diff options
| author | Peter Zijlstra <[email protected]> | 2024-07-04 16:00:24 +0200 |
|---|---|---|
| committer | Peter Zijlstra <[email protected]> | 2024-07-04 16:00:24 +0200 |
| commit | 0c8ea05e9b3d8e5287e2a968f2a2e744dfd31b99 (patch) | |
| tree | ba0443b74f063471c5d81d85e795e04e7e1dc79c /tools/include/uapi/linux | |
| parent | 0ca4da2412da05fb9dd0b5d90dcc8026219f0f29 (diff) | |
| parent | 34b3fc558b537bdf99644dcde539e151716f6331 (diff) | |
Merge branch 'tip/x86/cpu'
The Lunarlake patches rely on the new VFM stuff.
Signed-off-by: Peter Zijlstra <[email protected]>
Diffstat (limited to 'tools/include/uapi/linux')
| -rw-r--r-- | tools/include/uapi/linux/bits.h | 15 | ||||
| -rw-r--r-- | tools/include/uapi/linux/bpf.h | 44 | ||||
| -rw-r--r-- | tools/include/uapi/linux/ethtool.h | 104 | ||||
| -rw-r--r-- | tools/include/uapi/linux/fcntl.h | 123 | ||||
| -rw-r--r-- | tools/include/uapi/linux/fs.h | 396 | ||||
| -rw-r--r-- | tools/include/uapi/linux/kvm.h | 2 | ||||
| -rw-r--r-- | tools/include/uapi/linux/memfd.h | 39 | ||||
| -rw-r--r-- | tools/include/uapi/linux/mount.h | 211 | ||||
| -rw-r--r-- | tools/include/uapi/linux/netdev.h | 21 | ||||
| -rw-r--r-- | tools/include/uapi/linux/openat2.h | 43 | ||||
| -rw-r--r-- | tools/include/uapi/linux/prctl.h | 309 | ||||
| -rw-r--r-- | tools/include/uapi/linux/sched.h | 148 | ||||
| -rw-r--r-- | tools/include/uapi/linux/usbdevice_fs.h | 231 | ||||
| -rw-r--r-- | tools/include/uapi/linux/userfaultfd.h | 386 | ||||
| -rw-r--r-- | tools/include/uapi/linux/vhost.h | 230 |
15 files changed, 499 insertions, 1803 deletions
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h new file mode 100644 index 000000000000..3c2a101986a3 --- /dev/null +++ b/tools/include/uapi/linux/bits.h @@ -0,0 +1,15 @@ +/* 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)) - (_UL(1) << (l)) + 1) & \ + (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) + +#define __GENMASK_ULL(h, l) \ + (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ + (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* _UAPI_LINUX_BITS_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c42b9f1bada..90706a47f6ff 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; @@ -1135,6 +1136,7 @@ enum bpf_link_type { 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, }; @@ -1662,8 +1664,10 @@ union bpf_attr { } 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 */ @@ -3392,6 +3396,10 @@ union bpf_attr { * 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. @@ -5020,7 +5028,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5506,7 +5514,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) @@ -6718,6 +6726,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); @@ -6936,6 +6948,8 @@ 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 @@ -7118,6 +7132,7 @@ enum { 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 { @@ -7150,7 +7165,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ @@ -7195,8 +7210,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + 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 { @@ -7283,6 +7309,10 @@ 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))); diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h deleted file mode 100644 index 47afae3895ec..000000000000 --- a/tools/include/uapi/linux/ethtool.h +++ /dev/null @@ -1,104 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * ethtool.h: Defines for Linux ethtool. - * - * Copyright (C) 1998 David S. Miller ([email protected]) - * Copyright 2001 Jeff Garzik <[email protected]> - * Portions Copyright 2001 Sun Microsystems ([email protected]) - * Portions Copyright 2002 Intel ([email protected], - * [email protected], - * [email protected]) - * 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; -}; - -#define ETHTOOL_FWVERS_LEN 32 -#define ETHTOOL_BUSINFO_LEN 32 -#define ETHTOOL_EROMVERS_LEN 32 - -/** - * struct ethtool_drvinfo - general driver and device information - * @cmd: Command number = %ETHTOOL_GDRVINFO - * @driver: Driver short name. This should normally match the name - * in its bus driver structure (e.g. pci_driver::name). Must - * not be an empty string. - * @version: Driver version string; may be an empty string - * @fw_version: Firmware version string; may be an empty string - * @erom_version: Expansion ROM version string; may be an empty string - * @bus_info: Device bus address. This should match the dev_name() - * string for the underlying bus device, if there is one. May be - * an empty string. - * @reserved2: Reserved for future use; see the note on reserved space. - * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and - * %ETHTOOL_SPFLAGS commands; also the number of strings in the - * %ETH_SS_PRIV_FLAGS set - * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS - * command; also the number of strings in the %ETH_SS_STATS set - * @testinfo_len: Number of