linux-brain/fs/btrfs/ctree.h
Filipe Manana c964d386e8 btrfs: fix readahead hang and use-after-free after removing a device
commit 66d204a16c94f24ad08290a7663ab67e7fc04e82 upstream.

Very sporadically I had test case btrfs/069 from fstests hanging (for
years, it is not a recent regression), with the following traces in
dmesg/syslog:

  [162301.160628] BTRFS info (device sdc): dev_replace from /dev/sdd (devid 2) to /dev/sdg started
  [162301.181196] BTRFS info (device sdc): scrub: finished on devid 4 with status: 0
  [162301.287162] BTRFS info (device sdc): dev_replace from /dev/sdd (devid 2) to /dev/sdg finished
  [162513.513792] INFO: task btrfs-transacti:1356167 blocked for more than 120 seconds.
  [162513.514318]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.514522] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.514747] task:btrfs-transacti state:D stack:    0 pid:1356167 ppid:     2 flags:0x00004000
  [162513.514751] Call Trace:
  [162513.514761]  __schedule+0x5ce/0xd00
  [162513.514765]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.514771]  schedule+0x46/0xf0
  [162513.514844]  wait_current_trans+0xde/0x140 [btrfs]
  [162513.514850]  ? finish_wait+0x90/0x90
  [162513.514864]  start_transaction+0x37c/0x5f0 [btrfs]
  [162513.514879]  transaction_kthread+0xa4/0x170 [btrfs]
  [162513.514891]  ? btrfs_cleanup_transaction+0x660/0x660 [btrfs]
  [162513.514894]  kthread+0x153/0x170
  [162513.514897]  ? kthread_stop+0x2c0/0x2c0
  [162513.514902]  ret_from_fork+0x22/0x30
  [162513.514916] INFO: task fsstress:1356184 blocked for more than 120 seconds.
  [162513.515192]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.515431] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.515680] task:fsstress        state:D stack:    0 pid:1356184 ppid:1356177 flags:0x00004000
  [162513.515682] Call Trace:
  [162513.515688]  __schedule+0x5ce/0xd00
  [162513.515691]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.515697]  schedule+0x46/0xf0
  [162513.515712]  wait_current_trans+0xde/0x140 [btrfs]
  [162513.515716]  ? finish_wait+0x90/0x90
  [162513.515729]  start_transaction+0x37c/0x5f0 [btrfs]
  [162513.515743]  btrfs_attach_transaction_barrier+0x1f/0x50 [btrfs]
  [162513.515753]  btrfs_sync_fs+0x61/0x1c0 [btrfs]
  [162513.515758]  ? __ia32_sys_fdatasync+0x20/0x20
  [162513.515761]  iterate_supers+0x87/0xf0
  [162513.515765]  ksys_sync+0x60/0xb0
  [162513.515768]  __do_sys_sync+0xa/0x10
  [162513.515771]  do_syscall_64+0x33/0x80
  [162513.515774]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [162513.515781] RIP: 0033:0x7f5238f50bd7
  [162513.515782] Code: Bad RIP value.
  [162513.515784] RSP: 002b:00007fff67b978e8 EFLAGS: 00000206 ORIG_RAX: 00000000000000a2
  [162513.515786] RAX: ffffffffffffffda RBX: 000055b1fad2c560 RCX: 00007f5238f50bd7
  [162513.515788] RDX: 00000000ffffffff RSI: 000000000daf0e74 RDI: 000000000000003a
  [162513.515789] RBP: 0000000000000032 R08: 000000000000000a R09: 00007f5239019be0
  [162513.515791] R10: fffffffffffff24f R11: 0000000000000206 R12: 000000000000003a
  [162513.515792] R13: 00007fff67b97950 R14: 00007fff67b97906 R15: 000055b1fad1a340
  [162513.515804] INFO: task fsstress:1356185 blocked for more than 120 seconds.
  [162513.516064]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.516329] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.516617] task:fsstress        state:D stack:    0 pid:1356185 ppid:1356177 flags:0x00000000
  [162513.516620] Call Trace:
  [162513.516625]  __schedule+0x5ce/0xd00
  [162513.516628]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.516634]  schedule+0x46/0xf0
  [162513.516647]  wait_current_trans+0xde/0x140 [btrfs]
  [162513.516650]  ? finish_wait+0x90/0x90
  [162513.516662]  start_transaction+0x4d7/0x5f0 [btrfs]
  [162513.516679]  btrfs_setxattr_trans+0x3c/0x100 [btrfs]
  [162513.516686]  __vfs_setxattr+0x66/0x80
  [162513.516691]  __vfs_setxattr_noperm+0x70/0x200
  [162513.516697]  vfs_setxattr+0x6b/0x120
  [162513.516703]  setxattr+0x125/0x240
  [162513.516709]  ? lock_acquire+0xb1/0x480
  [162513.516712]  ? mnt_want_write+0x20/0x50
  [162513.516721]  ? rcu_read_lock_any_held+0x8e/0xb0
  [162513.516723]  ? preempt_count_add+0x49/0xa0
  [162513.516725]  ? __sb_start_write+0x19b/0x290
  [162513.516727]  ? preempt_count_add+0x49/0xa0
  [162513.516732]  path_setxattr+0xba/0xd0
  [162513.516739]  __x64_sys_setxattr+0x27/0x30
  [162513.516741]  do_syscall_64+0x33/0x80
  [162513.516743]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [162513.516745] RIP: 0033:0x7f5238f56d5a
  [162513.516746] Code: Bad RIP value.
  [162513.516748] RSP: 002b:00007fff67b97868 EFLAGS: 00000202 ORIG_RAX: 00000000000000bc
  [162513.516750] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f5238f56d5a
  [162513.516751] RDX: 000055b1fbb0d5a0 RSI: 00007fff67b978a0 RDI: 000055b1fbb0d470
  [162513.516753] RBP: 000055b1fbb0d5a0 R08: 0000000000000001 R09: 00007fff67b97700
  [162513.516754] R10: 0000000000000004 R11: 0000000000000202 R12: 0000000000000004
  [162513.516756] R13: 0000000000000024 R14: 0000000000000001 R15: 00007fff67b978a0
  [162513.516767] INFO: task fsstress:1356196 blocked for more than 120 seconds.
  [162513.517064]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.517365] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.517763] task:fsstress        state:D stack:    0 pid:1356196 ppid:1356177 flags:0x00004000
  [162513.517780] Call Trace:
  [162513.517786]  __schedule+0x5ce/0xd00
  [162513.517789]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.517796]  schedule+0x46/0xf0
  [162513.517810]  wait_current_trans+0xde/0x140 [btrfs]
  [162513.517814]  ? finish_wait+0x90/0x90
  [162513.517829]  start_transaction+0x37c/0x5f0 [btrfs]
  [162513.517845]  btrfs_attach_transaction_barrier+0x1f/0x50 [btrfs]
  [162513.517857]  btrfs_sync_fs+0x61/0x1c0 [btrfs]
  [162513.517862]  ? __ia32_sys_fdatasync+0x20/0x20
  [162513.517865]  iterate_supers+0x87/0xf0
  [162513.517869]  ksys_sync+0x60/0xb0
  [162513.517872]  __do_sys_sync+0xa/0x10
  [162513.517875]  do_syscall_64+0x33/0x80
  [162513.517878]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [162513.517881] RIP: 0033:0x7f5238f50bd7
  [162513.517883] Code: Bad RIP value.
  [162513.517885] RSP: 002b:00007fff67b978e8 EFLAGS: 00000206 ORIG_RAX: 00000000000000a2
  [162513.517887] RAX: ffffffffffffffda RBX: 000055b1fad2c560 RCX: 00007f5238f50bd7
  [162513.517889] RDX: 0000000000000000 RSI: 000000007660add2 RDI: 0000000000000053
  [162513.517891] RBP: 0000000000000032 R08: 0000000000000067 R09: 00007f5239019be0
  [162513.517893] R10: fffffffffffff24f R11: 0000000000000206 R12: 0000000000000053
  [162513.517895] R13: 00007fff67b97950 R14: 00007fff67b97906 R15: 000055b1fad1a340
  [162513.517908] INFO: task fsstress:1356197 blocked for more than 120 seconds.
  [162513.518298]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.518672] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.519157] task:fsstress        state:D stack:    0 pid:1356197 ppid:1356177 flags:0x00000000
  [162513.519160] Call Trace:
  [162513.519165]  __schedule+0x5ce/0xd00
  [162513.519168]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.519174]  schedule+0x46/0xf0
  [162513.519190]  wait_current_trans+0xde/0x140 [btrfs]
  [162513.519193]  ? finish_wait+0x90/0x90
  [162513.519206]  start_transaction+0x4d7/0x5f0 [btrfs]
  [162513.519222]  btrfs_create+0x57/0x200 [btrfs]
  [162513.519230]  lookup_open+0x522/0x650
  [162513.519246]  path_openat+0x2b8/0xa50
  [162513.519270]  do_filp_open+0x91/0x100
  [162513.519275]  ? find_held_lock+0x32/0x90
  [162513.519280]  ? lock_acquired+0x33b/0x470
  [162513.519285]  ? do_raw_spin_unlock+0x4b/0xc0
  [162513.519287]  ? _raw_spin_unlock+0x29/0x40
  [162513.519295]  do_sys_openat2+0x20d/0x2d0
  [162513.519300]  do_sys_open+0x44/0x80
  [162513.519304]  do_syscall_64+0x33/0x80
  [162513.519307]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [162513.519309] RIP: 0033:0x7f5238f4a903
  [162513.519310] Code: Bad RIP value.
  [162513.519312] RSP: 002b:00007fff67b97758 EFLAGS: 00000246 ORIG_RAX: 0000000000000055
  [162513.519314] RAX: ffffffffffffffda RBX: 00000000ffffffff RCX: 00007f5238f4a903
  [162513.519316] RDX: 0000000000000000 RSI: 00000000000001b6 RDI: 000055b1fbb0d470
  [162513.519317] RBP: 00007fff67b978c0 R08: 0000000000000001 R09: 0000000000000002
  [162513.519319] R10: 00007fff67b974f7 R11: 0000000000000246 R12: 0000000000000013
  [162513.519320] R13: 00000000000001b6 R14: 00007fff67b97906 R15: 000055b1fad1c620
  [162513.519332] INFO: task btrfs:1356211 blocked for more than 120 seconds.
  [162513.519727]       Not tainted 5.9.0-rc6-btrfs-next-69 #1
  [162513.520115] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [162513.520508] task:btrfs           state:D stack:    0 pid:1356211 ppid:1356178 flags:0x00004002
  [162513.520511] Call Trace:
  [162513.520516]  __schedule+0x5ce/0xd00
  [162513.520519]  ? _raw_spin_unlock_irqrestore+0x3c/0x60
  [162513.520525]  schedule+0x46/0xf0
  [162513.520544]  btrfs_scrub_pause+0x11f/0x180 [btrfs]
  [162513.520548]  ? finish_wait+0x90/0x90
  [162513.520562]  btrfs_commit_transaction+0x45a/0xc30 [btrfs]
  [162513.520574]  ? start_transaction+0xe0/0x5f0 [btrfs]
  [162513.520596]  btrfs_dev_replace_finishing+0x6d8/0x711 [btrfs]
  [162513.520619]  btrfs_dev_replace_by_ioctl.cold+0x1cc/0x1fd [btrfs]
  [162513.520639]  btrfs_ioctl+0x2a25/0x36f0 [btrfs]
  [162513.520643]  ? do_sigaction+0xf3/0x240
  [162513.520645]  ? find_held_lock+0x32/0x90
  [162513.520648]  ? do_sigaction+0xf3/0x240
  [162513.520651]  ? lock_acquired+0x33b/0x470
  [162513.520655]  ? _raw_spin_unlock_irq+0x24/0x50
  [162513.520657]  ? lockdep_hardirqs_on+0x7d/0x100
  [162513.520660]  ? _raw_spin_unlock_irq+0x35/0x50
  [162513.520662]  ? do_sigaction+0xf3/0x240
  [162513.520671]  ? __x64_sys_ioctl+0x83/0xb0
  [162513.520672]  __x64_sys_ioctl+0x83/0xb0
  [162513.520677]  do_syscall_64+0x33/0x80
  [162513.520679]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
  [162513.520681] RIP: 0033:0x7fc3cd307d87
  [162513.520682] Code: Bad RIP value.
  [162513.520684] RSP: 002b:00007ffe30a56bb8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
  [162513.520686] RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007fc3cd307d87
  [162513.520687] RDX: 00007ffe30a57a30 RSI: 00000000ca289435 RDI: 0000000000000003
  [162513.520689] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  [162513.520690] R10: 0000000000000008 R11: 0000000000000202 R12: 0000000000000003
  [162513.520692] R13: 0000557323a212e0 R14: 00007ffe30a5a520 R15: 0000000000000001
  [162513.520703]
		  Showing all locks held in the system:
  [162513.520712] 1 lock held by khungtaskd/54:
  [162513.520713]  #0: ffffffffb40a91a0 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x15/0x197
  [162513.520728] 1 lock held by in:imklog/596:
  [162513.520729]  #0: ffff8f3f0d781400 (&f->f_pos_lock){+.+.}-{3:3}, at: __fdget_pos+0x4d/0x60
  [162513.520782] 1 lock held by btrfs-transacti/1356167:
  [162513.520784]  #0: ffff8f3d810cc848 (&fs_info->transaction_kthread_mutex){+.+.}-{3:3}, at: transaction_kthread+0x4a/0x170 [btrfs]
  [162513.520798] 1 lock held by btrfs/1356190:
  [162513.520800]  #0: ffff8f3d57644470 (sb_writers#15){.+.+}-{0:0}, at: mnt_want_write_file+0x22/0x60
  [162513.520805] 1 lock held by fsstress/1356184:
  [162513.520806]  #0: ffff8f3d576440e8 (&type->s_umount_key#62){++++}-{3:3}, at: iterate_supers+0x6f/0xf0
  [162513.520811] 3 locks held by fsstress/1356185:
  [162513.520812]  #0: ffff8f3d57644470 (sb_writers#15){.+.+}-{0:0}, at: mnt_want_write+0x20/0x50
  [162513.520815]  #1: ffff8f3d80a650b8 (&type->i_mutex_dir_key#10){++++}-{3:3}, at: vfs_setxattr+0x50/0x120
  [162513.520820]  #2: ffff8f3d57644690 (sb_internal#2){.+.+}-{0:0}, at: start_transaction+0x40e/0x5f0 [btrfs]
  [162513.520833] 1 lock held by fsstress/1356196:
  [162513.520834]  #0: ffff8f3d576440e8 (&type->s_umount_key#62){++++}-{3:3}, at: iterate_supers+0x6f/0xf0
  [162513.520838] 3 locks held by fsstress/1356197:
  [162513.520839]  #0: ffff8f3d57644470 (sb_writers#15){.+.+}-{0:0}, at: mnt_want_write+0x20/0x50
  [162513.520843]  #1: ffff8f3d506465e8 (&type->i_mutex_dir_key#10){++++}-{3:3}, at: path_openat+0x2a7/0xa50
  [162513.520846]  #2: ffff8f3d57644690 (sb_internal#2){.+.+}-{0:0}, at: start_transaction+0x40e/0x5f0 [btrfs]
  [162513.520858] 2 locks held by btrfs/1356211:
  [162513.520859]  #0: ffff8f3d810cde30 (&fs_info->dev_replace.lock_finishing_cancel_unmount){+.+.}-{3:3}, at: btrfs_dev_replace_finishing+0x52/0x711 [btrfs]
  [162513.520877]  #1: ffff8f3d57644690 (sb_internal#2){.+.+}-{0:0}, at: start_transaction+0x40e/0x5f0 [btrfs]

