msm-4.14/fs/ioctl.c
azrim e9e83ae080
Merge remote-tracking branch 'google/upstream-f2fs-stable-linux-4.14.y' into sheesh
* google/upstream-f2fs-stable-linux-4.14.y:
  f2fs: fix to do sanity check on .cp_pack_total_block_count
  f2fs: make gc_urgent and gc_segment_mode sysfs node readable
  f2fs: use aggressive GC policy during f2fs_disable_checkpoint()
  f2fs: fix compressed file start atomic write may cause data corruption
  f2fs: initialize sbi->gc_mode explicitly
  f2fs: introduce gc_urgent_mid mode
  f2fs: compress: fix to print raw data size in error path of lz4 decompression
  f2fs: remove redundant parameter judgment
  f2fs: use spin_lock to avoid hang
  f2fs: don't get FREEZE lock in f2fs_evict_inode in frozen fs
  f2fs: remove unnecessary read for F2FS_FITS_IN_INODE
  f2fs: fix to do sanity check on curseg->alloc_type
  f2fs: fix to avoid potential deadlock
  f2fs: quota: fix loop condition at f2fs_quota_sync()
  f2fs: Restore rwsem lockdep support
  f2fs: fix missing free nid in f2fs_handle_failed_inode
  f2fs: add a way to limit roll forward recovery time
  f2fs: introduce F2FS_IPU_HONOR_OPU_WRITE ipu policy
  f2fs: adjust readahead block number during recovery
  f2fs: fix to unlock page correctly in error path of is_alive()
  f2fs: expose discard related parameters in sysfs
  f2fs: move discard parameters into discard_cmd_control
  f2fs: fix to enable ATGC correctly via gc_idle sysfs interface
  f2fs: move f2fs to use reader-unfair rwsems
  f2fs: do not allow partial truncation on pinned file
  f2fs: remove redunant invalidate compress pages
  f2fs: Simplify bool conversion
  f2fs: don't drop compressed page cache in .{invalidate,release}page
  f2fs: fix to reserve space for IO align feature
  f2fs: fix to check available space of CP area correctly in update_ckpt_flags()
  f2fs: support fault injection to f2fs_trylock_op()
  f2fs: clean up __find_inline_xattr() with __find_xattr()
  f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr()
  f2fs: do not bother checkpoint by f2fs_get_node_info
  f2fs: avoid down_write on nat_tree_lock during checkpoint
  f2fs: compress: fix potential deadlock of compress file
  f2fs: avoid EINVAL by SBI_NEED_FSCK when pinning a file
  f2fs: add gc_urgent_high_remaining sysfs node
  f2fs: fix to do sanity check in is_alive()
  f2fs: fix to avoid panic in is_alive() if metadata is inconsistent
  f2fs: fix to do sanity check on inode type during garbage collection
  f2fs: avoid duplicate call of mark_inode_dirty
  f2fs: fix remove page failed in invalidate compress pages
  f2fs: fix the f2fs_file_write_iter tracepoint
  f2fs: do not expose unwritten blocks to user by DIO
  f2fs: reduce indentation in f2fs_file_write_iter()
  f2fs: rework write preallocations
  f2fs: compress: reduce one page array alloc and free when write compressed page
  f2fs: show number of pending discard commands
  f2fs: check nr_pages for readahead
  f2fs: fix UAF in f2fs_available_free_memory
  f2fs: invalidate META_MAPPING before IPU/DIO write
  f2fs: support fault injection for dquot_initialize()
  f2fs: fix incorrect return value in f2fs_sanity_check_ckpt()
  f2fs: compress: disallow disabling compress on non-empty compressed file
  f2fs: compress: fix overwrite may reduce compress ratio unproperly
  f2fs: multidevice: support direct IO
  f2fs: introduce fragment allocation mode mount option
  f2fs: include non-compressed blocks in compr_written_block
  f2fs: fix wrong condition to trigger background checkpoint correctly
  f2fs: fix to use WHINT_MODE
  f2fs: fix up f2fs_lookup tracepoints
  f2fs: set SBI_NEED_FSCK flag when inconsistent node block found
  f2fs: introduce excess_dirty_threshold()
  f2fs: avoid attaching SB_ACTIVE flag during mount
  f2fs: quota: fix potential deadlock
  f2fs: should use GFP_NOFS for directory inodes
  f2fs: should put a page beyond EOF when preparing a write
  f2fs: deallocate compressed pages when error happens
  f2fs: enable realtime discard iff device supports discard
  f2fs: guarantee to write dirty data when enabling checkpoint back
  f2fs: fix to unmap pages from userspace process in punch_hole()
  f2fs: fix unexpected ENOENT comes from f2fs_map_blocks()
  f2fs: fix to account missing .skipped_gc_rwsem
  f2fs: adjust unlock order for cleanup
  f2fs: Don't create discard thread when device doesn't support realtime discard
  f2fs: rebuild nat_bits during umount
  f2fs: introduce periodic iostat io latency traces
  f2fs: separate out iostat feature
  f2fs: compress: do sanity check on cluster
  f2fs: fix description about main_blkaddr node
  f2fs: convert S_IRUGO to 0444
  f2fs: fix to keep compatibility of fault injection interface
  f2fs: support fault injection for f2fs_kmem_cache_alloc()
  f2fs: compress: allow write compress released file after truncate to zero
  f2fs: correct comment in segment.h
  f2fs: improve sbi status info in debugfs/f2fs/status
  f2fs: compress: avoid duplicate counting of valid blocks when read compressed file
  f2fs: fix to do sanity check for sb/cp fields correctly
  f2fs: avoid unneeded memory allocation in __add_ino_entry()
  f2fs: extent cache: support unaligned extent
  f2fs: Kconfig: clean up config options about compression
  f2fs: reduce the scope of setting fsck tag when de->name_len is zero
  f2fs: fix to stop filesystem update once CP failed
  f2fs: introduce discard_unit mount option
  f2fs: fix min_seq_blocks can not make sense in some scenes.