results returned by the %ETHTOOL_TEST - * command; also the number of strings in the %ETH_SS_TEST set - * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM - * and %ETHTOOL_SEEPROM commands, in bytes - * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS - * command, in bytes - * - * Users can use the %ETHTOOL_GSSET_INFO command to get the number of - * strings in any string set (from Linux 2.6.34). - * - * Drivers should set at most @driver, @version, @fw_version and - * @bus_info in their get_drvinfo() implementation. The ethtool - * core fills in the other fields using other driver operations. - */ -struct ethtool_drvinfo { - __u32 cmd; - char driver[32]; - char version[32]; - char fw_version[ETHTOOL_FWVERS_LEN]; - char bus_info[ETHTOOL_BUSINFO_LEN]; - char erom_version[ETHTOOL_EROMVERS_LEN]; - char reserved2[12]; - __u32 n_priv_flags; - __u32 n_stats; - __u32 testinfo_len; - __u32 eedump_len; - __u32 regdump_len; -}; - -#define ETHTOOL_GDRVINFO 0x00000003 - -#endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h deleted file mode 100644 index 282e90aeb163..000000000000 --- a/tools/include/uapi/linux/fcntl.h +++ /dev/null @@ -1,123 +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 */ -#define F_SEAL_EXEC 0x0020 /* prevent chmod modifying exec bits */ -/* (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 */ - -/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */ -#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to - compare object identity and may not - be usable to open_by_handle_at(2) */ -#if defined(__KERNEL__) -#define AT_GETATTR_NOSEC 0x80000000 -#endif - -#endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h deleted file mode 100644 index 45e4e64fd664..000000000000 --- a/tools/include/uapi/linux/fs.h +++ /dev/null @@ -1,396 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI_LINUX_FS_H -#define _UAPI_LINUX_FS_H - -/* - * This file has definitions for some important file table structures - * and constants and structures used by various generic file system - * ioctl's. Please do not make any changes in this file before - * sending patches for review to [email protected] and - * [email protected]. - */ - -#include <linux/limits.h> -#include <linux/ioctl.h> -#include <linux/types.h> -#ifndef __KERNEL__ -#include <linux/fscrypt.h> -#endif - -/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ -#if !defined(__KERNEL__) -#include <linux/mount.h> -#endif - -/* - * It's silly to have NR_OPEN bigger than NR_FILE, but you can change - * the file limit at runtime and only root can increase the per-process - * nr_file rlimit, so it's safe to set up a ridiculously high absolute - * upper limit on files-per-process. - * - * Some programs (notably those using select()) may have to be - * recompiled to take full advantage of the new limits.. - */ - -/* Fixed constants first: */ -#undef NR_OPEN -#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ -#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ - -#define BLOCK_SIZE_BITS 10 -#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS) - -#define SEEK_SET 0 /* seek relative to beginning of file */ -#define SEEK_CUR 1 /* seek relative to current file position */ -#define SEEK_END 2 /* seek relative to end of file */ -#define SEEK_DATA 3 /* seek to the next data */ -#define SEEK_HOLE 4 /* seek to the next hole */ -#define SEEK_MAX SEEK_HOLE - -#define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */ -#define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ -#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ - -struct file_clone_range { - __s64 src_fd; - __u64 src_offset; - __u64 src_length; - __u64 dest_offset; -}; - -struct fstrim_range { - __u64 start; - __u64 len; - __u64 minlen; -}; - -/* - * We include a length field because some filesystems (vfat) have an identifier - * that we do want to expose as a UUID, but doesn't have the standard length. - * - * We use a fixed size buffer beacuse this interface will, by fiat, never - * support "UUIDs" longer than 16 bytes; we don't want to force all downstream - * users to have to deal with that. - */ -struct fsuuid2 { - __u8 len; - __u8 uuid[16]; -}; - -struct fs_sysfs_path { - __u8 len; - __u8 name[128]; -}; - -/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ -#define FILE_DEDUPE_RANGE_SAME 0 -#define FILE_DEDUPE_RANGE_DIFFERS 1 - -/* from struct btrfs_ioctl_file_extent_same_info */ -struct file_dedupe_range_info { - __s64 dest_fd; /* in - destination file */ - __u64 dest_offset; /* in - start of extent in destination */ - __u64 bytes_deduped; /* out - total # of bytes we were able - * to dedupe from this file. */ - /* status of this dedupe operation: - * < 0 for error - * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds - * == FILE_DEDUPE_RANGE_DIFFERS if data differs - */ - __s32 status; /* out - see above description */ - __u32 