct ethtool_channels - configuring number of network channel
- * @cmd: ETHTOOL_{G,S}CHANNELS
- * @max_rx: Read only. Maximum number of receive channel the driver support.
- * @max_tx: Read only. Maximum number of transmit channel the driver support.
- * @max_other: Read only. Maximum number of other channel the driver support.
- * @max_combined: Read only. Maximum number of combined channel the driver
- * support. Set of queues RX, TX or other.
- * @rx_count: Valid values are in the range 1 to the max_rx.
- * @tx_count: Valid values are in the range 1 to the max_tx.
- * @other_count: Valid values are in the range 1 to the max_other.
- * @combined_count: Valid values are in the range 1 to the max_combined.
- *
- * This can be used to configure RX, TX and other channels.
- */
-
-struct ethtool_channels {
- __u32 cmd;
- __u32 max_rx;
- __u32 max_tx;
- __u32 max_other;
- __u32 max_combined;
- __u32 rx_count;
- __u32 tx_count;
- __u32 other_count;
- __u32 combined_count;
-};
-
-#endif /* _UAPI_LINUX_ETHTOOL_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/fcntl.h b/tools/include/uapi/linux/fcntl.h
deleted file mode 100644
index 2f86b2ad6d7e..000000000000
--- a/tools/include/uapi/linux/fcntl.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_FCNTL_H
-#define _UAPI_LINUX_FCNTL_H
-
-#include <asm/fcntl.h>
-#include <linux/openat2.h>
-
-#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0)
-#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1)
-
-/*
- * Cancel a blocking posix lock; internal use only until we expose an
- * asynchronous lock api to userspace:
- */
-#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5)
-
-/* Create a file descriptor with FD_CLOEXEC set. */
-#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6)
-
-/*
- * Request nofications on a directory.
- * See below for events that may be notified.
- */
-#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2)
-
-/*
- * Set and get of pipe page size array
- */
-#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7)
-#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8)
-
-/*
- * Set/Get seals
- */
-#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
-#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
-
-/*
- * Types of seals
- */
-#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
-#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
-#define F_SEAL_GROW 0x0004 /* prevent file from growing */
-#define F_SEAL_WRITE 0x0008 /* prevent writes */
-#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
-/* (1U << 31) is reserved for signed error codes */
-
-/*
- * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
- * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
- * the specific file.
- */
-#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11)
-#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12)
-#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13)
-#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14)
-
-/*
- * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
- * used to clear any hints previously set.
- */
-#define RWH_WRITE_LIFE_NOT_SET 0
-#define RWH_WRITE_LIFE_NONE 1
-#define RWH_WRITE_LIFE_SHORT 2
-#define RWH_WRITE_LIFE_MEDIUM 3
-#define RWH_WRITE_LIFE_LONG 4
-#define RWH_WRITE_LIFE_EXTREME 5
-
-/*
- * The originally introduced spelling is remained from the first
- * versions of the patch set that introduced the feature, see commit
- * v4.13-rc1~212^2~51.
- */
-#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET
-
-/*
- * Types of directory notifications that may be requested.
- */
-#define DN_ACCESS 0x00000001 /* File accessed */
-#define DN_MODIFY 0x00000002 /* File modified */
-#define DN_CREATE 0x00000004 /* File created */
-#define DN_DELETE 0x00000008 /* File removed */
-#define DN_RENAME 0x00000010 /* File renamed */
-#define DN_ATTRIB 0x00000020 /* File changed attibutes */
-#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
-
-/*
- * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is
- * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
- * unlinkat. The two functions do completely different things and therefore,
- * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to
- * faccessat would be undefined behavior and thus treating it equivalent to
- * AT_EACCESS is valid undefined behavior.
- */
-#define AT_FDCWD -100 /* Special value used to indicate
- openat should use the current
- working directory. */
-#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
-#define AT_EACCESS 0x200 /* Test access permitted for
- effective IDs, not real IDs. */
-#define AT_REMOVEDIR 0x200 /* Remove directory instead of
- unlinking file. */
-#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
-#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */
-#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */
-
-#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */
-#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */
-#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
-#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
-
-#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-
-#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h
new file mode 100644
index 000000000000..eaef459e7bd4
--- /dev/null
+++ b/tools/include/uapi/linux/filter.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Socket Filter Data Structures
+ */
+
+#ifndef __LINUX_FILTER_H__
+#define __LINUX_FILTER_H__
+
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/*
+ * Current version of the filter code architecture.
+ */
+#define BPF_MAJOR_VERSION 1
+#define BPF_MINOR_VERSION 1
+
+/*
+ * Try and keep these values and structures similar to BSD, especially
+ * the BPF code definitions which need to match so you can share filters
+ */
+
+struct sock_filter { /* Filter block */
+ __u16 code; /* Actual filter code */
+ __u8 jt; /* Jump true */
+ __u8 jf; /* Jump false */
+ __u32 k; /* Generic multiuse field */
+};
+
+struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
+ unsigned short len; /* Number of filter blocks */
+ struct sock_filter *filter;
+};
+
+/* ret - BPF_K and BPF_X also apply */
+#define BPF_RVAL(code) ((code) & 0x18)
+#define BPF_A 0x10
+
+/* misc */
+#define BPF_MISCOP(code) ((code) & 0xf8)
+#define BPF_TAX 0x00
+#define BPF_TXA 0x80
+
+/*
+ * Macros for filter block array initializers.
+ */
+#ifndef BPF_STMT
+#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
+#endif
+#ifndef BPF_JUMP
+#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
+#endif
+
+/*
+ * Number of scratch memory words for: BPF_ST and BPF_STX
+ */
+#define BPF_MEMWORDS 16
+
+/* RATIONALE. Negative offsets are invalid in BPF.
+ We use them to reference ancillary data.
+ Unlike introduction new instructions, it does not break
+ existing compilers/optimizers.
+ */
+#define SKF_AD_OFF (-0x1000)
+#define SKF_AD_PROTOCOL 0
+#define SKF_AD_PKTTYPE 4
+#define SKF_AD_IFINDEX 8
+#define SKF_AD_NLATTR 12
+#define SKF_AD_NLATTR_NEST 16
+#define SKF_AD_MARK 20
+#define SKF_AD_QUEUE 24
+#define SKF_AD_HATYPE 28
+#define SKF_AD_RXHASH 32
+#define SKF_AD_CPU 36
+#define SKF_AD_ALU_XOR_X 40
+#define SKF_AD_VLAN_TAG 44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_PAY_OFFSET 52
+#define SKF_AD_RANDOM 56
+#define SKF_AD_VLAN_TPID 60
+#define SKF_AD_MAX 64
+
+#define SKF_NET_OFF (-0x100000)
+#define SKF_LL_OFF (-0x200000)
+
+#define BPF_NET_OFF SKF_NET_OFF
+#define BPF_LL_OFF SKF_LL_OFF
+
+#endif /* __LINUX_FILTER_H__ */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index f44eb0a04afd..24ddf7bc4f25 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -28,8 +28,8 @@
* 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..
+ * Some programs (notably those using select()) may have to be
+ * recompiled to take full advantage of the new limits..
*/
/* Fixed constants first: */
@@ -40,6 +40,15 @@
#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 */
@@ -64,6 +73,24 @@ struct fstrim_range {
__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
@@ -90,7 +117,7 @@ struct file_dedupe_range {
__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[0];
+ struct file_dedupe_range_info info[];
};
/* And dynamically-tunable limits and defaults: */
@@ -184,8 +211,9 @@ struct fsxattr {
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
+#define BLKGETDISKSEQ _IOR(0x12,128,__u64)
/*
- * A jump here: 130-131 are reserved for zoned block devices
+ * A jump here: 130-136 are reserved for zoned block devices
* (see uapi/linux/blkzoned.h)
*/
@@ -214,6 +242,13 @@ 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)
@@ -300,8 +335,235 @@ typedef int __bitwise __kernel_rwf_t;
/* 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_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 7875709ccfeb..3aff99f2696a 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -20,15 +20,17 @@
#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08
#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10
-#define FSCRYPT_POLICY_FLAGS_VALID 0x1F
/* Encryption algorithms */
#define FSCRYPT_MODE_AES_256_XTS 1
#define FSCRYPT_MODE_AES_256_CTS 4
#define FSCRYPT_MODE_AES_128_CBC 5
#define FSCRYPT_MODE_AES_128_CTS 6
+#define FSCRYPT_MODE_SM4_XTS 7
+#define FSCRYPT_MODE_SM4_CTS 8
#define FSCRYPT_MODE_ADIANTUM 9
-#define __FSCRYPT_MODE_MAX 9
+#define FSCRYPT_MODE_AES_256_HCTR2 10
+/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
/*
* Legacy policy version; ad-hoc KDF and no key verification.
@@ -45,7 +47,6 @@ struct fscrypt_policy_v1 {
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
-#define fscrypt_policy fscrypt_policy_v1
/*
* Process-subscribed "logon" key description prefix and payload format.
@@ -70,7 +71,8 @@ struct fscrypt_policy_v2 {
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
- __u8 __reserved[4];
+ __u8 log2_data_unit_size;
+ __u8 __reserved[3];
__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
};
@@ -117,7 +119,7 @@ struct fscrypt_key_specifier {
*/
struct fscrypt_provisioning_key_payload {
__u32 type;
- __u32 __reserved;
+ __u32 flags;
__u8 raw[];
};
@@ -126,7 +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[];
};
@@ -156,9 +160,9 @@ struct fscrypt_get_key_status_arg {
__u32 __out_reserved[13];
};
-#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +174,7 @@ struct fscrypt_get_key_status_arg {
/* old names; don't add anything new here! */
#ifndef __KERNEL__
+#define fscrypt_policy fscrypt_policy_v1
#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
@@ -177,7 +182,7 @@ struct fscrypt_get_key_status_arg {
#define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32
#define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK
#define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY
-#define FS_POLICY_FLAGS_VALID FSCRYPT_POLICY_FLAGS_VALID
+#define FS_POLICY_FLAGS_VALID 0x07 /* contains old flags only */
#define FS_ENCRYPTION_MODE_INVALID 0 /* never used */
#define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS
#define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */
@@ -185,8 +190,6 @@ struct fscrypt_get_key_status_arg {
#define FS_ENCRYPTION_MODE_AES_256_CTS FSCRYPT_MODE_AES_256_CTS
#define FS_ENCRYPTION_MODE_AES_128_CBC FSCRYPT_MODE_AES_128_CBC
#define FS_ENCRYPTION_MODE_AES_128_CTS FSCRYPT_MODE_AES_128_CTS
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* removed */
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* removed */
#define FS_ENCRYPTION_MODE_ADIANTUM FSCRYPT_MODE_ADIANTUM
#define FS_KEY_DESC_PREFIX FSCRYPT_KEY_DESC_PREFIX
#define FS_KEY_DESC_PREFIX_SIZE FSCRYPT_KEY_DESC_PREFIX_SIZE
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index 965e4d8606d8..1575d3ca6f0d 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -22,14 +22,4 @@ enum {
HW_BREAKPOINT_INVALID = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
};
-enum bp_type_idx {
- TYPE_INST = 0,
-#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
- TYPE_DATA = 0,
-#else
- TYPE_DATA = 1,
-#endif
- TYPE_MAX
-};
-
#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index cafedbbfefbe..7e46ca4cd31b 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -7,24 +7,23 @@
/* This struct should be in sync with struct rtnl_link_stats64 */
struct rtnl_link_stats {
- __u32 rx_packets; /* total packets received */
- __u32 tx_packets; /* total packets transmitted */
- __u32 rx_bytes; /* total bytes received */
- __u32 tx_bytes; /* total bytes transmitted */
- __u32 rx_errors; /* bad packets received */
- __u32 tx_errors; /* packet transmit problems */
- __u32 rx_dropped; /* no space in linux buffers */
- __u32 tx_dropped; /* no space available in linux */
- __u32 multicast; /* multicast packets received */
+ __u32 rx_packets;
+ __u32 tx_packets;
+ __u32 rx_bytes;
+ __u32 tx_bytes;
+ __u32 rx_errors;
+ __u32 tx_errors;
+ __u32 rx_dropped;
+ __u32 tx_dropped;
+ __u32 multicast;
__u32 collisions;
-
/* detailed rx_errors: */
__u32 rx_length_errors;
- __u32 rx_over_errors; /* receiver ring buff overflow */
- __u32 rx_crc_errors; /* recved pkt with crc error */
- __u32 rx_frame_errors; /* recv'd frame alignment error */
- __u32 rx_fifo_errors; /* recv'r fifo overrun */
- __u32 rx_missed_errors; /* receiver missed packet */
+ __u32 rx_over_errors;
+ __u32 rx_crc_errors;
+ __u32 rx_frame_errors;
+ __u32 rx_fifo_errors;
+ __u32 rx_missed_errors;
/* detailed tx_errors */
__u32 tx_aborted_errors;
@@ -37,29 +36,204 @@ struct rtnl_link_stats {
__u32 rx_compressed;
__u32 tx_compressed;
- __u32 rx_nohandler; /* dropped, no handler found */
+ __u32 rx_nohandler;
};
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ * For hardware interfaces counts all good packets received from the device
+ * by the host, including packets which host had to drop at various stages
+ * of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ * For hardware interfaces counts packets which host was able to successfully
+ * hand over to the device, which does not necessarily mean that packets
+ * had been successfully transmitted out of the device, only that device
+ * acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ * This counter must include events counted by @rx_length_errors,
+ * @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ * counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ * This counter must include events counter by @tx_aborted_errors,
+ * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ * @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ * e.g. due to lack of resources or unsupported protocol.
+ * For hardware interfaces this counter may include packets discarded
+ * due to L2 address filtering but should not include packets dropped
+ * by the device due to buffer exhaustion which are counted separately in
+ * @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ * e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ * For hardware interfaces this statistic is commonly calculated
+ * at the device level (unlike @rx_packets) and therefore may include
+ * packets which did not reach the host.
+ *
+ * For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ * - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to a sum
+ * of the following attributes:
+ *
+ * - 30.3.1.1.23 aInRangeLengthErrors
+ * - 30.3.1.1.24 aOutOfRangeLengthField
+ * - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ * Historically the count of overflow events. Such events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * The recommended interpretation for high speed interfaces is -
+ * number of packets dropped because they did not fit into buffers
+ * provided by the host, e.g. packets larger than MTU or next buffer
+ * in the ring was not available for a scatter transfer.
+ *
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * This statistics was historically used interchangeably with
+ * @rx_fifo_errors.
+ *
+ * This statistic corresponds to hardware events and is not commonly used
+ * on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ * - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ * Historically the count of overflow events. Those events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * This statistics was used interchangeably with @rx_over_errors.
+ * Not recommended for use in drivers for high speed interfaces.
+ *
+ * This statistic is used on software devices, e.g. to count software
+ * packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ * Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ * Counts number of packets dropped by the device due to lack
+ * of buffer space. This usually indicates that the host interface
+ * is slower than the network interface, or host is not keeping up
+ * with the receive packet rate.
+ *
+ * This statistic corresponds to hardware events and is not used
+ * on software devices.
+ *
+ * @tx_aborted_errors:
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ * For IEEE 802.3 devices capable of half-duplex operation this counter
+ * must be equivalent to:
+ *
+ * - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ * High speed interfaces may use this counter as a general device
+ * discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ * of carrier during transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ * FIFO underrun / underflow. This condition occurs when the device
+ * begins transmission of a frame but is unable to deliver the
+ * entire frame to the transmitter in time for transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ * old half-duplex Ethernet.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices possibly equivalent to:
+ *
+ * - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ * to late collisions (for Ethernet - after the first 64B of transmission).
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ * but dropped by the networking stack because the device is
+ * not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ * in destination MAC address.
+ */
struct rtnl_link_stats64 {
- __u64 rx_packets; /* total packets received */
- __u64 tx_packets; /* total packets transmitted */
- __u64 rx_bytes; /* total bytes received */
- __u64 tx_bytes; /* total bytes transmitted */
- __u64 rx_errors; /* bad packets received */
- __u64 tx_errors; /* packet transmit problems */
- __u64 rx_dropped; /* no space in linux buffers */
- __u64 tx_dropped; /* no space available in linux */
- __u64 multicast; /* multicast packets received */
+ __u64 rx_packets;
+ __u64 tx_packets;
+ __u64 rx_bytes;
+ __u64 tx_bytes;
+ __u64 rx_errors;
+ __u64 tx_errors;
+ __u64 rx_dropped;
+ __u64 tx_dropped;
+ __u64 multicast;
__u64 collisions;
/* detailed rx_errors: */
__u64 rx_length_errors;
- __u64 rx_over_errors; /* receiver ring buff overflow */
- __u64 rx_crc_errors; /* recved pkt with crc error */
- __u64 rx_frame_errors; /* recv'd frame alignment error */
- __u64 rx_fifo_errors; /* recv'r fifo overrun */
- __u64 rx_missed_errors; /* receiver missed packet */
+ __u64 rx_over_errors;
+ __u64 rx_crc_errors;
+ __u64 rx_frame_errors;
+ __u64 rx_fifo_errors;
+ __u64 rx_missed_errors;
/* detailed tx_errors */
__u64 tx_aborted_errors;
@@ -71,8 +245,24 @@ struct rtnl_link_stats64 {
/* for cslip etc */
__u64 rx_compressed;
__u64 tx_compressed;
+ __u64 rx_nohandler;
+
+ __u64 rx_otherhost_dropped;
+};
- __u64 rx_nohandler; /* dropped, no handler found */
+/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
+ * for struct rtnl_link_stats64.