  f2fs: fix to force keeping write barrier for strict fsync mode
  f2fs: fix wrong checkpoint_changed value in f2fs_remount()
  f2fs: show sbi status in debugfs/f2fs/status
  f2fs: turn back remapped address in compressed page endio
  f2fs: change fiemap way in printing compression chunk
  f2fs: do not submit NEW_ADDR to read node block
  f2fs: compress: remove unneeded read when rewrite whole cluster
  f2fs: don't sleep while grabing nat_tree_lock
  f2fs: remove allow_outplace_dio()
  f2fs: make f2fs_write_failed() take struct inode
  f2fs: quota: fix potential deadlock
  f2fs: let's keep writing IOs on SBI_NEED_FSCK
  f2fs: Revert "f2fs: Fix indefinite loop in f2fs_gc() v1"
  f2fs: avoid to create an empty string as the extension_list
  f2fs: compress: fix to set zstd compress level correctly
  f2fs: add sysfs nodes to get GC info for each GC mode
  f2fs: drop dirty node pages when cp is in error status
  f2fs: initialize page->private when using for our internal use
  f2fs: compress: add nocompress extensions support
  Revert "f2fs: avoid attaching SB_ACTIVE flag during mount/remount"
  f2fs: remove false alarm on iget failure during GC
  f2fs: enable extent cache for compression files in read-only
  f2fs: fix to avoid adding tab before doc section
  f2fs: introduce f2fs_casefolded_name slab cache
  f2fs: swap: support migrating swapfile in aligned write mode
  f2fs: swap: remove dead codes
  f2fs: compress: add compress_inode to cache compressed blocks
  f2fs: clean up /sys/fs/f2fs/<disk>/features
  f2fs: add pin_file in feature list
  f2fs: Advertise encrypted casefolding in sysfs
  f2fs: Show casefolding support only when supported
  f2fs: support RO feature
  f2fs: logging neatening
  f2fs: restructure f2fs page.private layout
  f2fs: introduce FI_COMPRESS_RELEASED instead of using IMMUTABLE bit
  f2fs: compress: remove unneeded preallocation
  f2fs: avoid attaching SB_ACTIVE flag during mount/remount
  f2fs: atgc: export entries for better tunability via sysfs
  f2fs: compress: fix to disallow temp extension
  f2fs: let's allow compression for mmap files
  f2fs: add MODULE_SOFTDEP to ensure crc32 is included in the initramfs
  f2fs: return success if there is no work to do
  f2fs: compress: clean up parameter of __f2fs_cluster_blocks()
  f2fs: compress: remove unneeded f2fs_put_dnode()
  f2fs: atgc: fix to set default age threshold
  f2fs: Prevent swap file in LFS mode
  f2fs: fix to avoid racing on fsync_entry_slab by multi filesystem instances
  f2fs: add cp_error check in f2fs_write_compressed_pages
  f2fs: compress: rename __cluster_may_compress
  f2fs: return EINVAL for hole cases in swap file
  f2fs: avoid swapon failure by giving a warning first
  f2fs: compress: fix to assign cc.cluster_idx correctly
  f2fs: compress: fix race condition of overwrite vs truncate
  f2fs: compress: fix to free compress page correctly
  f2fs: support iflag change given the mask
  f2fs: avoid null pointer access when handling IPU error
  f2fs: drop inplace IO if fs status is abnormal
  f2fs: compress: remove unneed check condition
  f2fs: clean up left deprecated IO trace codes
  f2fs: avoid using native allocate_segment_by_default()
  f2fs: remove unnecessary struct declaration