reserved; /* must be zero */ -}; - -/* from struct btrfs_ioctl_file_extent_same_args */ -struct file_dedupe_range { - __u64 src_offset; /* in - start of extent in source */ - __u64 src_length; /* in - length of extent */ - __u16 dest_count; /* in - total elements in info array */ - __u16 reserved1; /* must be zero */ - __u32 reserved2; /* must be zero */ - struct file_dedupe_range_info info[]; -}; - -/* And dynamically-tunable limits and defaults: */ -struct files_stat_struct { - unsigned long nr_files; /* read only */ - unsigned long nr_free_files; /* read only */ - unsigned long max_files; /* tunable */ -}; - -struct inodes_stat_t { - long nr_inodes; - long nr_unused; - long dummy[5]; /* padding for sysctl ABI compatibility */ -}; - - -#define NR_FILE 8192 /* this can well be larger on a larger system */ - -/* - * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR. - */ -struct fsxattr { - __u32 fsx_xflags; /* xflags field value (get/set) */ - __u32 fsx_extsize; /* extsize field value (get/set)*/ - __u32 fsx_nextents; /* nextents field value (get) */ - __u32 fsx_projid; /* project identifier (get/set) */ - __u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ - unsigned char fsx_pad[8]; -}; - -/* - * Flags for the fsx_xflags field - */ -#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ -#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ -#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ -#define FS_XFLAG_APPEND 0x00000010 /* all writes append */ -#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ -#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */ -#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ -#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ -#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ -#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ -#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ -#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ -#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ -#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ -#define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ -#define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ -#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ - -/* the read-only stuff doesn't really belong here, but any other place is - probably as bad and I don't want to create yet another include file. */ - -#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */ -#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */ -#define BLKRRPART _IO(0x12,95) /* re-read partition table */ -#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */ -#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */ -#define BLKRASET _IO(0x12,98) /* set read ahead for block device */ -#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */ -#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */ -#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */ -#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */ -#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */ -#define BLKSSZGET _IO(0x12,104)/* get block device sector size */ -#if 0 -#define BLKPG _IO(0x12,105)/* See blkpg.h */ - -/* Some people are morons. Do not use sizeof! */ - -#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */ -#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */ -/* This was here just to show that the number is taken - - probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */ -#endif -/* A jump here: 108-111 have been used for various private purposes. */ -#define BLKBSZGET _IOR(0x12,112,size_t) -#define BLKBSZSET _IOW(0x12,113,size_t) -#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ -#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) -#define BLKTRACESTART _IO(0x12,116) -#define BLKTRACESTOP _IO(0x12,117) -#define BLKTRACETEARDOWN _IO(0x12,118) -#define BLKDISCARD _IO(0x12,119) -#define BLKIOMIN _IO(0x12,120) -#define BLKIOOPT _IO(0x12,121) -#define BLKALIGNOFF _IO(0x12,122) -#define BLKPBSZGET _IO(0x12,123) -#define BLKDISCARDZEROES _IO(0x12,124) -#define BLKSECDISCARD _IO(0x12,125) -#define BLKROTATIONAL _IO(0x12,126) -#define BLKZEROOUT _IO(0x12,127) -#define BLKGETDISKSEQ _IOR(0x12,128,__u64) -/* - * A jump here: 130-136 are reserved for zoned block devices - * (see uapi/linux/blkzoned.h) - */ - -#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ -#define FIBMAP _IO(0x00,1) /* bmap access */ -#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ -#define FIFREEZE _IOWR('X', 119, int) /* Freeze */ -#define FITHAW _IOWR('X', 120, int) /* Thaw */ -#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */ -#define FICLONE _IOW(0x94, 9, int) -#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range) -#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range) - -#define FSLABEL_MAX 256 /* Max chars for the interface; each fs may differ */ - -#define