+ */
+struct rtnl_hw_stats64 {
+ __u64 rx_packets;
+ __u64 tx_packets;
+ __u64 rx_bytes;
+ __u64 tx_bytes;
+ __u64 rx_errors;
+ __u64 tx_errors;
+ __u64 rx_dropped;
+ __u64 tx_dropped;
+ __u64 multicast;
};
/* The struct should be in sync with struct ifmap */
@@ -170,12 +360,39 @@ enum {
IFLA_PROP_LIST,
IFLA_ALT_IFNAME, /* Alternative ifname */
IFLA_PERM_ADDRESS,
+ IFLA_PROTO_DOWN_REASON,
+
+ /* device (sysfs) name as parent, used instead
+ * of IFLA_LINK where there's no parent netdev
+ */
+ IFLA_PARENT_DEV_NAME,
+ IFLA_PARENT_DEV_BUS_NAME,
+ IFLA_GRO_MAX_SIZE,
+ IFLA_TSO_MAX_SIZE,
+ IFLA_TSO_MAX_SEGS,
+ IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */
+
+ IFLA_DEVLINK_PORT,
+
+ IFLA_GSO_IPV4_MAX_SIZE,
+ IFLA_GRO_IPV4_MAX_SIZE,
+ IFLA_DPLL_PIN,
+ IFLA_MAX_PACING_OFFLOAD_HORIZON,
__IFLA_MAX
};
#define IFLA_MAX (__IFLA_MAX - 1)
+enum {
+ IFLA_PROTO_DOWN_REASON_UNSPEC,
+ IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */
+ IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */
+
+ __IFLA_PROTO_DOWN_REASON_CNT,
+ IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
/* backwards compatibility for userspace */
#ifndef __KERNEL__
#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -230,6 +447,7 @@ enum {
IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
IFLA_INET6_TOKEN, /* device token */
IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+ IFLA_INET6_RA_MTU, /* mtu carried in the RA message */
__IFLA_INET6_MAX
};
@@ -244,6 +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,
@@ -292,6 +790,9 @@ enum {
IFLA_BR_MCAST_MLD_VERSION,
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,
};
@@ -302,11 +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 */
@@ -344,6 +1086,15 @@ enum {
IFLA_BRPORT_ISOLATED,
IFLA_BRPORT_BACKUP_PORT,
IFLA_BRPORT_MRP_RING_OPEN,
+ IFLA_BRPORT_MRP_IN_OPEN,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
+ IFLA_BRPORT_LOCKED,
+ IFLA_BRPORT_MAB,
+ IFLA_BRPORT_MCAST_N_GROUPS,
+ IFLA_BRPORT_MCAST_MAX_GROUPS,
+ IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+ IFLA_BRPORT_BACKUP_NHID,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -408,6 +1159,9 @@ enum {
IFLA_MACVLAN_MACADDR,
IFLA_MACVLAN_MACADDR_DATA,
IFLA_MACVLAN_MACADDR_COUNT,
+ IFLA_MACVLAN_BC_QUEUE_LEN,
+ IFLA_MACVLAN_BC_QUEUE_LEN_USED,
+ IFLA_MACVLAN_BC_CUTOFF,
__IFLA_MACVLAN_MAX,
};
@@ -429,6 +1183,7 @@ enum macvlan_macaddr_mode {
};
#define MACVLAN_FLAG_NOPROMISC 1
+#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */
/* VRF section */
enum {
@@ -475,6 +1230,7 @@ enum {
IFLA_XFRM_UNSPEC,
IFLA_XFRM_LINK,
IFLA_XFRM_IF_ID,
+ IFLA_XFRM_COLLECT_METADATA,
__IFLA_XFRM_MAX
};
@@ -516,7 +1272,96 @@ enum ipvlan_mode {
#define IPVLAN_F_PRIVATE 0x01
#define IPVLAN_F_VEPA 0x02
+/* Tunnel RTM header */
+struct tunnel_msg {
+ __u8 family;
+ __u8 flags;
+ __u16 reserved2;
+ __u32 ifindex;
+};
+
+/* netkit section */
+enum netkit_action {
+ NETKIT_NEXT = -1,
+ NETKIT_PASS = 0,
+ NETKIT_DROP = 2,
+ NETKIT_REDIRECT = 7,
+};
+
+enum netkit_mode {
+ NETKIT_L2,
+ 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,
+ IFLA_NETKIT_PRIMARY,
+ 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)
+
/* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS 0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+ VNIFILTER_ENTRY_STATS_UNSPEC,
+ VNIFILTER_ENTRY_STATS_RX_BYTES,
+ VNIFILTER_ENTRY_STATS_RX_PKTS,
+ VNIFILTER_ENTRY_STATS_RX_DROPS,
+ VNIFILTER_ENTRY_STATS_RX_ERRORS,
+ VNIFILTER_ENTRY_STATS_TX_BYTES,
+ VNIFILTER_ENTRY_STATS_TX_PKTS,
+ VNIFILTER_ENTRY_STATS_TX_DROPS,
+ VNIFILTER_ENTRY_STATS_TX_ERRORS,
+ VNIFILTER_ENTRY_STATS_PAD,
+ __VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+ VXLAN_VNIFILTER_ENTRY_UNSPEC,
+ VXLAN_VNIFILTER_ENTRY_START,
+ VXLAN_VNIFILTER_ENTRY_END,
+ VXLAN_VNIFILTER_ENTRY_GROUP,
+ VXLAN_VNIFILTER_ENTRY_GROUP6,
+ VXLAN_VNIFILTER_ENTRY_STATS,
+ __VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+ VXLAN_VNIFILTER_UNSPEC,
+ VXLAN_VNIFILTER_ENTRY,
+ __VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1)
+
enum {
IFLA_VXLAN_UNSPEC,
IFLA_VXLAN_ID,
@@ -548,6 +1393,9 @@ enum {
IFLA_VXLAN_GPE,
IFLA_VXLAN_TTL_INHERIT,
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)
@@ -565,6 +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,
@@ -581,6 +1436,7 @@ enum {
IFLA_GENEVE_LABEL,
IFLA_GENEVE_TTL_INHERIT,
IFLA_GENEVE_DF,
+ IFLA_GENEVE_INNER_PROTO_INHERIT,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
@@ -593,6 +1449,18 @@ enum ifla_geneve_df {
GENEVE_DF_MAX = __GENEVE_DF_END - 1,
};
+/* Bareudp section */
+enum {
+ IFLA_BAREUDP_UNSPEC,
+ IFLA_BAREUDP_PORT,
+ IFLA_BAREUDP_ETHERTYPE,
+ IFLA_BAREUDP_SRCPORT_MIN,
+ IFLA_BAREUDP_MULTIPROTO_MODE,
+ __IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
/* PPP section */
enum {
IFLA_PPP_UNSPEC,
@@ -614,6 +1482,10 @@ enum {
IFLA_GTP_FD1,
IFLA_GTP_PDP_HASHSIZE,
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)
@@ -650,6 +1522,10 @@ enum {
IFLA_BOND_AD_ACTOR_SYSTEM,
IFLA_BOND_TLB_DYNAMIC_LB,
IFLA_BOND_PEER_NOTIF_DELAY,
+ IFLA_BOND_AD_LACP_ACTIVE,
+ IFLA_BOND_MISSED_MAX,
+ IFLA_BOND_NS_IP6_TARGET,
+ IFLA_BOND_COUPLED_CONTROL,
__IFLA_BOND_MAX,
};
@@ -677,6 +1553,7 @@ enum {
IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+ IFLA_BOND_SLAVE_PRIO,
__IFLA_BOND_SLAVE_MAX,
};
@@ -894,7 +1771,14 @@ enum {
#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+ HSR_PROTOCOL_HSR,
+ HSR_PROTOCOL_PRP,
+ HSR_PROTOCOL_MAX,
+};
enum {
IFLA_HSR_UNSPEC,
@@ -904,6 +1788,10 @@ enum {
IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */
IFLA_HSR_SEQ_NR,
IFLA_HSR_VERSION, /* HSR version */
+ IFLA_HSR_PROTOCOL, /* Indicate different protocol than
+ * HSR. For example PRP.
+ */
+ IFLA_HSR_INTERLINK, /* HSR interlink network device */
__IFLA_HSR_MAX,
};
@@ -936,6 +1824,17 @@ enum {
#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1))
+enum {
+ IFLA_STATS_GETSET_UNSPEC,
+ IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
+ * a filter mask for the corresponding group.
+ */
+ IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
+ __IFLA_STATS_GETSET_MAX,
+};
+
+#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
+
/* These are embedded into IFLA_STATS_LINK_XSTATS:
* [IFLA_STATS_LINK_XSTATS]
* -> [LINK_XSTATS_TYPE_xxx]
@@ -953,10 +1852,21 @@ enum {
enum {
IFLA_OFFLOAD_XSTATS_UNSPEC,
IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */
+ IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */
__IFLA_OFFLOAD_XSTATS_MAX
};
#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
+enum {
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */
+ __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
+};
+#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
+ (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
+
/* XDP section */
#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
@@ -1028,6 +1938,8 @@ enum {
#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5)
enum {
IFLA_RMNET_UNSPEC,
@@ -1043,4 +1955,26 @@ struct ifla_rmnet_flags {
__u32 mask;
};
+/* MCTP section */
+
+enum {
+ IFLA_MCTP_UNSPEC,
+ IFLA_MCTP_NET,
+ __IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
+/* DSA section */
+
+enum {
+ IFLA_DSA_UNSPEC,
+ IFLA_DSA_CONDUIT,
+ /* Deprecated, use IFLA_DSA_CONDUIT instead */
+ IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
+ __IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1)
+
#endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
index 454ae31b93c7..2ec07de1d73b 100644
--- a/tools/include/uapi/linux/if_tun.h
+++ b/tools/include/uapi/linux/if_tun.h
@@ -108,7 +108,7 @@ struct tun_pi {
struct tun_filter {
__u16 flags; /* TUN_FLT_ flags see above */
__u16 count; /* Number of addresses */
- __u8 addr[0][ETH_ALEN];
+ __u8 addr[][ETH_ALEN];
};
#endif /* _UAPI__IF_TUN_H */
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index be328c59389d..44f2bb93e7e6 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>
@@ -25,9 +25,25 @@
* application.
*/
#define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped.
+ */
+#define XDP_USE_SG (1 << 4)
/* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#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;
@@ -70,12 +86,16 @@ struct xdp_umem_reg {
__u32 chunk_size;
__u32 headroom;
__u32 flags;
+ __u32 tx_metadata_len;
};
struct xdp_statistics {
- __u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+ __u64 rx_dropped; /* Dropped for other reasons */
__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+ __u64 rx_ring_full; /* Dropped due to rx ring being full */
+ __u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+ __u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
};
struct xdp_options {
@@ -96,6 +116,51 @@ struct xdp_options {
#define XSK_UNALIGNED_BUF_ADDR_MASK \
((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * 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 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.
+ */
+struct xsk_tx_metadata {
+ __u64 flags;
+
+ union {
+ struct {
+ /* XDP_TXMD_FLAGS_CHECKSUM */
+
+ /* Offset from desc->addr where checksumming should start. */
+ __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 {
+ /* XDP_TXMD_FLAGS_TIMESTAMP */
+ __u64 tx_timestamp;
+ } completion;
+ };
+};
+
/* Rx/Tx descriptor */
struct xdp_desc {
__u64 addr;
@@ -105,4 +170,14 @@ struct xdp_desc {
/* UMEM descriptor is __u64 */
-#endif /* _LINUX_IF_XDP_H */
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
+#define XDP_PKT_CONTD (1 << 0)
+
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
+#endif /* _UAPI_LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 8533bf07450f..ced0fc3c3aa5 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -20,6 +20,7 @@
#define _UAPI_LINUX_IN_H
#include <linux/types.h>
+#include <linux/stddef.h>
#include <linux/libc-compat.h>
#include <linux/socket.h>
@@ -68,6 +69,8 @@ enum {
#define IPPROTO_PIM IPPROTO_PIM
IPPROTO_COMP = 108, /* Compression Header Protocol */
#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_L2TP = 115, /* Layer 2 Tunnelling Protocol */
+#define IPPROTO_L2TP IPPROTO_L2TP
IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
#define IPPROTO_SCTP IPPROTO_SCTP
IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
@@ -76,8 +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
@@ -123,6 +130,7 @@ struct in_addr {
#define IP_CHECKSUM 23
#define IP_BIND_ADDRESS_NO_PORT 24
#define IP_RECVFRAGSIZE 25
+#define IP_RECVERR_RFC4884 26
/* IP_MTU_DISCOVER values */
#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
@@ -134,8 +142,8 @@ struct in_addr {
* this socket to prevent accepting spoofed ones.
*/
#define IP_PMTUDISC_INTERFACE 4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
- * fragmented if they exeed the interface mtu
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
+ * fragmented if they exceed the interface mtu
*/
#define IP_PMTUDISC_OMIT 5
@@ -158,6 +166,8 @@ struct in_addr {
#define MCAST_MSFILTER 48
#define IP_MULTICAST_ALL 49
#define IP_UNICAST_IF 50
+#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
#define MCAST_EXCLUDE 0
#define MCAST_INCLUDE 1
@@ -191,7 +201,10 @@ struct ip_msfilter {
__be32 imsf_interface;
__u32 imsf_fmode;
__u32 imsf_numsrc;
- __be32 imsf_slist[1];
+ union {
+ __be32 imsf_slist[1];
+ __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex);
+ };
};
#define IP_MSFILTER_SIZE(numsrc) \
@@ -210,11 +223,22 @@ struct group_source_req {
};
struct group_filter {
- __u32 gf_interface; /* interface index */
- struct __kernel_sockaddr_storage gf_group; /* multicast address */
- __u32 gf_fmode; /* filter mode */
- __u32 gf_numsrc; /* number of sources */
- struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+ union {
+ struct {
+ __u32 gf_interface_aux; /* interface index */
+ struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */
+ __u32 gf_fmode_aux; /* filter mode */
+ __u32 gf_numsrc_aux; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+ };
+ struct {
+ __u32 gf_interface; /* interface index */
+ struct __kernel_sockaddr_storage gf_group; /* multicast address */
+ __u32 gf_fmode; /* filter mode */
+ __u32 gf_numsrc; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */
+ };
+ };
};
#define GROUP_FILTER_SIZE(numsrc) \
@@ -288,6 +312,9 @@ struct sockaddr_in {
/* Address indicating an error return. */
#define INADDR_NONE ((unsigned long int) 0xffffffff)
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
/* Network number for local host loopback. */
#define IN_LOOPBACKNET 127
diff --git a/tools/include/uapi/linux/io_uring.h b/tools/include/uapi/linux/io_uring.h
new file mode 100644
index 000000000000..f1c16f817742
--- /dev/null
+++ b/tools/include/uapi/linux/io_uring.h
@@ -0,0 +1,757 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
+/*
+ * Header file for the io_uring interface.
+ *
+ * Copyright (C) 2019 Jens Axboe
+ * Copyright (C) 2019 Christoph Hellwig
+ */
+#ifndef LINUX_IO_URING_H
+#define LINUX_IO_URING_H
+
+#include <linux/fs.h>
+#include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+#include <linux/time_types.h>
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+ * IO submission data structure (Submission Queue Entry)
+ */
+struct io_uring_sqe {
+ __u8 opcode; /* type of operation for this sqe */
+ __u8 flags; /* IOSQE_ flags */
+ __u16 ioprio; /* ioprio for the request */
+ __s32 fd; /* file descriptor to do IO on */
+ union {
+ __u64 off; /* offset into file */
+ __u64 addr2;
+ struct {
+ __u32 cmd_op;
+ __u32 __pad1;
+ };
+ };
+ union {
+ __u64 addr; /* pointer to buffer or iovecs */
+ __u64 splice_off_in;
+ struct {
+ __u32 level;
+ __u32 optname;
+ };
+ };
+ __u32 len; /* buffer size or number of iovecs */
+ union {
+ __kernel_rwf_t rw_flags;
+ __u32 fsync_flags;
+ __u16 poll_events; /* compatibility */
+ __u32 poll32_events; /* word-reversed for BE */
+ __u32 sync_range_flags;
+ __u32 msg_flags;
+ __u32 timeout_flags;
+ __u32 accept_flags;
+ __u32 cancel_flags;
+ __u32 open_flags;
+ __u32 statx_flags;
+ __u32 fadvise_advice;
+ __u32 splice_flags;
+ __u32 rename_flags;
+ __u32 unlink_flags;
+ __u32 hardlink_flags;
+ __u32 xattr_flags;
+ __u32 msg_ring_flags;
+ __u32 uring_cmd_flags;
+ __u32 waitid_flags;
+ __u32 futex_flags;
+ };
+ __u64 user_data; /* data to be passed back at completion time */
+ /* pack this to avoid bogus arm OABI complaints */
+ union {
+ /* index into fixed buffers, if used */
+ __u16 buf_index;
+ /* for grouped buffer selection */
+ __u16 buf_group;
+ } __attribute__((packed));
+ /* personality to use, if used */
+ __u16 personality;
+ union {
+ __s32 splice_fd_in;
+ __u32 file_index;
+ __u32 optlen;
+ struct {
+ __u16 addr_len;
+ __u16 __pad3[1];
+ };
+ };
+ union {
+ struct {
+ __u64 addr3;
+ __u64 __pad2[1];
+ };
+ __u64 optval;
+ /*
+ * If the ring is initialized with IORING_SETUP_SQE128, then
+ * this field is used for 80 bytes of arbitrary command data
+ */
+ __u8 cmd[0];
+ };
+};
+
+/*
+ * If sqe->file_index is set to this for opcodes that instantiate a new
+ * direct descriptor (like openat/openat2/accept), then io_uring will allocate
+ * an available direct descriptor instead of having the application pass one
+ * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE
+ * if the space is full.
+ */
+#define IORING_FILE_INDEX_ALLOC (~0U)
+
+enum {
+ IOSQE_FIXED_FILE_BIT,
+ IOSQE_IO_DRAIN_BIT,
+ IOSQE_IO_LINK_BIT,
+ IOSQE_IO_HARDLINK_BIT,
+ IOSQE_ASYNC_BIT,
+ IOSQE_BUFFER_SELECT_BIT,
+ IOSQE_CQE_SKIP_SUCCESS_BIT,
+};
+
+/*
+ * sqe->flags
+ */
+/* use fixed fileset */
+#define IOSQE_FIXED_FILE (1U << IOSQE_FIXED_FILE_BIT)
+/* issue after inflight IO */
+#define IOSQE_IO_DRAIN (1U << IOSQE_IO_DRAIN_BIT)
+/* links next sqe */
+#define IOSQE_IO_LINK (1U << IOSQE_IO_LINK_BIT)
+/* like LINK, but stronger */
+#define IOSQE_IO_HARDLINK (1U << IOSQE_IO_HARDLINK_BIT)
+/* always go async */
+#define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT)
+/* don't post CQE if request succeeded */
+#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
+
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
+#define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */
+#define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */
+#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */
+#define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */
+#define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */
+#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */
+#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */
+/*
+ * Cooperative task running. When requests complete, they often require
+ * forcing the submitter to transition to the kernel to complete. If this
+ * flag is set, work will be done when the task transitions anyway, rather
+ * than force an inter-processor interrupt reschedule. This avoids interrupting
+ * a task running in userspace, and saves an IPI.
+ */
+#define IORING_SETUP_COOP_TASKRUN (1U << 8)
+/*
+ * If COOP_TASKRUN is set, get notified if task work is available for
+ * running and a kernel transition would be needed to run it. This sets
+ * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
+ */
+#define IORING_SETUP_TASKRUN_FLAG (1U << 9)
+#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */
+#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */
+/*
+ * Only one task is allowed to submit requests
+ */
+#define IORING_SETUP_SINGLE_ISSUER (1U << 12)
+
+/*
+ * Defer running task work to get events.
+ * Rather than running bits of task work whenever the task transitions
+ * try to do it just before it is needed.
+ */
+#define IORING_SETUP_DEFER_TASKRUN (1U << 13)
+
+/*
+ * Application provides the memory for the rings
+ */
+#define IORING_SETUP_NO_MMAP (1U << 14)
+
+/*
+ * Register the ring fd in itself for use with
+ * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather
+ * than an fd.
+ */
+#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15)
+
+/*
+ * Removes indirection through the SQ index array.
+ */
+#define IORING_SETUP_NO_SQARRAY (1U << 16)
+
+enum io_uring_op {
+ IORING_OP_NOP,
+ IORING_OP_READV,
+ IORING_OP_WRITEV,
+ IORING_OP_FSYNC,
+ IORING_OP_READ_FIXED,
+ IORING_OP_WRITE_FIXED,
+ IORING_OP_POLL_ADD,
+ IORING_OP_POLL_REMOVE,
+ IORING_OP_SYNC_FILE_RANGE,
+ IORING_OP_SENDMSG,
+ IORING_OP_RECVMSG,
+ IORING_OP_TIMEOUT,
+ IORING_OP_TIMEOUT_REMOVE,
+ IORING_OP_ACCEPT,
+ IORING_OP_ASYNC_CANCEL,
+ IORING_OP_LINK_TIMEOUT,
+ IORING_OP_CONNECT,
+ IORING_OP_FALLOCATE,
+ IORING_OP_OPENAT,
+ IORING_OP_CLOSE,
+ IORING_OP_FILES_UPDATE,
+ IORING_OP_STATX,
+ IORING_OP_READ,
+ IORING_OP_WRITE,
+ IORING_OP_FADVISE,
+ IORING_OP_MADVISE,
+ IORING_OP_SEND,
+ IORING_OP_RECV,
+ IORING_OP_OPENAT2,
+ IORING_OP_EPOLL_CTL,
+ IORING_OP_SPLICE,
+ IORING_OP_PROVIDE_BUFFERS,
+ IORING_OP_REMOVE_BUFFERS,
+ IORING_OP_TEE,
+ IORING_OP_SHUTDOWN,
+ IORING_OP_RENAMEAT,
+ IORING_OP_UNLINKAT,
+ IORING_OP_MKDIRAT,
+ IORING_OP_SYMLINKAT,
+ IORING_OP_LINKAT,
+ IORING_OP_MSG_RING,
+ IORING_OP_FSETXATTR,
+ IORING_OP_SETXATTR,
+ IORING_OP_FGETXATTR,
+ IORING_OP_GETXATTR,
+ IORING_OP_SOCKET,
+ IORING_OP_URING_CMD,
+ IORING_OP_SEND_ZC,
+ IORING_OP_SENDMSG_ZC,
+ IORING_OP_READ_MULTISHOT,
+ IORING_OP_WAITID,
+ IORING_OP_FUTEX_WAIT,
+ IORING_OP_FUTEX_WAKE,
+ IORING_OP_FUTEX_WAITV,
+
+ /* this goes last, obviously */
+ IORING_OP_LAST,
+};
+
+/*
+ * sqe->uring_cmd_flags top 8bits aren't available for userspace
+ * IORING_URING_CMD_FIXED use registered buffer; pass this flag
+ * along with setting sqe->buf_index.