  f2fs: fix to avoid NULL pointer dereference
  f2fs: avoid duplicated codes for cleanup
  f2fs: document: add description about compressed space handling
  f2fs: clean up build warnings
  f2fs: fix the periodic wakeups of discard thread
  f2fs: fix to avoid accessing invalid fio in f2fs_allocate_data_block()
  f2fs: fix to avoid GC/mmap race with f2fs_truncate()
  f2fs: set checkpoint_merge by default
  f2fs: Fix a hungtask problem in atomic write
  f2fs: fix to restrict mount condition on readonly block device
  f2fs: introduce gc_merge mount option
  f2fs: fix to cover __allocate_new_section() with curseg_lock
  f2fs: fix wrong alloc_type in f2fs_do_replace_block
  f2fs: delete empty compress.h
  f2fs: fix a typo in inode.c
  f2fs: allow to change discard policy based on cached discard cmds
  f2fs: fix to avoid touching checkpointed data in get_victim()
  f2fs: fix to update last i_size if fallocate partially succeeds
  f2fs: fix error path of f2fs_remount()
  f2fs: fix wrong comment of nat_tree_lock
  f2fs: fix to avoid out-of-bounds memory access
  f2fs: don't start checkpoint thread in readonly mountpoint
  f2fs: do not use AT_SSR mode in FG_GC & high urgent BG_GC
  f2fs: add sysfs nodes to get runtime compression stat
  f2fs: fix to use per-inode maxbytes in f2fs_fiemap
  f2fs: fix to align to section for fallocate() on pinned file
  f2fs: expose # of overprivision segments
  f2fs: fix error handling in f2fs_end_enable_verity()
  f2fs: fix a redundant call to f2fs_balance_fs if an error occurs
  f2fs: remove unused file_clear_encrypt()
  f2fs: check if swapfile is section-alligned
  f2fs: fix last_lblock check in check_swap_activate_fast
  f2fs: remove unnecessary IS_SWAPFILE check
  f2fs: Replace one-element array with flexible-array member
  f2fs: compress: Allow modular (de)compression algorithms
  f2fs: check discard command number before traversing discard pending list
  f2fs: update comments for explicit memory barrier
  f2fs: remove unused FORCE_FG_GC macro
  f2fs: avoid unused f2fs_show_compress_options()
  f2fs: fix panic during f2fs_resize_fs()
  f2fs: fix to allow migrating fully valid segment
  f2fs: fix a spelling error
  f2fs: fix a spacing coding style
  fs: Enable bmap() function to properly return errors
  f2fs: remove obsolete f2fs.txt
  fs-verity: support reading signature with ioctl
  fs-verity: support reading descriptor with ioctl
  fs-verity: support reading Merkle tree with ioctl
  fs-verity: add FS_IOC_READ_VERITY_METADATA ioctl
  fs-verity: don't pass whole descriptor to fsverity_verify_signature()
  fs-verity: factor out fsverity_get_descriptor()
  fs-verity: move structs needed for file signing to UAPI header
  fs-verity: rename "file measurement" to "file digest"
  fs-verity: rename fsverity_signed_digest to fsverity_formatted_digest
  fs-verity: remove filenames from file comments
  fs-verity: use smp_load_acquire() for ->i_verity_info
  f2fs: remove FAULT_ALLOC_BIO
  f2fs: use blkdev_issue_flush in __submit_flush_wait
  f2fs: remove a few bd_part checks
  quota: Cleanup list iteration in dqcache_shrink_scan()
  quota: reclaim least recently used dquots
  fs: quota: Replace GFP_ATOMIC with GFP_KERNEL in dquot_init
  quota: Check for register_shrinker() failure.