FS_IOC_GETFLAGS _IOR('f', 1, long) -#define FS_IOC_SETFLAGS _IOW('f', 2, long) -#define FS_IOC_GETVERSION _IOR('v', 1, long) -#define FS_IOC_SETVERSION _IOW('v', 2, long) -#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap) -#define FS_IOC32_GETFLAGS _IOR('f', 1, int) -#define FS_IOC32_SETFLAGS _IOW('f', 2, int) -#define FS_IOC32_GETVERSION _IOR('v', 1, int) -#define FS_IOC32_SETVERSION _IOW('v', 2, int) -#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr) -#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) -#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) -#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) -/* Returns the external filesystem UUID, the same one blkid returns */ -#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) -/* - * Returns the path component under /sys/fs/ that refers to this filesystem; - * also /sys/kernel/debug/ for filesystems with debugfs exports - */ -#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) - -/* - * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) - * - * Note: for historical reasons, these flags were originally used and - * defined for use by ext2/ext3, and then other file systems started - * using these flags so they wouldn't need to write their own version - * of chattr/lsattr (which was shipped as part of e2fsprogs). You - * should think twice before trying to use these flags in new - * contexts, or trying to assign these flags, since they are used both - * as the UAPI and the on-disk encoding for ext2/3/4. Also, we are - * almost out of 32-bit flags. :-) - * - * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from - * XFS to the generic FS level interface. This uses a structure that - * has padding and hence has more room to grow, so it may be more - * appropriate for many new use cases. - * - * Please do not change these flags or interfaces before checking with - * [email protected] and [email protected]. - */ -#define FS_SECRM_FL 0x00000001 /* Secure deletion */ -#define FS_UNRM_FL 0x00000002 /* Undelete */ -#define FS_COMPR_FL 0x00000004 /* Compress file */ -#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ -#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ -#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ -#define FS_NODUMP_FL 0x00000040 /* do not dump file */ -#define FS_NOATIME_FL 0x00000080 /* do not update atime */ -/* Reserved for compression usage... */ -#define FS_DIRTY_FL 0x00000100 -#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ -#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ -/* End compression flags --- maybe not all used */ -#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */ -#define FS_BTREE_FL 0x00001000 /* btree format dir */ -#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ -#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ -#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ -#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ -#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ -#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define FS_HUGE_FILE_FL 0x00040000 /* Reserved for ext4 */ -#define FS_EXTENT_FL 0x00080000 /* Extents */ -#define FS_VERITY_FL 0x00100000 /* Verity protected inode */ -#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ -#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */ -#define FS_NOCOW_FL 0x00800000 /* Do not cow file */ -#define FS_DAX_FL 0x02000000 /* Inode is DAX */ -#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ -#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ -#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */ -#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ - -#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ - - -#define SYNC_FILE_RANGE_WAIT_BEFORE 1 -#define SYNC_FILE_RANGE_WRITE 2 -#define SYNC_FILE_RANGE_WAIT_AFTER 4 -#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \ - SYNC_FILE_RANGE_WAIT_BEFORE | \ - SYNC_FILE_RANGE_WAIT_AFTER) - -/* - * Flags for preadv2/pwritev2: - */ - -typedef int __bitwise __kernel_rwf_t; - -/* high priority request, poll if possible */ -#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001) - -/* per-IO O_DSYNC */ -#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002) - -/* per-IO O_SYNC */ -#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004) - -/* per-IO, return -EAGAIN if operation would block */ -#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008) - -/* per-IO O_APPEND */ -#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) - -/* per-IO negation of O_APPEND */ -#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) - -/* mask of flags supported by the kernel */ -#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) - -/* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 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) - -/* - * 