Linus Torvalds
d080827f85
1/ Media error handling: The 'badblocks' implementation that originated
in md-raid is up-levelled to a generic capability of a block device.
This initial implementation is limited to being consulted in the pmem
block-i/o path. Later, 'badblocks' will be consulted when creating
dax mappings.
2/ Raw block device dax: For virtualization and other cases that want
large contiguous mappings of persistent memory, add the capability to
dax-mmap a block device directly.
3/ Increased /dev/mem restrictions: Add an option to treat all io-memory
as IORESOURCE_EXCLUSIVE, i.e. disable /dev/mem access while a driver is
actively using an address range. This behavior is controlled via the
new CONFIG_IO_STRICT_DEVMEM option and can be overridden by the
existing "iomem=relaxed" kernel command line option.
4/ Miscellaneous fixes include a 'pfn'-device huge page alignment fix,
block device shutdown crash fix, and other small libnvdimm fixes.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=7V5r
-----END PGP SIGNATURE-----
Merge tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams:
"The bulk of this has appeared in -next and independently received a
build success notification from the kbuild robot. The 'for-4.5/block-
dax' topic branch was rebased over the weekend to drop the "block
device end-of-life" rework that Al would like to see re-implemented
with a notifier, and to address bug reports against the badblocks
integration.
There is pending feedback against "libnvdimm: Add a poison list and
export badblocks" received last week. Linda identified some localized
fixups that we will handle incrementally.
Summary:
- Media error handling: The 'badblocks' implementation that
originated in md-raid is up-levelled to a generic capability of a
block device. This initial implementation is limited to being
consulted in the pmem block-i/o path. Later, 'badblocks' will be
consulted when creating dax mappings.
- Raw block device dax: For virtualization and other cases that want
large contiguous mappings of persistent memory, add the capability
to dax-mmap a block device directly.
- Increased /dev/mem restrictions: Add an option to treat all
io-memory as IORESOURCE_EXCLUSIVE, i.e. disable /dev/mem access
while a driver is actively using an address range. This behavior
is controlled via the new CONFIG_IO_STRICT_DEVMEM option and can be
overridden by the existing "iomem=relaxed" kernel command line
option.
- Miscellaneous fixes include a 'pfn'-device huge page alignment fix,
block device shutdown crash fix, and other small libnvdimm fixes"
* tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (32 commits)
block: kill disk_{check|set|clear|alloc}_badblocks
libnvdimm, pmem: nvdimm_read_bytes() badblocks support
pmem, dax: disable dax in the presence of bad blocks
pmem: fail io-requests to known bad blocks
libnvdimm: convert to statically allocated badblocks
libnvdimm: don't fail init for full badblocks list
block, badblocks: introduce devm_init_badblocks
block: clarify badblocks lifetime
badblocks: rename badblocks_free to badblocks_exit
libnvdimm, pmem: move definition of nvdimm_namespace_add_poison to nd.h
libnvdimm: Add a poison list and export badblocks
nfit_test: Enable DSMs for all test NFITs
md: convert to use the generic badblocks code
block: Add badblock management for gendisks
badblocks: Add core badblock management code
block: fix del_gendisk() vs blkdev_ioctl crash
block: enable dax for raw block devices
block: introduce bdev_file_inode()
restrict /dev/mem to idle io memory ranges
arch: consolidate CONFIG_STRICT_DEVM in lib/Kconfig.debug
...
252 lines
9.5 KiB
C
252 lines
9.5 KiB
C
#ifndef _UAPI_LINUX_FS_H
|
|
#define _UAPI_LINUX_FS_H
|
|
|
|
/*
|
|
* This file has definitions for some important file table
|
|
* structures etc.
|
|
*/
|
|
|
|
#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
|
|
|
|
/* 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 BLKDAXSET _IO(0x12,128)
|
|
#define BLKDAXGET _IO(0x12,129)
|
|
|
|
#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)
|
|
|
|
/*
|
|
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
|
|
*/
|
|
#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 */
|
|
#define FS_ECOMPR_FL 0x00000800 /* Compression error */
|
|
/* End compression flags --- maybe not all used */
|
|
#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_EXTENT_FL 0x00080000 /* Extents */
|
|
#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
|
|
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
|
|
#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
|
|
|
|
#endif /* _UAPI_LINUX_FS_H */
|