  quota: propagate error from __dquot_initialize
  quota: be aware of error from dquot_initialize
  Documentation: f2fs: fix typo s/automaic/automatic
  f2fs: give a warning only for readonly partition
  f2fs: don't grab superblock freeze for flush/ckpt thread
  f2fs: add ckpt_thread_ioprio sysfs node
  f2fs: introduce checkpoint_merge mount option
  f2fs: relocate inline conversion from mmap() to mkwrite()
  f2fs: fix a wrong condition in __submit_bio
  f2fs: remove unnecessary initialization in xattr.c
  f2fs: fix to avoid inconsistent quota data
  f2fs: flush data when enabling checkpoint back
  f2fs: deprecate f2fs_trace_io
  f2fs: remove unused stat_{inc, dec}_atomic_write
  f2fs: introduce sb_status sysfs node
  f2fs: fix to use per-inode maxbytes
  f2fs: compress: fix potential deadlock
  libfs: unexport generic_ci_d_compare() and generic_ci_d_hash()
  f2fs: fix to set/clear I_LINKABLE under i_lock
  f2fs: fix null page reference in redirty_blocks
  f2fs: clean up post-read processing
  f2fs: trival cleanup in move_data_block()
  f2fs: fix out-of-repair __setattr_copy()
  f2fs: fix to tag FIEMAP_EXTENT_MERGED in f2fs_fiemap()
  f2fs: introduce a new per-sb directory in sysfs
  f2fs: compress: support compress level
  f2fs: compress: deny setting unsupported compress algorithm
  f2fs: relocate f2fs_precache_extents()
  f2fs: enforce the immutable flag on open files
  f2fs: enhance to update i_mode and acl atomically in f2fs_setattr()
  f2fs: fix to set inode->i_mode correctly for posix_acl_update_mode
  f2fs: Replace expression with offsetof()
  f2fs: handle unallocated section and zone on pinned/atgc
  f2fs: compress: fix compression chksum
  f2fs: fix shift-out-of-bounds in sanity_check_raw_super()
  f2fs: fix race of pending_pages in decompression
  f2fs: fix to account inline xattr correctly during recovery
  f2fs: inline: fix wrong inline inode stat
  f2fs: inline: correct comment in f2fs_recover_inline_data
  f2fs: don't check PAGE_SIZE again in sanity_check_raw_super()
  f2fs: convert to F2FS_*_INO macro
  f2fs: introduce max_io_bytes, a sysfs entry, to limit bio size
  f2fs: don't allow any writes on readonly mount
  f2fs: avoid race condition for shrinker count
  f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE
  f2fs: add compress_mode mount option
  f2fs: Remove unnecessary unlikely()
  f2fs: init dirty_secmap incorrectly
  f2fs: remove buffer_head which has 32bits limit
  f2fs: fix wrong block count instead of bytes
  f2fs: use new conversion functions between blks and bytes
  f2fs: rename logical_to_blk and blk_to_logical
  f2fs: fix kbytes written stat for multi-device case
  f2fs: compress: support chksum
  f2fs: fix to avoid REQ_TIME and CP_TIME collision
  f2fs: change to use rwsem for cp_mutex
  f2fs: Handle casefolding with Encryption
  fscrypt: Have filesystems handle their d_ops
  libfs: Add generic function for setting dentry_ops
  f2fs: Remove the redundancy initialization
  f2fs: remove writeback_inodes_sb in f2fs_remount
  f2fs: fix double free of unicode map
  f2fs: fix compat F2FS_IOC_{MOVE,GARBAGE_COLLECT}_RANGE
  f2fs: avoid unneeded data copy in f2fs_ioc_move_range()
  f2fs: add F2FS_IOC_SET_COMPRESS_OPTION ioctl
  f2fs: add F2FS_IOC_GET_COMPRESS_OPTION ioctl
  f2fs: move ioctl interface definitions to separated file
  f2fs: fix to seek incorrect data offset in inline data file
  f2fs: check fiemap parameters
  f2fs: call f2fs_get_meta_page_retry for nat page
  fscrypt: rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME
  fscrypt: don't call no-key names "ciphertext names"
  fscrypt: export fscrypt_d_revalidate()
  f2fs: code cleanup by removing unnecessary check
  f2fs: wait for sysfs kobject removal before freeing f2fs_sb_info
  f2fs: fix writecount false positive in releasing compress blocks
  f2fs: introduce check_swap_activate_fast()
  f2fs: don't issue flush in f2fs_flush_device_cache() for nobarrier case
  f2fs: handle errors of f2fs_get_meta_page_nofail
  f2fs: fix to set SBI_NEED_FSCK flag for inconsistent inode
  f2fs: reject CASEFOLD inode flag without casefold feature
  f2fs: fix memory alignment to support 32bit
  f2fs: fix slab leak of rpages pointer
  f2fs: compress: fix to disallow enabling compress on non-empty file
  f2fs: compress: introduce cic/dic slab cache
  f2fs: compress: introduce page array slab cache
  f2fs: fix to do sanity check on segment/section count
  f2fs: fix to check segment boundary during SIT page readahead
  f2fs: fix uninit-value in f2fs_lookup
  fs/buffer.c: record blockdev write errors in super_block that it backs
  vfs: track per-sb writeback errors and report them to syncfs
  f2fs: remove unneeded parameter in find_in_block()
  f2fs: fix wrong total_sections check and fsmeta check
  f2fs: remove duplicated code in sanity_check_area_boundary
  f2fs: remove unused check on version_bitmap
  f2fs: relocate blkzoned feature check
  f2fs: do sanity check on zoned block device path
  f2fs: add trace exit in exception path
  f2fs: change return value of reserved_segments to unsigned int
  f2fs: clean up kvfree
  f2fs: change virtual mapping way for compression pages
  f2fs: change return value of f2fs_disable_compressed_file to bool
  f2fs: change i_compr_blocks of inode to atomic value
  f2fs: ignore compress mount option on image w/o compression feature
  f2fs: allocate proper size memory for zstd decompress