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; -}; - -#endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 2190adbe3002..ea32b101b999 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1221,7 +1221,7 @@ struct kvm_vfio_spapr_tce { /* 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_RADIX_MMU 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 */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) 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/mount.h b/tools/include/uapi/linux/mount.h deleted file mode 100644 index ad5478dbad00..000000000000 --- a/tools/include/uapi/linux/mount.h +++ /dev/null @@ -1,211 +0,0 @@ -#ifndef _UAPI_LINUX_MOUNT_H -#define _UAPI_LINUX_MOUNT_H - -#include <linux/types.h> - -/* - * These are the fs-independent mount-flags: up to 32 flags are supported - * - * Usage of these is restricted within the kernel to core mount(2) code and - * callers of sys_mount() only. Filesystems should be using the SB_* - * equivalent instead. - */ -#define MS_RDONLY 1 /* Mount read-only */ -#define MS_NOSUID 2 /* Ignore suid and sgid bits */ -#define MS_NODEV 4 /* Disallow access to device special files */ -#define MS_NOEXEC 8 /* Disallow program execution */ -#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ -#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ -#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ -#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ -#define MS_NOATIME 1024 /* Do not update access times. */ -#define MS_NODIRATIME 2048 /* Do not update directory access times */ -#define MS_BIND 4096 -#define MS_MOVE 8192 -#define MS_REC 16384 -#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. - MS_VERBOSE is deprecated. */ -#define MS_SILENT 32768 -#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define MS_UNBINDABLE (1<<17) /* change to unbindable */ -#define MS_PRIVATE (1<<18) /* change to private */ -#define MS_SLAVE (1<<19) /* change to slave */ -#define MS_SHARED (1<<20) /* change to shared */ -#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ -#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define MS_I_VERSION (1<<23) /* Update inode I_version field */ -#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ -#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define MS_SUBMOUNT (1<<26) -#define MS_NOREMOTELOCK (1<<27) -#define MS_NOSEC (1<<28) -#define MS_BORN (1<<29) -#define MS_ACTIVE (1<<30) -#define MS_NOUSER (1<<31) - -/* - * Superblock flags that can be altered by MS_REMOUNT - */ -#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ - MS_LAZYTIME) - -/* - * Old magic mount flag and mask - */ -#define MS_MGC_VAL 0xC0ED0000 -#define MS_MGC_MSK 0xffff0000 - -/* - * open_tree() flags. - */ -#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ -#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ - -/* - * move_mount() flags. - */ -#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */ -#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */ -#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ -#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ -#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ -#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ -#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ -#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ -#define MOVE_MOUNT__MASK 0x00000377 - -/* - * fsopen() flags. - */ -#define FSOPEN_CLOEXEC 0x00000001 - -/* - * fspick() flags. - */ -#define FSPICK_CLOEXEC 0x00000001 -#define FSPICK_SYMLINK_NOFOLLOW 0x00000002 -#define FSPICK_NO_AUTOMOUNT 0x00000004 -#define FSPICK_EMPTY_PATH 0x00000008 - -/* - * The type of fsconfig() call made. - */ -enum fsconfig_command { - FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */ - FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */ - FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */ - FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */ - FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */ - FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */ - FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */ - FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */ - FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */ -}; - -/* - * fsmount() flags. - */ -#define FSMOUNT_CLOEXEC 0x00000001 - -/* - * Mount attributes. - */ -#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ -#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ -#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ -#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ -#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ -#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ -#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ -#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ -#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ -#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ -#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */ - -/* - * mount_setattr() - */ -struct mount_attr { - __u64 attr_set; - __u64 attr_clr; - __u64 propagation; - __u64 userns_fd; -}; - -/* List of all mount_attr versions. */ -#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ - - -/* - * Structure for getting mount/superblock/filesystem info with statmount(2). - * - * The interface is similar to statx(2): individual fields or groups can be - * selected with the @mask argument of statmount(). Kernel will set the @mask - * field according to the supported fields. - * - * If string fields are selected, then the caller needs to pass a buffer that - * has space after the fixed part of the structure. Nul terminated strings are - * copied there and offsets relative to @str are stored in the relevant fields. - * If the buffer is too small, then EOVERFLOW is returned. The actually used - * size is returned in @size. - */ -struct statmount { - __u32 size; /* Total size, including strings */ - __u32 __spare1; - __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 __spare2[50]; - 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; -}; - -/* List of all mnt_id_req versions. */ -#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first 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 */ - -/* - * Special @mnt_id values that can be passed to listmount - */ -#define LSMT_ROOT 0xffffffffffffffff /* root mount */ - -#endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index bb65ee840cda..a8188202413e 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -146,6 +146,27 @@ enum { 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_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) diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h deleted file mode 100644 index a5feb7604948..000000000000 --- a/tools/include/uapi/linux/openat2.h +++ /dev/null @@ -1,43 +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)). */ -#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be - completed through cached lookup. May - return -EAGAIN if that's not - possible. */ - -#endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h deleted file mode 100644 index 370ed14b1ae0..000000000000 --- a/tools/include/uapi/linux/prctl.h +++ /dev/null @@ -1,309 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_PRCTL_H -#define _LINUX_PRCTL_H - -#include <linux/types.h> - -/* Values to pass as first argument to prctl() */ - -#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */ -#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */ - -/* Get/set current->mm->dumpable */ -#define PR_GET_DUMPABLE 3 -#define PR_SET_DUMPABLE 4 - -/* Get/set unaligned access control bits (if meaningful) */ -#define PR_GET_UNALIGN 5 -#define PR_SET_UNALIGN 6 -# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */ -# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */ - -/* Get/set whether or not to drop capabilities on setuid() away from - * uid 0 (as per security/commoncap.c) */ -#define PR_GET_KEEPCAPS 7 -#define PR_SET_KEEPCAPS 8 - -/* Get/set floating-point emulation control bits (if meaningful) */ -#define PR_GET_FPEMU 9 -#define PR_SET_FPEMU 10 -# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */ -# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */ - -/* Get/set floating-point exception mode (if meaningful) */ -#define PR_GET_FPEXC 11 -#define PR_SET_FPEXC 12 -# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */ -# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */ -# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */ -# define PR_FP_EXC_UND 0x040000 /* floating point underflow */ -# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */ -# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */ -# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */ -# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */ -# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */ -# define PR_FP_EXC_PRECISE 3 /* precise exception mode */ - -/* Get/set whether we use statistical process timing or accurate timestamp - * based process timing */ -#define PR_GET_TIMING 13 -#define PR_SET_TIMING 14 -# define PR_TIMING_STATISTICAL 0 /* Normal, traditional, - statistical process timing */ -# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based - process timing */ - -#define PR_SET_NAME 15 /* Set process name */ -#define PR_GET_NAME 16 /* Get process name */ - -/* Get/set process endian */ -#define PR_GET_ENDIAN 19 -#define PR_SET_ENDIAN 20 -# define PR_ENDIAN_BIG 0 -# define PR_ENDIAN_LITTLE 1 /* True little endian mode */ -# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */ - -/* Get/set process seccomp mode */ -#define PR_GET_SECCOMP 21 -#define PR_SET_SECCOMP 22 - -/* Get/set the capability bounding set (as per security/commoncap.c) */ -#define PR_CAPBSET_READ 23 -#define PR_CAPBSET_DROP 24 - -/* Get/set the process' ability