diff options
Diffstat (limited to 'include/uapi/linux/fs.h')
| -rw-r--r-- | include/uapi/linux/fs.h | 365 |
1 files changed, 359 insertions, 6 deletions
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 379a612f8f1d..66ca526cf786 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -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 */ @@ -51,6 +60,17 @@ #define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ #define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ +/* + * The root inode of procfs is guaranteed to always have the same inode number. + * For programs that make heavy use of procfs, verifying that the root is a + * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH}) + * will allow you to make sure you are never tricked into operating on the + * wrong procfs file. + */ +enum procfs_ino { + PROCFS_ROOT_INO = 1, +}; + struct file_clone_range { __s64 src_fd; __u64 src_offset; @@ -64,6 +84,81 @@ 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]; +}; + +/* Protection info capability flags */ +#define LBMD_PI_CAP_INTEGRITY (1 << 0) +#define LBMD_PI_CAP_REFTAG (1 << 1) + +/* Checksum types for Protection Information */ +#define LBMD_PI_CSUM_NONE 0 +#define LBMD_PI_CSUM_IP 1 +#define LBMD_PI_CSUM_CRC16_T10DIF 2 +#define LBMD_PI_CSUM_CRC64_NVME 4 + +/* sizeof first published struct */ +#define LBMD_SIZE_VER0 16 + +/* + * Logical block metadata capability descriptor + * If the device does not support metadata, all the fields will be zero. + * Applications must check lbmd_flags to determine whether metadata is + * supported or not. + */ +struct logical_block_metadata_cap { + /* Bitmask of logical block metadata capability flags */ + __u32 lbmd_flags; + /* + * The amount of data described by each unit of logical block + * metadata + */ + __u16 lbmd_interval; + /* + * Size in bytes of the logical block metadata associated with each + * interval + */ + __u8 lbmd_size; + /* + * Size in bytes of the opaque block tag associated with each + * interval + */ + __u8 lbmd_opaque_size; + /* + * Offset in bytes of the opaque block tag within the logical block + * metadata + */ + __u8 lbmd_opaque_offset; + /* Size in bytes of the T10 PI tuple associated with each interval */ + __u8 lbmd_pi_size; + /* Offset in bytes of T10 PI tuple within the logical block metadata */ + __u8 lbmd_pi_offset; + /* T10 PI guard tag type */ + __u8 lbmd_guard_tag_type; + /* Size in bytes of the T10 PI application tag */ + __u8 lbmd_app_tag_size; + /* Size in bytes of the T10 PI reference tag */ + __u8 lbmd_ref_tag_size; + /* Size in bytes of the T10 PI storage tag */ + __u8 lbmd_storage_tag_size; + __u8 pad; +}; + /* 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 +185,7 @@ 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: */ @@ -122,6 +217,24 @@ struct fsxattr { }; /* + * Variable size structure for file_[sg]et_attr(). + * + * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'. + * As this structure is passed to/from userspace with its size, this can + * be versioned based on the size. + */ +struct file_attr { + __u64 fa_xflags; /* xflags field value (get/set) */ + __u32 fa_extsize; /* extsize field value (get/set)*/ + __u32 fa_nextents; /* nextents field value (get) */ + __u32 fa_projid; /* project identifier (get/set) */ + __u32 fa_cowextsize; /* CoW extsize field value (get/set) */ +}; + +#define FILE_ATTR_SIZE_VER0 24 +#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0 + +/* * Flags for the fsx_xflags field */ #define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ @@ -184,10 +297,10 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) -/* - * A jump here: 130-131 are reserved for zoned block devices - * (see uapi/linux/blkzoned.h) - */ +#define BLKGETDISKSEQ _IOR(0x12,128,__u64) +/* 130-136 and 142 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ +/* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */ +#define BLKTRACESETUP2 _IOWR(0x12, 142, struct blk_user_trace_setup2) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ @@ -214,6 +327,15 @@ 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) +/* Get logical block metadata capability details */ +#define FS_IOC_GETLBMD_CAP _IOWR(0x15, 2, struct logical_block_metadata_cap) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) @@ -262,6 +384,7 @@ struct fsxattr { #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 */ @@ -299,8 +422,238 @@ 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) + +/* prevent pipe and socket writes from raising SIGPIPE */ +#define RWF_NOSIGNAL ((__force __kernel_rwf_t)0x00000100) + /* 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 | RWF_NOSIGNAL) + +#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 */ |