  f2fs: change compr_blocks of superblock info to 64bit
  f2fs: add block address limit check to compressed file
  f2fs: check position in move range ioctl
  f2fs: correct statistic of APP_DIRECT_IO/APP_DIRECT_READ_IO
  f2fs: support age threshold based garbage collection
  f2fs: Use generic casefolding support
  fs: Add standard casefolding support
  unicode: Add utf8_casefold_hash
  f2fs: compress: use more readable atomic_t type for {cic,dic}.ref
  f2fs: fix compile warning
  f2fs: support 64-bits key in f2fs rb-tree node entry
  f2fs: inherit mtime of original block during GC
  f2fs: record average update time of segment
  f2fs: introduce inmem curseg
  f2fs: compress: remove unneeded code
  f2fs: remove duplicated type casting
  f2fs: support zone capacity less than zone size
  f2fs: update changes in upstream on GC_URGENT_HIGH
  f2fs: Return EOF on unaligned end of file DIO read
  f2fs: fix indefinite loop scanning for free nid
  f2fs: Fix type of section block count variables
  f2fs: prepare a waiter before entering io_schedule
  f2fs: update_sit_entry: Make the judgment condition of f2fs_bug_on more intuitive
  f2fs: replace test_and_set/clear_bit() with set/clear_bit()
  f2fs: make file immutable even if releasing zero compression block
  f2fs: compress: disable compression mount option if compression is off
  f2fs: compress: add sanity check during compressed cluster read
  f2fs: use macro instead of f2fs verity version
  f2fs: fix deadlock between quota writes and checkpoint
  f2fs: correct comment of f2fs_exist_written_data
  f2fs: compress: delay temp page allocation
  f2fs: compress: fix to update isize when overwriting compressed file
  f2fs: space related cleanup
  f2fs: fix use-after-free issue
  f2fs: Change the type of f2fs_flush_inline_data() to void
  f2fs: add F2FS_IOC_SEC_TRIM_FILE ioctl
  f2fs: segment.h: delete a duplicated word
  f2fs: compress: fix to avoid memory leak on cc->cpages
  f2fs: use generic names for generic ioctls
  f2fs: don't keep meta inode pages used for compressed block migration
  f2fs: fix error path in do_recover_data()
  f2fs: fix to wait GCed compressed page writeback
  f2fs: remove write attribute of main_blkaddr sysfs node
  f2fs: add GC_URGENT_LOW mode in gc_urgent
  f2fs: avoid readahead race condition
  f2fs: fix return value of move_data_block()
  f2fs: add parameter op_flag in f2fs_submit_page_read()
  f2fs: split f2fs_allocate_new_segments()
  f2fs: lost matching-pair of trace in f2fs_truncate_inode_blocks
  f2fs: fix an oops in f2fs_is_compressed_page
  f2fs: make trace enter and end in pairs for unlink
  f2fs: fix to check page dirty status before writeback
  f2fs: remove the unused compr parameter
  f2fs: support to trace f2fs_fiemap()
  f2fs: support to trace f2fs_bmap()
  f2fs: fix wrong return value of f2fs_bmap_compress()
  f2fs: remove useless parameter of __insert_free_nid()
  f2fs: fix typo in comment of f2fs_do_add_link
  f2fs: fix to wait page writeback before update
  f2fs: show more debug info for per-temperature log
  f2fs: add f2fs_gc exception handle in f2fs_ioc_gc_range
  f2fs: clean up parameter of f2fs_allocate_data_block()
  f2fs: shrink node_write lock coverage
  f2fs: add prefix for exported symbols
  f2fs: use kfree() to free variables allocated by match_strdup()
  f2fs: get the right gc victim section when section has several segments
  f2fs: fix a race condition between f2fs_write_end_io and f2fs_del_fsync_node_entry
  f2fs: remove useless truncate in f2fs_collapse_range()
  f2fs: use kfree() instead of kvfree() to free superblock data
  f2fs: avoid checkpatch error
  f2fs: should avoid inode eviction in synchronous path
2022-05-20 14:51:11 +09:00

733 lines
18 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ioctl.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/falloc.h>
#include <linux/sched/signal.h>
#include "internal.h"
#include <asm/ioctls.h>
/* So that the fiemap access checks can't overflow on 32 bit machines. */
#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent))
/**
* vfs_ioctl - call filesystem specific ioctl methods
* @filp: open file to invoke ioctl method on
* @cmd: ioctl command to execute
* @arg: command-specific argument for ioctl
*
* Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
* returns -ENOTTY.
*
* Returns 0 on success, -errno on error.
*/
long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
int error = -ENOTTY;
if (!filp->f_op->unlocked_ioctl)
goto out;
error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
if (error == -ENOIOCTLCMD)
error = -ENOTTY;
out:
return error;
}
static int ioctl_fibmap(struct file *filp, int __user *p)
{
struct address_space *mapping = filp->f_mapping;
int res, block;
/* do we support this mess? */
if (!mapping->a_ops->bmap)
return -EINVAL;
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
res = get_user(block, p);
if (res)
return res;
res = mapping->a_ops->bmap(mapping, block);
return put_user(res, p);
}
/**
* fiemap_fill_next_extent - Fiemap helper function
* @fieinfo: Fiemap context passed into ->fiemap
* @logical: Extent logical start offset, in bytes
* @phys: Extent physical start offset, in bytes
* @len: Extent length, in bytes
* @flags: FIEMAP_EXTENT flags that describe this extent
*
* Called from file system ->fiemap callback. Will populate extent
* info as passed in via arguments and copy to user memory. On
* success, extent count on fieinfo is incremented.