to use the timestamp counter instruction */ -#define PR_GET_TSC 25 -#define PR_SET_TSC 26 -# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */ -# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */ - -/* Get/set securebits (as per security/commoncap.c) */ -#define PR_GET_SECUREBITS 27 -#define PR_SET_SECUREBITS 28 - -/* - * Get/set the timerslack as used by poll/select/nanosleep - * A value of 0 means "use default" - */ -#define PR_SET_TIMERSLACK 29 -#define PR_GET_TIMERSLACK 30 - -#define PR_TASK_PERF_EVENTS_DISABLE 31 -#define PR_TASK_PERF_EVENTS_ENABLE 32 - -/* - * Set early/late kill mode for hwpoison memory corruption. - * This influences when the process gets killed on a memory corruption. - */ -#define PR_MCE_KILL 33 -# define PR_MCE_KILL_CLEAR 0 -# define PR_MCE_KILL_SET 1 - -# define PR_MCE_KILL_LATE 0 -# define PR_MCE_KILL_EARLY 1 -# define PR_MCE_KILL_DEFAULT 2 - -#define PR_MCE_KILL_GET 34 - -/* - * Tune up process memory map specifics. - */ -#define PR_SET_MM 35 -# define PR_SET_MM_START_CODE 1 -# define PR_SET_MM_END_CODE 2 -# define PR_SET_MM_START_DATA 3 -# define PR_SET_MM_END_DATA 4 -# define PR_SET_MM_START_STACK 5 -# define PR_SET_MM_START_BRK 6 -# define PR_SET_MM_BRK 7 -# define PR_SET_MM_ARG_START 8 -# define PR_SET_MM_ARG_END 9 -# define PR_SET_MM_ENV_START 10 -# define PR_SET_MM_ENV_END 11 -# define PR_SET_MM_AUXV 12 -# define PR_SET_MM_EXE_FILE 13 -# define PR_SET_MM_MAP 14 -# define PR_SET_MM_MAP_SIZE 15 - -/* - * This structure provides new memory descriptor - * map which mostly modifies /proc/pid/stat[m] - * output for a task. This mostly done in a - * sake of checkpoint/restore functionality. - */ -struct prctl_mm_map { - __u64 start_code; /* code section bounds */ - __u64 end_code; - __u64 start_data; /* data section bounds */ - __u64 end_data; - __u64 start_brk; /* heap for brk() syscall */ - __u64 brk; - __u64 start_stack; /* stack starts at */ - __u64 arg_start; /* command line arguments bounds */ - __u64 arg_end; - __u64 env_start; /* environment variables bounds */ - __u64 env_end; - __u64 *auxv; /* auxiliary vector */ - __u32 auxv_size; /* vector size */ - __u32 exe_fd; /* /proc/$pid/exe link file */ -}; - -/* - * Set specific pid that is allowed to ptrace the current task. - * A value of 0 mean "no process". - */ -#define PR_SET_PTRACER 0x59616d61 -# define PR_SET_PTRACER_ANY ((unsigned long)-1) - -#define PR_SET_CHILD_SUBREAPER 36 -#define PR_GET_CHILD_SUBREAPER 37 - -/* - * If no_new_privs is set, then operations that grant new privileges (i.e. - * execve) will either fail or not grant them. This affects suid/sgid, - * file capabilities, and LSMs. - * - * Operations that merely manipulate or drop existing privileges (setresuid, - * capset, etc.) will still work. Drop those privileges if you want them gone. - * - * Changing LSM security domain is considered a new privilege. So, for example, - * asking selinux for a specific new context (e.g. with runcon) will result - * in execve returning -EPERM. - * - * See Documentation/userspace-api/no_new_privs.rst for more details. - */ -#define PR_SET_NO_NEW_PRIVS 38 -#define PR_GET_NO_NEW_PRIVS 39 - -#define PR_GET_TID_ADDRESS 40 - -#define PR_SET_THP_DISABLE 41 -#define PR_GET_THP_DISABLE 42 - -/* - * No longer implemented, but left here to ensure the numbers stay reserved: - */ -#define PR_MPX_ENABLE_MANAGEMENT 43 -#define PR_MPX_DISABLE_MANAGEMENT 44 - -#define PR_SET_FP_MODE 45 -#define PR_GET_FP_MODE 46 -# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */ -# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */ - -/* Control the ambient capability set */ -#define PR_CAP_AMBIENT 47 -# define PR_CAP_AMBIENT_IS_SET 1 -# define PR_CAP_AMBIENT_RAISE 2 -# define PR_CAP_AMBIENT_LOWER 3 -# define PR_CAP_AMBIENT_CLEAR_ALL 4 - -/* arm64 Scalable Vector Extension controls */ -/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ -#define PR_SVE_SET_VL 50 /* set task vector length */ -# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ -#define PR_SVE_GET_VL 51 /* get task vector length */ -/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ -# define PR_SVE_VL_LEN_MASK 0xffff -# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ - -/* Per task speculation control */ -#define PR_GET_SPECULATION_CTRL 52 -#define PR_SET_SPECULATION_CTRL 53 -/* Speculation control variants */ -# define PR_SPEC_STORE_BYPASS 0 -# define PR_SPEC_INDIRECT_BRANCH 1 -# define PR_SPEC_L1D_FLUSH 2 -/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ -# define PR_SPEC_NOT_AFFECTED 0 -# define PR_SPEC_PRCTL (1UL << 0) -# define PR_SPEC_ENABLE (1UL << 1) -# define PR_SPEC_DISABLE (1UL << 2) -# define PR_SPEC_FORCE_DISABLE (1UL << 3) -# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) - -/* Reset arm64 pointer authentication keys */ -#define PR_PAC_RESET_KEYS 54 -# define PR_PAC_APIAKEY (1UL << 0) -# define PR_PAC_APIBKEY (1UL << 1) -# define PR_PAC_APDAKEY (1UL << 2) -# define PR_PAC_APDBKEY (1UL << 3) -# define PR_PAC_APGAKEY (1UL << 4) - -/* Tagged user address controls for arm64 */ -#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 - -/* 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 - -#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/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h deleted file mode 100644 index 74a84e02422a..