This was weird because the stack traces show that a transaction commit,
triggered by a device replace operation, is blocking trying to pause any
running scrubs but there are no stack traces of blocked tasks doing a
scrub.

After poking around with drgn, I noticed there was a scrub task that was
constantly running and blocking for shorts periods of time:

  >>> t = find_task(prog, 1356190)
  >>> prog.stack_trace(t)
  #0  __schedule+0x5ce/0xcfc
  #1  schedule+0x46/0xe4
  #2  schedule_timeout+0x1df/0x475
  #3  btrfs_reada_wait+0xda/0x132
  #4  scrub_stripe+0x2a8/0x112f
  #5  scrub_chunk+0xcd/0x134
  #6  scrub_enumerate_chunks+0x29e/0x5ee
  #7  btrfs_scrub_dev+0x2d5/0x91b
  #8  btrfs_ioctl+0x7f5/0x36e7
  #9  __x64_sys_ioctl+0x83/0xb0
  #10 do_syscall_64+0x33/0x77
  #11 entry_SYSCALL_64+0x7c/0x156

Which corresponds to:

int btrfs_reada_wait(void *handle)
{
    struct reada_control *rc = handle;
    struct btrfs_fs_info *fs_info = rc->fs_info;

    while (atomic_read(&rc->elems)) {
        if (!atomic_read(&fs_info->reada_works_cnt))
            reada_start_machine(fs_info);
        wait_event_timeout(rc->wait, atomic_read(&rc->elems) == 0,
                          (HZ + 9) / 10);
    }
(...)

So the counter "rc->elems" was set to 1 and never decreased to 0, causing
the scrub task to loop forever in that function. Then I used the following
script for drgn to check the readahead requests:

  $ cat dump_reada.py
  import sys
  import drgn
  from drgn import NULL, Object, cast, container_of, execscript, \
      reinterpret, sizeof
  from drgn.helpers.linux import *

  mnt_path = b"/home/fdmanana/btrfs-tests/scratch_1"

  mnt = None
  for mnt in for_each_mount(prog, dst = mnt_path):
      pass

  if mnt is None:
      sys.stderr.write(f'Error: mount point {mnt_path} not found\n')
      sys.exit(1)

  fs_info = cast('struct btrfs_fs_info *', mnt.mnt.mnt_sb.s_fs_info)

  def dump_re(re):
      nzones = re.nzones.value_()
      print(f're at {hex(re.value_())}')
      print(f'\t logical {re.logical.value_()}')
      print(f'\t refcnt {re.refcnt.value_()}')
      print(f'\t nzones {nzones}')
      for i in range(nzones):
          dev = re.zones[i].device
          name = dev.name.str.string_()
          print(f'\t\t dev id {dev.devid.value_()} name {name}')
      print()

  for _, e in radix_tree_for_each(fs_info.reada_tree):
      re = cast('struct reada_extent *', e)
      dump_re(re)

  $ drgn dump_reada.py
  re at 0xffff8f3da9d25ad8
          logical 38928384
          refcnt 1
          nzones 1
                 dev id 0 name b'/dev/sdd'
  $

So there was one readahead extent with a single zone corresponding to the
source device of that last device replace operation logged in dmesg/syslog.
Also the ID of that zone's device was 0 which is a special value set in
the source device of a device replace operation when the operation finishes
(constant BTRFS_DEV_REPLACE_DEVID set at btrfs_dev_replace_finishing()),
confirming again that device /dev/sdd was the source of a device replace
operation.

Normally there should be as many zones in the readahead extent as there are
devices, and I wasn't expecting the extent to be in a block group with a
'single' profile, so I went and confirmed with the following drgn script
that there weren't any single profile block groups:

  $ cat dump_block_groups.py
  import sys
  import drgn
  from drgn import NULL, Object, cast, container_of, execscript, \
      reinterpret, sizeof
  from drgn.helpers.linux import *

  mnt_path = b"/home/fdmanana/btrfs-tests/scratch_1"

  mnt = None
  for mnt in for_each_mount(prog, dst = mnt_path):
      pass

  if mnt is None:
      sys.stderr.write(f'Error: mount point {mnt_path} not found\n')
      sys.exit(1)

  fs_info = cast('struct btrfs_fs_info *', mnt.mnt.mnt_sb.s_fs_info)

  BTRFS_BLOCK_GROUP_DATA = (1 << 0)
  BTRFS_BLOCK_GROUP_SYSTEM = (1 << 1)
  BTRFS_BLOCK_GROUP_METADATA = (1 << 2)
  BTRFS_BLOCK_GROUP_RAID0 = (1 << 3)
  BTRFS_BLOCK_GROUP_RAID1 = (1 << 4)
  BTRFS_BLOCK_GROUP_DUP = (1 << 5)
  BTRFS_BLOCK_GROUP_RAID10 = (1 << 6)
  BTRFS_BLOCK_GROUP_RAID5 = (1 << 7)
  BTRFS_BLOCK_GROUP_RAID6 = (1 << 8)
  BTRFS_BLOCK_GROUP_RAID1C3 = (1 << 9)
  BTRFS_BLOCK_GROUP_RAID1C4 = (1 << 10)

  def bg_flags_string(bg):
      flags = bg.flags.value_()
      ret = ''
      if flags & BTRFS_BLOCK_GROUP_DATA:
          ret = 'data'
      if flags & BTRFS_BLOCK_GROUP_METADATA:
          if len(ret) > 0:
              ret += '|'
          ret += 'meta'
      if flags & BTRFS_BLOCK_GROUP_SYSTEM:
          if len(ret) > 0:
              ret += '|'
          ret += 'system'
      if flags & BTRFS_BLOCK_GROUP_RAID0:
          ret += ' raid0'
      elif flags & BTRFS_BLOCK_GROUP_RAID1:
          ret += ' raid1'
      elif flags & BTRFS_BLOCK_GROUP_DUP:
          ret += ' dup'
      elif flags & BTRFS_BLOCK_GROUP_RAID10:
          ret += ' raid10'
      elif flags & BTRFS_BLOCK_GROUP_RAID5:
          ret += ' raid5'
      elif flags & BTRFS_BLOCK_GROUP_RAID6:
          ret += ' raid6'
      elif flags & BTRFS_BLOCK_GROUP_RAID1C3:
          ret += ' raid1c3'
      elif flags & BTRFS_BLOCK_GROUP_RAID1C4:
          ret += ' raid1c4'
      else:
          ret += ' single'

      return ret

  def dump_bg(bg):
      print()
      print(f'block group at {hex(bg.value_())}')
      print(f'\t start {bg.start.value_()} length {bg.length.value_()}')
      print(f'\t flags {bg.flags.value_()} - {bg_flags_string(bg)}')

  bg_root = fs_info.block_group_cache_tree.address_of_()
  for bg in rbtree_inorder_for_each_entry('struct btrfs_block_group', bg_root, 'cache_node'):
      dump_bg(bg)

  $ drgn dump_block_groups.py

  block group at 0xffff8f3d673b0400
         start 22020096 length 16777216
         flags 258 - system raid6

  block group at 0xffff8f3d53ddb400
         start 38797312 length 536870912
         flags 260 - meta raid6

  block group at 0xffff8f3d5f4d9c00
         start 575668224 length 2147483648
         flags 257 - data raid6

  block group at 0xffff8f3d08189000
         start 2723151872 length 67108864
         flags 258 - system raid6

  block group at 0xffff8f3db70ff000
         start 2790260736 length 1073741824
         flags 260 - meta raid6

  block group at 0xffff8f3d5f4dd800
         start 3864002560 length 67108864
         flags 258 - system raid6

  block group at 0xffff8f3d67037000
         start 3931111424 length 2147483648
         flags 257 - data raid6
  $

So there were only 2 reasons left for having a readahead extent with a
single zone: reada_find_zone(), called when creating a readahead extent,
returned NULL either because we failed to find the corresponding block
group or because a memory allocation failed. With some additional and
custom tracing I figured out that on every further ocurrence of the
problem the block group had just been deleted when we were looping to
create the zones for the readahead extent (at reada_find_extent()), so we
ended up with only one zone in the readahead extent, corresponding to a
device that ends up getting replaced.

So after figuring that out it became obvious why the hang happens:

1) Task A starts a scrub on any device of the filesystem, except for
   device /dev/sdd;

2) Task B starts a device replace with /dev/sdd as the source device;

3) Task A calls btrfs_reada_add() from scrub_stripe() and it is currently
   starting to scrub a stripe from block group X. This call to
   btrfs_reada_add() is the one for the extent tree. When btrfs_reada_add()
   calls reada_add_block(), it passes the logical address of the extent
   tree's root node as its 'logical' argument - a value of 38928384;

4) Task A then enters reada_find_extent(), called from reada_add_block().
   It finds there isn't any existing readahead extent for the logical
   address 38928384, so it proceeds to the path of creating a new one.

   It calls btrfs_map_block() to find out which stripes exist for the block
   group X. On the first iteration of the for loop that iterates over the
   stripes, it finds the stripe for device /dev/sdd, so it creates one
   zone for that device and adds it to the readahead extent. Before getting
   into the second iteration of the loop, the cleanup kthread deletes block
   group X because it was empty. So in the iterations for the remaining
   stripes it does not add more zones to the readahead extent, because the
   calls to reada_find_zone() returned NULL because they couldn't find
   block group X anymore.

   As a result the new readahead extent has a single zone, corresponding to
   the device /dev/sdd;

4) Before task A returns to btrfs_reada_add() and queues the readahead job
   for the readahead work queue, task B finishes the device replace and at
   btrfs_dev_replace_finishing() swaps the device /dev/sdd with the new
   device /dev/sdg;

5) Task A returns to reada_add_block(), which increments the counter
   "->elems" of the reada_control structure allocated at btrfs_reada_add().

   Then it returns back to btrfs_reada_add() and calls
   reada_start_machine(). This queues a job in the readahead work queue to
   run the function reada_start_machine_worker(), which calls
   __reada_start_machine().

   At __reada_start_machine() we take the device list mutex and for each
   device found in the current device list, we call
   reada_start_machine_dev() to start the readahead work. However at this
   point the device /dev/sdd was already freed and is not in the device
   list anymore.

   This means the corresponding readahead for the extent at 38928384 is
   never started, and therefore the "->elems" counter of the reada_control
   structure allocated at btrfs_reada_add() never goes down to 0, causing
   the call to btrfs_reada_wait(), done by the scrub task, to wait forever.

Note that the readahead request can be made either after the device replace
started or before it started, however in pratice it is very unlikely that a
device replace is able to start after a readahead request is made and is
able to complete before the readahead request completes - maybe only on a
very small and nearly empty filesystem.