+ */
+#define IORING_URING_CMD_FIXED (1U << 0)
+#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED
+
+
+/*
+ * sqe->fsync_flags
+ */
+#define IORING_FSYNC_DATASYNC (1U << 0)
+
+/*
+ * sqe->timeout_flags
+ */
+#define IORING_TIMEOUT_ABS (1U << 0)
+#define IORING_TIMEOUT_UPDATE (1U << 1)
+#define IORING_TIMEOUT_BOOTTIME (1U << 2)
+#define IORING_TIMEOUT_REALTIME (1U << 3)
+#define IORING_LINK_TIMEOUT_UPDATE (1U << 4)
+#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5)
+#define IORING_TIMEOUT_MULTISHOT (1U << 6)
+#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
+#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
+/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */
+
+/*
+ * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the
+ * command flags for POLL_ADD are stored in sqe->len.
+ *
+ * IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if
+ * the poll handler will continue to report
+ * CQEs on behalf of the same SQE.
+ *
+ * IORING_POLL_UPDATE Update existing poll request, matching
+ * sqe->addr as the old user_data field.
+ *
+ * IORING_POLL_LEVEL Level triggered poll.
+ */
+#define IORING_POLL_ADD_MULTI (1U << 0)
+#define IORING_POLL_UPDATE_EVENTS (1U << 1)
+#define IORING_POLL_UPDATE_USER_DATA (1U << 2)
+#define IORING_POLL_ADD_LEVEL (1U << 3)
+
+/*
+ * ASYNC_CANCEL flags.
+ *
+ * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key
+ * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the
+ * request 'user_data'
+ * IORING_ASYNC_CANCEL_ANY Match any request
+ * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor
+ * IORING_ASYNC_CANCEL_USERDATA Match on user_data, default for no other key
+ * IORING_ASYNC_CANCEL_OP Match request based on opcode
+ */
+#define IORING_ASYNC_CANCEL_ALL (1U << 0)
+#define IORING_ASYNC_CANCEL_FD (1U << 1)
+#define IORING_ASYNC_CANCEL_ANY (1U << 2)
+#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3)
+#define IORING_ASYNC_CANCEL_USERDATA (1U << 4)
+#define IORING_ASYNC_CANCEL_OP (1U << 5)
+
+/*
+ * send/sendmsg and recv/recvmsg flags (sqe->ioprio)
+ *
+ * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send
+ * or receive and arm poll if that yields an
+ * -EAGAIN result, arm poll upfront and skip
+ * the initial transfer attempt.
+ *
+ * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if
+ * the handler will continue to report
+ * CQEs on behalf of the same SQE.
+ *
+ * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in
+ * the buf_index field.
+ *
+ * IORING_SEND_ZC_REPORT_USAGE
+ * If set, SEND[MSG]_ZC should report
+ * the zerocopy usage in cqe.res
+ * for the IORING_CQE_F_NOTIF cqe.
+ * 0 is reported if zerocopy was actually possible.
+ * IORING_NOTIF_USAGE_ZC_COPIED if data was copied
+ * (at least partially).
+ */
+#define IORING_RECVSEND_POLL_FIRST (1U << 0)
+#define IORING_RECV_MULTISHOT (1U << 1)
+#define IORING_RECVSEND_FIXED_BUF (1U << 2)
+#define IORING_SEND_ZC_REPORT_USAGE (1U << 3)
+
+/*
+ * cqe.res for IORING_CQE_F_NOTIF if
+ * IORING_SEND_ZC_REPORT_USAGE was requested
+ *
+ * It should be treated as a flag, all other
+ * bits of cqe.res should be treated as reserved!
+ */
+#define IORING_NOTIF_USAGE_ZC_COPIED (1U << 31)
+
+/*
+ * accept flags stored in sqe->ioprio
+ */
+#define IORING_ACCEPT_MULTISHOT (1U << 0)
+
+/*
+ * IORING_OP_MSG_RING command types, stored in sqe->addr
+ */
+enum {
+ IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */
+ IORING_MSG_SEND_FD, /* send a registered fd to another ring */
+};
+
+/*
+ * IORING_OP_MSG_RING flags (sqe->msg_ring_flags)
+ *
+ * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not
+ * applicable for IORING_MSG_DATA, obviously.
+ */
+#define IORING_MSG_RING_CQE_SKIP (1U << 0)
+/* Pass through the flags from sqe->file_index to cqe->flags */
+#define IORING_MSG_RING_FLAGS_PASS (1U << 1)
+
+/*
+ * IO completion data structure (Completion Queue Entry)
+ */
+struct io_uring_cqe {
+ __u64 user_data; /* sqe->data submission passed back */
+ __s32 res; /* result code for this event */
+ __u32 flags;
+
+ /*
+ * If the ring is initialized with IORING_SETUP_CQE32, then this field
+ * contains 16-bytes of padding, doubling the size of the CQE.
+ */
+ __u64 big_cqe[];
+};
+
+/*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID
+ * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries
+ * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv
+ * IORING_CQE_F_NOTIF Set for notification CQEs. Can be used to distinct
+ * them from sends.
+ */
+#define IORING_CQE_F_BUFFER (1U << 0)
+#define IORING_CQE_F_MORE (1U << 1)
+#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2)
+#define IORING_CQE_F_NOTIF (1U << 3)
+
+enum {
+ IORING_CQE_BUFFER_SHIFT = 16,
+};
+
+/*
+ * Magic offsets for the application to mmap the data it needs
+ */
+#define IORING_OFF_SQ_RING 0ULL
+#define IORING_OFF_CQ_RING 0x8000000ULL
+#define IORING_OFF_SQES 0x10000000ULL
+#define IORING_OFF_PBUF_RING 0x80000000ULL
+#define IORING_OFF_PBUF_SHIFT 16
+#define IORING_OFF_MMAP_MASK 0xf8000000ULL
+
+/*
+ * Filled with the offset for mmap(2)
+ */
+struct io_sqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 flags;
+ __u32 dropped;
+ __u32 array;
+ __u32 resv1;
+ __u64 user_addr;
+};
+
+/*
+ * sq_ring->flags
+ */
+#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */
+#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */
+#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */
+
+struct io_cqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 overflow;
+ __u32 cqes;
+ __u32 flags;
+ __u32 resv1;
+ __u64 user_addr;
+};
+
+/*
+ * cq_ring->flags
+ */
+
+/* disable eventfd notifications */
+#define IORING_CQ_EVENTFD_DISABLED (1U << 0)
+
+/*
+ * io_uring_enter(2) flags
+ */
+#define IORING_ENTER_GETEVENTS (1U << 0)
+#define IORING_ENTER_SQ_WAKEUP (1U << 1)
+#define IORING_ENTER_SQ_WAIT (1U << 2)
+#define IORING_ENTER_EXT_ARG (1U << 3)
+#define IORING_ENTER_REGISTERED_RING (1U << 4)
+
+/*
+ * Passed in for io_uring_setup(2). Copied back with updated info on success
+ */
+struct io_uring_params {
+ __u32 sq_entries;
+ __u32 cq_entries;
+ __u32 flags;
+ __u32 sq_thread_cpu;
+ __u32 sq_thread_idle;
+ __u32 features;
+ __u32 wq_fd;
+ __u32 resv[3];
+ struct io_sqring_offsets sq_off;
+ struct io_cqring_offsets cq_off;
+};
+
+/*
+ * io_uring_params->features flags
+ */
+#define IORING_FEAT_SINGLE_MMAP (1U << 0)
+#define IORING_FEAT_NODROP (1U << 1)
+#define IORING_FEAT_SUBMIT_STABLE (1U << 2)
+#define IORING_FEAT_RW_CUR_POS (1U << 3)
+#define IORING_FEAT_CUR_PERSONALITY (1U << 4)
+#define IORING_FEAT_FAST_POLL (1U << 5)
+#define IORING_FEAT_POLL_32BITS (1U << 6)
+#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7)
+#define IORING_FEAT_EXT_ARG (1U << 8)
+#define IORING_FEAT_NATIVE_WORKERS (1U << 9)
+#define IORING_FEAT_RSRC_TAGS (1U << 10)
+#define IORING_FEAT_CQE_SKIP (1U << 11)
+#define IORING_FEAT_LINKED_FILE (1U << 12)
+#define IORING_FEAT_REG_REG_RING (1U << 13)
+
+/*
+ * io_uring_register(2) opcodes and arguments
+ */
+enum {
+ IORING_REGISTER_BUFFERS = 0,
+ IORING_UNREGISTER_BUFFERS = 1,
+ IORING_REGISTER_FILES = 2,
+ IORING_UNREGISTER_FILES = 3,
+ IORING_REGISTER_EVENTFD = 4,
+ IORING_UNREGISTER_EVENTFD = 5,
+ IORING_REGISTER_FILES_UPDATE = 6,
+ IORING_REGISTER_EVENTFD_ASYNC = 7,
+ IORING_REGISTER_PROBE = 8,
+ IORING_REGISTER_PERSONALITY = 9,
+ IORING_UNREGISTER_PERSONALITY = 10,
+ IORING_REGISTER_RESTRICTIONS = 11,
+ IORING_REGISTER_ENABLE_RINGS = 12,
+
+ /* extended with tagging */
+ IORING_REGISTER_FILES2 = 13,
+ IORING_REGISTER_FILES_UPDATE2 = 14,
+ IORING_REGISTER_BUFFERS2 = 15,
+ IORING_REGISTER_BUFFERS_UPDATE = 16,
+
+ /* set/clear io-wq thread affinities */
+ IORING_REGISTER_IOWQ_AFF = 17,
+ IORING_UNREGISTER_IOWQ_AFF = 18,
+
+ /* set/get max number of io-wq workers */
+ IORING_REGISTER_IOWQ_MAX_WORKERS = 19,
+
+ /* register/unregister io_uring fd with the ring */
+ IORING_REGISTER_RING_FDS = 20,
+ IORING_UNREGISTER_RING_FDS = 21,
+
+ /* register ring based provide buffer group */
+ IORING_REGISTER_PBUF_RING = 22,
+ IORING_UNREGISTER_PBUF_RING = 23,
+
+ /* sync cancelation API */
+ IORING_REGISTER_SYNC_CANCEL = 24,
+
+ /* register a range of fixed file slots for automatic slot allocation */
+ IORING_REGISTER_FILE_ALLOC_RANGE = 25,
+
+ /* this goes last */
+ IORING_REGISTER_LAST,
+
+ /* flag added to the opcode to use a registered ring fd */
+ IORING_REGISTER_USE_REGISTERED_RING = 1U << 31
+};
+
+/* io-wq worker categories */
+enum {
+ IO_WQ_BOUND,
+ IO_WQ_UNBOUND,
+};
+
+/* deprecated, see struct io_uring_rsrc_update */
+struct io_uring_files_update {
+ __u32 offset;
+ __u32 resv;
+ __aligned_u64 /* __s32 * */ fds;
+};
+
+/*
+ * Register a fully sparse file space, rather than pass in an array of all
+ * -1 file descriptors.
+ */
+#define IORING_RSRC_REGISTER_SPARSE (1U << 0)
+
+struct io_uring_rsrc_register {
+ __u32 nr;
+ __u32 flags;
+ __u64 resv2;
+ __aligned_u64 data;
+ __aligned_u64 tags;
+};
+
+struct io_uring_rsrc_update {
+ __u32 offset;
+ __u32 resv;
+ __aligned_u64 data;
+};
+
+struct io_uring_rsrc_update2 {
+ __u32 offset;
+ __u32 resv;
+ __aligned_u64 data;
+ __aligned_u64 tags;
+ __u32 nr;
+ __u32 resv2;
+};
+
+/* Skip updating fd indexes set to this value in the fd table */
+#define IORING_REGISTER_FILES_SKIP (-2)
+
+#define IO_URING_OP_SUPPORTED (1U << 0)
+
+struct io_uring_probe_op {
+ __u8 op;
+ __u8 resv;
+ __u16 flags; /* IO_URING_OP_* flags */
+ __u32 resv2;
+};
+
+struct io_uring_probe {
+ __u8 last_op; /* last opcode supported */
+ __u8 ops_len; /* length of ops[] array below */
+ __u16 resv;
+ __u32 resv2[3];
+ struct io_uring_probe_op ops[];
+};
+
+struct io_uring_restriction {
+ __u16 opcode;
+ union {
+ __u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
+ __u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */
+ __u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */
+ };
+ __u8 resv;
+ __u32 resv2[3];
+};
+
+struct io_uring_buf {
+ __u64 addr;
+ __u32 len;
+ __u16 bid;
+ __u16 resv;
+};
+
+struct io_uring_buf_ring {
+ union {
+ /*
+ * To avoid spilling into more pages than we need to, the
+ * ring tail is overlaid with the io_uring_buf->resv field.
+ */
+ struct {
+ __u64 resv1;
+ __u32 resv2;
+ __u16 resv3;
+ __u16 tail;
+ };
+ __DECLARE_FLEX_ARRAY(struct io_uring_buf, bufs);
+ };
+};
+
+/*
+ * Flags for IORING_REGISTER_PBUF_RING.
+ *
+ * IOU_PBUF_RING_MMAP: If set, kernel will allocate the memory for the ring.
+ * The application must not set a ring_addr in struct
+ * io_uring_buf_reg, instead it must subsequently call
+ * mmap(2) with the offset set as:
+ * IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT)
+ * to get a virtual mapping for the ring.
+ */
+enum {
+ IOU_PBUF_RING_MMAP = 1,
+};
+
+/* argument for IORING_(UN)REGISTER_PBUF_RING */
+struct io_uring_buf_reg {
+ __u64 ring_addr;
+ __u32 ring_entries;
+ __u16 bgid;
+ __u16 flags;
+ __u64 resv[3];
+};
+
+/*
+ * io_uring_restriction->opcode values
+ */
+enum {
+ /* Allow an io_uring_register(2) opcode */
+ IORING_RESTRICTION_REGISTER_OP = 0,
+
+ /* Allow an sqe opcode */
+ IORING_RESTRICTION_SQE_OP = 1,
+
+ /* Allow sqe flags */
+ IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2,
+
+ /* Require sqe flags (these flags must be set on each submission) */
+ IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3,
+
+ IORING_RESTRICTION_LAST
+};
+
+struct io_uring_getevents_arg {
+ __u64 sigmask;
+ __u32 sigmask_sz;
+ __u32 pad;
+ __u64 ts;
+};
+
+/*
+ * Argument for IORING_REGISTER_SYNC_CANCEL
+ */
+struct io_uring_sync_cancel_reg {
+ __u64 addr;
+ __s32 fd;
+ __u32 flags;
+ struct __kernel_timespec timeout;
+ __u8 opcode;
+ __u8 pad[7];
+ __u64 pad2[3];
+};
+
+/*
+ * Argument for IORING_REGISTER_FILE_ALLOC_RANGE
+ * The range is specified as [off, off + len)
+ */
+struct io_uring_file_index_range {
+ __u32 off;
+ __u32 len;
+ __u64 resv;
+};
+
+struct io_uring_recvmsg_out {
+ __u32 namelen;
+ __u32 controllen;
+ __u32 payloadlen;
+ __u32 flags;
+};
+
+/*
+ * Argument for IORING_OP_URING_CMD when file is a socket
+ */
+enum {
+ SOCKET_URING_OP_SIOCINQ = 0,
+ SOCKET_URING_OP_SIOCOUTQ,
+ SOCKET_URING_OP_GETSOCKOPT,
+ SOCKET_URING_OP_SETSOCKOPT,
+};
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 4fdf30316582..d00b85cb168c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -8,6 +8,7 @@
* Note: you must update KVM_API_VERSION if you change this interface.
*/
+#include <linux/const.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/ioctl.h>
@@ -15,100 +16,41 @@
#define KVM_API_VERSION 12
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT 16
-
-#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE 12
-#define KVM_TRC_CYCLE_SIZE 8
-#define KVM_TRC_EXTRA_MAX 7
-
-#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
- __u32 buf_size;
- __u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
- _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
- __u32 enabled;
- __u32 padding;
- __u64 address;
-};
-
-struct kvm_debug_guest {
- __u32 enabled;
- __u32 pad;
- struct kvm_breakpoint breakpoints[4];
- __u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
+/*
+ * Backwards-compatible definitions.
+ */
+#define __KVM_HAVE_GUEST_DEBUG
-/* for KVM_CREATE_MEMORY_REGION */
-struct kvm_memory_region {
+/* for KVM_SET_USER_MEMORY_REGION */
+struct kvm_userspace_memory_region {
__u32 slot;
__u32 flags;
__u64 guest_phys_addr;
__u64 memory_size; /* bytes */
+ __u64 userspace_addr; /* start of the userspace allocated memory */
};
-/* for KVM_SET_USER_MEMORY_REGION */
-struct kvm_userspace_memory_region {
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
__u32 slot;
__u32 flags;
__u64 guest_phys_addr;
- __u64 memory_size; /* bytes */
- __u64 userspace_addr; /* start of the userspace allocated memory */
+ __u64 memory_size;
+ __u64 userspace_addr;
+ __u64 guest_memfd_offset;
+ __u32 guest_memfd;
+ __u32 pad1;
+ __u64 pad2[14];
};
/*
- * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
- * other bits are reserved for kvm internal use which are defined in
- * include/linux/kvm_host.h.
+ * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
+ * userspace, other bits are reserved for kvm internal use which are defined
+ * in include/linux/kvm_host.h.
*/
#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
#define KVM_MEM_READONLY (1UL << 1)
+#define KVM_MEM_GUEST_MEMFD (1UL << 2)
/* for KVM_IRQ_LINE */
struct kvm_irq_level {
@@ -148,43 +90,6 @@ struct kvm_pit_config {
#define KVM_PIT_SPEAKER_DUMMY 1
-struct kvm_s390_skeys {
- __u64 start_gfn;
- __u64 count;
- __u64 skeydata_addr;
- __u32 flags;
- __u32 reserved[9];
-};
-
-#define KVM_S390_CMMA_PEEK (1 << 0)
-
-/**
- * kvm_s390_cmma_log - Used for CMMA migration.
- *
- * Used both for input and output.
- *
- * @start_gfn: Guest page number to start from.
- * @count: Size of the result buffer.
- * @flags: Control operation mode via KVM_S390_CMMA_* flags
- * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
- * pages are still remaining.
- * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
- * in the PGSTE.
- * @values: Pointer to the values buffer.
- *
- * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
- */
-struct kvm_s390_cmma_log {
- __u64 start_gfn;
- __u32 count;
- __u32 flags;
- union {
- __u64 remaining;
- __u64 mask;
- };
- __u64 values;
-};
-
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
@@ -216,6 +121,20 @@ struct kvm_hyperv_exit {
} u;
};
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL 1
+ __u32 type;
+ union {
+ struct {
+ __u32 longmode;
+ __u32 cpl;
+ __u64 input;
+ __u64 result;
+ __u64 params[6];
+ } hcall;
+ } u;
+};
+
#define KVM_S390_GET_SKEYS_NONE 1
#define KVM_S390_SKEYS_MAX 1048576
@@ -248,6 +167,17 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_IOAPIC_EOI 26
#define KVM_EXIT_HYPERV 27
#define KVM_EXIT_ARM_NISV 28
+#define KVM_EXIT_X86_RDMSR 29
+#define KVM_EXIT_X86_WRMSR 30
+#define KVM_EXIT_DIRTY_RING_FULL 31
+#define KVM_EXIT_AP_RESET_HOLD 32
+#define KVM_EXIT_X86_BUS_LOCK 33
+#define KVM_EXIT_XEN 34
+#define KVM_EXIT_RISCV_SBI 35
+#define KVM_EXIT_RISCV_CSR 36
+#define KVM_EXIT_NOTIFY 37
+#define KVM_EXIT_LOONGARCH_IOCSR 38
+#define KVM_EXIT_MEMORY_FAULT 39
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -259,11 +189,27 @@ struct kvm_hyperv_exit {
/* Encounter unexpected vm-exit reason */
#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4
+/* 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 */
@@ -289,6 +235,7 @@ struct kvm_run {
/* KVM_EXIT_FAIL_ENTRY */
struct {
__u64 hardware_entry_failure_reason;
+ __u32 cpu;
} fail_entry;
/* KVM_EXIT_EXCEPTION */
struct {
@@ -316,13 +263,25 @@ struct kvm_run {
__u32 len;
__u8 is_write;
} mmio;
+ /* KVM_EXIT_LOONGARCH_IOCSR */
+ struct {
+ __u64 phys_addr;
+ __u8 data[8];
+ __u32 len;
+ __u8 is_write;
+ } iocsr_io;
/* KVM_EXIT_HYPERCALL */
struct {
__u64 nr;
__u64 args[6];
__u64 ret;
- __u32 longmode;
- __u32 pad;
+
+ union {
+#ifndef __KERNEL__
+ __u32 longmode;
+#endif
+ __u64 flags;
+ };
} hypercall;
/* KVM_EXIT_TPR_ACCESS */
struct {
@@ -337,11 +296,6 @@ struct kvm_run {
__u32 ipb;
} s390_sieic;
/* KVM_EXIT_S390_RESET */
-#define KVM_S390_RESET_POR 1
-#define KVM_S390_RESET_CLEAR 2
-#define KVM_S390_RESET_SUBSYSTEM 4
-#define KVM_S390_RESET_CPU_INIT 8
-#define KVM_S390_RESET_IPL 16
__u64 s390_reset_flags;
/* KVM_EXIT_S390_UCONTROL */
struct {
@@ -361,6 +315,35 @@ struct kvm_run {
__u32 ndata;
__u64 data[16];
} internal;
+ /*
+ * KVM_INTERNAL_ERROR_EMULATION
+ *
+ * "struct emulation_failure" is an overlay of "struct internal"
+ * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+ * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error
+ * sub-types, this struct is ABI! It also needs to be backwards
+ * compatible with "struct internal". Take special care that
+ * "ndata" is correct, that new fields are enumerated in "flags",
+ * and that each flag enumerates fields that are 64-bit aligned
+ * and sized (so that ndata+internal.data[] is valid/accurate).
