mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 18:32:14 +07:00
1f40c49570
1/ Device DAX for persistent memory: Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows memory ranges to be allocated and mapped without need of an intervening file system. Device DAX is strict, precise and predictable. Specifically this interface: a) Guarantees fault granularity with respect to a given page size (pte, pmd, or pud) set at configuration time. b) Enforces deterministic behavior by being strict about what fault scenarios are supported. Persistent memory is the first target, but the mechanism is also targeted for exclusive allocations of performance/feature differentiated memory ranges. 2/ Support for the HPE DSM (device specific method) command formats. This enables management of these first generation devices until a unified DSM specification materializes. 3/ Further ACPI 6.1 compliance with support for the common dimm identifier format. 4/ Various fixes and cleanups across the subsystem. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXQhdeAAoJEB7SkWpmfYgCYP8P/RAgHkroL5lUKKU45TQUBKcY diC9POeNSccme4tIRIQCGQUZ7+7mKM5ECv2ulF4xYOHvFBCcd/8OF6xKAXs48r3v oguYhvX1YvIkBc9FUfBQbR1IsCOJ7uWp/UYiYCIQEXS5tS9Jv545j3ASqDt9xWoV TWlceZn3yWSbASiV9qZ2eXhEkk75pg4yara++rsm2/7rs/TTXn5EIjBs+57BtAo+ 6utI4fTy0CQvBYwVzam3m7y9dt2Z2jWXL4hgmT7pkvJ7HDoctVly0P9+bknJPUAo g+NugKgTGeiqH5GYp5CTZ9KvL91sDF4q00pfinITVdFl0E3VE293cIHlAzSQBm5/ w58xxaRV958ZvpH7EaBmYQG82QDi/eFNqeHqVGn0xAM6MlaqO7avUMQp2lRPYMCJ u1z/NloR5yo+sffHxsn5Luiq9KqOf6zk33PuxEkKbN74OayCSPn/SeVCO7rQR0B6 yPMJTTcTiCLnId1kOWAPaEmuK2U3BW/+ogg7hKgeCQSysuy5n6Ok5a2vEx/gJRAm v9yF68RmIWumpHr+QB0TmB8mVbD5SY+xWTm3CqJb9MipuFIOF7AVsPyTgucBvE7s v+i5F6MDO6tcVfiDT4AiZEt6D2TM5RbtckkUEX3ZTD6j7CGuR5D8bH0HNRrghrYk KT1lAk6tjWBOGAHc5Ji7 =Y3Xv -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm updates from Dan Williams: "The bulk of this update was stabilized before the merge window and appeared in -next. The "device dax" implementation was revised this week in response to review feedback, and to address failures detected by the recently expanded ndctl unit test suite. Not included in this pull request are two dax topic branches (dax error handling, and dax radix-tree locking). These topics were deferred to get a few more days of -next integration testing, and to coordinate a branch baseline with Ted and the ext4 tree. Vishal and Ross will send the error handling and locking topics respectively in the next few days. This branch has received a positive build result from the kbuild robot across 226 configs. Summary: - Device DAX for persistent memory: Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows memory ranges to be allocated and mapped without need of an intervening file system. Device DAX is strict, precise and predictable. Specifically this interface: a) Guarantees fault granularity with respect to a given page size (pte, pmd, or pud) set at configuration time. b) Enforces deterministic behavior by being strict about what fault scenarios are supported. Persistent memory is the first target, but the mechanism is also targeted for exclusive allocations of performance/feature differentiated memory ranges. - Support for the HPE DSM (device specific method) command formats. This enables management of these first generation devices until a unified DSM specification materializes. - Further ACPI 6.1 compliance with support for the common dimm identifier format. - Various fixes and cleanups across the subsystem" * tag 'libnvdimm-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (40 commits) libnvdimm, dax: fix deletion libnvdimm, dax: fix alignment validation libnvdimm, dax: autodetect support libnvdimm: release ida resources Revert "block: enable dax for raw block devices" /dev/dax, core: file operations and dax-mmap /dev/dax, pmem: direct access to persistent memory libnvdimm: stop requiring a driver ->remove() method libnvdimm, dax: record the specified alignment of a dax-device instance libnvdimm, dax: reserve space to store labels for device-dax libnvdimm, dax: introduce device-dax infrastructure nfit: add sysfs dimm 'family' and 'dsm_mask' attributes tools/testing/nvdimm: ND_CMD_CALL support nfit: disable vendor specific commands nfit: export subsystem ids as attributes nfit: fix format interface code byte order per ACPI6.1 nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism nfit, libnvdimm: clarify "commands" vs "_DSMs" libnvdimm: increase max envelope size for ioctl acpi/nfit: Add sysfs "id" for NVDIMM ID ...