This hang however is not the only problem we can have with readahead and
device removals. When the readahead extent has other zones other than the
one corresponding to the device that is being removed (either by a device
replace or a device remove operation), we risk having a use-after-free on
the device when dropping the last reference of the readahead extent.

For example if we create a readahead extent with two zones, one for the
device /dev/sdd and one for the device /dev/sde:

1) Before the readahead worker starts, the device /dev/sdd is removed,
   and the corresponding btrfs_device structure is freed. However the
   readahead extent still has the zone pointing to the device structure;

2) When the readahead worker starts, it only finds device /dev/sde in the
   current device list of the filesystem;

3) It starts the readahead work, at reada_start_machine_dev(), using the
   device /dev/sde;

4) Then when it finishes reading the extent from device /dev/sde, it calls
   __readahead_hook() which ends up dropping the last reference on the
   readahead extent through the last call to reada_extent_put();

5) At reada_extent_put() it iterates over each zone of the readahead extent
   and attempts to delete an element from the device's 'reada_extents'
   radix tree, resulting in a use-after-free, as the device pointer of the
   zone for /dev/sdd is now stale. We can also access the device after
   dropping the last reference of a zone, through reada_zone_release(),
   also called by reada_extent_put().

And a device remove suffers the same problem, however since it shrinks the
device size down to zero before removing the device, it is very unlikely to
still have readahead requests not completed by the time we free the device,
the only possibility is if the device has a very little space allocated.

While the hang problem is exclusive to scrub, since it is currently the
only user of btrfs_reada_add() and btrfs_reada_wait(), the use-after-free
problem affects any path that triggers readhead, which includes
btree_readahead_hook() and __readahead_hook() (a readahead worker can
trigger readahed for the children of a node) for example - any path that
ends up calling reada_add_block() can trigger the use-after-free after a
device is removed.

So fix this by waiting for any readahead requests for a device to complete
before removing a device, ensuring that while waiting for existing ones no
new ones can be made.

This problem has been around for a very long time - the readahead code was
added in 2011, device remove exists since 2008 and device replace was
introduced in 2013, hard to pick a specific commit for a git Fixes tag.

CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-11-05 11:43:27 +01:00

3443 lines
117 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#ifndef BTRFS_CTREE_H
#define BTRFS_CTREE_H
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/highmem.h>
#include <linux/fs.h>
#include <linux/rwsem.h>
#include <linux/semaphore.h>
#include <linux/completion.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include <trace/events/btrfs.h>
#include <asm/kmap_types.h>
#include <asm/unaligned.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
#include <linux/btrfs_tree.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/sizes.h>
#include <linux/dynamic_debug.h>
#include <linux/refcount.h>
#include <linux/crc32c.h>
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
#include "block-rsv.h"
struct btrfs_trans_handle;
struct btrfs_transaction;
struct btrfs_pending_snapshot;
struct btrfs_delayed_ref_root;
struct btrfs_space_info;
struct btrfs_block_group_cache;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
extern struct kmem_cache *btrfs_free_space_cachep;
extern struct kmem_cache *btrfs_free_space_bitmap_cachep;
struct btrfs_ordered_sum;
struct btrfs_ref;
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
/*
* Maximum number of mirrors that can be available for all profiles counting
* the target device of dev-replace as one. During an active device replace
* procedure, the target device of the copy operation is a mirror for the
* filesystem data as well that can be used to read data in order to repair
* read errors on other disks.
*
* Current value is derived from RAID1 with 2 copies.
*/
#define BTRFS_MAX_MIRRORS (2 + 1)
#define BTRFS_MAX_LEVEL 8
#define BTRFS_OLDEST_GENERATION 0ULL
/*
* the max metadata block size. This limit is somewhat artificial,
* but the memmove costs go through the roof for larger blocks.
*/
#define BTRFS_MAX_METADATA_BLOCKSIZE 65536
/*
* we can actually store much bigger names, but lets not confuse the rest
* of linux
*/
#define BTRFS_NAME_LEN 255
/*
* Theoretical limit is larger, but we keep this down to a sane
* value. That should limit greatly the possibility of collisions on
* inode ref items.
*/
#define BTRFS_LINK_MAX 65535U
#define BTRFS_EMPTY_DIR_SIZE 0
/* ioprio of readahead is set to idle */
#define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
#define BTRFS_DIRTY_METADATA_THRESH SZ_32M
/*
* Use large batch size to reduce overhead of metadata updates. On the reader
* side, we only read it when we are close to ENOSPC and the read overhead is
* mostly related to the number of CPUs, so it is OK to use arbitrary large
* value here.
*/
#define BTRFS_TOTAL_BYTES_PINNED_BATCH SZ_128M
#define BTRFS_MAX_EXTENT_SIZE SZ_128M
/*
* Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
*/
static inline u32 count_max_extents(u64 size)
{
return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
}
static inline unsigned long btrfs_chunk_item_size(int num_stripes)
{
BUG_ON(num_stripes == 0);
return sizeof(struct btrfs_chunk) +
sizeof(struct btrfs_stripe) * (num_stripes - 1);
}
/*
* Runtime (in-memory) states of filesystem
*/
enum {
/* Global indicator of serious filesystem errors */
BTRFS_FS_STATE_ERROR,
/*
* Filesystem is being remounted, allow to skip some operations, like
* defrag
*/
BTRFS_FS_STATE_REMOUNTING,
/* Track if a transaction abort has been reported on this filesystem */
BTRFS_FS_STATE_TRANS_ABORTED,
/*
* Bio operations should be blocked on this filesystem because a source
* or target device is being destroyed as part of a device replace
*/
BTRFS_FS_STATE_DEV_REPLACING,
/* The btrfs_fs_info created for self-tests */
BTRFS_FS_STATE_DUMMY_FS_INFO,
};
#define BTRFS_BACKREF_REV_MAX 256
#define BTRFS_BACKREF_REV_SHIFT 56
#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \
BTRFS_BACKREF_REV_SHIFT)
#define BTRFS_OLD_BACKREF_REV 0
#define BTRFS_MIXED_BACKREF_REV 1
/*
* every tree block (leaf or node) starts with this header.
*/
struct btrfs_header {
/* these first four must match the super block */
u8 csum[BTRFS_CSUM_SIZE];
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
__le64 bytenr; /* which block this node is supposed to live in */
__le64 flags;
/* allowed to be different from the super from here on down */
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
__le64 generation;
__le64 owner;
__le32 nritems;
u8 level;
} __attribute__ ((__packed__));
/*
* this is a very generous portion of the super block, giving us
* room to translate 14 chunks with 3 stripes each.
*/
#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048
/*
* just in case we somehow lose the roots and are not able to mount,
* we store an array of the roots from previous transactions
* in the super.
*/
#define BTRFS_NUM_BACKUP_ROOTS 4
struct btrfs_root_backup {
__le64 tree_root;
__le64 tree_root_gen;
__le64 chunk_root;
__le64 chunk_root_gen;
__le64 extent_root;
__le64 extent_root_gen;
__le64 fs_root;
__le64 fs_root_gen;
__le64 dev_root;
__le64 dev_root_gen;
__le64 csum_root;
__le64 csum_root_gen;
__le64 total_bytes;
__le64 bytes_used;
__le64 num_devices;
/* future */
__le64 unused_64[4];
u8 tree_root_level;
u8 chunk_root_level;
u8 extent_root_level;
u8 fs_root_level;
u8 dev_root_level;
u8 csum_root_level;
/* future and to align */
u8 unused_8[10];
} __attribute__ ((__packed__));
/*
* the super block basically lists the main trees of the FS
* it currently lacks any block count etc etc
*/
struct btrfs_super_block {
/* the first 4 fields must match struct btrfs_header */
u8 csum[BTRFS_CSUM_SIZE];
/* FS specific UUID, visible to user */
u8 fsid[BTRFS_FSID_SIZE];
__le64 bytenr; /* this block number */
__le64 flags;
/* allowed to be different from the btrfs_header from here own down */
__le64 magic;
__le64 generation;
__le64 root;
__le64 chunk_root;
__le64 log_root;
/* this will help find the new super based on the log root */
__le64 log_root_transid;
__le64 total_bytes;
__le64 bytes_used;
__le64 root_dir_objectid;
__le64 num_devices;
__le32 sectorsize;
__le32 nodesize;
__le32 __unused_leafsize;
__le32 stripesize;
__le32 sys_chunk_array_size;
__le64 chunk_root_generation;
__le64 compat_flags;
__le64 compat_ro_flags;
__le64 incompat_flags;
__le16 csum_type;
u8 root_level;
u8 chunk_root_level;
u8 log_root_level;
struct btrfs_dev_item dev_item;
char label[BTRFS_LABEL_SIZE];
__le64 cache_generation;
__le64 uuid_tree_generation;
/* the UUID written into btree blocks */
u8 metadata_uuid[BTRFS_FSID_SIZE];
/* future expansion */
__le64 reserved[28];
u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
} __attribute__ ((__packed__));
/*
* Compat flags that we support. If any incompat flags are set other than the
* ones specified below then we will fail to mount
*/
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SUPP \
(BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \
BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID)
#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL
#define BTRFS_FEATURE_INCOMPAT_SUPP \
(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \
BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \
BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \
BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD | \
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
BTRFS_FEATURE_INCOMPAT_NO_HOLES | \
BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL
/*
* A leaf is full of items. offset and size tell us where to find
* the item in the leaf (relative to the start of the data area)
*/
struct btrfs_item {
struct btrfs_disk_key key;
__le32 offset;
__le32 size;
} __attribute__ ((__packed__));
/*
* leaves have an item area and a data area:
* [item0, item1....itemN] [free space] [dataN...data1, data0]
*
* The data is separate from the items to get the keys closer together
* during searches.
*/
struct btrfs_leaf {
struct btrfs_header header;
struct btrfs_item items[];
} __attribute__ ((__packed__));
/*
* all non-leaf blocks are nodes, they hold only keys and pointers to
* other blocks
*/
struct btrfs_key_ptr {
struct btrfs_disk_key key;
__le64 blockptr;
__le64 generation;
} __attribute__ ((__packed__));
struct btrfs_node {
struct btrfs_header header;
struct btrfs_key_ptr ptrs[];
} __attribute__ ((__packed__));
/*
* btrfs_paths remember the path taken from the root down to the leaf.
* level 0 is always the leaf, and nodes[1...BTRFS_MAX_LEVEL] will point
* to any other levels that are present.
*
* The slots array records the index of the item or block pointer
* used while walking the tree.
*/
enum { READA_NONE, READA_BACK, READA_FORWARD };
struct btrfs_path {
struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
int slots[BTRFS_MAX_LEVEL];
/* if there is real range locking, this locks field will change */
u8 locks[BTRFS_MAX_LEVEL];
u8 reada;
/* keep some upper locks as we walk down */
u8 lowest_level;
/*
* set by btrfs_split_item, tells search_slot to keep all locks
* and to force calls to keep space in the nodes
*/
unsigned int search_for_split:1;
unsigned int keep_locks:1;
unsigned int skip_locking:1;
unsigned int leave_spinning:1;
unsigned int search_commit_root:1;
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
};
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
sizeof(struct btrfs_item))
struct btrfs_dev_replace {
u64 replace_state; /* see #define above */
time64_t time_started; /* seconds since 1-Jan-1970 */
time64_t time_stopped; /* seconds since 1-Jan-1970 */
atomic64_t num_write_errors;
atomic64_t num_uncorrectable_read_errors;
u64 cursor_left;
u64 committed_cursor_left;
u64 cursor_left_last_write_of_item;
u64 cursor_right;
u64 cont_reading_from_srcdev_mode; /* see #define above */
int is_valid;
int item_needs_writeback;
struct btrfs_device *srcdev;
struct btrfs_device *tgtdev;
struct mutex lock_finishing_cancel_unmount;
struct rw_semaphore rwsem;
struct btrfs_scrub_progress scrub_progress;
struct percpu_counter bio_counter;
wait_queue_head_t replace_wait;
};
/*
* free clusters are used to claim free space in relatively large chunks,
* allowing us to do less seeky writes. They are used for all metadata
* allocations. In ssd_spread mode they are also used for data allocations.
*/
struct btrfs_free_cluster {
spinlock_t lock;
spinlock_t refill_lock;
struct rb_root root;
/* largest extent in this cluster */
u64 max_size;
/* first extent starting offset */
u64 window_start;
/* We did a full search and couldn't create a cluster */
bool fragmented;
struct btrfs_block_group_cache *block_group;
/*
* when a cluster is allocated from a block group, we put the
* cluster onto a list in the block group so that it can
* be freed before the block group is freed.
*/
struct list_head block_group_list;
};
enum btrfs_caching_type {
BTRFS_CACHE_NO,
BTRFS_CACHE_STARTED,
BTRFS_CACHE_FAST,
BTRFS_CACHE_FINISHED,
BTRFS_CACHE_ERROR,
};
/*
* Tree to record all locked full stripes of a RAID5/6 block group
*/
struct btrfs_full_stripe_locks_tree {
struct rb_root root;
struct mutex lock;
};
/* delayed seq elem */
struct seq_list {
struct list_head list;
u64 seq;
};
#define SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
#define SEQ_LAST ((u64)-1)
enum btrfs_orphan_cleanup_state {
ORPHAN_CLEANUP_STARTED = 1,
ORPHAN_CLEANUP_DONE = 2,
};
void btrfs_init_async_reclaim_work(struct work_struct *work);
/* fs_info */
struct reloc_control;
struct btrfs_device;
struct btrfs_fs_devices;
struct btrfs_balance_control;
struct btrfs_delayed_root;
/*
* Block group or device which contains an active swapfile. Used for preventing
* unsafe operations while a swapfile is active.
*
* These are sorted on (ptr, inode) (note that a block group or device can
* contain more than one swapfile). We compare the pointer values because we
* don't actually care what the object is, we just need a quick check whether
* the object exists in the rbtree.
*/
struct btrfs_swapfile_pin {
struct rb_node node;
void *ptr;
struct inode *inode;
/*
* If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
* ptr points to a struct btrfs_device.
*/
bool is_block_group;
};
bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
enum {
BTRFS_FS_BARRIER,
BTRFS_FS_CLOSING_START,
BTRFS_FS_CLOSING_DONE,
BTRFS_FS_LOG_RECOVERING,
BTRFS_FS_OPEN,
BTRFS_FS_QUOTA_ENABLED,
BTRFS_FS_UPDATE_UUID_TREE_GEN,
BTRFS_FS_CREATING_FREE_SPACE_TREE,
BTRFS_FS_BTREE_ERR,
BTRFS_FS_LOG1_ERR,
BTRFS_FS_LOG2_ERR,
BTRFS_FS_QUOTA_OVERRIDE,
/* Used to record internally whether fs has been frozen */
BTRFS_FS_FROZEN,
/*
* Indicate that a whole-filesystem exclusive operation is running
* (device replace, resize, device add/delete, balance)
*/
BTRFS_FS_EXCL_OP,
/*
* To info transaction_kthread we need an immediate commit so it
* doesn't need to wait for commit_interval
*/
BTRFS_FS_NEED_ASYNC_COMMIT,
/*
* Indicate that balance has been set up from the ioctl and is in the
* main phase. The fs_info::balance_ctl is initialized.
* Set and cleared while holding fs_info::balance_mutex.
*/
BTRFS_FS_BALANCE_RUNNING,
/* Indicate that the cleaner thread is awake and doing something. */
BTRFS_FS_CLEANER_RUNNING,
/*
* The checksumming has an optimized version and is considered fast,
* so we don't need to offload checksums to workqueues.
*/
BTRFS_FS_CSUM_IMPL_FAST,
};
struct btrfs_fs_info {
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
unsigned long flags;
struct btrfs_root *extent_root;
struct btrfs_root *tree_root;
struct btrfs_root *chunk_root;
struct btrfs_root *dev_root;
struct btrfs_root *fs_root;
struct btrfs_root *csum_root;
struct btrfs_root *quota_root;
struct btrfs_root *uuid_root;
struct btrfs_root *free_space_root;
/* the log root tree is a directory of all the other log roots */
struct btrfs_root *log_root_tree;
spinlock_t fs_roots_radix_lock;
struct radix_tree_root fs_roots_radix;
/* block group cache stuff */
spinlock_t block_group_cache_lock;
u64 first_logical_byte;
struct rb_root block_group_cache_tree;
/* keep track of unallocated space */
atomic64_t free_chunk_space;
struct extent_io_tree freed_extents[2];
struct extent_io_tree *pinned_extents;
/* logical->physical extent mapping */
struct extent_map_tree mapping_tree;
/*
* block reservation for extent, checksum, root tree and
* delayed dir index item
*/
struct btrfs_block_rsv global_block_rsv;
/* block reservation for metadata operations */
struct btrfs_block_rsv trans_block_rsv;
/* block reservation for chunk tree */
struct btrfs_block_rsv chunk_block_rsv;
/* block reservation for delayed operations */
struct btrfs_block_rsv delayed_block_rsv;
/* block reservation for delayed refs */
struct btrfs_block_rsv delayed_refs_rsv;
struct btrfs_block_rsv empty_block_rsv;
u64 generation;
u64 last_trans_committed;
u64 avg_delayed_ref_runtime;
/*
* this is updated to the current trans every time a full commit
* is required instead of the faster short fsync log commits
*/
u64 last_trans_log_full_commit;
unsigned long mount_opt;
/*
* Track requests for actions that need to be done during transaction
* commit (like for some mount options).
*/
unsigned long pending_changes;
unsigned long compress_type:4;