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 ([email protected]) - * - * 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[]; -}; - -/* 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[]; -}; - -/* - * 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 <[email protected]> + * 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 649560c685f1..000000000000 --- a/tools/include/uapi/linux/vhost.h +++ /dev/null @@ -1,230 +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) -/* By default, a device gets one vhost_worker that its virtqueues share. This - * command allows the owner of the device to create an additional vhost_worker - * for the device. It can later be bound to 1 or more of its virtqueues using - * the VHOST_ATTACH_VRING_WORKER command. - * - * This must be called after VHOST_SET_OWNER and the caller must be the owner - * of the device. The new thread will inherit caller's cgroups and namespaces, - * and will share the caller's memory space. The new thread will also be - * counted against the caller's RLIMIT_NPROC value. - * - * The worker's ID used in other commands will be returned in - * vhost_worker_state. - */ -#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state) -/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any - * virtqueue. If userspace is not able to call this for workers its created, - * the kernel will free all the device's workers when the device is closed. - */ -#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state) - -/* 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) -/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's - * virtqueues. - * - * This will replace the virtqueue's existing worker. If the replaced worker - * is no longer attached to any virtqueues, it can be freed with - * VHOST_FREE_WORKER. - */ -#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15, \ - struct vhost_vring_worker) -/* Return the vring worker's ID */ -#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16, \ - struct vhost_vring_worker) - -/* 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 */ - -#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) - -/* Get the valid iova range */ -#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ - struct vhost_vdpa_iova_range) -/* Get the config size */ -#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) - -/* Get the count of all virtqueues */ -#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) - -/* Get the number of virtqueue groups. */ -#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) - -/* Get the number of address spaces. */ -#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) - -/* Get the group for a virtqueue: read index, write group in num, - * The virtqueue index is stored in the index field of - * vhost_vring_state. The group for this specific virtqueue is - * returned via num field of vhost_vring_state. - */ -#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ - struct vhost_vring_state) -/* Set the ASID for a virtqueue group. The group index is stored in - * the index field of vhost_vring_state, the ASID associated with this - * group is stored at num field of vhost_vring_state. - */ -#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ - struct vhost_vring_state) - -/* Suspend a device so it does not process virtqueue requests anymore - * - * After the return of ioctl the device must preserve all the necessary state - * (the virtqueue vring base plus the possible device specific states) that is - * required for restoring in the future. The device must not change its - * configuration after that point. - */ -#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) - -/* Resume a device so it can resume processing virtqueue requests - * - * After the return of this ioctl the device will have restored all the - * necessary states and it is fully operational to continue processing the - * virtqueue descriptors. - */ -#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) - -/* Get the group for the descriptor table including driver & device areas - * of a virtqueue: read index, write group in num. - * The virtqueue index is stored in the index field of vhost_vring_state. - * The group ID of the descriptor table for this specific virtqueue - * is returned via num field of vhost_vring_state. - */ -#define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ - struct vhost_vring_state) -#endif |