+ *
+ * Space beyond the defined fields may be used to store arbitrary
+ * debug information relating to the emulation failure. It is
+ * accounted for in "ndata" but the format is unspecified and is
+ * not represented in "flags". Any such information is *not* ABI!
+ */
+ struct {
+ __u32 suberror;
+ __u32 ndata;
+ __u64 flags;
+ union {
+ struct {
+ __u8 insn_size;
+ __u8 insn_bytes[15];
+ };
+ };
+ /* Arbitrary debug data may follow. */
+ } emulation_failure;
/* KVM_EXIT_OSI */
struct {
__u64 gprs[32];
@@ -389,8 +372,18 @@ struct kvm_run {
#define KVM_SYSTEM_EVENT_SHUTDOWN 1
#define KVM_SYSTEM_EVENT_RESET 2
#define KVM_SYSTEM_EVENT_CRASH 3
+#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;
- __u64 flags;
+ __u32 ndata;
+ union {
+#ifndef __KERNEL__
+ __u64 flags;
+#endif
+ __u64 data[16];
+ };
} system_event;
/* KVM_EXIT_S390_STSI */
struct {
@@ -412,6 +405,48 @@ struct kvm_run {
__u64 esr_iss;
__u64 fault_ipa;
} arm_nisv;
+ /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+ struct {
+ __u8 error; /* user -> kernel */
+ __u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \
+ KVM_MSR_EXIT_REASON_UNKNOWN | \
+ KVM_MSR_EXIT_REASON_FILTER)
+ __u32 reason; /* kernel -> user */
+ __u32 index; /* kernel -> user */
+ __u64 data; /* kernel <-> user */
+ } msr;
+ /* KVM_EXIT_XEN */
+ struct kvm_xen_exit xen;
+ /* KVM_EXIT_RISCV_SBI */
+ struct {
+ unsigned long extension_id;
+ unsigned long function_id;
+ unsigned long args[6];
+ unsigned long ret[2];
+ } riscv_sbi;
+ /* KVM_EXIT_RISCV_CSR */
+ struct {
+ unsigned long csr_num;
+ unsigned long new_value;
+ unsigned long write_mask;
+ unsigned long ret_value;
+ } riscv_csr;
+ /* KVM_EXIT_NOTIFY */
+ struct {
+#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0)
+ __u32 flags;
+ } notify;
+ /* KVM_EXIT_MEMORY_FAULT */
+ struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3)
+ __u64 flags;
+ __u64 gpa;
+ __u64 size;
+ } memory_fault;
/* Fix the size of the union. */
char padding[256];
};
@@ -458,7 +493,7 @@ struct kvm_coalesced_mmio {
struct kvm_coalesced_mmio_ring {
__u32 first, last;
- struct kvm_coalesced_mmio coalesced_mmio[0];
+ struct kvm_coalesced_mmio coalesced_mmio[];
};
#define KVM_COALESCED_MMIO_MAX \
@@ -478,29 +513,6 @@ struct kvm_translation {
__u8 pad[5];
};
-/* for KVM_S390_MEM_OP */
-struct kvm_s390_mem_op {
- /* in */
- __u64 gaddr; /* the guest address */
- __u64 flags; /* flags */
- __u32 size; /* amount of bytes */
- __u32 op; /* type of operation */
- __u64 buf; /* buffer in userspace */
- union {
- __u8 ar; /* the access register number */
- __u32 sida_offset; /* offset into the sida */
- __u8 reserved[32]; /* should be set to 0 */
- };
-};
-/* types for kvm_s390_mem_op->op */
-#define KVM_S390_MEMOP_LOGICAL_READ 0
-#define KVM_S390_MEMOP_LOGICAL_WRITE 1
-#define KVM_S390_MEMOP_SIDA_READ 2
-#define KVM_S390_MEMOP_SIDA_WRITE 3
-/* flags for kvm_s390_mem_op->flags */
-#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
-#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
-
/* for KVM_INTERRUPT */
struct kvm_interrupt {
/* in */
@@ -531,7 +543,7 @@ struct kvm_clear_dirty_log {
/* for KVM_SET_SIGNAL_MASK */
struct kvm_signal_mask {
__u32 len;
- __u8 sigset[0];
+ __u8 sigset[];
};
/* for KVM_TPR_ACCESS_REPORTING */
@@ -558,129 +570,13 @@ struct kvm_vapic_addr {
#define KVM_MP_STATE_CHECK_STOP 6
#define KVM_MP_STATE_OPERATING 7
#define KVM_MP_STATE_LOAD 8
+#define KVM_MP_STATE_AP_RESET_HOLD 9
+#define KVM_MP_STATE_SUSPENDED 10
struct kvm_mp_state {
__u32 mp_state;
};
-struct kvm_s390_psw {
- __u64 mask;
- __u64 addr;
-};
-
-/* valid values for type in kvm_s390_interrupt */
-#define KVM_S390_SIGP_STOP 0xfffe0000u
-#define KVM_S390_PROGRAM_INT 0xfffe0001u
-#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
-#define KVM_S390_RESTART 0xfffe0003u
-#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
-#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
-#define KVM_S390_MCHK 0xfffe1000u
-#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
-#define KVM_S390_INT_CPU_TIMER 0xffff1005u
-#define KVM_S390_INT_VIRTIO 0xffff2603u
-#define KVM_S390_INT_SERVICE 0xffff2401u
-#define KVM_S390_INT_EMERGENCY 0xffff1201u
-#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
-/* Anything below 0xfffe0000u is taken by INT_IO */
-#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
- (((schid)) | \
- ((ssid) << 16) | \
- ((cssid) << 18) | \
- ((ai) << 26))
-#define KVM_S390_INT_IO_MIN 0x00000000u
-#define KVM_S390_INT_IO_MAX 0xfffdffffu
-#define KVM_S390_INT_IO_AI_MASK 0x04000000u
-
-
-struct kvm_s390_interrupt {
- __u32 type;
- __u32 parm;
- __u64 parm64;
-};
-
-struct kvm_s390_io_info {
- __u16 subchannel_id;
- __u16 subchannel_nr;
- __u32 io_int_parm;
- __u32 io_int_word;
-};
-
-struct kvm_s390_ext_info {
- __u32 ext_params;
- __u32 pad;
- __u64 ext_params2;
-};
-
-struct kvm_s390_pgm_info {
- __u64 trans_exc_code;
- __u64 mon_code;
- __u64 per_address;
- __u32 data_exc_code;
- __u16 code;
- __u16 mon_class_nr;
- __u8 per_code;
- __u8 per_atmid;
- __u8 exc_access_id;
- __u8 per_access_id;
- __u8 op_access_id;
-#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
-#define KVM_S390_PGM_FLAGS_ILC_0 0x02
-#define KVM_S390_PGM_FLAGS_ILC_1 0x04
-#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
-#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
- __u8 flags;
- __u8 pad[2];
-};
-
-struct kvm_s390_prefix_info {
- __u32 address;
-};
-
-struct kvm_s390_extcall_info {
- __u16 code;
-};
-
-struct kvm_s390_emerg_info {
- __u16 code;
-};
-
-#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
-struct kvm_s390_stop_info {
- __u32 flags;
-};
-
-struct kvm_s390_mchk_info {
- __u64 cr14;
- __u64 mcic;
- __u64 failing_storage_address;
- __u32 ext_damage_code;
- __u32 pad;
- __u8 fixed_logout[16];
-};
-
-struct kvm_s390_irq {
- __u64 type;
- union {
- struct kvm_s390_io_info io;
- struct kvm_s390_ext_info ext;
- struct kvm_s390_pgm_info pgm;
- struct kvm_s390_emerg_info emerg;
- struct kvm_s390_extcall_info extcall;
- struct kvm_s390_prefix_info prefix;
- struct kvm_s390_stop_info stop;
- struct kvm_s390_mchk_info mchk;
- char reserved[64];
- } u;
-};
-
-struct kvm_s390_irq_state {
- __u64 buf;
- __u32 flags; /* will stay unused for compatibility reasons */
- __u32 len;
- __u32 reserved[4]; /* will stay unused for compatibility reasons */
-};
-
/* for KVM_SET_GUEST_DEBUG */
#define KVM_GUESTDBG_ENABLE 0x00000001
@@ -722,10 +618,6 @@ 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)
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
@@ -736,50 +628,6 @@ struct kvm_enable_cap {
__u8 pad[64];
};
-/* for KVM_PPC_GET_PVINFO */
-
-#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
-
-struct kvm_ppc_pvinfo {
- /* out */
- __u32 flags;
- __u32 hcall[4];
- __u8 pad[108];
-};
-
-/* for KVM_PPC_GET_SMMU_INFO */
-#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
-
-struct kvm_ppc_one_page_size {
- __u32 page_shift; /* Page shift (or 0) */
- __u32 pte_enc; /* Encoding in the HPTE (>>12) */
-};
-
-struct kvm_ppc_one_seg_page_size {
- __u32 page_shift; /* Base page shift of segment (or 0) */
- __u32 slb_enc; /* SLB encoding for BookS */
- struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
-#define KVM_PPC_1T_SEGMENTS 0x00000002
-#define KVM_PPC_NO_HASH 0x00000004
-
-struct kvm_ppc_smmu_info {
- __u64 flags;
- __u32 slb_size;
- __u16 data_keys; /* # storage keys supported for data */
- __u16 instr_keys; /* # storage keys supported for instructions */
- struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
-struct kvm_ppc_resize_hpt {
- __u64 flags;
- __u32 shift;
- __u32 pad;
-};
-
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -789,9 +637,10 @@ struct kvm_ppc_resize_hpt {
#define KVM_VM_PPC_HV 1
#define KVM_VM_PPC_PR 2
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE 0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO 0
#define KVM_VM_MIPS_VZ 1
+#define KVM_VM_MIPS_TE 2
#define KVM_S390_SIE_PAGE_OFFSET 1
@@ -822,9 +671,6 @@ struct kvm_ppc_resize_hpt {
*/
#define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */
#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08
#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
@@ -851,9 +697,7 @@ struct kvm_ppc_resize_hpt {
/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
#define KVM_CAP_USER_NMI 22
-#ifdef __KVM_HAVE_GUEST_DEBUG
#define KVM_CAP_SET_GUEST_DEBUG 23
-#endif
#ifdef __KVM_HAVE_PIT
#define KVM_CAP_REINJECT_CONTROL 24
#endif
@@ -1031,8 +875,65 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_PPC_SECURE_GUEST 181
#define KVM_CAP_HALT_POLL 182
#define KVM_CAP_ASYNC_PF_INT 183
-
-#ifdef KVM_CAP_IRQ_ROUTING
+#define KVM_CAP_LAST_CPU 184
+#define KVM_CAP_SMALLER_MAXPHYADDR 185
+#define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
+#define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_SET_GUEST_DEBUG2 195
+#define KVM_CAP_SGX_ATTRIBUTE 196
+#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
+#define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_HYPERV_ENFORCE_CPUID 199
+#define KVM_CAP_SREGS2 200
+#define KVM_CAP_EXIT_HYPERCALL 201
+#define KVM_CAP_PPC_RPT_INVALIDATE 202
+#define KVM_CAP_BINARY_STATS_FD 203
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
+#define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
+#define KVM_CAP_VM_GPA_BITS 207
+#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
+#define KVM_CAP_S390_MEM_OP_EXTENSION 211
+#define KVM_CAP_PMU_CAPABILITY 212
+#define KVM_CAP_DISABLE_QUIRKS2 213
+#define KVM_CAP_VM_TSC_CONTROL 214
+#define KVM_CAP_SYSTEM_EVENT_DATA 215
+#define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
+#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
+#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
+#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
+#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#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
struct kvm_irq_routing_irqchip {
__u32 irqchip;
@@ -1062,11 +963,20 @@ struct kvm_irq_routing_hv_sint {
__u32 sint;
};
+struct kvm_irq_routing_xen_evtchn {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+};
+
+#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1))
+
/* gsi routing entry types */
#define KVM_IRQ_ROUTING_IRQCHIP 1
#define KVM_IRQ_ROUTING_MSI 2
#define KVM_IRQ_ROUTING_S390_ADAPTER 3
#define KVM_IRQ_ROUTING_HV_SINT 4
+#define KVM_IRQ_ROUTING_XEN_EVTCHN 5
struct kvm_irq_routing_entry {
__u32 gsi;
@@ -1078,6 +988,7 @@ struct kvm_irq_routing_entry {
struct kvm_irq_routing_msi msi;
struct kvm_irq_routing_s390_adapter adapter;
struct kvm_irq_routing_hv_sint hv_sint;
+ struct kvm_irq_routing_xen_evtchn xen_evtchn;
__u32 pad[8];
} u;
};
@@ -1085,36 +996,9 @@ struct kvm_irq_routing_entry {
struct kvm_irq_routing {
__u32 nr;
__u32 flags;
- struct kvm_irq_routing_entry entries[0];
+ struct kvm_irq_routing_entry entries[];
};
-#endif
-
-#ifdef KVM_CAP_MCE
-/* x86 MCE */
-struct kvm_x86_mce {
- __u64 status;
- __u64 addr;
- __u64 misc;
- __u64 mcg_status;
- __u8 bank;
- __u8 pad1[7];
- __u64 pad2[3];
-};
-#endif
-
-#ifdef KVM_CAP_XEN_HVM
-struct kvm_xen_hvm_config {
- __u32 flags;
- __u32 msr;
- __u64 blob_addr_32;
- __u64 blob_addr_64;
- __u8 blob_size_32;
- __u8 blob_size_64;
- __u8 pad2[30];
-};
-#endif
-
#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
/*
* Available with KVM_CAP_IRQFD_RESAMPLE
@@ -1137,11 +1021,16 @@ struct kvm_irqfd {
/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */
#define KVM_CLOCK_TSC_STABLE 2
+#define KVM_CLOCK_REALTIME (1 << 2)
+#define KVM_CLOCK_HOST_TSC (1 << 3)
struct kvm_clock_data {
__u64 clock;
__u32 flags;
- __u32 pad[9];
+ __u32 pad0;
+ __u64 realtime;
+ __u64 host_tsc;
+ __u32 pad[4];
};
/* For KVM_CAP_SW_TLB */
@@ -1178,9 +1067,14 @@ struct kvm_dirty_tlb {
#define KVM_REG_ARM64 0x6000000000000000ULL
#define KVM_REG_MIPS 0x7000000000000000ULL
#define KVM_REG_RISCV 0x8000000000000000ULL
+#define KVM_REG_LOONGARCH 0x9000000000000000ULL
#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
@@ -1193,7 +1087,7 @@ struct kvm_dirty_tlb {
struct kvm_reg_list {
__u64 n; /* number of regs */
- __u64 reg[0];
+ __u64 reg[];
};
struct kvm_one_reg {
@@ -1234,9 +1128,16 @@ struct kvm_device_attr {
__u64 addr; /* userspace address of attr data */
};
-#define KVM_DEV_VFIO_GROUP 1
-#define KVM_DEV_VFIO_GROUP_ADD 1
-#define KVM_DEV_VFIO_GROUP_DEL 2
+#define KVM_DEV_VFIO_FILE 1
+
+#define KVM_DEV_VFIO_FILE_ADD 1
+#define KVM_DEV_VFIO_FILE_DEL 2
+
+/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */
+#define KVM_DEV_VFIO_GROUP KVM_DEV_VFIO_FILE
+
+#define KVM_DEV_VFIO_GROUP_ADD KVM_DEV_VFIO_FILE_ADD
+#define KVM_DEV_VFIO_GROUP_DEL KVM_DEV_VFIO_FILE_DEL
#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3
enum kvm_device_type {
@@ -1260,7 +1161,17 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
KVM_DEV_TYPE_ARM_PV_TIME,
#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 {
@@ -1269,30 +1180,21 @@ struct kvm_vfio_spapr_tce {
};
/*
- * ioctls for VM fds
- */
-#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region)
-/*
* KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
* a vcpu fd.
*/
#define KVM_CREATE_VCPU _IO(KVMIO, 0x41)
#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log)
-/* KVM_SET_MEMORY_ALIAS is obsolete: */
-#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias)
#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44)
-#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45)
+#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */
#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
struct kvm_userspace_memory_region)
#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47)
#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+ struct kvm_userspace_memory_region2)
/* enable ucontrol for s390 */
-struct kvm_s390_ucas_mapping {
- __u64 user_addr;
- __u64 vcpu_addr;
- __u64 length;
-};
#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long)
@@ -1310,20 +1212,8 @@ struct kvm_s390_ucas_mapping {
_IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone)
#define KVM_UNREGISTER_COALESCED_MMIO \
_IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \
- struct kvm_assigned_pci_dev)
#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq)
#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71)
-#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
- struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \
- struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \
- struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd)
#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config)
#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78)
@@ -1336,12 +1226,10 @@ struct kvm_s390_ucas_mapping {
#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2)
/* Available with KVM_CAP_PPC_GET_PVINFO */
#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo)
-/* Available with KVM_CAP_TSC_CONTROL */
+/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with
+* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2)
#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \
- struct kvm_assigned_pci_dev)
/* Available with KVM_CAP_SIGNAL_MSI */
#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi)
/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1362,15 +1250,19 @@ struct kvm_s390_ucas_mapping {
/* Available with KVM_CAP_SPAPR_RESIZE_HPT */
#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */
#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg)
-/* Available with KVM_CAP_PPC_RADIX_MMU */
+/* Available with KVM_CAP_PPC_MMU_RADIX */
#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info)
/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
/* Available with KVM_CAP_PMU_EVENT_FILTER */
#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3)
+#define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset)
+#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO, 0xb6, struct reg_mask_range)
/* ioctl for vm fd */
#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)
@@ -1390,8 +1282,6 @@ struct kvm_s390_ucas_mapping {
#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs)
#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation)
#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87
#define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs)
#define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs)
#define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid)
@@ -1433,7 +1323,7 @@ struct kvm_s390_ucas_mapping {
#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs)
#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs)
/*
- * vcpu version available with KVM_ENABLE_CAP
+ * vcpu version available with KVM_CAP_ENABLE_CAP
* vm version available with KVM_CAP_ENABLE_CAP_VM
*/
#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap)
@@ -1489,7 +1379,7 @@ struct kvm_enc_region {
/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
/* Available with KVM_CAP_ARM_SVE */
@@ -1499,190 +1389,201 @@ struct kvm_enc_region {
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
-struct kvm_s390_pv_sec_parm {
- __u64 origin;
- __u64 length;
-};
-
-struct kvm_s390_pv_unp {
- __u64 addr;
- __u64 size;
- __u64 tweak;
-};
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
-enum pv_cmd_id {
- KVM_PV_ENABLE,
- KVM_PV_DISABLE,
- KVM_PV_SET_SEC_PARMS,
- KVM_PV_UNPACK,
- KVM_PV_VERIFY,
- KVM_PV_PREP_RESET,
- KVM_PV_UNSHARE_ALL,
-};
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
-struct kvm_pv_cmd {
- __u32 cmd; /* Command to be executed */
- __u16 rc; /* Ultravisor return code */
- __u16 rrc; /* Ultravisor return reason code */
- __u64 data; /* Data or address */
- __u32 flags; /* flags for future extensions. Must be 0 for now */
- __u32 reserved[3];
-};
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7)
-/* Available with KVM_CAP_S390_PROTECTED */
-#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr)
-/* Secure Encrypted Virtualization command */
-enum sev_cmd_id {
- /* Guest initialization commands */
- KVM_SEV_INIT = 0,
- KVM_SEV_ES_INIT,
- /* Guest launch commands */
- KVM_SEV_LAUNCH_START,
- KVM_SEV_LAUNCH_UPDATE_DATA,
- KVM_SEV_LAUNCH_UPDATE_VMSA,
- KVM_SEV_LAUNCH_SECRET,
- KVM_SEV_LAUNCH_MEASURE,
- KVM_SEV_LAUNCH_FINISH,
- /* Guest migration commands (outgoing) */
- KVM_SEV_SEND_START,
- KVM_SEV_SEND_UPDATE_DATA,
- KVM_SEV_SEND_UPDATE_VMSA,
- KVM_SEV_SEND_FINISH,
- /* Guest migration commands (incoming) */
- KVM_SEV_RECEIVE_START,
- KVM_SEV_RECEIVE_UPDATE_DATA,
- KVM_SEV_RECEIVE_UPDATE_VMSA,
- KVM_SEV_RECEIVE_FINISH,
- /* Guest status and debug commands */
- KVM_SEV_GUEST_STATUS,
- KVM_SEV_DBG_DECRYPT,
- KVM_SEV_DBG_ENCRYPT,
- /* Guest certificates commands */
- KVM_SEV_CERT_EXPORT,
-
- KVM_SEV_NR_MAX,
-};
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr)
-struct kvm_sev_cmd {
- __u32 id;
- __u64 data;
- __u32 error;
- __u32 sev_fd;
-};
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn)
-struct kvm_sev_launch_start {
- __u32 handle;
- __u32 policy;
- __u64 dh_uaddr;
- __u32 dh_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
+#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2)
+#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2)
-struct kvm_sev_launch_update_data {
- __u64 uaddr;
- __u32 len;
-};
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
-struct kvm_sev_launch_secret {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status |
+ * |---------------+---------------+--------------|
+ * | 0 | 0 | Invalid GFN |
+ * | 0 | 1 | Dirty GFN |
+ * | 1 | X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ * dirtied harvested reset
+ * 00 -----------> 01 -------------> 1X -------+
+ * ^ |
+ * | |
+ * +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry. Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET _BITUL(1)
+#define KVM_DIRTY_GFN_F_MASK 0x3
-struct kvm_sev_launch_measure {
- __u64 uaddr;
- __u32 len;
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+ __u32 flags;
+ __u32 slot;
+ __u64 offset;
};
-struct kvm_sev_guest_status {
- __u32 handle;
- __u32 policy;
- __u32 state;
-};
+#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
-struct kvm_sev_dbg {
- __u64 src_uaddr;
- __u64 dst_uaddr;
- __u32 len;
-};
+#define KVM_PMU_CAP_DISABLE (1 << 0)
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
-#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
-#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
+/**
+ * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
+ * @flags: Some extra information for header, always 0 for now.