unsigned int compress_level;
u32 commit_interval;
/*
* It is a suggestive number, the read side is safe even it gets a
* wrong number because we will write out the data into a regular
* extent. The write side(mount/remount) is under ->s_umount lock,
* so it is also safe.
*/
u64 max_inline;
struct btrfs_transaction *running_transaction;
wait_queue_head_t transaction_throttle;
wait_queue_head_t transaction_wait;
wait_queue_head_t transaction_blocked_wait;
wait_queue_head_t async_submit_wait;
/*
* Used to protect the incompat_flags, compat_flags, compat_ro_flags
* when they are updated.
*
* Because we do not clear the flags for ever, so we needn't use
* the lock on the read side.
*
* We also needn't use the lock when we mount the fs, because
* there is no other task which will update the flag.
*/
spinlock_t super_lock;
struct btrfs_super_block *super_copy;
struct btrfs_super_block *super_for_commit;
struct super_block *sb;
struct inode *btree_inode;
struct mutex tree_log_mutex;
struct mutex transaction_kthread_mutex;
struct mutex cleaner_mutex;
struct mutex chunk_mutex;
/*
* this is taken to make sure we don't set block groups ro after
* the free space cache has been allocated on them
*/
struct mutex ro_block_group_mutex;
/* this is used during read/modify/write to make sure
* no two ios are trying to mod the same stripe at the same
* time
*/
struct btrfs_stripe_hash_table *stripe_hash_table;
/*
* this protects the ordered operations list only while we are
* processing all of the entries on it. This way we make
* sure the commit code doesn't find the list temporarily empty
* because another function happens to be doing non-waiting preflush
* before jumping into the main commit.
*/
struct mutex ordered_operations_mutex;
struct rw_semaphore commit_root_sem;
struct rw_semaphore cleanup_work_sem;
struct rw_semaphore subvol_sem;
struct srcu_struct subvol_srcu;
spinlock_t trans_lock;
/*
* the reloc mutex goes with the trans lock, it is taken
* during commit to protect us from the relocation code
*/
struct mutex reloc_mutex;
struct list_head trans_list;
struct list_head dead_roots;
struct list_head caching_block_groups;
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
atomic_t nr_delayed_iputs;
wait_queue_head_t delayed_iputs_wait;
atomic64_t tree_mod_seq;
/* this protects tree_mod_log and tree_mod_seq_list */
rwlock_t tree_mod_log_lock;
struct rb_root tree_mod_log;
struct list_head tree_mod_seq_list;
atomic_t async_delalloc_pages;
/*
* this is used to protect the following list -- ordered_roots.
*/
spinlock_t ordered_root_lock;
/*
* all fs/file tree roots in which there are data=ordered extents
* pending writeback are added into this list.
*
* these can span multiple transactions and basically include
* every dirty data page that isn't from nodatacow
*/
struct list_head ordered_roots;
struct mutex delalloc_root_mutex;
spinlock_t delalloc_root_lock;
/* all fs/file tree roots that have delalloc inodes. */
struct list_head delalloc_roots;
/*
* there is a pool of worker threads for checksumming during writes
* and a pool for checksumming after reads. This is because readers
* can run with FS locks held, and the writers may be waiting for
* those locks. We don't want ordering in the pending list to cause
* deadlocks, and so the two are serviced separately.
*
* A third pool does submit_bio to avoid deadlocking with the other
* two
*/
struct btrfs_workqueue *workers;
struct btrfs_workqueue *delalloc_workers;
struct btrfs_workqueue *flush_workers;
struct btrfs_workqueue *endio_workers;
struct btrfs_workqueue *endio_meta_workers;
struct btrfs_workqueue *endio_raid56_workers;
struct btrfs_workqueue *endio_repair_workers;
struct btrfs_workqueue *rmw_workers;
struct btrfs_workqueue *endio_meta_write_workers;
struct btrfs_workqueue *endio_write_workers;
struct btrfs_workqueue *endio_freespace_worker;
struct btrfs_workqueue *submit_workers;
struct btrfs_workqueue *caching_workers;
struct btrfs_workqueue *readahead_workers;
/*
* fixup workers take dirty pages that didn't properly go through
* the cow mechanism and make them safe to write. It happens
* for the sys_munmap function call path
*/
struct btrfs_workqueue *fixup_workers;
struct btrfs_workqueue *delayed_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
u32 thread_pool_size;
struct kobject *space_info_kobj;
u64 total_pinned;
/* used to keep from writing metadata until there is a nice batch */
struct percpu_counter dirty_metadata_bytes;
struct percpu_counter delalloc_bytes;
struct percpu_counter dio_bytes;
s32 dirty_metadata_batch;
s32 delalloc_batch;
struct list_head dirty_cowonly_roots;
struct btrfs_fs_devices *fs_devices;
/*
* The space_info list is effectively read only after initial
* setup. It is populated at mount time and cleaned up after
* all block groups are removed. RCU is used to protect it.
*/
struct list_head space_info;
struct btrfs_space_info *data_sinfo;
struct reloc_control *reloc_ctl;
/* data_alloc_cluster is only used in ssd_spread mode */
struct btrfs_free_cluster data_alloc_cluster;
/* all metadata allocations go through this cluster */
struct btrfs_free_cluster meta_alloc_cluster;
/* auto defrag inodes go here */
spinlock_t defrag_inodes_lock;
struct rb_root defrag_inodes;
atomic_t defrag_running;
/* Used to protect avail_{data, metadata, system}_alloc_bits */
seqlock_t profiles_lock;
/*
* these three are in extended format (availability of single
* chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other
* types are denoted by corresponding BTRFS_BLOCK_GROUP_* bits)
*/
u64 avail_data_alloc_bits;
u64 avail_metadata_alloc_bits;
u64 avail_system_alloc_bits;
/* restriper state */
spinlock_t balance_lock;
struct mutex balance_mutex;
atomic_t balance_pause_req;
atomic_t balance_cancel_req;
struct btrfs_balance_control *balance_ctl;
wait_queue_head_t balance_wait_q;
u32 data_chunk_allocations;
u32 metadata_ratio;
void *bdev_holder;
/* private scrub information */
struct mutex scrub_lock;
atomic_t scrubs_running;
atomic_t scrub_pause_req;
atomic_t scrubs_paused;
atomic_t scrub_cancel_req;
wait_queue_head_t scrub_pause_wait;
/*
* The worker pointers are NULL iff the refcount is 0, ie. scrub is not
* running.
*/
refcount_t scrub_workers_refcnt;
struct btrfs_workqueue *scrub_workers;
struct btrfs_workqueue *scrub_wr_completion_workers;
struct btrfs_workqueue *scrub_parity_workers;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
u32 check_integrity_print_mask;
#endif
/* is qgroup tracking in a consistent state? */
u64 qgroup_flags;
/* holds configuration and tracking. Protected by qgroup_lock */
struct rb_root qgroup_tree;
spinlock_t qgroup_lock;
/*
* used to avoid frequently calling ulist_alloc()/ulist_free()
* when doing qgroup accounting, it must be protected by qgroup_lock.
*/
struct ulist *qgroup_ulist;
/* protect user change for quota operations */
struct mutex qgroup_ioctl_lock;
/* list of dirty qgroups to be written at next commit */
struct list_head dirty_qgroups;
/* used by qgroup for an efficient tree traversal */
u64 qgroup_seq;
/* qgroup rescan items */
struct mutex qgroup_rescan_lock; /* protects the progress item */
struct btrfs_key qgroup_rescan_progress;
struct btrfs_workqueue *qgroup_rescan_workers;
struct completion qgroup_rescan_completion;
struct btrfs_work qgroup_rescan_work;
bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */
/* filesystem state */
unsigned long fs_state;
struct btrfs_delayed_root *delayed_root;
/* readahead tree */
spinlock_t reada_lock;
struct radix_tree_root reada_tree;
/* readahead works cnt */
atomic_t reada_works_cnt;
/* Extent buffer radix tree */
spinlock_t buffer_lock;
struct radix_tree_root buffer_radix;
/* next backup root to be overwritten */
int backup_root_index;
/* device replace state */
struct btrfs_dev_replace dev_replace;
struct semaphore uuid_tree_rescan_sem;
/* Used to reclaim the metadata space in the background. */
struct work_struct async_reclaim_work;
spinlock_t unused_bgs_lock;
struct list_head unused_bgs;
struct mutex unused_bg_unpin_mutex;
struct mutex delete_unused_bgs_mutex;
/* Cached block sizes */
u32 nodesize;
u32 sectorsize;
u32 stripesize;
/* Block groups and devices containing active swapfiles. */
spinlock_t swapfile_pins_lock;
struct rb_root swapfile_pins;
struct crypto_shash *csum_shash;
/*
* Number of send operations in progress.
* Updated while holding fs_info::balance_mutex.
*/
int send_in_progress;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
struct rb_root block_tree;
#endif
};
static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
{
return sb->s_fs_info;
}
struct btrfs_subvolume_writers {
struct percpu_counter counter;
wait_queue_head_t wait;
};
/*
* The state of btrfs root
*/
enum {
/*
* btrfs_record_root_in_trans is a multi-step process, and it can race
* with the balancing code. But the race is very small, and only the
* first time the root is added to each transaction. So IN_TRANS_SETUP
* is used to tell us when more checks are required
*/
BTRFS_ROOT_IN_TRANS_SETUP,
BTRFS_ROOT_REF_COWS,
BTRFS_ROOT_TRACK_DIRTY,
BTRFS_ROOT_IN_RADIX,
BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
BTRFS_ROOT_DEFRAG_RUNNING,
BTRFS_ROOT_FORCE_COW,
BTRFS_ROOT_MULTI_LOG_TASKS,
BTRFS_ROOT_DIRTY,
BTRFS_ROOT_DELETING,
/*
* Reloc tree is orphan, only kept here for qgroup delayed subtree scan
*
* Set for the subvolume tree owning the reloc tree.
*/
BTRFS_ROOT_DEAD_RELOC_TREE,
/* Mark dead root stored on device whose cleanup needs to be resumed */
BTRFS_ROOT_DEAD_TREE,
/* The root has a log tree. Used only for subvolume roots. */
BTRFS_ROOT_HAS_LOG_TREE,
};
/*
* Record swapped tree blocks of a subvolume tree for delayed subtree trace
* code. For detail check comment in fs/btrfs/qgroup.c.
*/
struct btrfs_qgroup_swapped_blocks {
spinlock_t lock;
/* RM_EMPTY_ROOT() of above blocks[] */
bool swapped;
struct rb_root blocks[BTRFS_MAX_LEVEL];
};
/*
* in ram representation of the tree. extent_root is used for all allocations
* and for the extent tree extent_root root.
*/
struct btrfs_root {
struct extent_buffer *node;
struct extent_buffer *commit_root;
struct btrfs_root *log_root;
struct btrfs_root *reloc_root;
unsigned long state;
struct btrfs_root_item root_item;
struct btrfs_key root_key;
struct btrfs_fs_info *fs_info;
struct extent_io_tree dirty_log_pages;
struct mutex objectid_mutex;
spinlock_t accounting_lock;
struct btrfs_block_rsv *block_rsv;
/* free ino cache stuff */
struct btrfs_free_space_ctl *free_ino_ctl;
enum btrfs_caching_type ino_cache_state;
spinlock_t ino_cache_lock;
wait_queue_head_t ino_cache_wait;
struct btrfs_free_space_ctl *free_ino_pinned;
u64 ino_cache_progress;
struct inode *ino_cache_inode;
struct mutex log_mutex;
wait_queue_head_t log_writer_wait;
wait_queue_head_t log_commit_wait[2];
struct list_head log_ctxs[2];
/* Used only for log trees of subvolumes, not for the log root tree */
atomic_t log_writers;
atomic_t log_commit[2];
/* Used only for log trees of subvolumes, not for the log root tree */
atomic_t log_batch;
int log_transid;
/* No matter the commit succeeds or not*/
int log_transid_committed;
/* Just be updated when the commit succeeds. */
int last_log_commit;
pid_t log_start_pid;
u64 last_trans;
u32 type;
u64 highest_objectid;
u64 defrag_trans_start;
struct btrfs_key defrag_progress;
struct btrfs_key defrag_max;
/* the dirty list is only used by non-reference counted roots */
struct list_head dirty_list;
struct list_head root_list;
spinlock_t log_extents_lock[2];
struct list_head logged_list[2];
int orphan_cleanup_state;
spinlock_t inode_lock;
/* red-black tree that keeps track of in-memory inodes */
struct rb_root inode_tree;
/*
* radix tree that keeps track of delayed nodes of every inode,
* protected by inode_lock
*/
struct radix_tree_root delayed_nodes_tree;
/*
* right now this just gets used so that a root has its own devid
* for stat. It may be used for more later
*/
dev_t anon_dev;
spinlock_t root_item_lock;
refcount_t refs;
struct mutex delalloc_mutex;
spinlock_t delalloc_lock;
/*
* all of the inodes that have delalloc bytes. It is possible for
* this list to be empty even when there is still dirty data=ordered
* extents waiting to finish IO.
*/
struct list_head delalloc_inodes;
struct list_head delalloc_root;
u64 nr_delalloc_inodes;
struct mutex ordered_extent_mutex;
/*
* this is used by the balancing code to wait for all the pending
* ordered extents
*/
spinlock_t ordered_extent_lock;
/*
* all of the data=ordered extents pending writeback
* these can span multiple transactions and basically include
* every dirty data page that isn't from nodatacow
*/
struct list_head ordered_extents;
struct list_head ordered_root;
u64 nr_ordered_extents;
/*
* Not empty if this subvolume root has gone through tree block swap
* (relocation)
*
* Will be used by reloc_control::dirty_subvol_roots.
*/
struct list_head reloc_dirty_list;
/*
* Number of currently running SEND ioctls to prevent
* manipulation with the read-only status via SUBVOL_SETFLAGS
*/
int send_in_progress;
/*
* Number of currently running deduplication operations that have a
* destination inode belonging to this root. Protected by the lock
* root_item_lock.
*/
int dedupe_in_progress;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshotted;
atomic_t snapshot_force_cow;
/* For qgroup metadata reserved space */
spinlock_t qgroup_meta_rsv_lock;
u64 qgroup_meta_rsv_pertrans;
u64 qgroup_meta_rsv_prealloc;
/* Number of active swapfiles */
atomic_t nr_swapfiles;
/* Record pairs of swapped blocks for qgroup */
struct btrfs_qgroup_swapped_blocks swapped_blocks;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
u64 alloc_bytenr;
#endif
};
struct btrfs_clone_extent_info {
u64 disk_offset;
u64 disk_len;
u64 data_offset;
u64 data_len;
u64 file_offset;
char *extent_buf;
u32 item_size;
};
struct btrfs_file_private {
void *filldir_buf;
};
static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
{
return btrfs_sb(inode->i_sb)->sectorsize;
}
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
{
return info->nodesize - sizeof(struct btrfs_header);
}
#define BTRFS_LEAF_DATA_OFFSET offsetof(struct btrfs_leaf, items)
static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info)
{
return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item);
}
static inline u32 BTRFS_NODEPTRS_PER_BLOCK(const struct btrfs_fs_info *info)
{
return BTRFS_LEAF_DATA_SIZE(info) / sizeof(struct btrfs_key_ptr);
}
#define BTRFS_FILE_EXTENT_INLINE_DATA_START \
(offsetof(struct btrfs_file_extent_item, disk_bytenr))
static inline u32 BTRFS_MAX_INLINE_DATA_SIZE(const struct btrfs_fs_info *info)
{
return BTRFS_MAX_ITEM_SIZE(info) -
BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
{
return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item);
}
/*
* Flags for mount options.
*
* Note: don't forget to add new options to btrfs_show_options()
*/
#define BTRFS_MOUNT_NODATASUM (1 << 0)
#define BTRFS_MOUNT_NODATACOW (1 << 1)
#define BTRFS_MOUNT_NOBARRIER (1 << 2)
#define BTRFS_MOUNT_SSD (1 << 3)