330 lines
13 KiB
C
330 lines
13 KiB
C
#ifndef _UAPI_LINUX_FS_H
|
|
#define _UAPI_LINUX_FS_H
|
|
|
|
/*
|
|
* This file has definitions for some important file table structures
|
|
* and constants and structures used by various generic file system
|
|
* ioctl's. Please do not make any changes in this file before
|
|
* sending patches for review to linux-fsdevel@vger.kernel.org and
|
|
* linux-api@vger.kernel.org.
|
|
*/
|
|
|
|
#include <linux/limits.h>
|
|
#include <linux/ioctl.h>
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* 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;
|
|
};
|
|
|
|
/* 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[0];
|
|
};
|
|
|
|
/* 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 */
|
|
|
|
|
|
/*
|
|
* These are the fs-independent mount-flags: up to 32 flags are supported
|
|
*/
|
|
#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_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_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
|
|
|
|
/*
|
|
* 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) */
|
|
unsigned char fsx_pad[12];
|
|
};
|
|
|
|
/*
|
|
* 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_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 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 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)
|
|
|
|
/*
|
|
* File system encryption support
|
|
*/
|
|
/* Policy provided via an ioctl on the topmost directory */
|
|
#define FS_KEY_DESCRIPTOR_SIZE 8
|
|
|
|
struct fscrypt_policy {
|
|
__u8 version;
|
|
__u8 contents_encryption_mode;
|
|
__u8 filenames_encryption_mode;
|
|
__u8 flags;
|
|
__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
|
|
} __packed;
|
|
|
|
#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
|
|
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
|
|
#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
|
|
|
|
/*
|
|
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
|
|
*
|
|
* Note: for historical reasons, these flags were originally used and
|
|
* defined for use by ext2/ext3, and then other file systems started
|
|
* using these flags so they wouldn't need to write their own version
|
|
* of chattr/lsattr (which was shipped as part of e2fsprogs). You
|
|
* should think twice before trying to use these flags in new
|
|
* contexts, or trying to assign these flags, since they are used both
|
|
* as the UAPI and the on-disk encoding for ext2/3/4. Also, we are
|
|
* almost out of 32-bit flags. :-)
|
|
*
|
|
* We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
|
|
* XFS to the generic FS level interface. This uses a structure that
|
|
* has padding and hence has more room to grow, so it may be more
|
|
* appropriate for many new use cases.
|
|
*
|
|
* Please do not change these flags or interfaces before checking with
|
|
* linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
|
|
*/
|
|
#define FS_SECRM_FL 0x00000001 /* Secure deletion */
|
|
#define FS_UNRM_FL 0x00000002 /* Undelete */
|
|
#define FS_COMPR_FL 0x00000004 /* Compress file */
|
|
#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
|
|
#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
|
|
#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
|
|
#define FS_NODUMP_FL 0x00000040 /* do not dump file */
|
|
#define FS_NOATIME_FL 0x00000080 /* do not update atime */
|
|
/* Reserved for compression usage... */
|
|
#define FS_DIRTY_FL 0x00000100
|
|
#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
|
|
#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
|
|
/* End compression flags --- maybe not all used */
|
|
#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */
|
|
#define FS_BTREE_FL 0x00001000 /* btree format dir */
|
|
#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
|
|
#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
|
|
#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
|
|
#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
|
|
#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
|
|
#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
|
|
#define FS_HUGE_FILE_FL 0x00040000 /* Reserved for ext4 */
|
|
#define FS_EXTENT_FL 0x00080000 /* Extents */
|
|
#define FS_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_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */
|
|
#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
|
|
#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
|
|
|
|
/* flags for preadv2/pwritev2: */
|
|
#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */
|
|
#define RWF_DSYNC 0x00000002 /* per-IO O_DSYNC */
|
|
#define RWF_SYNC 0x00000004 /* per-IO O_SYNC */
|
|
|
|
#endif /* _UAPI_LINUX_FS_H */
|