+ * @name_size: The size in bytes of the memory which contains statistics
+ * name string including trailing '\0'. The memory is allocated
+ * at the send of statistics descriptor.
+ * @num_desc: The number of statistics the vm or vcpu has.
+ * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed
+ * by vm/vcpu stats fd.
+ * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file
+ * pointd by vm/vcpu stats fd.
+ * @data_offset: The offset of the vm/vcpu stats' data block in the file
+ * pointed by vm/vcpu stats fd.
+ *
+ * This is the header userspace needs to read from stats fd before any other
+ * readings. It is used by userspace to discover all the information about the
+ * vm/vcpu's binary statistics.
+ * Userspace reads this header from the start of the vm/vcpu's stats fd.
+ */
+struct kvm_stats_header {
+ __u32 flags;
+ __u32 name_size;
+ __u32 num_desc;
+ __u32 id_offset;
+ __u32 desc_offset;
+ __u32 data_offset;
+};
+
+#define KVM_STATS_TYPE_SHIFT 0
+#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST
+
+#define KVM_STATS_UNIT_SHIFT 4
+#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN
+
+#define KVM_STATS_BASE_SHIFT 8
+#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2
-struct kvm_assigned_pci_dev {
- __u32 assigned_dev_id;
- __u32 busnr;
- __u32 devfn;
+/**
+ * struct kvm_stats_desc - Descriptor of a KVM statistics.
+ * @flags: Annotations of the stats, like type, unit, etc.
+ * @exponent: Used together with @flags to determine the unit.
+ * @size: The number of data items for this stats.
+ * Every data item is of type __u64.
+ * @offset: The offset of the stats to the start of stat structure in
+ * structure kvm or kvm_vcpu.
+ * @bucket_size: A parameter value used for histogram stats. It is only used
+ * for linear histogram stats, specifying the size of the bucket;
+ * @name: The name string for the stats. Its size is indicated by the
+ * &kvm_stats_header->name_size.
+ */
+struct kvm_stats_desc {
__u32 flags;
- __u32 segnr;
- union {
- __u32 reserved[11];
- };
+ __s16 exponent;
+ __u16 size;
+ __u32 offset;
+ __u32 bucket_size;
+ char name[];
};
-#define KVM_DEV_IRQ_HOST_INTX (1 << 0)
-#define KVM_DEV_IRQ_HOST_MSI (1 << 1)
-#define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
+#define KVM_GET_STATS_FD _IO(KVMIO, 0xce)
-#define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
-#define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
-#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
-#define KVM_DEV_IRQ_HOST_MASK 0x00ff
-#define KVM_DEV_IRQ_GUEST_MASK 0xff00
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
-struct kvm_assigned_irq {
- __u32 assigned_dev_id;
- __u32 host_irq; /* ignored (legacy field) */
- __u32 guest_irq;
- __u32 flags;
- union {
- __u32 reserved[12];
- };
-};
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1)
-struct kvm_assigned_msix_nr {
- __u32 assigned_dev_id;
- __u16 entry_nr;
- __u16 padding;
-};
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op)
-#define KVM_MAX_MSIX_PER_DEV 256
-struct kvm_assigned_msix_entry {
- __u32 assigned_dev_id;
- __u32 gsi;
- __u16 entry; /* The index of entry in the MSI-X table */
- __u16 padding[3];
-};
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes)
-#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+struct kvm_memory_attributes {
+ __u64 address;
+ __u64 size;
+ __u64 attributes;
+ __u64 flags;
+};
-/* Available with KVM_CAP_ARM_USER_IRQ */
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
-/* Bits for run->s.regs.device_irq_level */
-#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
-#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
-#define KVM_ARM_DEV_PMU (1 << 2)
+#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd)
-struct kvm_hyperv_eventfd {
- __u32 conn_id;
- __s32 fd;
- __u32 flags;
- __u32 padding[3];
+struct kvm_create_guest_memfd {
+ __u64 size;
+ __u64 flags;
+ __u64 reserved[6];
};
-#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
-#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory)
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
+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/lirc.h b/tools/include/uapi/linux/lirc.h
deleted file mode 100644
index 45fcbf99d72e..000000000000
--- a/tools/include/uapi/linux/lirc.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * lirc.h - linux infrared remote control header file
- * last modified 2010/07/13 by Jarod Wilson
- */
-
-#ifndef _LINUX_LIRC_H
-#define _LINUX_LIRC_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define PULSE_BIT 0x01000000
-#define PULSE_MASK 0x00FFFFFF
-
-#define LIRC_MODE2_SPACE 0x00000000
-#define LIRC_MODE2_PULSE 0x01000000
-#define LIRC_MODE2_FREQUENCY 0x02000000
-#define LIRC_MODE2_TIMEOUT 0x03000000
-
-#define LIRC_VALUE_MASK 0x00FFFFFF
-#define LIRC_MODE2_MASK 0xFF000000
-
-#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
-#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
-#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
-#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
-
-#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
-#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
-
-#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
-#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
-#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
-#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
-
-/* used heavily by lirc userspace */
-#define lirc_t int
-
-/*** lirc compatible hardware features ***/
-
-#define LIRC_MODE2SEND(x) (x)
-#define LIRC_SEND2MODE(x) (x)
-#define LIRC_MODE2REC(x) ((x) << 16)
-#define LIRC_REC2MODE(x) ((x) >> 16)
-
-#define LIRC_MODE_RAW 0x00000001
-#define LIRC_MODE_PULSE 0x00000002
-#define LIRC_MODE_MODE2 0x00000004
-#define LIRC_MODE_SCANCODE 0x00000008
-#define LIRC_MODE_LIRCCODE 0x00000010
-
-
-#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW)
-#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE)
-#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2)
-#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_SEND_MASK 0x0000003f
-
-#define LIRC_CAN_SET_SEND_CARRIER 0x00000100
-#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200
-#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400
-
-#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW)
-#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE)
-#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2)
-#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE)
-#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
-
-#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16)
-#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
-
-#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
-#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000
-#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000
-#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000
-#define LIRC_CAN_SET_REC_FILTER 0x08000000
-
-#define LIRC_CAN_MEASURE_CARRIER 0x02000000
-#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000
-
-#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
-#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
-
-#define LIRC_CAN_NOTIFY_DECODE 0x01000000
-
-/*** IOCTL commands for lirc driver ***/
-
-#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32)
-
-#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32)
-#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32)
-#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32)
-
-#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32)
-#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32)
-
-/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
-#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32)
-
-#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32)
-#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32)
-/* Note: these can reset the according pulse_width */
-#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32)
-#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32)
-#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32)
-#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32)
-
-/*
- * when a timeout != 0 is set the driver will send a
- * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
- * never sent, timeout is disabled by default
- */
-#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32)
-
-/* 1 enables, 0 disables timeout reports in MODE2 */
-#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32)
-
-/*
- * if enabled from the next key press on the driver will send
- * LIRC_MODE2_FREQUENCY packets
- */
-#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32)
-
-/*
- * to set a range use LIRC_SET_REC_CARRIER_RANGE with the
- * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound
- */
-#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32)
-
-#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
-
-/*
- * Return the recording timeout, which is either set by
- * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols.
- */
-#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32)
-
-/*
- * struct lirc_scancode - decoded scancode with protocol for use with
- * LIRC_MODE_SCANCODE
- *
- * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR
- * was decoded.
- * @flags: should be 0 for transmit. When receiving scancodes,
- * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set
- * depending on the protocol
- * @rc_proto: see enum rc_proto
- * @keycode: the translated keycode. Set to 0 for transmit.
- * @scancode: the scancode received or to be sent
- */
-struct lirc_scancode {
- __u64 timestamp;
- __u16 flags;
- __u16 rc_proto;
- __u32 keycode;
- __u64 scancode;
-};
-
-/* Set if the toggle bit of rc-5 or rc-6 is enabled */
-#define LIRC_SCANCODE_FLAG_TOGGLE 1
-/* Set if this is a nec or sanyo repeat */
-#define LIRC_SCANCODE_FLAG_REPEAT 2
-
-/**
- * enum rc_proto - the Remote Controller protocol
- *
- * @RC_PROTO_UNKNOWN: Protocol not known
- * @RC_PROTO_OTHER: Protocol known but proprietary
- * @RC_PROTO_RC5: Philips RC5 protocol
- * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol
- * @RC_PROTO_RC5_SZ: StreamZap variant of RC5
- * @RC_PROTO_JVC: JVC protocol
- * @RC_PROTO_SONY12: Sony 12 bit protocol
- * @RC_PROTO_SONY15: Sony 15 bit protocol
- * @RC_PROTO_SONY20: Sony 20 bit protocol
- * @RC_PROTO_NEC: NEC protocol
- * @RC_PROTO_NECX: Extended NEC protocol
- * @RC_PROTO_NEC32: NEC 32 bit protocol
- * @RC_PROTO_SANYO: Sanyo protocol
- * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard
- * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse
- * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol
- * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol
- * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol
- * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol
- * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol
- * @RC_PROTO_SHARP: Sharp protocol
- * @RC_PROTO_XMP: XMP protocol
- * @RC_PROTO_CEC: CEC protocol
- * @RC_PROTO_IMON: iMon Pad protocol
- * @RC_PROTO_RCMM12: RC-MM protocol 12 bits
- * @RC_PROTO_RCMM24: RC-MM protocol 24 bits
- * @RC_PROTO_RCMM32: RC-MM protocol 32 bits
- */
-enum rc_proto {
- RC_PROTO_UNKNOWN = 0,
- RC_PROTO_OTHER = 1,
- RC_PROTO_RC5 = 2,
- RC_PROTO_RC5X_20 = 3,
- RC_PROTO_RC5_SZ = 4,
- RC_PROTO_JVC = 5,
- RC_PROTO_SONY12 = 6,
- RC_PROTO_SONY15 = 7,
- RC_PROTO_SONY20 = 8,
- RC_PROTO_NEC = 9,
- RC_PROTO_NECX = 10,
- RC_PROTO_NEC32 = 11,
- RC_PROTO_SANYO = 12,
- RC_PROTO_MCIR2_KBD = 13,
- RC_PROTO_MCIR2_MSE = 14,
- RC_PROTO_RC6_0 = 15,
- RC_PROTO_RC6_6A_20 = 16,
- RC_PROTO_RC6_6A_24 = 17,
- RC_PROTO_RC6_6A_32 = 18,
- RC_PROTO_RC6_MCE = 19,
- RC_PROTO_SHARP = 20,
- RC_PROTO_XMP = 21,
- RC_PROTO_CEC = 22,
- RC_PROTO_IMON = 23,
- RC_PROTO_RCMM12 = 24,
- RC_PROTO_RCMM24 = 25,
- RC_PROTO_RCMM32 = 26,
-};
-
-#endif
diff --git a/tools/include/uapi/linux/memfd.h b/tools/include/uapi/linux/memfd.h
new file mode 100644
index 000000000000..01c0324e7733
--- /dev/null
+++ b/tools/include/uapi/linux/memfd.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_MEMFD_H
+#define _LINUX_MEMFD_H
+
+#include <asm-generic/hugetlb_encode.h>
+
+/* flags for memfd_create(2) (unsigned int) */
+#define MFD_CLOEXEC 0x0001U
+#define MFD_ALLOW_SEALING 0x0002U
+#define MFD_HUGETLB 0x0004U
+/* not executable and sealed to prevent changing to executable. */
+#define MFD_NOEXEC_SEAL 0x0008U
+/* executable */
+#define MFD_EXEC 0x0010U
+
+/*
+ * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
+ * size other than the default is desired. See hugetlb_encode.h.
+ * All known huge page size encodings are provided here. It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system. See mmap(2) man page for details.
+ */
+#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+
+#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
+#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
+#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
+#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB
+#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB
+#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB
+#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB
+#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB
+#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB
+#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB
+#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
+#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
+
+#endif /* _LINUX_MEMFD_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 923cc162609c..e89d00528f2f 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -4,6 +4,7 @@
#include <asm/mman.h>
#include <asm-generic/hugetlb_encode.h>
+#include <linux/types.h>
#define MREMAP_MAYMOVE 1
#define MREMAP_FIXED 2
@@ -16,6 +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
@@ -27,6 +29,7 @@
#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB
#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
@@ -40,4 +43,17 @@
#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
+struct cachestat_range {
+ __u64 off;
+ __u64 len;
+};
+
+struct cachestat {
+ __u64 nr_cache;
+ __u64 nr_dirty;
+ __u64 nr_writeback;
+ __u64 nr_evicted;
+ __u64 nr_recently_evicted;
+};
+
#endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 96a0240f23fe..7fa67c2031a5 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -1,6 +1,8 @@
#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
*
@@ -16,6 +18,7 @@
#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
@@ -70,7 +73,9 @@
#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__MASK 0x00000077
+#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.
@@ -95,8 +100,9 @@ enum fsconfig_command {
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, /* Invoke superblock creation */
+ 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 */
};
/*
@@ -116,5 +122,114 @@ enum fsconfig_command {
#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/netdev.h b/tools/include/uapi/linux/netdev.h
new file mode 100644
index 000000000000..7eb9571786b8
--- /dev/null
+++ b/tools/include/uapi/linux/netdev.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * offloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+
+ /* private: */
+ NETDEV_XDP_ACT_MASK = 127,
+};
+
+/**
+ * enum netdev_xdp_rx_metadata
+ * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
+ * timestamp via bpf_xdp_metadata_rx_timestamp().
+ * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
+ * hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ */
+enum netdev_xdp_rx_metadata {
+ NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
+ NETDEV_XDP_RX_METADATA_HASH = 2,
+ NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+};
+
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ * 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 {
+ NETDEV_QUEUE_TYPE_RX,
+ NETDEV_QUEUE_TYPE_TX,
+};
+
+enum netdev_qstats_scope {
+ NETDEV_QSTATS_SCOPE_QUEUE = 1,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+ NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+ NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+ NETDEV_A_DEV_XSK_FEATURES,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+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)
+};
+
+enum {
+ NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+ __NETDEV_A_PAGE_POOL_STATS_MAX,
+ NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
+enum {
+ NETDEV_A_NAPI_IFINDEX = 1,
+ 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_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)
+};
+
+enum {
+ NETDEV_A_QSTATS_IFINDEX = 1,
+ NETDEV_A_QSTATS_QUEUE_TYPE,
+ NETDEV_A_QSTATS_QUEUE_ID,
+ NETDEV_A_QSTATS_SCOPE,
+ NETDEV_A_QSTATS_RX_PACKETS = 8,
+ NETDEV_A_QSTATS_RX_BYTES,
+ NETDEV_A_QSTATS_TX_PACKETS,
+ NETDEV_A_QSTATS_TX_BYTES,
+ NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+ NETDEV_A_QSTATS_RX_HW_DROPS,
+ NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+ NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
+ NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
+ NETDEV_A_QSTATS_RX_CSUM_NONE,
+ NETDEV_A_QSTATS_RX_CSUM_BAD,
+ NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
+ NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
+ NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
+ NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
+ NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
+ NETDEV_A_QSTATS_TX_HW_DROPS,
+ NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
+ NETDEV_A_QSTATS_TX_CSUM_NONE,
+ NETDEV_A_QSTATS_TX_NEEDS_CSUM,
+ NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
+ NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
+ NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
+ NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
+ NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
+ NETDEV_A_QSTATS_TX_STOP,
+ NETDEV_A_QSTATS_TX_WAKE,
+
+ __NETDEV_A_QSTATS_MAX,
+ NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
+};
+
+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,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+ NETDEV_CMD_PAGE_POOL_GET,
+ NETDEV_CMD_PAGE_POOL_ADD_NTF,
+ NETDEV_CMD_PAGE_POOL_DEL_NTF,
+ NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+ NETDEV_CMD_PAGE_POOL_STATS_GET,
+ 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)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+#define NETDEV_MCGRP_PAGE_POOL "page-pool"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/tools/include/uapi/linux/nsfs.h b/tools/include/uapi/linux/nsfs.h
new file mode 100644
index 000000000000..34127653fd00
--- /dev/null
+++ b/tools/include/uapi/linux/nsfs.h
@@ -0,0 +1,45 @@
+/* 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)
+/* Get the id for a mount namespace */
+#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64)
+/* 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)
+
+#endif /* __LINUX_NSFS_H */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
deleted file mode 100644
index 58b1eb711360..000000000000
--- a/tools/include/uapi/linux/openat2.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_OPENAT2_H
-#define _UAPI_LINUX_OPENAT2_H
-
-#include <linux/types.h>
-
-/*
- * Arguments for how openat2(2) should open the target path. If only @flags and
- * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
- *
- * However, unlike openat(2), unknown or invalid bits in @flags result in
- * -EINVAL rather than being silently ignored. @mode must be zero unless one of
- * {O_CREAT, O_TMPFILE} are set.
- *
- * @flags: O_* flags.
- * @mode: O_CREAT/O_TMPFILE file mode.
- * @resolve: RESOLVE_* flags.