*
* Returns 0 on success, -errno on error, 1 if this was the last
* extent that will fit in user array.
*/
#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
u64 phys, u64 len, u32 flags)
{
struct fiemap_extent extent;
struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
/* only count the extents */
if (fieinfo->fi_extents_max == 0) {
fieinfo->fi_extents_mapped++;
return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
}
if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
return 1;
if (flags & SET_UNKNOWN_FLAGS)
flags |= FIEMAP_EXTENT_UNKNOWN;
if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
flags |= FIEMAP_EXTENT_ENCODED;
if (flags & SET_NOT_ALIGNED_FLAGS)
flags |= FIEMAP_EXTENT_NOT_ALIGNED;
memset(&extent, 0, sizeof(extent));
extent.fe_logical = logical;
extent.fe_physical = phys;
extent.fe_length = len;
extent.fe_flags = flags;
dest += fieinfo->fi_extents_mapped;
if (copy_to_user(dest, &extent, sizeof(extent)))
return -EFAULT;
fieinfo->fi_extents_mapped++;
if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
return 1;
return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
}
EXPORT_SYMBOL(fiemap_fill_next_extent);
/**
* fiemap_check_flags - check validity of requested flags for fiemap
* @fieinfo: Fiemap context passed into ->fiemap
* @fs_flags: Set of fiemap flags that the file system understands
*
* Called from file system ->fiemap callback. This will compute the
* intersection of valid fiemap flags and those that the fs supports. That
* value is then compared against the user supplied flags. In case of bad user
* flags, the invalid values will be written into the fieinfo structure, and
* -EBADR is returned, which tells ioctl_fiemap() to return those values to
* userspace. For this reason, a return code of -EBADR should be preserved.
*
* Returns 0 on success, -EBADR on bad flags.
*/
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
{
u32 incompat_flags;
incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
if (incompat_flags) {
fieinfo->fi_flags = incompat_flags;
return -EBADR;
}
return 0;
}
EXPORT_SYMBOL(fiemap_check_flags);
static int fiemap_check_ranges(struct super_block *sb,
u64 start, u64 len, u64 *new_len)
{
u64 maxbytes = (u64) sb->s_maxbytes;
*new_len = len;
if (len == 0)
return -EINVAL;
if (start > maxbytes)
return -EFBIG;
/*
* Shrink request scope to what the fs can actually handle.
*/
if (len > maxbytes || (maxbytes - len) < start)
*new_len = maxbytes - start;
return 0;
}
int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 *len, u32 supported_flags)
{
u64 maxbytes = inode->i_sb->s_maxbytes;
u32 incompat_flags;
if (*len == 0)
return -EINVAL;
if (start > maxbytes)
return -EFBIG;
/*
* Shrink request scope to what the fs can actually handle.
*/
if (*len > maxbytes || (maxbytes - *len) < start)
*len = maxbytes - start;
supported_flags &= FIEMAP_FLAGS_COMPAT;
incompat_flags = fieinfo->fi_flags & ~supported_flags;
if (incompat_flags) {
fieinfo->fi_flags = incompat_flags;
return -EBADR;
}
return 0;
}
EXPORT_SYMBOL(fiemap_prep);
static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
struct fiemap fiemap;
struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
struct fiemap_extent_info fieinfo = { 0, };
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
u64 len;
int error;
if (!inode->i_op->fiemap)
return -EOPNOTSUPP;
if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
return -EFAULT;
if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
return -EINVAL;
error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
&len);
if (error)
return error;
fieinfo.fi_flags = fiemap.fm_flags;
fieinfo.fi_extents_max = fiemap.fm_extent_count;
fieinfo.fi_extents_start = ufiemap->fm_extents;
if (fiemap.fm_extent_count != 0 &&
!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
return -EFAULT;
if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
filemap_write_and_wait(inode->i_mapping);
error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
fiemap.fm_flags = fieinfo.fi_flags;
fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
error = -EFAULT;
return error;
}
static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
u64 off, u64 olen, u64 destoff)
{
struct fd src_file = fdget(srcfd);
int ret;
if (!src_file.file)
return -EBADF;
ret = -EXDEV;
if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
goto fdput;
ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
fdput:
fdput(src_file);
return ret;
}
static long ioctl_file_clone_range(struct file *file, void __user *argp)
{
struct file_clone_range args;
if (copy_from_user(&args, argp, sizeof(args)))
return -EFAULT;
return ioctl_file_clone(file, args.src_fd, args.src_offset,
args.src_length, args.dest_offset);
}
#ifdef CONFIG_BLOCK
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
return (offset >> inode->i_blkbits);
}
static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
{
return (blk << inode->i_blkbits);
}
/**
* __generic_block_fiemap - FIEMAP for block based inodes (no locking)
* @inode: the inode to map
* @fieinfo: the fiemap info struct that will be passed back to userspace
* @start: where to start mapping in the inode
* @len: how much space to map
* @get_block: the fs's get_block function
*
* This does FIEMAP for block based inodes. Basically it will just loop
* through get_block until we hit the number of extents we want to map, or we
* go past the end of the file and hit a hole.