#define BTRFS_MOUNT_DEGRADED (1 << 4)
#define BTRFS_MOUNT_COMPRESS (1 << 5)
#define BTRFS_MOUNT_NOTREELOG (1 << 6)
#define BTRFS_MOUNT_FLUSHONCOMMIT (1 << 7)
#define BTRFS_MOUNT_SSD_SPREAD (1 << 8)
#define BTRFS_MOUNT_NOSSD (1 << 9)
#define BTRFS_MOUNT_DISCARD (1 << 10)
#define BTRFS_MOUNT_FORCE_COMPRESS (1 << 11)
#define BTRFS_MOUNT_SPACE_CACHE (1 << 12)
#define BTRFS_MOUNT_CLEAR_CACHE (1 << 13)
#define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
#define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15)
#define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16)
#define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17)
#define BTRFS_MOUNT_USEBACKUPROOT (1 << 18)
#define BTRFS_MOUNT_SKIP_BALANCE (1 << 19)
#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20)
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
#define BTRFS_MOUNT_FRAGMENT_DATA (1 << 24)
#define BTRFS_MOUNT_FRAGMENT_METADATA (1 << 25)
#define BTRFS_MOUNT_FREE_SPACE_TREE (1 << 26)
#define BTRFS_MOUNT_NOLOGREPLAY (1 << 27)
#define BTRFS_MOUNT_REF_VERIFY (1 << 28)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define BTRFS_DEFAULT_MAX_INLINE (2048)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
#define btrfs_raw_test_opt(o, opt) ((o) & BTRFS_MOUNT_##opt)
#define btrfs_test_opt(fs_info, opt) ((fs_info)->mount_opt & \
BTRFS_MOUNT_##opt)
#define btrfs_set_and_info(fs_info, opt, fmt, args...) \
{ \
if (!btrfs_test_opt(fs_info, opt)) \
btrfs_info(fs_info, fmt, ##args); \
btrfs_set_opt(fs_info->mount_opt, opt); \
}
#define btrfs_clear_and_info(fs_info, opt, fmt, args...) \
{ \
if (btrfs_test_opt(fs_info, opt)) \
btrfs_info(fs_info, fmt, ##args); \
btrfs_clear_opt(fs_info->mount_opt, opt); \
}
/*
* Requests for changes that need to be done during transaction commit.
*
* Internal mount options that are used for special handling of the real
* mount options (eg. cannot be set during remount and have to be set during
* transaction commit)
*/
#define BTRFS_PENDING_SET_INODE_MAP_CACHE (0)
#define BTRFS_PENDING_CLEAR_INODE_MAP_CACHE (1)
#define BTRFS_PENDING_COMMIT (2)
#define btrfs_test_pending(info, opt) \
test_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
#define btrfs_set_pending(info, opt) \
set_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
#define btrfs_clear_pending(info, opt) \
clear_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
/*
* Helpers for setting pending mount option changes.
*
* Expects corresponding macros
* BTRFS_PENDING_SET_ and CLEAR_ + short mount option name
*/
#define btrfs_set_pending_and_info(info, opt, fmt, args...) \
do { \
if (!btrfs_raw_test_opt((info)->mount_opt, opt)) { \
btrfs_info((info), fmt, ##args); \
btrfs_set_pending((info), SET_##opt); \
btrfs_clear_pending((info), CLEAR_##opt); \
} \
} while(0)
#define btrfs_clear_pending_and_info(info, opt, fmt, args...) \
do { \
if (btrfs_raw_test_opt((info)->mount_opt, opt)) { \
btrfs_info((info), fmt, ##args); \
btrfs_set_pending((info), CLEAR_##opt); \
btrfs_clear_pending((info), SET_##opt); \
} \
} while(0)
/*
* Inode flags
*/
#define BTRFS_INODE_NODATASUM (1 << 0)
#define BTRFS_INODE_NODATACOW (1 << 1)
#define BTRFS_INODE_READONLY (1 << 2)
#define BTRFS_INODE_NOCOMPRESS (1 << 3)
#define BTRFS_INODE_PREALLOC (1 << 4)
#define BTRFS_INODE_SYNC (1 << 5)
#define BTRFS_INODE_IMMUTABLE (1 << 6)
#define BTRFS_INODE_APPEND (1 << 7)
#define BTRFS_INODE_NODUMP (1 << 8)
#define BTRFS_INODE_NOATIME (1 << 9)
#define BTRFS_INODE_DIRSYNC (1 << 10)
#define BTRFS_INODE_COMPRESS (1 << 11)
#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31)
#define BTRFS_INODE_FLAG_MASK \
(BTRFS_INODE_NODATASUM | \
BTRFS_INODE_NODATACOW | \
BTRFS_INODE_READONLY | \
BTRFS_INODE_NOCOMPRESS | \
BTRFS_INODE_PREALLOC | \
BTRFS_INODE_SYNC | \
BTRFS_INODE_IMMUTABLE | \
BTRFS_INODE_APPEND | \
BTRFS_INODE_NODUMP | \
BTRFS_INODE_NOATIME | \
BTRFS_INODE_DIRSYNC | \
BTRFS_INODE_COMPRESS | \
BTRFS_INODE_ROOT_ITEM_INIT)
struct btrfs_map_token {
const struct extent_buffer *eb;
char *kaddr;
unsigned long offset;
};
#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
((bytes) >> (fs_info)->sb->s_blocksize_bits)
static inline void btrfs_init_map_token(struct btrfs_map_token *token,
struct extent_buffer *eb)
{
token->eb = eb;
token->kaddr = NULL;
}
/* some macros to generate set/get functions for the struct fields. This
* assumes there is a lefoo_to_cpu for every type, so lets make a simple
* one for u8:
*/
#define le8_to_cpu(v) (v)
#define cpu_to_le8(v) (v)
#define __le8 u8
#define read_eb_member(eb, ptr, type, member, result) (\
read_extent_buffer(eb, (char *)(result), \
((unsigned long)(ptr)) + \
offsetof(type, member), \
sizeof(((type *)0)->member)))
#define write_eb_member(eb, ptr, type, member, result) (\
write_extent_buffer(eb, (char *)(result), \
((unsigned long)(ptr)) + \
offsetof(type, member), \
sizeof(((type *)0)->member)))
#define DECLARE_BTRFS_SETGET_BITS(bits) \
u##bits btrfs_get_token_##bits(const struct extent_buffer *eb, \
const void *ptr, unsigned long off, \
struct btrfs_map_token *token); \
void btrfs_set_token_##bits(struct extent_buffer *eb, const void *ptr, \
unsigned long off, u##bits val, \
struct btrfs_map_token *token); \
u##bits btrfs_get_##bits(const struct extent_buffer *eb, \
const void *ptr, unsigned long off); \
void btrfs_set_##bits(struct extent_buffer *eb, void *ptr, \
unsigned long off, u##bits val);
DECLARE_BTRFS_SETGET_BITS(8)
DECLARE_BTRFS_SETGET_BITS(16)
DECLARE_BTRFS_SETGET_BITS(32)
DECLARE_BTRFS_SETGET_BITS(64)
#define BTRFS_SETGET_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const struct extent_buffer *eb, \
const type *s) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
return btrfs_get_##bits(eb, s, offsetof(type, member)); \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, type *s, \
u##bits val) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
btrfs_set_##bits(eb, s, offsetof(type, member), val); \
} \
static inline u##bits btrfs_token_##name(const struct extent_buffer *eb,\
const type *s, \
struct btrfs_map_token *token) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
return btrfs_get_token_##bits(eb, s, offsetof(type, member), token); \
} \
static inline void btrfs_set_token_##name(struct extent_buffer *eb, \
type *s, u##bits val, \
struct btrfs_map_token *token) \
{ \
BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
btrfs_set_token_##bits(eb, s, offsetof(type, member), val, token); \
}
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const struct extent_buffer *eb) \
{ \
const type *p = page_address(eb->pages[0]); \
u##bits res = le##bits##_to_cpu(p->member); \
return res; \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, \
u##bits val) \
{ \
type *p = page_address(eb->pages[0]); \
p->member = cpu_to_le##bits(val); \
}
#define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const type *s) \
{ \
return le##bits##_to_cpu(s->member); \
} \
static inline void btrfs_set_##name(type *s, u##bits val) \
{ \
s->member = cpu_to_le##bits(val); \
}
static inline u64 btrfs_device_total_bytes(struct extent_buffer *eb,
struct btrfs_dev_item *s)
{
BUILD_BUG_ON(sizeof(u64) !=
sizeof(((struct btrfs_dev_item *)0))->total_bytes);
return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item,
total_bytes));
}
static inline void btrfs_set_device_total_bytes(struct extent_buffer *eb,
struct btrfs_dev_item *s,
u64 val)
{
BUILD_BUG_ON(sizeof(u64) !=
sizeof(((struct btrfs_dev_item *)0))->total_bytes);
WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize));
btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val);
}
BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64);
BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64);
BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32);
BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32);
BTRFS_SETGET_FUNCS(device_start_offset, struct btrfs_dev_item,
start_offset, 64);
BTRFS_SETGET_FUNCS(device_sector_size, struct btrfs_dev_item, sector_size, 32);
BTRFS_SETGET_FUNCS(device_id, struct btrfs_dev_item, devid, 64);
BTRFS_SETGET_FUNCS(device_group, struct btrfs_dev_item, dev_group, 32);
BTRFS_SETGET_FUNCS(device_seek_speed, struct btrfs_dev_item, seek_speed, 8);
BTRFS_SETGET_FUNCS(device_bandwidth, struct btrfs_dev_item, bandwidth, 8);
BTRFS_SETGET_FUNCS(device_generation, struct btrfs_dev_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_type, struct btrfs_dev_item, type, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_total_bytes, struct btrfs_dev_item,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_bytes_used, struct btrfs_dev_item,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_io_align, struct btrfs_dev_item,
io_align, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_io_width, struct btrfs_dev_item,
io_width, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_sector_size, struct btrfs_dev_item,
sector_size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_id, struct btrfs_dev_item, devid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_device_group, struct btrfs_dev_item,
dev_group, 32);
BTRFS_SETGET_STACK_FUNCS(stack_device_seek_speed, struct btrfs_dev_item,
seek_speed, 8);
BTRFS_SETGET_STACK_FUNCS(stack_device_bandwidth, struct btrfs_dev_item,
bandwidth, 8);
BTRFS_SETGET_STACK_FUNCS(stack_device_generation, struct btrfs_dev_item,
generation, 64);
static inline unsigned long btrfs_device_uuid(struct btrfs_dev_item *d)
{
return (unsigned long)d + offsetof(struct btrfs_dev_item, uuid);
}
static inline unsigned long btrfs_device_fsid(struct btrfs_dev_item *d)
{
return (unsigned long)d + offsetof(struct btrfs_dev_item, fsid);
}
BTRFS_SETGET_FUNCS(chunk_length, struct btrfs_chunk, length, 64);
BTRFS_SETGET_FUNCS(chunk_owner, struct btrfs_chunk, owner, 64);
BTRFS_SETGET_FUNCS(chunk_stripe_len, struct btrfs_chunk, stripe_len, 64);
BTRFS_SETGET_FUNCS(chunk_io_align, struct btrfs_chunk, io_align, 32);
BTRFS_SETGET_FUNCS(chunk_io_width, struct btrfs_chunk, io_width, 32);
BTRFS_SETGET_FUNCS(chunk_sector_size, struct btrfs_chunk, sector_size, 32);
BTRFS_SETGET_FUNCS(chunk_type, struct btrfs_chunk, type, 64);
BTRFS_SETGET_FUNCS(chunk_num_stripes, struct btrfs_chunk, num_stripes, 16);
BTRFS_SETGET_FUNCS(chunk_sub_stripes, struct btrfs_chunk, sub_stripes, 16);
BTRFS_SETGET_FUNCS(stripe_devid, struct btrfs_stripe, devid, 64);
BTRFS_SETGET_FUNCS(stripe_offset, struct btrfs_stripe, offset, 64);
static inline char *btrfs_stripe_dev_uuid(struct btrfs_stripe *s)
{
return (char *)s + offsetof(struct btrfs_stripe, dev_uuid);
}
BTRFS_SETGET_STACK_FUNCS(stack_chunk_length, struct btrfs_chunk, length, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_owner, struct btrfs_chunk, owner, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_stripe_len, struct btrfs_chunk,
stripe_len, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_align, struct btrfs_chunk,
io_align, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_io_width, struct btrfs_chunk,
io_width, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_sector_size, struct btrfs_chunk,
sector_size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_type, struct btrfs_chunk, type, 64);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_num_stripes, struct btrfs_chunk,
num_stripes, 16);
BTRFS_SETGET_STACK_FUNCS(stack_chunk_sub_stripes, struct btrfs_chunk,
sub_stripes, 16);
BTRFS_SETGET_STACK_FUNCS(stack_stripe_devid, struct btrfs_stripe, devid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_stripe_offset, struct btrfs_stripe, offset, 64);
static inline struct btrfs_stripe *btrfs_stripe_nr(struct btrfs_chunk *c,
int nr)
{
unsigned long offset = (unsigned long)c;
offset += offsetof(struct btrfs_chunk, stripe);
offset += nr * sizeof(struct btrfs_stripe);
return (struct btrfs_stripe *)offset;
}
static inline char *btrfs_stripe_dev_uuid_nr(struct btrfs_chunk *c, int nr)
{
return btrfs_stripe_dev_uuid(btrfs_stripe_nr(c, nr));
}
static inline u64 btrfs_stripe_offset_nr(struct extent_buffer *eb,
struct btrfs_chunk *c, int nr)
{
return btrfs_stripe_offset(eb, btrfs_stripe_nr(c, nr));
}
static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
struct btrfs_chunk *c, int nr)
{
return btrfs_stripe_devid(eb, btrfs_stripe_nr(c, nr));
}
/* struct btrfs_block_group_item */
BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
used, 64);
BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
used, 64);
BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
BTRFS_SETGET_FUNCS(disk_block_group_flags,
struct btrfs_block_group_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(block_group_flags,
struct btrfs_block_group_item, flags, 64);
/* struct btrfs_free_space_info */
BTRFS_SETGET_FUNCS(free_space_extent_count, struct btrfs_free_space_info,
extent_count, 32);
BTRFS_SETGET_FUNCS(free_space_flags, struct btrfs_free_space_info, flags, 32);
/* struct btrfs_inode_ref */
BTRFS_SETGET_FUNCS(inode_ref_name_len, struct btrfs_inode_ref, name_len, 16);
BTRFS_SETGET_FUNCS(inode_ref_index, struct btrfs_inode_ref, index, 64);
/* struct btrfs_inode_extref */
BTRFS_SETGET_FUNCS(inode_extref_parent, struct btrfs_inode_extref,
parent_objectid, 64);
BTRFS_SETGET_FUNCS(inode_extref_name_len, struct btrfs_inode_extref,
name_len, 16);
BTRFS_SETGET_FUNCS(inode_extref_index, struct btrfs_inode_extref, index, 64);
/* struct btrfs_inode_item */
BTRFS_SETGET_FUNCS(inode_generation, struct btrfs_inode_item, generation, 64);
BTRFS_SETGET_FUNCS(inode_sequence, struct btrfs_inode_item, sequence, 64);
BTRFS_SETGET_FUNCS(inode_transid, struct btrfs_inode_item, transid, 64);
BTRFS_SETGET_FUNCS(inode_size, struct btrfs_inode_item, size, 64);
BTRFS_SETGET_FUNCS(inode_nbytes, struct btrfs_inode_item, nbytes, 64);
BTRFS_SETGET_FUNCS(inode_block_group, struct btrfs_inode_item, block_group, 64);
BTRFS_SETGET_FUNCS(inode_nlink, struct btrfs_inode_item, nlink, 32);
BTRFS_SETGET_FUNCS(inode_uid, struct btrfs_inode_item, uid, 32);
BTRFS_SETGET_FUNCS(inode_gid, struct btrfs_inode_item, gid, 32);
BTRFS_SETGET_FUNCS(inode_mode, struct btrfs_inode_item, mode, 32);
BTRFS_SETGET_FUNCS(inode_rdev, struct btrfs_inode_item, rdev, 64);
BTRFS_SETGET_FUNCS(inode_flags, struct btrfs_inode_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item,
sequence, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item,
transid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item,
nbytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item,
block_group, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64);
BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
/* struct btrfs_dev_extent */
BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent,
chunk_tree, 64);
BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent,
chunk_objectid, 64);
BTRFS_SETGET_FUNCS(dev_extent_chunk_offset, struct btrfs_dev_extent,
chunk_offset, 64);
BTRFS_SETGET_FUNCS(dev_extent_length, struct btrfs_dev_extent, length, 64);
static inline unsigned long btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev)
{