- */
-struct open_how {
- __u64 flags;
- __u64 mode;
- __u64 resolve;
-};
-
-/* how->resolve flags for openat2(2). */
-#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings
- (includes bind-mounts). */
-#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style
- "magic-links". */
-#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks
- (implies OEXT_NO_MAGICLINKS) */
-#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like
- "..", symlinks, and absolute
- paths which escape the dirfd. */
-#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
- be scoped inside the dirfd
- (similar to chroot(2)). */
-
-#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 7b2d6fc9e6ed..78a362b80027 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -38,6 +38,24 @@ 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, PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT 32
+#define PERF_HW_EVENT_MASK 0xffffffff
+
+/*
* Generalized performance event event_id types, used by the
* attr.event_id parameter of the sys_perf_event_open()
* syscall:
@@ -97,7 +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 {
@@ -112,6 +130,7 @@ enum perf_sw_ids {
PERF_COUNT_SW_EMULATION_FAULTS = 8,
PERF_COUNT_SW_DUMMY = 9,
PERF_COUNT_SW_BPF_OUTPUT = 10,
+ PERF_COUNT_SW_CGROUP_SWITCHES = 11,
PERF_COUNT_SW_MAX, /* non-ABI */
};
@@ -143,14 +162,17 @@ enum perf_event_sample_format {
PERF_SAMPLE_PHYS_ADDR = 1U << 19,
PERF_SAMPLE_AUX = 1U << 20,
PERF_SAMPLE_CGROUP = 1U << 21,
+ PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22,
+ PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23,
+ PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24,
- PERF_SAMPLE_MAX = 1U << 22, /* non-ABI */
-
- __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */
+ PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */
};
+#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
@@ -160,20 +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 */
@@ -184,56 +206,104 @@ enum perf_branch_sample_type_shift {
PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */
+ PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */
+
+ PERF_SAMPLE_BRANCH_COUNTERS_SHIFT = 19, /* save occurrences of events on a branch */
+
PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
};
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_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_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_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_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 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_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_MAX,
+};
+
+enum {
+ 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_SAMPLE_BRANCH_PLM_ALL \
(PERF_SAMPLE_BRANCH_USER|\
PERF_SAMPLE_BRANCH_KERNEL|\
@@ -243,9 +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,
};
/*
@@ -253,21 +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,
};
/*
@@ -279,6 +349,7 @@ enum {
* { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
* { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
* { u64 id; } && PERF_FORMAT_ID
+ * { u64 lost; } && PERF_FORMAT_LOST
* } && !PERF_FORMAT_GROUP
*
* { u64 nr;
@@ -286,6 +357,7 @@ enum {
* { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
* { u64 value;
* { u64 id; } && PERF_FORMAT_ID
+ * { u64 lost; } && PERF_FORMAT_LOST
* } cntr[nr];
* } && PERF_FORMAT_GROUP
* };
@@ -295,24 +367,27 @@ enum perf_event_read_format {
PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1,
PERF_FORMAT_ID = 1U << 2,
PERF_FORMAT_GROUP = 1U << 3,
+ PERF_FORMAT_LOST = 1U << 4,
- PERF_FORMAT_MAX = 1U << 4, /* non-ABI */
+ 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_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 */
/*
- * 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 {
@@ -322,7 +397,7 @@ 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;
@@ -377,16 +452,21 @@ 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 */
- __reserved_1 : 31;
+ text_poke : 1, /* include text poke 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;
union {
- __u32 wakeup_events; /* wakeup every n events */
+ __u32 wakeup_events; /* wake up every n events */
__u32 wakeup_watermark; /* bytes before wakeup */
};
@@ -395,13 +475,13 @@ 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 */
@@ -431,15 +511,43 @@ 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
+ * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+ * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+ * truncated accordingly on 32 bit architectures.
+ */
+ __u64 sig_data;
+
+ __u64 config3; /* extension of config2 */
};
/*
* 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 {
@@ -455,27 +563,27 @@ struct perf_event_query_bpf {
/*
* User provided buffer to store program ids
*/
- __u32 ids[0];
+ __u32 ids[];
};
/*
* 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,
};
/*
@@ -486,7 +594,7 @@ 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;
@@ -524,7 +632,7 @@ 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 {
@@ -532,9 +640,10 @@ struct perf_event_mmap_page {
cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */
cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
- cap_user_time : 1, /* The time_* fields are used */
+ cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */
cap_user_time_zero : 1, /* The time_zero field is used */
- cap_____res : 59;
+ cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */
+ cap_____res : 58;
};
};
@@ -551,7 +660,7 @@ 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;
@@ -593,13 +702,29 @@ struct perf_event_mmap_page {
* ((rem * time_mult) >> time_shift);
*/
__u64 time_zero;
+
__u32 size; /* Header size up to __reserved[] fields. */
+ __u32 __reserved_1;
+
+ /*
+ * If cap_usr_time_short, the hardware clock is less than 64bit wide
+ * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+ *
+ * cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+ *
+ * NOTE: this form is explicitly chosen such that cap_usr_time_short
+ * is a correction on top of cap_usr_time, and code that doesn't
+ * know about cap_usr_time_short still works under the assumption
+ * the counter doesn't wrap.
+ */
+ __u64 time_cycles;
+ __u64 time_mask;
/*
* Hole for extension of the self monitor capabilities
*/
- __u8 __reserved[118*8+4]; /* align to 1k. */
+ __u8 __reserved[116*8]; /* align to 1k. */
/*
* Control data for the mmap() data buffer.
@@ -608,7 +733,7 @@ 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.
*
@@ -624,7 +749,7 @@ 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
*
@@ -639,6 +764,22 @@ struct perf_event_mmap_page {
__u64 aux_size;
};
+/*
+ * The current state of perf_event_header::misc bits usage:
+ * ('|' used bit, '-' unused bit)
+ *
+ * 012 CDEF
+ * |||---------||||
+ *
+ * Where:
+ * 0-2 CPUMODE_MASK
+ *
+ * C PROC_MAP_PARSE_TIMEOUT
+ * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT
+ * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT
+ * F (reserved)
+ */
+
#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0)
#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0)
#define PERF_RECORD_MISC_KERNEL (1 << 0)
@@ -670,6 +811,7 @@ struct perf_event_mmap_page {
*
* PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event
*
*
* PERF_RECORD_MISC_EXACT_IP:
@@ -679,35 +821,39 @@ struct perf_event_mmap_page {
*
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
* Indicates that thread was preempted in TASK_RUNNING state.
+ *
+ * PERF_RECORD_MISC_MMAP_BUILD_ID:
+ * 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)
+#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
#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 {
@@ -723,11 +869,11 @@ 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
*
@@ -738,7 +884,7 @@ 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;
@@ -748,7 +894,7 @@ enum perf_event_type {
* u64 len;
* u64 pgoff;
* char filename[];
- * struct sample_id sample_id;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_MMAP = 1,
@@ -758,7 +904,7 @@ 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,
@@ -769,7 +915,7 @@ enum perf_event_type {
*
* u32 pid, tid;
* char comm[];
- * struct sample_id sample_id;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_COMM = 3,
@@ -780,7 +926,7 @@ 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,
@@ -791,7 +937,7 @@ 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,
@@ -803,7 +949,7 @@ 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,
@@ -814,7 +960,7 @@ 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,
@@ -861,21 +1007,47 @@ enum perf_event_type {
* { u64 nr;
* { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
* { u64 from, to, flags } lbr[nr];
+ * #
+ * # The format of the counters is decided by the
+ * # "branch_counter_nr" and "branch_counter_width",
+ * # which are defined in the ABI.
+ * #
+ * { 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
*
- * { u64 weight; } && PERF_SAMPLE_WEIGHT
+ * { union perf_sample_weight
+ * {
+ * u64 full; && PERF_SAMPLE_WEIGHT
+ * #if defined(__LITTLE_ENDIAN_BITFIELD)
+ * struct {
+ * u32 var1_dw;
+ * u16 var2_w;
+ * u16 var3_w;
+ * } && PERF_SAMPLE_WEIGHT_STRUCT
+ * #elif defined(__BIG_ENDIAN_BITFIELD)
+ * struct {
+ * u16 var3_w;
+ * u16 var2_w;
+ * u32 var1_dw;
+ * } && PERF_SAMPLE_WEIGHT_STRUCT
+ * #endif
+ * }
+ * }
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
* { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR
+ * { 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
* };
@@ -893,13 +1065,23 @@ enum perf_event_type {
* u64 addr;
* u64 len;
* u64 pgoff;
- * u32 maj;
- * u32 min;
- * u64 ino;
- * u64 ino_generation;
+ * union {
+ * struct {
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * };
+ * struct {
+ * u8 build_id_size;
+ * u8 __reserved_1;
+ * u16 __reserved_2;
+ * u8 build_id[20];
+ * };
+ * };
* u32 prot, flags;
* char filename[];
- * struct sample_id sample_id;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_MMAP2 = 10,
@@ -908,12 +1090,12 @@ 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,
@@ -996,7 +1178,7 @@ 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,
@@ -1024,159 +1206,231 @@ enum perf_event_type {
*/
PERF_RECORD_CGROUP = 19,
+ /*
+ * Records changes to kernel text i.e. self-modified code. 'old_len' is
+ * the number of old bytes, 'new_len' is the number of new bytes. Either
+ * 'old_len' or 'new_len' may be zero to indicate, for example, the
+ * addition or removal of a trampoline. 'bytes' contains the old bytes
+ * followed immediately by the new bytes.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 addr;
+ * u16 old_len;
+ * u16 new_len;
+ * u8 bytes[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_TEXT_POKE = 20,
+
+ /*
+ * Data written to the AUX area by hardware due to aux_output, may need
+ * to be matched to the event by an architecture-specific hardware ID.
+ * This records the hardware ID, but requires sample_id to provide the
+ * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT
+ * records from multiple events.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 hw_id;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_AUX_OUTPUT_HW_ID = 21,
+
PERF_RECORD_MAX, /* non-ABI */
};
enum perf_record_ksymbol_type {
PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0,
PERF_RECORD_KSYMBOL_TYPE_BPF = 1,
+ /*
+ * Out of line code such as kprobe-replaced instructions or optimized
+ * kprobes or ftrace trampolines.
+ */
+ PERF_RECORD_KSYMBOL_TYPE_OOL = 2,
PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */
};
#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_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_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_rsvd:24;
+ __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:24,
- 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
-
-/* 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 */
-/* 5-0xa available */
-#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 */
-/* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT 37
-
-/* locked instruction */
-#define PERF_MEM_LOCK_NA 0x01 /* not available */
-#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
-#define PERF_MEM_LOCK_SHIFT 24
+/* 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
+
+/*
+ * The PERF_MEM_LVL_* namespace is being deprecated to some extent in
+ * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields.
+ * We support this namespace in order to not break defined ABIs.
+ *
+ * Memory hierarchy (memory level, hit or miss)
+ */
+#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 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_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
@@ -1190,17 +1444,43 @@ union perf_mem_data_src {
* abort: aborting a hardware transaction
* cycles: cycles from last branch (or 0 if not supported)
* type: branch type
+ * spec: branch speculation info (or 0 if not supported)
*/
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 */
- reserved:40;
+ __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;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ struct {
+ __u32 var1_dw;
+ __u16 var2_w;
+ __u16 var3_w;
+ };
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ struct {
+ __u16 var3_w;
+ __u16 var2_w;
+ __u32 var1_dw;
+ };
+#else
+# error "Unknown endianness"
+#endif
};
#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
index 12153771396a..bd4b227ab4ba 100644
--- a/tools/include/uapi/linux/pkt_cls.h
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -180,7 +180,7 @@ struct tc_u32_sel {
short hoff;
__be32 hmask;
- struct tc_u32_key keys[0];
+ struct tc_u32_key keys[];
};
struct tc_u32_mark {
@@ -192,7 +192,7 @@ struct tc_u32_mark {
struct tc_u32_pcnt {
__u64 rcnt;
__u64 rhit;
- __u64 kcnts[0];
+ __u64 kcnts[];
};
/* Flags */
@@ -204,37 +204,6 @@ struct tc_u32_pcnt {
#define TC_U32_MAXDEPTH 8
-
-/* RSVP filter */
-
-enum {
- TCA_RSVP_UNSPEC,
- TCA_RSVP_CLASSID,
- TCA_RSVP_DST,
- TCA_RSVP_SRC,
- TCA_RSVP_PINFO,
- TCA_RSVP_POLICE,
- TCA_RSVP_ACT,
- __TCA_RSVP_MAX
-};
-
-#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
-
-struct tc_rsvp_gpi {
- __u32 key;
- __u32 mask;
- int offset;
-};
-
-struct tc_rsvp_pinfo {
- struct tc_rsvp_gpi dpi;
- struct tc_rsvp_gpi spi;
- __u8 protocol;
- __u8 tunnelid;
- __u8 tunnelhdr;
- __u8 pad;
-};
-
/* ROUTE filter */
enum {
@@ -265,22 +234,6 @@ enum {
#define TCA_FW_MAX (__TCA_FW_MAX - 1)
-/* TC index filter */
-
-enum {
- TCA_TCINDEX_UNSPEC,
- TCA_TCINDEX_HASH,
- TCA_TCINDEX_MASK,
- TCA_TCINDEX_SHIFT,
- TCA_TCINDEX_FALL_THROUGH,
- TCA_TCINDEX_CLASSID,
- TCA_TCINDEX_POLICE,
- TCA_TCINDEX_ACT,
- __TCA_TCINDEX_MAX
-};
-
-#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1)
-
/* Flow filter */
enum {
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 0d18b1d1fbbc..587481a19433 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -414,6 +414,7 @@ enum {
TCA_HTB_RATE64,
TCA_HTB_CEIL64,
TCA_HTB_PAD,
+ TCA_HTB_OFFLOAD,
__TCA_HTB_MAX,
};
@@ -456,115 +457,6 @@ enum {
#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO 8
-#define TC_CBQ_MAXLEVEL 8
-#define TC_CBQ_DEF_EWMA 5
-
-struct tc_cbq_lssopt {
- unsigned char change;
- unsigned char flags;
-#define TCF_CBQ_LSS_BOUNDED 1
-#define TCF_CBQ_LSS_ISOLATED 2
- unsigned char ewma_log;
- unsigned char level;
-#define TCF_CBQ_LSS_FLAGS 1
-#define TCF_CBQ_LSS_EWMA 2
-#define TCF_CBQ_LSS_MAXIDLE 4
-#define TCF_CBQ_LSS_MINIDLE 8
-#define TCF_CBQ_LSS_OFFTIME 0x10
-#define TCF_CBQ_LSS_AVPKT 0x20
- __u32 maxidle;
- __u32 minidle;
- __u32 offtime;
- __u32 avpkt;
-};
-
-struct tc_cbq_wrropt {
- unsigned char flags;
- unsigned char priority;
- unsigned char cpriority;
- unsigned char __reserved;
- __u32 allot;
- __u32 weight;
-};
-
-struct tc_cbq_ovl {
- unsigned char strategy;
-#define TC_CBQ_OVL_CLASSIC 0
-#define TC_CBQ_OVL_DELAY 1
-#define TC_CBQ_OVL_LOWPRIO 2
-#define TC_CBQ_OVL_DROP 3
-#define TC_CBQ_OVL_RCLASSIC 4
- unsigned char priority2;
- __u16 pad;
- __u32 penalty;
-};
-
-struct tc_cbq_police {
- unsigned char police;
- unsigned char __res1;
- unsigned short __res2;
-};
-
-struct tc_cbq_fopt {
- __u32 split;
- __u32 defmap;
- __u32 defchange;
-};
-
-struct tc_cbq_xstats {
- __u32 borrows;
- __u32 overactions;
- __s32 avgidle;
- __s32 undertime;
-};
-
-enum {
- TCA_CBQ_UNSPEC,
- TCA_CBQ_LSSOPT,
- TCA_CBQ_WRROPT,
- TCA_CBQ_FOPT,
- TCA_CBQ_OVL_STRATEGY,
- TCA_CBQ_RATE,
- TCA_CBQ_RTAB,
- TCA_CBQ_POLICE,
- __TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1)
-
-/* dsmark section */
-
-enum {
- TCA_DSMARK_UNSPEC,
- TCA_DSMARK_INDICES,
- TCA_DSMARK_DEFAULT_INDEX,
- TCA_DSMARK_SET_TC_INDEX,
- TCA_DSMARK_MASK,
- TCA_DSMARK_VALUE,
- __TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
-/* ATM section */
-
-enum {
- TCA_ATM_UNSPEC,
- TCA_ATM_FD, /* file/socket descriptor */
- TCA_ATM_PTR, /* pointer to descriptor - later */
- TCA_ATM_HDR, /* LL header */
- TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */
- TCA_ATM_ADDR, /* PVC address (for output only) */
- TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */
- __TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX (__TCA_ATM_MAX - 1)
-
/* Network emulator */
enum {
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 07b4f8131e36..43dec6eed559 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -213,6 +213,7 @@ struct prctl_mm_map {
/* 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)
@@ -229,13 +230,145 @@ struct prctl_mm_map {
# define PR_PAC_APDBKEY (1UL << 3)
# define PR_PAC_APGAKEY (1UL << 4)
-/* Tagged user address controls for arm64 */
+/* 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
+# define PR_SYS_DISPATCH_ON 1
+/* 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 FH_FLAG_IMMUTABLE (1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS 2
+# define PR_FUTEX_HASH_GET_IMMUTABLE 3
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
deleted file mode 100644
index 3bac0a8ceab2..000000000000
--- a/tools/include/uapi/linux/sched.h
+++ /dev/null
@@ -1,148 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_SCHED_H
-#define _UAPI_LINUX_SCHED_H
-
-#include <linux/types.h>
-
-/*
- * cloning flags:
- */
-#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
-#define CLONE_VM 0x00000100 /* set if VM shared between processes */
-#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
-#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
-#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
-#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
-#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
-#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
-#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
-#define CLONE_THREAD 0x00010000 /* Same thread group? */
-#define CLONE_NEWNS 0x00020000 /* New mount namespace group */
-#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
-#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
-#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
-#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
-#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
-#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
-#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
-#define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */
-#define CLONE_NEWUTS 0x04000000 /* New utsname namespace */
-#define CLONE_NEWIPC 0x08000000 /* New ipc namespace */
-#define CLONE_NEWUSER 0x10000000 /* New user namespace */
-#define CLONE_NEWPID 0x20000000 /* New pid namespace */
-#define CLONE_NEWNET 0x40000000 /* New network namespace */
-#define CLONE_IO 0x80000000 /* Clone io context */
-
-/* Flags for the clone3() syscall. */
-#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
-#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
-
-/*
- * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
- * syscalls only:
- */
-#define CLONE_NEWTIME 0x00000080 /* New time namespace */
-
-#ifndef __ASSEMBLY__
-/**
- * struct clone_args - arguments for the clone3 syscall
- * @flags: Flags for the new process as listed above.
- * All flags are valid except for CSIGNAL and
- * CLONE_DETACHED.
- * @pidfd: If CLONE_PIDFD is set, a pidfd will be
- * returned in this argument.
- * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
- * child process will be returned in the child's
- * memory.
- * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
- * the child process will be returned in the
- * parent's memory.
- * @exit_signal: The exit_signal the parent process will be
- * sent when the child exits.
- * @stack: Specify the location of the stack for the
- * child process.
- * Note, @stack is expected to point to the
- * lowest address. The stack direction will be
- * determined by the kernel and set up
- * appropriately based on @stack_size.
- * @stack_size: The size of the stack for the child process.
- * @tls: If CLONE_SETTLS is set, the tls descriptor
- * is set to tls.
- * @set_tid: Pointer to an array of type *pid_t. The size
- * of the array is defined using @set_tid_size.
- * This array is used to select PIDs/TIDs for
- * newly created processes. The first element in
- * this defines the PID in the most nested PID
- * namespace. Each additional element in the array
- * defines the PID in the parent PID namespace of
- * the original PID namespace. If the array has
- * less entries than the number of currently
- * nested PID namespaces only the PIDs in the
- * corresponding namespaces are set.
- * @set_tid_size: This defines the size of the array referenced
- * in @set_tid. This cannot be larger than the
- * kernel's limit of nested PID namespaces.
- * @cgroup: If CLONE_INTO_CGROUP is specified set this to
- * a file descriptor for the cgroup.
- *
- * The structure is versioned by size and thus extensible.
- * New struct members must go at the end of the struct and
- * must be properly 64bit aligned.