*
* If it is possible to have data blocks beyond a hole past @inode->i_size, then
* please do not use this function, it will stop at the first unmapped block
* beyond i_size.
*
* If you use this function directly, you need to do your own locking. Use
* generic_block_fiemap if you want the locking done for you.
*/
int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, loff_t start,
loff_t len, get_block_t *get_block)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
loff_t isize = i_size_read(inode);
u64 logical = 0, phys = 0, size = 0;
u32 flags = FIEMAP_EXTENT_MERGED;
bool past_eof = false, whole_file = false;
int ret = 0;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
/*
* Either the i_mutex or other appropriate locking needs to be held
* since we expect isize to not change at all through the duration of
* this call.
*/
if (len >= isize) {
whole_file = true;
len = isize;
}
/*
* Some filesystems can't deal with being asked to map less than
* blocksize, so make sure our len is at least block length.
*/
if (logical_to_blk(inode, len) == 0)
len = blk_to_logical(inode, 1);
start_blk = logical_to_blk(inode, start);
last_blk = logical_to_blk(inode, start + len - 1);
do {
/*
* we set b_size to the total size we want so it will map as
* many contiguous blocks as possible at once
*/
memset(&map_bh, 0, sizeof(struct buffer_head));
map_bh.b_size = len;
ret = get_block(inode, start_blk, &map_bh, 0);
if (ret)
break;
/* HOLE */
if (!buffer_mapped(&map_bh)) {
start_blk++;
/*
* We want to handle the case where there is an
* allocated block at the front of the file, and then
* nothing but holes up to the end of the file properly,
* to make sure that extent at the front gets properly
* marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof &&
blk_to_logical(inode, start_blk) >= isize)
past_eof = 1;
/*
* First hole after going past the EOF, this is our
* last extent
*/
if (past_eof && size) {
flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
} else if (size) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
size = 0;
}
/* if we have holes up to/past EOF then we're done */
if (start_blk > last_blk || past_eof || ret)
break;
} else {
/*
* We have gone over the length of what we wanted to
* map, and it wasn't the entire file, so add the extent
* we got last time and exit.
*
* This is for the case where say we want to map all the
* way up to the second to the last block in a file, but
* the last block is a hole, making the second to last
* block FIEMAP_EXTENT_LAST. In this case we want to
* see if there is a hole after the second to last block
* so we can mark it properly. If we found data after
* we exceeded the length we were requesting, then we
* are good to go, just add the extent to the fieinfo
* and break
*/
if (start_blk > last_blk && !whole_file) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
break;
}
/*
* if size != 0 then we know we already have an extent
* to add, so add it.
*/
if (size) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
if (ret)
break;
}
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, map_bh.b_blocknr);
size = map_bh.b_size;
flags = FIEMAP_EXTENT_MERGED;
start_blk += logical_to_blk(inode, size);
/*
* If we are past the EOF, then we need to make sure as
* soon as we find a hole that the last extent we found
* is marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof && logical + size >= isize)
past_eof = true;
}
cond_resched();
if (fatal_signal_pending(current)) {
ret = -EINTR;
break;
}
} while (1);
/* If ret is 1 then we just hit the end of the extent array */
if (ret == 1)
ret = 0;
return ret;
}
EXPORT_SYMBOL(__generic_block_fiemap);
/**
* generic_block_fiemap - FIEMAP for block based inodes
* @inode: The inode to map
* @fieinfo: The mapping information
* @start: The initial block to map
* @len: The length of the extect to attempt to map
* @get_block: The block mapping function for the fs
*
* Calls __generic_block_fiemap to map the inode, after taking
* the inode's mutex lock.
*/
int generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start,
u64 len, get_block_t *get_block)
{
int ret;
inode_lock(inode);
ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
inode_unlock(inode);
return ret;
}
EXPORT_SYMBOL(generic_block_fiemap);
#endif /* CONFIG_BLOCK */
/*
* This provides compatibility with legacy XFS pre-allocation ioctls
* which predate the fallocate syscall.
*
* Only the l_start, l_len and l_whence fields of the 'struct space_resv'
* are used here, rest are ignored.