unsigned long ptr = offsetof(struct btrfs_dev_extent, chunk_tree_uuid);
return (unsigned long)dev + ptr;
}
BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64);
BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item,
generation, 64);
BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64);
BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32);
BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8);
static inline void btrfs_tree_block_key(struct extent_buffer *eb,
struct btrfs_tree_block_info *item,
struct btrfs_disk_key *key)
{
read_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
}
static inline void btrfs_set_tree_block_key(struct extent_buffer *eb,
struct btrfs_tree_block_info *item,
struct btrfs_disk_key *key)
{
write_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
}
BTRFS_SETGET_FUNCS(extent_data_ref_root, struct btrfs_extent_data_ref,
root, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_objectid, struct btrfs_extent_data_ref,
objectid, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_offset, struct btrfs_extent_data_ref,
offset, 64);
BTRFS_SETGET_FUNCS(extent_data_ref_count, struct btrfs_extent_data_ref,
count, 32);
BTRFS_SETGET_FUNCS(shared_data_ref_count, struct btrfs_shared_data_ref,
count, 32);
BTRFS_SETGET_FUNCS(extent_inline_ref_type, struct btrfs_extent_inline_ref,
type, 8);
BTRFS_SETGET_FUNCS(extent_inline_ref_offset, struct btrfs_extent_inline_ref,
offset, 64);
static inline u32 btrfs_extent_inline_ref_size(int type)
{
if (type == BTRFS_TREE_BLOCK_REF_KEY ||
type == BTRFS_SHARED_BLOCK_REF_KEY)
return sizeof(struct btrfs_extent_inline_ref);
if (type == BTRFS_SHARED_DATA_REF_KEY)
return sizeof(struct btrfs_shared_data_ref) +
sizeof(struct btrfs_extent_inline_ref);
if (type == BTRFS_EXTENT_DATA_REF_KEY)
return sizeof(struct btrfs_extent_data_ref) +
offsetof(struct btrfs_extent_inline_ref, offset);
return 0;
}
BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64);
BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0,
generation, 64);
BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64);
BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32);
/* struct btrfs_node */
BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64);
BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_key_blockptr, struct btrfs_key_ptr,
blockptr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_key_generation, struct btrfs_key_ptr,
generation, 64);
static inline u64 btrfs_node_blockptr(struct extent_buffer *eb, int nr)
{
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
return btrfs_key_blockptr(eb, (struct btrfs_key_ptr *)ptr);
}
static inline void btrfs_set_node_blockptr(struct extent_buffer *eb,
int nr, u64 val)
{
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
btrfs_set_key_blockptr(eb, (struct btrfs_key_ptr *)ptr, val);
}
static inline u64 btrfs_node_ptr_generation(struct extent_buffer *eb, int nr)
{
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
return btrfs_key_generation(eb, (struct btrfs_key_ptr *)ptr);
}
static inline void btrfs_set_node_ptr_generation(struct extent_buffer *eb,
int nr, u64 val)
{
unsigned long ptr;
ptr = offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
btrfs_set_key_generation(eb, (struct btrfs_key_ptr *)ptr, val);
}
static inline unsigned long btrfs_node_key_ptr_offset(int nr)
{
return offsetof(struct btrfs_node, ptrs) +
sizeof(struct btrfs_key_ptr) * nr;
}
void btrfs_node_key(const struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr);
static inline void btrfs_set_node_key(struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
{
unsigned long ptr;
ptr = btrfs_node_key_ptr_offset(nr);
write_eb_member(eb, (struct btrfs_key_ptr *)ptr,
struct btrfs_key_ptr, key, disk_key);
}
/* struct btrfs_item */
BTRFS_SETGET_FUNCS(item_offset, struct btrfs_item, offset, 32);
BTRFS_SETGET_FUNCS(item_size, struct btrfs_item, size, 32);
BTRFS_SETGET_STACK_FUNCS(stack_item_offset, struct btrfs_item, offset, 32);
BTRFS_SETGET_STACK_FUNCS(stack_item_size, struct btrfs_item, size, 32);
static inline unsigned long btrfs_item_nr_offset(int nr)
{
return offsetof(struct btrfs_leaf, items) +
sizeof(struct btrfs_item) * nr;
}
static inline struct btrfs_item *btrfs_item_nr(int nr)
{
return (struct btrfs_item *)btrfs_item_nr_offset(nr);
}
static inline u32 btrfs_item_end(const struct extent_buffer *eb,
struct btrfs_item *item)
{
return btrfs_item_offset(eb, item) + btrfs_item_size(eb, item);
}
static inline u32 btrfs_item_end_nr(const struct extent_buffer *eb, int nr)
{
return btrfs_item_end(eb, btrfs_item_nr(nr));
}
static inline u32 btrfs_item_offset_nr(const struct extent_buffer *eb, int nr)
{
return btrfs_item_offset(eb, btrfs_item_nr(nr));
}
static inline u32 btrfs_item_size_nr(const struct extent_buffer *eb, int nr)
{
return btrfs_item_size(eb, btrfs_item_nr(nr));
}
static inline void btrfs_item_key(const struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
{
struct btrfs_item *item = btrfs_item_nr(nr);
read_eb_member(eb, item, struct btrfs_item, key, disk_key);
}
static inline void btrfs_set_item_key(struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
{
struct btrfs_item *item = btrfs_item_nr(nr);
write_eb_member(eb, item, struct btrfs_item, key, disk_key);
}
BTRFS_SETGET_FUNCS(dir_log_end, struct btrfs_dir_log_item, end, 64);
/*
* struct btrfs_root_ref
*/
BTRFS_SETGET_FUNCS(root_ref_dirid, struct btrfs_root_ref, dirid, 64);
BTRFS_SETGET_FUNCS(root_ref_sequence, struct btrfs_root_ref, sequence, 64);
BTRFS_SETGET_FUNCS(root_ref_name_len, struct btrfs_root_ref, name_len, 16);
/* struct btrfs_dir_item */
BTRFS_SETGET_FUNCS(dir_data_len, struct btrfs_dir_item, data_len, 16);
BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8);
BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16);
BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8);
BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item,
data_len, 16);
BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item,
name_len, 16);
BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item,
transid, 64);
static inline void btrfs_dir_item_key(const struct extent_buffer *eb,
const struct btrfs_dir_item *item,
struct btrfs_disk_key *key)
{
read_eb_member(eb, item, struct btrfs_dir_item, location, key);
}
static inline void btrfs_set_dir_item_key(struct extent_buffer *eb,
struct btrfs_dir_item *item,
const struct btrfs_disk_key *key)
{
write_eb_member(eb, item, struct btrfs_dir_item, location, key);
}
BTRFS_SETGET_FUNCS(free_space_entries, struct btrfs_free_space_header,
num_entries, 64);
BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header,
num_bitmaps, 64);
BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header,
generation, 64);
static inline void btrfs_free_space_key(const struct extent_buffer *eb,
const struct btrfs_free_space_header *h,
struct btrfs_disk_key *key)
{
read_eb_member(eb, h, struct btrfs_free_space_header, location, key);
}
static inline void btrfs_set_free_space_key(struct extent_buffer *eb,
struct btrfs_free_space_header *h,
const struct btrfs_disk_key *key)
{
write_eb_member(eb, h, struct btrfs_free_space_header, location, key);
}
/* struct btrfs_disk_key */
BTRFS_SETGET_STACK_FUNCS(disk_key_objectid, struct btrfs_disk_key,
objectid, 64);
BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64);
BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8);
static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu,
const struct btrfs_disk_key *disk)
{
cpu->offset = le64_to_cpu(disk->offset);
cpu->type = disk->type;
cpu->objectid = le64_to_cpu(disk->objectid);
}
static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk,
const struct btrfs_key *cpu)
{
disk->offset = cpu_to_le64(cpu->offset);
disk->type = cpu->type;
disk->objectid = cpu_to_le64(cpu->objectid);
}
static inline void btrfs_node_key_to_cpu(const struct extent_buffer *eb,
struct btrfs_key *key, int nr)
{
struct btrfs_disk_key disk_key;
btrfs_node_key(eb, &disk_key, nr);
btrfs_disk_key_to_cpu(key, &disk_key);
}
static inline void btrfs_item_key_to_cpu(const struct extent_buffer *eb,
struct btrfs_key *key, int nr)
{
struct btrfs_disk_key disk_key;
btrfs_item_key(eb, &disk_key, nr);
btrfs_disk_key_to_cpu(key, &disk_key);
}
static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb,
const struct btrfs_dir_item *item,
struct btrfs_key *key)
{
struct btrfs_disk_key disk_key;
btrfs_dir_item_key(eb, item, &disk_key);
btrfs_disk_key_to_cpu(key, &disk_key);
}
/* struct btrfs_header */
BTRFS_SETGET_HEADER_FUNCS(header_bytenr, struct btrfs_header, bytenr, 64);
BTRFS_SETGET_HEADER_FUNCS(header_generation, struct btrfs_header,
generation, 64);
BTRFS_SETGET_HEADER_FUNCS(header_owner, struct btrfs_header, owner, 64);
BTRFS_SETGET_HEADER_FUNCS(header_nritems, struct btrfs_header, nritems, 32);
BTRFS_SETGET_HEADER_FUNCS(header_flags, struct btrfs_header, flags, 64);
BTRFS_SETGET_HEADER_FUNCS(header_level, struct btrfs_header, level, 8);
BTRFS_SETGET_STACK_FUNCS(stack_header_generation, struct btrfs_header,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_header_owner, struct btrfs_header, owner, 64);
BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header,
nritems, 32);
BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64);
static inline int btrfs_header_flag(const struct extent_buffer *eb, u64 flag)
{
return (btrfs_header_flags(eb) & flag) == flag;
}
static inline void btrfs_set_header_flag(struct extent_buffer *eb, u64 flag)
{
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags | flag);
}
static inline void btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
{
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags & ~flag);
}
static inline int btrfs_header_backref_rev(const struct extent_buffer *eb)
{
u64 flags = btrfs_header_flags(eb);
return flags >> BTRFS_BACKREF_REV_SHIFT;
}
static inline void btrfs_set_header_backref_rev(struct extent_buffer *eb,
int rev)
{
u64 flags = btrfs_header_flags(eb);
flags &= ~BTRFS_BACKREF_REV_MASK;
flags |= (u64)rev << BTRFS_BACKREF_REV_SHIFT;
btrfs_set_header_flags(eb, flags);
}
static inline unsigned long btrfs_header_fsid(void)
{
return offsetof(struct btrfs_header, fsid);
}
static inline unsigned long btrfs_header_chunk_tree_uuid(const struct extent_buffer *eb)
{
return offsetof(struct btrfs_header, chunk_tree_uuid);
}
static inline int btrfs_is_leaf(const struct extent_buffer *eb)
{
return btrfs_header_level(eb) == 0;
}
/* struct btrfs_root_item */
BTRFS_SETGET_FUNCS(disk_root_generation, struct btrfs_root_item,
generation, 64);
BTRFS_SETGET_FUNCS(disk_root_refs, struct btrfs_root_item, refs, 32);
BTRFS_SETGET_FUNCS(disk_root_bytenr, struct btrfs_root_item, bytenr, 64);
BTRFS_SETGET_FUNCS(disk_root_level, struct btrfs_root_item, level, 8);
BTRFS_SETGET_STACK_FUNCS(root_generation, struct btrfs_root_item,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(root_bytenr, struct btrfs_root_item, bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(root_level, struct btrfs_root_item, level, 8);
BTRFS_SETGET_STACK_FUNCS(root_dirid, struct btrfs_root_item, root_dirid, 64);
BTRFS_SETGET_STACK_FUNCS(root_refs, struct btrfs_root_item, refs, 32);
BTRFS_SETGET_STACK_FUNCS(root_flags, struct btrfs_root_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(root_used, struct btrfs_root_item, bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64);
BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item,
last_snapshot, 64);
BTRFS_SETGET_STACK_FUNCS(root_generation_v2, struct btrfs_root_item,
generation_v2, 64);
BTRFS_SETGET_STACK_FUNCS(root_ctransid, struct btrfs_root_item,
ctransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_otransid, struct btrfs_root_item,
otransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item,
stransid, 64);
BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item,
rtransid, 64);
static inline bool btrfs_root_readonly(const struct btrfs_root *root)
{
return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0;
}
static inline bool btrfs_root_dead(const struct btrfs_root *root)
{
return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
}
/* struct btrfs_root_backup */
BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
tree_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_tree_root_gen, struct btrfs_root_backup,
tree_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_tree_root_level, struct btrfs_root_backup,
tree_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root, struct btrfs_root_backup,
chunk_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_gen, struct btrfs_root_backup,
chunk_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_level, struct btrfs_root_backup,
chunk_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root, struct btrfs_root_backup,
extent_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root_gen, struct btrfs_root_backup,
extent_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_extent_root_level, struct btrfs_root_backup,
extent_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root, struct btrfs_root_backup,
fs_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root_gen, struct btrfs_root_backup,
fs_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_fs_root_level, struct btrfs_root_backup,
fs_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root, struct btrfs_root_backup,
dev_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root_gen, struct btrfs_root_backup,
dev_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_dev_root_level, struct btrfs_root_backup,
dev_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root, struct btrfs_root_backup,
csum_root, 64);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root_gen, struct btrfs_root_backup,
csum_root_gen, 64);
BTRFS_SETGET_STACK_FUNCS(backup_csum_root_level, struct btrfs_root_backup,
csum_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(backup_total_bytes, struct btrfs_root_backup,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup,
num_devices, 64);
/* struct btrfs_balance_item */
BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64);
static inline void btrfs_balance_data(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
{
read_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
}
static inline void btrfs_set_balance_data(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
{
write_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
}
static inline void btrfs_balance_meta(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
{
read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
}
static inline void btrfs_set_balance_meta(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
{
write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
}
static inline void btrfs_balance_sys(const struct extent_buffer *eb,
const struct btrfs_balance_item *bi,
struct btrfs_disk_balance_args *ba)
{
read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
}
static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
struct btrfs_balance_item *bi,