- */
-struct clone_args {
- __aligned_u64 flags;
- __aligned_u64 pidfd;
- __aligned_u64 child_tid;
- __aligned_u64 parent_tid;
- __aligned_u64 exit_signal;
- __aligned_u64 stack;
- __aligned_u64 stack_size;
- __aligned_u64 tls;
- __aligned_u64 set_tid;
- __aligned_u64 set_tid_size;
- __aligned_u64 cgroup;
-};
-#endif
-
-#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
-#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
-#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
-
-/*
- * Scheduling policies
- */
-#define SCHED_NORMAL 0
-#define SCHED_FIFO 1
-#define SCHED_RR 2
-#define SCHED_BATCH 3
-/* SCHED_ISO: reserved but not implemented yet */
-#define SCHED_IDLE 5
-#define SCHED_DEADLINE 6
-
-/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
-#define SCHED_RESET_ON_FORK 0x40000000
-
-/*
- * For the sched_{set,get}attr() calls
- */
-#define SCHED_FLAG_RESET_ON_FORK 0x01
-#define SCHED_FLAG_RECLAIM 0x02
-#define SCHED_FLAG_DL_OVERRUN 0x04
-#define SCHED_FLAG_KEEP_POLICY 0x08
-#define SCHED_FLAG_KEEP_PARAMS 0x10
-#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
-#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
-
-#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
- SCHED_FLAG_KEEP_PARAMS)
-
-#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \
- SCHED_FLAG_UTIL_CLAMP_MAX)
-
-#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
- SCHED_FLAG_RECLAIM | \
- SCHED_FLAG_DL_OVERRUN | \
- SCHED_FLAG_KEEP_ALL | \
- SCHED_FLAG_UTIL_CLAMP)
-
-#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h
new file mode 100644
index 000000000000..dbfc9b37fcae
--- /dev/null
+++ b/tools/include/uapi/linux/seccomp.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SECCOMP_H
+#define _UAPI_LINUX_SECCOMP_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+
+/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
+#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */
+#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
+#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+#define SECCOMP_GET_ACTION_AVAIL 2
+#define SECCOMP_GET_NOTIF_SIZES 3
+
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
+#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
+/* Received notifications wait in killable state (only respond to fatal signals) */
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5)
+
+/*
+ * All BPF programs must return a 32-bit value.
+ * The bottom 16-bits are for optional return data.
+ * The upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
+ *
+ * The ordering ensures that a min_t() over composed return values always
+ * selects the least permissive choice.
+ */
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
+#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
+
+/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL 0xffff0000U
+#define SECCOMP_RET_ACTION 0x7fff0000U
+#define SECCOMP_RET_DATA 0x0000ffffU
+
+/**
+ * struct seccomp_data - the format the BPF program executes over.
+ * @nr: the system call number
+ * @arch: indicates system call convention as an AUDIT_ARCH_* value
+ * as defined in <linux/audit.h>.
+ * @instruction_pointer: at the time of the system call.
+ * @args: up to 6 system call arguments always stored as 64-bit values
+ * regardless of the architecture.
+ */
+struct seccomp_data {
+ int nr;
+ __u32 arch;
+ __u64 instruction_pointer;
+ __u64 args[6];
+};
+
+struct seccomp_notif_sizes {
+ __u16 seccomp_notif;
+ __u16 seccomp_notif_resp;
+ __u16 seccomp_data;
+};
+
+struct seccomp_notif {
+ __u64 id;
+ __u32 pid;
+ __u32 flags;
+ struct seccomp_data data;
+};
+
+/*
+ * Valid flags for struct seccomp_notif_resp
+ *
+ * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
+ * If set by the process supervising the syscalls of another process the
+ * syscall will continue. This is problematic because of an inherent TOCTOU.
+ * An attacker can exploit the time while the supervised process is waiting on
+ * a response from the supervising process to rewrite syscall arguments which
+ * are passed as pointers of the intercepted syscall.
+ * It should be absolutely clear that this means that the seccomp notifier
+ * _cannot_ be used to implement a security policy! It should only ever be used
+ * in scenarios where a more privileged process supervises the syscalls of a
+ * lesser privileged process to get around kernel-enforced security
+ * restrictions when the privileged process deems this safe. In other words,
+ * in order to continue a syscall the supervising process should be sure that
+ * another security mechanism or the kernel itself will sufficiently block
+ * syscalls if arguments are rewritten to something unsafe.
+ *
+ * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
+ * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
+ * same syscall, the most recently added filter takes precedence. This means
+ * that the new SECCOMP_RET_USER_NOTIF filter can override any
+ * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
+ * such filtered syscalls to be executed by sending the response
+ * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
+ * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
+ */
+#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)
+
+struct seccomp_notif_resp {
+ __u64 id;
+ __s64 val;
+ __s32 error;
+ __u32 flags;
+};
+
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
+#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */
+
+/**
+ * struct seccomp_notif_addfd
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: The O_* flags the remote FD should have applied
+ */
+struct seccomp_notif_addfd {
+ __u64 id;
+ __u32 flags;
+ __u32 srcfd;
+ __u32 newfd;
+ __u32 newfd_flags;
+};
+
+#define SECCOMP_IOC_MAGIC '!'
+#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
+#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type)
+
+/* Flags for seccomp notification fd ioctl. */
+#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif)
+#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
+ struct seccomp_notif_resp)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
+ struct seccomp_notif_addfd)
+
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64)
+
+#endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h
index 286e8d6a8e98..f94baf154c47 100644
--- a/tools/include/uapi/linux/seg6.h
+++ b/tools/include/uapi/linux/seg6.h
@@ -30,7 +30,7 @@ struct ipv6_sr_hdr {
__u8 flags;
__u16 tag;
- struct in6_addr segments[0];
+ struct in6_addr segments[];
};
#define SR6_FLAG1_PROTECTED (1 << 6)
@@ -49,7 +49,7 @@ struct ipv6_sr_hdr {
struct sr6_tlv {
__u8 type;
__u8 len;
- __u8 data[0];
+ __u8 data[];
};
#endif
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 82cc58fe9368..1686861aae20 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -98,35 +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;
- __u64 __spare2;
+
+ /* 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[12]; /* 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 */
};
@@ -152,6 +214,11 @@ struct statx {
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
+#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 */
@@ -171,9 +238,12 @@ struct statx {
* be of use to ordinary userspace programs such as GUIs or ls rather than
* specialised tools.
*
- * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
* semantically. Where possible, the numerical value is picked to correspond
- * also.
+ * also. Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state. It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
*/
#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */
#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */
@@ -183,7 +253,8 @@ struct statx {
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
-#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */
+#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
new file mode 100644
index 000000000000..c53cde425406
--- /dev/null
+++ b/tools/include/uapi/linux/stddef.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+
+
+#ifndef __always_inline
+#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
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * 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 (C only),
+ * as well as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+ union { \
+ struct { MEMBERS } ATTRS; \
+ struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+ } ATTRS
+
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \
+ struct { \
+ struct { } __empty_ ## NAME; \
+ TYPE NAME[]; \
+ }
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
index 653c4f94f76e..fe6c8f8f3e8c 100644
--- a/tools/include/uapi/linux/tc_act/tc_bpf.h
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -1,11 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
/*
* Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
*/
#ifndef __LINUX_TC_BPF_H
diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h
new file mode 100644
index 000000000000..13ceeb395eb8
--- /dev/null
+++ b/tools/include/uapi/linux/tcp.h
@@ -0,0 +1,357 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the TCP protocol.
+ *
+ * Version: @(#)tcp.h 1.0.2 04/28/93
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_TCP_H
+#define _UAPI_LINUX_TCP_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/socket.h>
+
+struct tcphdr {
+ __be16 source;
+ __be16 dest;
+ __be32 seq;
+ __be32 ack_seq;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 res1:4,
+ doff:4,
+ fin:1,
+ syn:1,
+ rst:1,
+ psh:1,
+ ack:1,
+ urg:1,
+ ece:1,
+ cwr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u16 doff:4,
+ res1:4,
+ cwr:1,
+ ece:1,
+ urg:1,
+ ack:1,
+ psh:1,
+ rst:1,
+ syn:1,
+ fin:1;
+#else
+#error "Adjust your <asm/byteorder.h> defines"
+#endif
+ __be16 window;
+ __sum16 check;
+ __be16 urg_ptr;
+};
+
+/*
+ * The union cast uses a gcc extension to avoid aliasing problems
+ * (union is compatible to any of its members)
+ * This means this part of the code is -fstrict-aliasing safe now.
+ */
+union tcp_word_hdr {
+ struct tcphdr hdr;
+ __be32 words[5];
+};
+
+#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
+
+enum {
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
+};
+
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
+/* TCP socket options */
+#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
+#define TCP_MAXSEG 2 /* Limit MSS */
+#define TCP_CORK 3 /* Never send partially complete segments */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Block/reenable quick acks */
+#define TCP_CONGESTION 13 /* Congestion control algorithm */
+#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
+#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE 20
+#define TCP_QUEUE_SEQ 21
+#define TCP_REPAIR_OPTIONS 22
+#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
+#define TCP_TIMESTAMP 24
+#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
+#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
+#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
+#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
+#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
+#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
+#define TCP_ZEROCOPY_RECEIVE 35
+#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */
+
+#define TCP_CM_INQ TCP_INQ
+
+#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */
+
+
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF 0
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
+struct tcp_repair_opt {
+ __u32 opt_code;
+ __u32 opt_val;
+};
+
+struct tcp_repair_window {
+ __u32 snd_wl1;
+ __u32 snd_wnd;
+ __u32 max_window;
+
+ __u32 rcv_wnd;
+ __u32 rcv_wup;
+};
+
+enum {
+ TCP_NO_QUEUE,
+ TCP_RECV_QUEUE,
+ TCP_SEND_QUEUE,
+ TCP_QUEUES_NR,
+};
+
+/* why fastopen failed from client perspective */
+enum tcp_fastopen_client_fail {
+ TFO_STATUS_UNSPEC, /* catch-all */
+ TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */
+ TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */
+ TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */
+};
+
+/* for TCP_INFO socket option */
+#define TCPI_OPT_TIMESTAMPS 1
+#define TCPI_OPT_SACK 2
+#define TCPI_OPT_WSCALE 4
+#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
+#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
+#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
+
+/*
+ * Sender's congestion state indicating normal or abnormal situations
+ * in the last round of packets sent. The state is driven by the ACK
+ * information and timer events.
+ */
+enum tcp_ca_state {
+ /*
+ * Nothing bad has been observed recently.
+ * No apparent reordering, packet loss, or ECN marks.
+ */
+ TCP_CA_Open = 0,
+#define TCPF_CA_Open (1<<TCP_CA_Open)
+ /*
+ * The sender enters disordered state when it has received DUPACKs or
+ * SACKs in the last round of packets sent. This could be due to packet
+ * loss or reordering but needs further information to confirm packets
+ * have been lost.
+ */
+ TCP_CA_Disorder = 1,
+#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
+ /*
+ * The sender enters Congestion Window Reduction (CWR) state when it
+ * has received ACKs with ECN-ECE marks, or has experienced congestion
+ * or packet discard on the sender host (e.g. qdisc).
+ */
+ TCP_CA_CWR = 2,
+#define TCPF_CA_CWR (1<<TCP_CA_CWR)
+ /*
+ * The sender is in fast recovery and retransmitting lost packets,
+ * typically triggered by ACK events.
+ */
+ TCP_CA_Recovery = 3,
+#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
+ /*
+ * The sender is in loss recovery triggered by retransmission timeout.
+ */
+ TCP_CA_Loss = 4
+#define TCPF_CA_Loss (1<<TCP_CA_Loss)
+};
+
+struct tcp_info {
+ __u8 tcpi_state;
+ __u8 tcpi_ca_state;
+ __u8 tcpi_retransmits;
+ __u8 tcpi_probes;
+ __u8 tcpi_backoff;
+ __u8 tcpi_options;
+ __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+ __u8 tcpi_delivery_rate_app_limited:1, tcpi_fastopen_client_fail:2;
+
+ __u32 tcpi_rto;
+ __u32 tcpi_ato;
+ __u32 tcpi_snd_mss;
+ __u32 tcpi_rcv_mss;
+
+ __u32 tcpi_unacked;
+ __u32 tcpi_sacked;
+ __u32 tcpi_lost;
+ __u32 tcpi_retrans;
+ __u32 tcpi_fackets;
+
+ /* Times. */
+ __u32 tcpi_last_data_sent;
+ __u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
+ __u32 tcpi_last_data_recv;
+ __u32 tcpi_last_ack_recv;
+
+ /* Metrics. */
+ __u32 tcpi_pmtu;
+ __u32 tcpi_rcv_ssthresh;
+ __u32 tcpi_rtt;
+ __u32 tcpi_rttvar;
+ __u32 tcpi_snd_ssthresh;
+ __u32 tcpi_snd_cwnd;
+ __u32 tcpi_advmss;
+ __u32 tcpi_reordering;
+
+ __u32 tcpi_rcv_rtt;
+ __u32 tcpi_rcv_space;
+
+ __u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+ __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
+ __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
+
+ __u32 tcpi_notsent_bytes;
+ __u32 tcpi_min_rtt;
+ __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */
+ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */
+
+ __u64 tcpi_delivery_rate;
+
+ __u64 tcpi_busy_time; /* Time (usec) busy sending data */
+ __u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */
+ __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */
+
+ __u32 tcpi_delivered;
+ __u32 tcpi_delivered_ce;
+
+ __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
+ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */
+ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */
+ __u32 tcpi_reord_seen; /* reordering events seen */
+
+ __u32 tcpi_rcv_ooopack; /* Out-of-order packets received */
+
+ __u32 tcpi_snd_wnd; /* peer's advertised receive window after
+ * scaling (bytes)
+ */
+};
+
+/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
+enum {
+ TCP_NLA_PAD,
+ TCP_NLA_BUSY, /* Time (usec) busy sending data */
+ TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */
+ TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */
+ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */
+ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */
+ TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */
+ TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */
+ TCP_NLA_SND_CWND, /* Sending congestion window */
+ TCP_NLA_REORDERING, /* Reordering metric */
+ TCP_NLA_MIN_RTT, /* minimum RTT */
+ TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */
+ TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */
+ TCP_NLA_SNDQ_SIZE, /* Data (bytes) pending in send queue */
+ TCP_NLA_CA_STATE, /* ca_state of socket */
+ TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */
+ TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */
+ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */
+ TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */
+ TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */
+ TCP_NLA_DSACK_DUPS, /* DSACK blocks received */
+ TCP_NLA_REORD_SEEN, /* reordering events seen */
+ TCP_NLA_SRTT, /* smoothed RTT in usecs */
+ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */
+ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */
+ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */
+};
+
+/* for TCP_MD5SIG socket option */
+#define TCP_MD5SIG_MAXKEYLEN 80
+
+/* tcp_md5sig extension flags for TCP_MD5SIG_EXT */
+#define TCP_MD5SIG_FLAG_PREFIX 0x1 /* address prefix length */
+#define TCP_MD5SIG_FLAG_IFINDEX 0x2 /* ifindex set */
+
+struct tcp_md5sig {
+ struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
+ __u8 tcpm_flags; /* extension flags */
+ __u8 tcpm_prefixlen; /* address prefix */
+ __u16 tcpm_keylen; /* key length */
+ int tcpm_ifindex; /* device index for scope */
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
+};
+
+/* INET_DIAG_MD5SIG */
+struct tcp_diag_md5sig {
+ __u8 tcpm_family;
+ __u8 tcpm_prefixlen;
+ __u16 tcpm_keylen;
+ __be32 tcpm_addr[4];
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN];
+};
+
+/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
+
+#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1
+struct tcp_zerocopy_receive {
+ __u64 address; /* in: address of mapping */
+ __u32 length; /* in/out: number of bytes to map/mapped */
+ __u32 recv_skip_hint; /* out: amount of bytes to skip */
+ __u32 inq; /* out: amount of bytes in read queue */
+ __s32 err; /* out: socket error */
+ __u64 copybuf_address; /* in: copybuf address (small reads) */
+ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */
+ __u32 flags; /* in: flags */
+};
+#endif /* _UAPI_LINUX_TCP_H */
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 */
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
deleted file mode 100644
index cf525cddeb94..000000000000
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ /dev/null
@@ -1,231 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*****************************************************************************/
-
-/*
- * usbdevice_fs.h -- USB device file system.
- *
- * Copyright (C) 2000
- * Thomas Sailer (sailer@ife.ee.ethz.ch)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * History:
- * 0.1 04.01.2000 Created
- */
-
-/*****************************************************************************/
-
-#ifndef _UAPI_LINUX_USBDEVICE_FS_H
-#define _UAPI_LINUX_USBDEVICE_FS_H
-
-#include <linux/types.h>
-#include <linux/magic.h>
-
-/* --------------------------------------------------------------------- */
-
-/* usbdevfs ioctl codes */
-
-struct usbdevfs_ctrltransfer {
- __u8 bRequestType;
- __u8 bRequest;
- __u16 wValue;
- __u16 wIndex;
- __u16 wLength;
- __u32 timeout; /* in milliseconds */
- void __user *data;
-};
-
-struct usbdevfs_bulktransfer {
- unsigned int ep;
- unsigned int len;
- unsigned int timeout; /* in milliseconds */
- void __user *data;
-};
-
-struct usbdevfs_setinterface {
- unsigned int interface;
- unsigned int altsetting;
-};
-
-struct usbdevfs_disconnectsignal {
- unsigned int signr;
- void __user *context;
-};
-
-#define USBDEVFS_MAXDRIVERNAME 255
-
-struct usbdevfs_getdriver {
- unsigned int interface;
- char driver[USBDEVFS_MAXDRIVERNAME + 1];
-};
-
-struct usbdevfs_connectinfo {
- unsigned int devnum;
- unsigned char slow;
-};
-
-struct usbdevfs_conninfo_ex {
- __u32 size; /* Size of the structure from the kernel's */
- /* point of view. Can be used by userspace */
- /* to determine how much data can be */
- /* used/trusted. */
- __u32 busnum; /* USB bus number, as enumerated by the */
- /* kernel, the device is connected to. */
- __u32 devnum; /* Device address on the bus. */
- __u32 speed; /* USB_SPEED_* constants from ch9.h */
- __u8 num_ports; /* Number of ports the device is connected */
- /* to on the way to the root hub. It may */
- /* be bigger than size of 'ports' array so */
- /* userspace can detect overflows. */
- __u8 ports[7]; /* List of ports on the way from the root */
- /* hub to the device. Current limit in */
- /* USB specification is 7 tiers (root hub, */
- /* 5 intermediate hubs, device), which */
- /* gives at most 6 port entries. */
-};
-
-#define USBDEVFS_URB_SHORT_NOT_OK 0x01
-#define USBDEVFS_URB_ISO_ASAP 0x02
-#define USBDEVFS_URB_BULK_CONTINUATION 0x04
-#define USBDEVFS_URB_NO_FSBR 0x20 /* Not used */
-#define USBDEVFS_URB_ZERO_PACKET 0x40
-#define USBDEVFS_URB_NO_INTERRUPT 0x80
-
-#define USBDEVFS_URB_TYPE_ISO 0
-#define USBDEVFS_URB_TYPE_INTERRUPT 1
-#define USBDEVFS_URB_TYPE_CONTROL 2
-#define USBDEVFS_URB_TYPE_BULK 3
-
-struct usbdevfs_iso_packet_desc {
- unsigned int length;
- unsigned int actual_length;
- unsigned int status;
-};
-
-struct usbdevfs_urb {
- unsigned char type;
- unsigned char endpoint;
- int status;
- unsigned int flags;
- void __user *buffer;
- int buffer_length;
- int actual_length;
- int start_frame;
- union {
- int number_of_packets; /* Only used for isoc urbs */
- unsigned int stream_id; /* Only used with bulk streams */
- };
- int error_count;
- unsigned int signr; /* signal to be sent on completion,
- or 0 if none should be sent. */
- void __user *usercontext;
- struct usbdevfs_iso_packet_desc iso_frame_desc[0];
-};
-
-/* ioctls for talking directly to drivers */
-struct usbdevfs_ioctl {
- int ifno; /* interface 0..N ; negative numbers reserved */
- int ioctl_code; /* MUST encode size + direction of data so the
- * macros in <asm/ioctl.h> give correct values */
- void __user *data; /* param buffer (in, or out) */
-};
-
-/* You can do most things with hubs just through control messages,
- * except find out what device connects to what port. */
-struct usbdevfs_hub_portinfo {
- char nports; /* number of downstream ports in this hub */
- char port [127]; /* e.g. port 3 connects to device 27 */
-};
-
-/* System and bus capability flags */
-#define USBDEVFS_CAP_ZERO_PACKET 0x01
-#define USBDEVFS_CAP_BULK_CONTINUATION 0x02
-#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04
-#define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08
-#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10
-#define USBDEVFS_CAP_MMAP 0x20
-#define USBDEVFS_CAP_DROP_PRIVILEGES 0x40
-#define USBDEVFS_CAP_CONNINFO_EX 0x80
-#define USBDEVFS_CAP_SUSPEND 0x100
-
-/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
-
-/* disconnect-and-claim if the driver matches the driver field */
-#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER 0x01
-/* disconnect-and-claim except when the driver matches the driver field */
-#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER 0x02
-
-struct usbdevfs_disconnect_claim {
- unsigned int interface;
- unsigned int flags;
- char driver[USBDEVFS_MAXDRIVERNAME + 1];
-};
-
-struct usbdevfs_streams {
- unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
- unsigned int num_eps;
- unsigned char eps[0];
-};
-
-/*
- * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
- * linux/usb/ch9.h
- */
-
-#define USBDEVFS_CONTROL _IOWR('U', 0, struct usbdevfs_ctrltransfer)
-#define USBDEVFS_CONTROL32 _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
-#define USBDEVFS_BULK _IOWR('U', 2, struct usbdevfs_bulktransfer)
-#define USBDEVFS_BULK32 _IOWR('U', 2, struct usbdevfs_bulktransfer32)
-#define USBDEVFS_RESETEP _IOR('U', 3, unsigned int)
-#define USBDEVFS_SETINTERFACE _IOR('U', 4, struct usbdevfs_setinterface)
-#define USBDEVFS_SETCONFIGURATION _IOR('U', 5, unsigned int)
-#define USBDEVFS_GETDRIVER _IOW('U', 8, struct usbdevfs_getdriver)
-#define USBDEVFS_SUBMITURB _IOR('U', 10, struct usbdevfs_urb)
-#define USBDEVFS_SUBMITURB32 _IOR('U', 10, struct usbdevfs_urb32)
-#define USBDEVFS_DISCARDURB _IO('U', 11)
-#define USBDEVFS_REAPURB _IOW('U', 12, void *)
-#define USBDEVFS_REAPURB32 _IOW('U', 12, __u32)
-#define USBDEVFS_REAPURBNDELAY _IOW('U', 13, void *)
-#define USBDEVFS_REAPURBNDELAY32 _IOW('U', 13, __u32)
-#define USBDEVFS_DISCSIGNAL _IOR('U', 14, struct usbdevfs_disconnectsignal)
-#define USBDEVFS_DISCSIGNAL32 _IOR('U', 14, struct usbdevfs_disconnectsignal32)
-#define USBDEVFS_CLAIMINTERFACE _IOR('U', 15, unsigned int)
-#define USBDEVFS_RELEASEINTERFACE _IOR('U', 16, unsigned int)
-#define USBDEVFS_CONNECTINFO _IOW('U', 17, struct usbdevfs_connectinfo)
-#define USBDEVFS_IOCTL _IOWR('U', 18, struct usbdevfs_ioctl)
-#define USBDEVFS_IOCTL32 _IOWR('U', 18, struct usbdevfs_ioctl32)
-#define USBDEVFS_HUB_PORTINFO _IOR('U', 19, struct usbdevfs_hub_portinfo)
-#define USBDEVFS_RESET _IO('U', 20)
-#define USBDEVFS_CLEAR_HALT _IOR('U', 21, unsigned int)
-#define USBDEVFS_DISCONNECT _IO('U', 22)
-#define USBDEVFS_CONNECT _IO('U', 23)
-#define USBDEVFS_CLAIM_PORT _IOR('U', 24, unsigned int)
-#define USBDEVFS_RELEASE_PORT _IOR('U', 25, unsigned int)
-#define USBDEVFS_GET_CAPABILITIES _IOR('U', 26, __u32)
-#define USBDEVFS_DISCONNECT_CLAIM _IOR('U', 27, struct usbdevfs_disconnect_claim)
-#define USBDEVFS_ALLOC_STREAMS _IOR('U', 28, struct usbdevfs_streams)
-#define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams)
-#define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32)
-#define USBDEVFS_GET_SPEED _IO('U', 31)
-/*
- * Returns struct usbdevfs_conninfo_ex; length is variable to allow
- * extending size of the data returned.