*/
int ioctl_preallocate(struct file *filp, void __user *argp)
{
struct inode *inode = file_inode(filp);
struct space_resv sr;
if (copy_from_user(&sr, argp, sizeof(sr)))
return -EFAULT;
switch (sr.l_whence) {
case SEEK_SET:
break;
case SEEK_CUR:
sr.l_start += filp->f_pos;
break;
case SEEK_END:
sr.l_start += i_size_read(inode);
break;
default:
return -EINVAL;
}
return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
}
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
struct inode *inode = file_inode(filp);
int __user *p = (int __user *)arg;
switch (cmd) {
case FIBMAP:
return ioctl_fibmap(filp, p);
case FIONREAD:
return put_user(i_size_read(inode) - filp->f_pos, p);
case FS_IOC_RESVSP:
case FS_IOC_RESVSP64:
return ioctl_preallocate(filp, p);
}
return vfs_ioctl(filp, cmd, arg);
}
static int ioctl_fionbio(struct file *filp, int __user *argp)
{
unsigned int flag;
int on, error;
error = get_user(on, argp);
if (error)
return error;
flag = O_NONBLOCK;
#ifdef __sparc__
/* SunOS compatibility item. */
if (O_NONBLOCK != O_NDELAY)
flag |= O_NDELAY;
#endif
spin_lock(&filp->f_lock);
if (on)
filp->f_flags |= flag;
else
filp->f_flags &= ~flag;
spin_unlock(&filp->f_lock);
return error;
}
static int ioctl_fioasync(unsigned int fd, struct file *filp,
int __user *argp)
{
unsigned int flag;
int on, error;
error = get_user(on, argp);
if (error)
return error;
flag = on ? FASYNC : 0;
/* Did FASYNC state change ? */
if ((flag ^ filp->f_flags) & FASYNC) {
if (filp->f_op->fasync)
/* fasync() adjusts filp->f_flags */
error = filp->f_op->fasync(fd, filp, on);
else
error = -ENOTTY;
}
return error < 0 ? error : 0;
}
static int ioctl_fsfreeze(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* If filesystem doesn't support freeze feature, return. */
if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL)
return -EOPNOTSUPP;
/* Freeze */
if (sb->s_op->freeze_super)
return sb->s_op->freeze_super(sb);
return freeze_super(sb);
}
static int ioctl_fsthaw(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* Thaw */
if (sb->s_op->thaw_super)
return sb->s_op->thaw_super(sb);
return thaw_super(sb);
}
static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
{
struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
int ret;
unsigned long size;
u16 count;
if (get_user(count, &argp->dest_count)) {
ret = -EFAULT;
goto out;
}
size = offsetof(struct file_dedupe_range __user, info[count]);
if (size > PAGE_SIZE) {
ret = -ENOMEM;
goto out;
}
same = memdup_user(argp, size);
if (IS_ERR(same)) {
ret = PTR_ERR(same);
same = NULL;
goto out;
}
same->dest_count = count;
ret = vfs_dedupe_file_range(file, same);
if (ret)
goto out;
ret = copy_to_user(argp, same, size);
if (ret)
ret = -EFAULT;
out:
kfree(same);
return ret;
}
/*
* When you add any new common ioctls to the switches above and below
* please update compat_sys_ioctl() too.
*
* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
*/
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg)
{
int error = 0;
int __user *argp = (int __user *)arg;
struct inode *inode = file_inode(filp);
switch (cmd) {
case FIOCLEX:
set_close_on_exec(fd, 1);
break;
case FIONCLEX:
set_close_on_exec(fd, 0);
break;
case FIONBIO:
error = ioctl_fionbio(filp, argp);
break;
case FIOASYNC:
error = ioctl_fioasync(fd, filp, argp);
break;
case FIOQSIZE:
if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) ||
S_ISLNK(inode->i_mode)) {
loff_t res = inode_get_bytes(inode);
error = copy_to_user(argp, &res, sizeof(res)) ?
-EFAULT : 0;
} else
error = -ENOTTY;
break;
case FIFREEZE:
error = ioctl_fsfreeze(filp);
break;
case FITHAW:
error = ioctl_fsthaw(filp);
break;
case FS_IOC_FIEMAP:
return ioctl_fiemap(filp, arg);
case FIGETBSZ:
return put_user(inode->i_sb->s_blocksize, argp);
case FICLONE:
return ioctl_file_clone(filp, arg, 0, 0, 0);
case FICLONERANGE:
return ioctl_file_clone_range(filp, argp);
case FIDEDUPERANGE:
return ioctl_file_dedupe_range(filp, argp);
default:
if (S_ISREG(inode->i_mode))
error = file_ioctl(filp, cmd, arg);
else
error = vfs_ioctl(filp, cmd, arg);
break;
}
return error;
}
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
int error;
struct fd f = fdget(fd);
if (!f.file)
return -EBADF;
error = security_file_ioctl(f.file, cmd, arg);
if (!error)
error = do_vfs_ioctl(f.file, fd, cmd, arg);
fdput(f);
return error;
}