- */
-#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len)
-#define USBDEVFS_FORBID_SUSPEND _IO('U', 33)
-#define USBDEVFS_ALLOW_SUSPEND _IO('U', 34)
-#define USBDEVFS_WAIT_FOR_RESUME _IO('U', 35)
-
-#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h
new file mode 100644
index 000000000000..4283de22d5b6
--- /dev/null
+++ b/tools/include/uapi/linux/userfaultfd.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * include/linux/userfaultfd.h
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ * Copyright (C) 2015 Red Hat, Inc.
+ *
+ */
+
+#ifndef _LINUX_USERFAULTFD_H
+#define _LINUX_USERFAULTFD_H
+
+#include <linux/types.h>
+
+/* ioctls for /dev/userfaultfd */
+#define USERFAULTFD_IOC 0xAA
+#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
+
+/*
+ * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
+ * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In
+ * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ
+ * means the userland is reading).
+ */
+#define UFFD_API ((__u64)0xAA)
+#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \
+ UFFDIO_REGISTER_MODE_WP | \
+ UFFDIO_REGISTER_MODE_MINOR)
+#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
+ UFFD_FEATURE_EVENT_FORK | \
+ UFFD_FEATURE_EVENT_REMAP | \
+ UFFD_FEATURE_EVENT_REMOVE | \
+ UFFD_FEATURE_EVENT_UNMAP | \
+ UFFD_FEATURE_MISSING_HUGETLBFS | \
+ UFFD_FEATURE_MISSING_SHMEM | \
+ UFFD_FEATURE_SIGBUS | \
+ UFFD_FEATURE_THREAD_ID | \
+ UFFD_FEATURE_MINOR_HUGETLBFS | \
+ UFFD_FEATURE_MINOR_SHMEM | \
+ UFFD_FEATURE_EXACT_ADDRESS | \
+ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \
+ UFFD_FEATURE_WP_UNPOPULATED | \
+ UFFD_FEATURE_POISON | \
+ UFFD_FEATURE_WP_ASYNC | \
+ UFFD_FEATURE_MOVE)
+#define UFFD_API_IOCTLS \
+ ((__u64)1 << _UFFDIO_REGISTER | \
+ (__u64)1 << _UFFDIO_UNREGISTER | \
+ (__u64)1 << _UFFDIO_API)
+#define UFFD_API_RANGE_IOCTLS \
+ ((__u64)1 << _UFFDIO_WAKE | \
+ (__u64)1 << _UFFDIO_COPY | \
+ (__u64)1 << _UFFDIO_ZEROPAGE | \
+ (__u64)1 << _UFFDIO_MOVE | \
+ (__u64)1 << _UFFDIO_WRITEPROTECT | \
+ (__u64)1 << _UFFDIO_CONTINUE | \
+ (__u64)1 << _UFFDIO_POISON)
+#define UFFD_API_RANGE_IOCTLS_BASIC \
+ ((__u64)1 << _UFFDIO_WAKE | \
+ (__u64)1 << _UFFDIO_COPY | \
+ (__u64)1 << _UFFDIO_WRITEPROTECT | \
+ (__u64)1 << _UFFDIO_CONTINUE | \
+ (__u64)1 << _UFFDIO_POISON)
+
+/*
+ * Valid ioctl command number range with this API is from 0x00 to
+ * 0x3F. UFFDIO_API is the fixed number, everything else can be
+ * changed by implementing a different UFFD_API. If sticking to the
+ * same UFFD_API more ioctl can be added and userland will be aware of
+ * which ioctl the running kernel implements through the ioctl command
+ * bitmask written by the UFFDIO_API.
+ */
+#define _UFFDIO_REGISTER (0x00)
+#define _UFFDIO_UNREGISTER (0x01)
+#define _UFFDIO_WAKE (0x02)
+#define _UFFDIO_COPY (0x03)
+#define _UFFDIO_ZEROPAGE (0x04)
+#define _UFFDIO_MOVE (0x05)
+#define _UFFDIO_WRITEPROTECT (0x06)
+#define _UFFDIO_CONTINUE (0x07)
+#define _UFFDIO_POISON (0x08)
+#define _UFFDIO_API (0x3F)
+
+/* userfaultfd ioctl ids */
+#define UFFDIO 0xAA
+#define UFFDIO_API _IOWR(UFFDIO, _UFFDIO_API, \
+ struct uffdio_api)
+#define UFFDIO_REGISTER _IOWR(UFFDIO, _UFFDIO_REGISTER, \
+ struct uffdio_register)
+#define UFFDIO_UNREGISTER _IOR(UFFDIO, _UFFDIO_UNREGISTER, \
+ struct uffdio_range)
+#define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \
+ struct uffdio_range)
+#define UFFDIO_COPY _IOWR(UFFDIO, _UFFDIO_COPY, \
+ struct uffdio_copy)
+#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \
+ struct uffdio_zeropage)
+#define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, \
+ struct uffdio_move)
+#define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+ struct uffdio_writeprotect)
+#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \
+ struct uffdio_continue)
+#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \
+ struct uffdio_poison)
+
+/* read() structure */
+struct uffd_msg {
+ __u8 event;
+
+ __u8 reserved1;
+ __u16 reserved2;
+ __u32 reserved3;
+
+ union {
+ struct {
+ __u64 flags;
+ __u64 address;
+ union {
+ __u32 ptid;
+ } feat;
+ } pagefault;
+
+ struct {
+ __u32 ufd;
+ } fork;
+
+ struct {
+ __u64 from;
+ __u64 to;
+ __u64 len;
+ } remap;
+
+ struct {
+ __u64 start;
+ __u64 end;
+ } remove;
+
+ struct {
+ /* unused reserved fields */
+ __u64 reserved1;
+ __u64 reserved2;
+ __u64 reserved3;
+ } reserved;
+ } arg;
+} __attribute__((packed));
+
+/*
+ * Start at 0x12 and not at 0 to be more strict against bugs.
+ */
+#define UFFD_EVENT_PAGEFAULT 0x12
+#define UFFD_EVENT_FORK 0x13
+#define UFFD_EVENT_REMAP 0x14
+#define UFFD_EVENT_REMOVE 0x15
+#define UFFD_EVENT_UNMAP 0x16
+
+/* flags for UFFD_EVENT_PAGEFAULT */
+#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
+#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */
+#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */
+
+struct uffdio_api {
+ /* userland asks for an API number and the features to enable */
+ __u64 api;
+ /*
+ * Kernel answers below with the all available features for
+ * the API, this notifies userland of which events and/or
+ * which flags for each event are enabled in the current
+ * kernel.
+ *
+ * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE
+ * are to be considered implicitly always enabled in all kernels as
+ * long as the uffdio_api.api requested matches UFFD_API.
+ *
+ * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER
+ * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on
+ * hugetlbfs virtual memory ranges. Adding or not adding
+ * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has
+ * no real functional effect after UFFDIO_API returns, but
+ * it's only useful for an initial feature set probe at
+ * UFFDIO_API time. There are two ways to use it:
+ *
+ * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the
+ * uffdio_api.features before calling UFFDIO_API, an error
+ * will be returned by UFFDIO_API on a kernel without
+ * hugetlbfs missing support
+ *
+ * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in
+ * uffdio_api.features and instead it will be set by the
+ * kernel in the uffdio_api.features if the kernel supports
+ * it, so userland can later check if the feature flag is
+ * present in uffdio_api.features after UFFDIO_API
+ * succeeded.
+ *
+ * UFFD_FEATURE_MISSING_SHMEM works the same as
+ * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem
+ * (i.e. tmpfs and other shmem based APIs).
+ *
+ * UFFD_FEATURE_SIGBUS feature means no page-fault
+ * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead
+ * a SIGBUS signal will be sent to the faulting process.
+ *
+ * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
+ * be returned, if feature is not requested 0 will be returned.
+ *
+ * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
+ * can be intercepted (via REGISTER_MODE_MINOR) for
+ * hugetlbfs-backed pages.
+ *
+ * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
+ * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
+ *
+ * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page
+ * faults would be provided and the offset within the page would not be
+ * masked.
+ *
+ * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
+ * write-protection mode is supported on both shmem and hugetlbfs.
+ *
+ * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd
+ * write-protection mode will always apply to unpopulated pages
+ * (i.e. empty ptes). This will be the default behavior for shmem
+ * & hugetlbfs, so this flag only affects anonymous memory behavior
+ * when userfault write-protection mode is registered.
+ *
+ * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection
+ * asynchronous mode is supported in which the write fault is
+ * automatically resolved and write-protection is un-set.
+ * It implies UFFD_FEATURE_WP_UNPOPULATED.
+ *
+ * UFFD_FEATURE_MOVE indicates that the kernel supports moving an
+ * existing page contents from userspace.
+ */
+#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
+#define UFFD_FEATURE_EVENT_FORK (1<<1)
+#define UFFD_FEATURE_EVENT_REMAP (1<<2)
+#define UFFD_FEATURE_EVENT_REMOVE (1<<3)
+#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4)
+#define UFFD_FEATURE_MISSING_SHMEM (1<<5)
+#define UFFD_FEATURE_EVENT_UNMAP (1<<6)
+#define UFFD_FEATURE_SIGBUS (1<<7)
+#define UFFD_FEATURE_THREAD_ID (1<<8)
+#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9)
+#define UFFD_FEATURE_MINOR_SHMEM (1<<10)
+#define UFFD_FEATURE_EXACT_ADDRESS (1<<11)
+#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12)
+#define UFFD_FEATURE_WP_UNPOPULATED (1<<13)
+#define UFFD_FEATURE_POISON (1<<14)
+#define UFFD_FEATURE_WP_ASYNC (1<<15)
+#define UFFD_FEATURE_MOVE (1<<16)
+ __u64 features;
+
+ __u64 ioctls;
+};
+
+struct uffdio_range {
+ __u64 start;
+ __u64 len;
+};
+
+struct uffdio_register {
+ struct uffdio_range range;
+#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0)
+#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1)
+#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2)
+ __u64 mode;
+
+ /*
+ * kernel answers which ioctl commands are available for the
+ * range, keep at the end as the last 8 bytes aren't read.
+ */
+ __u64 ioctls;
+};
+
+struct uffdio_copy {
+ __u64 dst;
+ __u64 src;
+ __u64 len;
+#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0)
+ /*
+ * UFFDIO_COPY_MODE_WP will map the page write protected on
+ * the fly. UFFDIO_COPY_MODE_WP is available only if the
+ * write protected ioctl is implemented for the range
+ * according to the uffdio_register.ioctls.
+ */
+#define UFFDIO_COPY_MODE_WP ((__u64)1<<1)
+ __u64 mode;
+
+ /*
+ * "copy" is written by the ioctl and must be at the end: the
+ * copy_from_user will not read the last 8 bytes.
+ */
+ __s64 copy;
+};
+
+struct uffdio_zeropage {
+ struct uffdio_range range;
+#define UFFDIO_ZEROPAGE_MODE_DONTWAKE ((__u64)1<<0)
+ __u64 mode;
+
+ /*
+ * "zeropage" is written by the ioctl and must be at the end:
+ * the copy_from_user will not read the last 8 bytes.
+ */
+ __s64 zeropage;
+};
+
+struct uffdio_writeprotect {
+ struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1. Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1)
+ __u64 mode;
+};
+
+struct uffdio_continue {
+ struct uffdio_range range;
+#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0)
+ /*
+ * UFFDIO_CONTINUE_MODE_WP will map the page write protected on
+ * the fly. UFFDIO_CONTINUE_MODE_WP is available only if the
+ * write protected ioctl is implemented for the range
+ * according to the uffdio_register.ioctls.
+ */
+#define UFFDIO_CONTINUE_MODE_WP ((__u64)1<<1)
+ __u64 mode;
+
+ /*
+ * Fields below here are written by the ioctl and must be at the end:
+ * the copy_from_user will not read past here.
+ */
+ __s64 mapped;
+};
+
+struct uffdio_poison {
+ struct uffdio_range range;
+#define UFFDIO_POISON_MODE_DONTWAKE ((__u64)1<<0)
+ __u64 mode;
+
+ /*
+ * Fields below here are written by the ioctl and must be at the end:
+ * the copy_from_user will not read past here.
+ */
+ __s64 updated;
+};
+
+struct uffdio_move {
+ __u64 dst;
+ __u64 src;
+ __u64 len;
+ /*
+ * Especially if used to atomically remove memory from the
+ * address space the wake on the dst range is not needed.
+ */
+#define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0)
+#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1)
+ __u64 mode;
+ /*
+ * "move" is written by the ioctl and must be at the end: the
+ * copy_from_user will not read the last 8 bytes.
+ */
+ __s64 move;
+};
+
+/*
+ * Flags for the userfaultfd(2) system call itself.
+ */
+
+/*
+ * Create a userfaultfd that can handle page faults only in user mode.
+ */
+#define UFFD_USER_MODE_ONLY 1
+
+#endif /* _LINUX_USERFAULTFD_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
deleted file mode 100644
index 0c2349612e77..000000000000
--- a/tools/include/uapi/linux/vhost.h
+++ /dev/null
@@ -1,147 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _LINUX_VHOST_H
-#define _LINUX_VHOST_H
-/* Userspace interface for in-kernel virtio accelerators. */
-
-/* vhost is used to reduce the number of system calls involved in virtio.
- *
- * Existing virtio net code is used in the guest without modification.
- *
- * This header includes interface used by userspace hypervisor for
- * device configuration.
- */
-
-#include <linux/vhost_types.h>
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define VHOST_FILE_UNBIND -1
-
-/* ioctls */
-
-#define VHOST_VIRTIO 0xAF
-
-/* Features bitmask for forward compatibility. Transport bits are used for
- * vhost specific features. */
-#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64)
-#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64)
-
-/* Set current process as the (exclusive) owner of this file descriptor. This
- * must be called before any other vhost command. Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
-#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
-/* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
-#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
-
-/* Set up/modify memory layout */
-#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
-
-/* Write logging setup. */
-/* Memory writes can optionally be logged by setting bit at an offset
- * (calculated from the physical address) from specified log base.
- * The bit is set using an atomic 32 bit operation. */
-/* Set base address for logging. */
-#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
-/* Specify an eventfd file descriptor to signal on log write. */
-#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
-
-/* Ring setup. */
-/* Set number of descriptors in ring. This parameter can not
- * be modified while ring is running (bound to a device). */
-#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
-/* Set addresses for the ring. */
-#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
-/* Base value where queue looks for available descriptors */
-#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
-/* Get accessor: reads index, writes value in num */
-#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
-
-/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
- * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
- * The byte order cannot be changed while the device is active: trying to do so
- * returns -EBUSY.
- * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
- * set.
- * Not all kernel configurations support this ioctl, but all configurations that
- * support SET also support GET.
- */
-#define VHOST_VRING_LITTLE_ENDIAN 0
-#define VHOST_VRING_BIG_ENDIAN 1
-#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
-#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
-
-/* The following ioctls use eventfd file descriptors to signal and poll
- * for events. */
-
-/* Set eventfd to poll for added buffers */
-#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
-/* Set eventfd to signal when buffers have beed used */
-#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
-/* Set eventfd to signal an error */
-#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
-/* Set busy loop timeout (in us) */
-#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23, \
- struct vhost_vring_state)
-/* Get busy loop timeout (in us) */
-#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \
- struct vhost_vring_state)
-
-/* Set or get vhost backend capability */
-
-/* Use message type V2 */
-#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
-
-#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
-#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
-
-/* VHOST_NET specific defines */
-
-/* Attach virtio net ring to a raw socket, or tap device.
- * The socket must be already bound to an ethernet device, this device will be
- * used for transmit. Pass fd -1 to unbind from the socket and the transmit
- * device. This can be used to stop the ring (e.g. for migration). */
-#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
-
-/* VHOST_SCSI specific defines */
-
-#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
-#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
-/* Changing this breaks userspace. */
-#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
-/* Set and get the events missed flag */
-#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
-#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
-
-/* VHOST_VSOCK specific defines */
-
-#define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64)
-#define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int)
-
-/* VHOST_VDPA specific defines */
-
-/* Get the device id. The device ids follow the same definition of
- * the device id defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_DEVICE_ID _IOR(VHOST_VIRTIO, 0x70, __u32)
-/* Get and set the status. The status bits follow the same definition
- * of the device status defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_STATUS _IOR(VHOST_VIRTIO, 0x71, __u8)
-#define VHOST_VDPA_SET_STATUS _IOW(VHOST_VIRTIO, 0x72, __u8)
-/* Get and set the device config. The device config follows the same
- * definition of the device config defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_CONFIG _IOR(VHOST_VIRTIO, 0x73, \
- struct vhost_vdpa_config)
-#define VHOST_VDPA_SET_CONFIG _IOW(VHOST_VIRTIO, 0x74, \
- struct vhost_vdpa_config)
-/* Enable/disable the ring. */
-#define VHOST_VDPA_SET_VRING_ENABLE _IOW(VHOST_VIRTIO, 0x75, \
- struct vhost_vring_state)
-/* Get the max ring size. */
-#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16)
-
-/* Set event fd for config interrupt*/
-#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
-#endif