const struct btrfs_disk_balance_args *ba)
{
write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
}
static inline void
btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
const struct btrfs_disk_balance_args *disk)
{
memset(cpu, 0, sizeof(*cpu));
cpu->profiles = le64_to_cpu(disk->profiles);
cpu->usage = le64_to_cpu(disk->usage);
cpu->devid = le64_to_cpu(disk->devid);
cpu->pstart = le64_to_cpu(disk->pstart);
cpu->pend = le64_to_cpu(disk->pend);
cpu->vstart = le64_to_cpu(disk->vstart);
cpu->vend = le64_to_cpu(disk->vend);
cpu->target = le64_to_cpu(disk->target);
cpu->flags = le64_to_cpu(disk->flags);
cpu->limit = le64_to_cpu(disk->limit);
cpu->stripes_min = le32_to_cpu(disk->stripes_min);
cpu->stripes_max = le32_to_cpu(disk->stripes_max);
}
static inline void
btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
const struct btrfs_balance_args *cpu)
{
memset(disk, 0, sizeof(*disk));
disk->profiles = cpu_to_le64(cpu->profiles);
disk->usage = cpu_to_le64(cpu->usage);
disk->devid = cpu_to_le64(cpu->devid);
disk->pstart = cpu_to_le64(cpu->pstart);
disk->pend = cpu_to_le64(cpu->pend);
disk->vstart = cpu_to_le64(cpu->vstart);
disk->vend = cpu_to_le64(cpu->vend);
disk->target = cpu_to_le64(cpu->target);
disk->flags = cpu_to_le64(cpu->flags);
disk->limit = cpu_to_le64(cpu->limit);
disk->stripes_min = cpu_to_le32(cpu->stripes_min);
disk->stripes_max = cpu_to_le32(cpu->stripes_max);
}
/* struct btrfs_super_block */
BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block,
generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_root, struct btrfs_super_block, root, 64);
BTRFS_SETGET_STACK_FUNCS(super_sys_array_size,
struct btrfs_super_block, sys_chunk_array_size, 32);
BTRFS_SETGET_STACK_FUNCS(super_chunk_root_generation,
struct btrfs_super_block, chunk_root_generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_root_level, struct btrfs_super_block,
root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_chunk_root, struct btrfs_super_block,
chunk_root, 64);
BTRFS_SETGET_STACK_FUNCS(super_chunk_root_level, struct btrfs_super_block,
chunk_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_log_root, struct btrfs_super_block,
log_root, 64);
BTRFS_SETGET_STACK_FUNCS(super_log_root_transid, struct btrfs_super_block,
log_root_transid, 64);
BTRFS_SETGET_STACK_FUNCS(super_log_root_level, struct btrfs_super_block,
log_root_level, 8);
BTRFS_SETGET_STACK_FUNCS(super_total_bytes, struct btrfs_super_block,
total_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(super_bytes_used, struct btrfs_super_block,
bytes_used, 64);
BTRFS_SETGET_STACK_FUNCS(super_sectorsize, struct btrfs_super_block,
sectorsize, 32);
BTRFS_SETGET_STACK_FUNCS(super_nodesize, struct btrfs_super_block,
nodesize, 32);
BTRFS_SETGET_STACK_FUNCS(super_stripesize, struct btrfs_super_block,
stripesize, 32);
BTRFS_SETGET_STACK_FUNCS(super_root_dir, struct btrfs_super_block,
root_dir_objectid, 64);
BTRFS_SETGET_STACK_FUNCS(super_num_devices, struct btrfs_super_block,
num_devices, 64);
BTRFS_SETGET_STACK_FUNCS(super_compat_flags, struct btrfs_super_block,
compat_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_compat_ro_flags, struct btrfs_super_block,
compat_ro_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_incompat_flags, struct btrfs_super_block,
incompat_flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block,
csum_type, 16);
BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block,
cache_generation, 64);
BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64);
BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
uuid_tree_generation, 64);
int btrfs_super_csum_size(const struct btrfs_super_block *s);
const char *btrfs_super_csum_name(u16 csum_type);
/*
* The leaf data grows from end-to-front in the node.
* this returns the address of the start of the last item,
* which is the stop of the leaf data stack
*/
static inline unsigned int leaf_data_end(const struct extent_buffer *leaf)
{
u32 nr = btrfs_header_nritems(leaf);
if (nr == 0)
return BTRFS_LEAF_DATA_SIZE(leaf->fs_info);
return btrfs_item_offset_nr(leaf, nr - 1);
}
/* struct btrfs_file_extent_item */
BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr,
struct btrfs_file_extent_item, disk_bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset,
struct btrfs_file_extent_item, offset, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation,
struct btrfs_file_extent_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes,
struct btrfs_file_extent_item, num_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_num_bytes,
struct btrfs_file_extent_item, disk_num_bytes, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression,
struct btrfs_file_extent_item, compression, 8);
static inline unsigned long
btrfs_file_extent_inline_start(const struct btrfs_file_extent_item *e)
{
return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize)
{
return BTRFS_FILE_EXTENT_INLINE_DATA_START + datasize;
}
BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item,
disk_bytenr, 64);
BTRFS_SETGET_FUNCS(file_extent_generation, struct btrfs_file_extent_item,
generation, 64);
BTRFS_SETGET_FUNCS(file_extent_disk_num_bytes, struct btrfs_file_extent_item,
disk_num_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_offset, struct btrfs_file_extent_item,
offset, 64);
BTRFS_SETGET_FUNCS(file_extent_num_bytes, struct btrfs_file_extent_item,
num_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_ram_bytes, struct btrfs_file_extent_item,
ram_bytes, 64);
BTRFS_SETGET_FUNCS(file_extent_compression, struct btrfs_file_extent_item,
compression, 8);
BTRFS_SETGET_FUNCS(file_extent_encryption, struct btrfs_file_extent_item,
encryption, 8);
BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
other_encoding, 16);
/*
* this returns the number of bytes used by the item on disk, minus the
* size of any extent headers. If a file is compressed on disk, this is
* the compressed size
*/
static inline u32 btrfs_file_extent_inline_item_len(
const struct extent_buffer *eb,
struct btrfs_item *e)
{
return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
/* btrfs_qgroup_status_item */
BTRFS_SETGET_FUNCS(qgroup_status_generation, struct btrfs_qgroup_status_item,
generation, 64);
BTRFS_SETGET_FUNCS(qgroup_status_version, struct btrfs_qgroup_status_item,
version, 64);
BTRFS_SETGET_FUNCS(qgroup_status_flags, struct btrfs_qgroup_status_item,
flags, 64);
BTRFS_SETGET_FUNCS(qgroup_status_rescan, struct btrfs_qgroup_status_item,
rescan, 64);
/* btrfs_qgroup_info_item */
BTRFS_SETGET_FUNCS(qgroup_info_generation, struct btrfs_qgroup_info_item,
generation, 64);
BTRFS_SETGET_FUNCS(qgroup_info_rfer, struct btrfs_qgroup_info_item, rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_info_rfer_cmpr, struct btrfs_qgroup_info_item,
rfer_cmpr, 64);
BTRFS_SETGET_FUNCS(qgroup_info_excl, struct btrfs_qgroup_info_item, excl, 64);
BTRFS_SETGET_FUNCS(qgroup_info_excl_cmpr, struct btrfs_qgroup_info_item,
excl_cmpr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_generation,
struct btrfs_qgroup_info_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_rfer, struct btrfs_qgroup_info_item,
rfer, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_rfer_cmpr,
struct btrfs_qgroup_info_item, rfer_cmpr, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_excl, struct btrfs_qgroup_info_item,
excl, 64);
BTRFS_SETGET_STACK_FUNCS(stack_qgroup_info_excl_cmpr,
struct btrfs_qgroup_info_item, excl_cmpr, 64);
/* btrfs_qgroup_limit_item */
BTRFS_SETGET_FUNCS(qgroup_limit_flags, struct btrfs_qgroup_limit_item,
flags, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_max_rfer, struct btrfs_qgroup_limit_item,
max_rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_max_excl, struct btrfs_qgroup_limit_item,
max_excl, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_rsv_rfer, struct btrfs_qgroup_limit_item,
rsv_rfer, 64);
BTRFS_SETGET_FUNCS(qgroup_limit_rsv_excl, struct btrfs_qgroup_limit_item,
rsv_excl, 64);
/* btrfs_dev_replace_item */
BTRFS_SETGET_FUNCS(dev_replace_src_devid,
struct btrfs_dev_replace_item, src_devid, 64);
BTRFS_SETGET_FUNCS(dev_replace_cont_reading_from_srcdev_mode,
struct btrfs_dev_replace_item, cont_reading_from_srcdev_mode,
64);
BTRFS_SETGET_FUNCS(dev_replace_replace_state, struct btrfs_dev_replace_item,
replace_state, 64);
BTRFS_SETGET_FUNCS(dev_replace_time_started, struct btrfs_dev_replace_item,
time_started, 64);
BTRFS_SETGET_FUNCS(dev_replace_time_stopped, struct btrfs_dev_replace_item,
time_stopped, 64);
BTRFS_SETGET_FUNCS(dev_replace_num_write_errors, struct btrfs_dev_replace_item,
num_write_errors, 64);
BTRFS_SETGET_FUNCS(dev_replace_num_uncorrectable_read_errors,
struct btrfs_dev_replace_item, num_uncorrectable_read_errors,
64);
BTRFS_SETGET_FUNCS(dev_replace_cursor_left, struct btrfs_dev_replace_item,
cursor_left, 64);
BTRFS_SETGET_FUNCS(dev_replace_cursor_right, struct btrfs_dev_replace_item,
cursor_right, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_src_devid,
struct btrfs_dev_replace_item, src_devid, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cont_reading_from_srcdev_mode,
struct btrfs_dev_replace_item,
cont_reading_from_srcdev_mode, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_replace_state,
struct btrfs_dev_replace_item, replace_state, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_time_started,
struct btrfs_dev_replace_item, time_started, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_time_stopped,
struct btrfs_dev_replace_item, time_stopped, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_num_write_errors,
struct btrfs_dev_replace_item, num_write_errors, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_num_uncorrectable_read_errors,
struct btrfs_dev_replace_item,
num_uncorrectable_read_errors, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_left,
struct btrfs_dev_replace_item, cursor_left, 64);
BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_right,
struct btrfs_dev_replace_item, cursor_right, 64);
/* helper function to cast into the data area of the leaf. */
#define btrfs_item_ptr(leaf, slot, type) \
((type *)(BTRFS_LEAF_DATA_OFFSET + \
btrfs_item_offset_nr(leaf, slot)))
#define btrfs_item_ptr_offset(leaf, slot) \
((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \
btrfs_item_offset_nr(leaf, slot)))
static inline u32 btrfs_crc32c(u32 crc, const void *address, unsigned length)
{
return crc32c(crc, address, length);
}
static inline void btrfs_crc32c_final(u32 crc, u8 *result)
{
put_unaligned_le32(~crc, result);
}
static inline u64 btrfs_name_hash(const char *name, int len)
{
return crc32c((u32)~1, name, len);
}
/*
* Figure the key offset of an extended inode ref
*/
static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name,
int len)
{
return (u64) crc32c(parent_objectid, name, len);
}
static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
{
return mapping_gfp_constraint(mapping, ~__GFP_FS);
}
/* extent-tree.c */
enum btrfs_inline_ref_type {
BTRFS_REF_TYPE_INVALID,
BTRFS_REF_TYPE_BLOCK,
BTRFS_REF_TYPE_DATA,
BTRFS_REF_TYPE_ANY,
};
int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
struct btrfs_extent_inline_ref *iref,
enum btrfs_inline_ref_type is_data);
u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset);
u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
/*
* Use this if we would be adding new items, as we could split nodes as we cow
* down the tree.
*/
static inline u64 btrfs_calc_insert_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
{
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
}
/*
* Doing a truncate or a modification won't result in new nodes or leaves, just
* what we need for COW.
*/
static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
{
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}
int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 num_bytes);
void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
unsigned long count);
void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head);
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 offset, int metadata, u64 *refs, u64 *flags);
int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num, int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes);
int btrfs_exclude_logged_extents(struct extent_buffer *eb);
int btrfs_cross_ref_exist(struct btrfs_root *root,
u64 objectid, u64 offset, u64 bytenr, bool strict);
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 parent, u64 root_objectid,
const struct btrfs_disk_key *key,
int level, u64 hint,
u64 empty_size);
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
u64 parent, int last_ref);
int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 owner,
u64 offset, u64 ram_bytes,
struct btrfs_key *ins);
int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref);
int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, u64 flags,
int level, int is_data);
int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);
int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len, int delalloc);
int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len);
void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
struct btrfs_ref *generic_ref);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
/* If we are in the transaction, we can't flush anything.*/
BTRFS_RESERVE_NO_FLUSH,
/*
* Flushing delalloc may cause deadlock somewhere, in this
* case, use FLUSH LIMIT
*/
BTRFS_RESERVE_FLUSH_LIMIT,
BTRFS_RESERVE_FLUSH_EVICT,
BTRFS_RESERVE_FLUSH_ALL,
BTRFS_RESERVE_FLUSH_ALL_STEAL,
};
enum btrfs_flush_state {
FLUSH_DELAYED_ITEMS_NR = 1,
FLUSH_DELAYED_ITEMS = 2,
FLUSH_DELAYED_REFS_NR = 3,
FLUSH_DELAYED_REFS = 4,
FLUSH_DELALLOC = 5,
FLUSH_DELALLOC_WAIT = 6,
ALLOC_CHUNK = 7,
ALLOC_CHUNK_FORCE = 8,
RUN_DELAYED_IPUTS = 9,
COMMIT_TRANS = 10,
};
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
u64 start, u64 end);
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 num_bytes, u64 *actual_bytes);
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
int level, int *slot);
int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
int btrfs_previous_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid,
int type);
int btrfs_previous_extent_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid);
void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
struct btrfs_path *path,
const struct btrfs_key *new_key);
struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *key, int lowest_level,
u64 min_trans);
int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
struct btrfs_path *path,
u64 min_trans);
struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
int slot);
int btrfs_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *buf,
struct extent_buffer *parent, int parent_slot,
struct extent_buffer **cow_ret);
int btrfs_copy_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
struct extent_buffer **cow_ret, u64 new_root_objectid);
int btrfs_block_can_be_shared(struct btrfs_root *root,
struct extent_buffer *buf);
void btrfs_extend_item(struct btrfs_path *path, u32 data_size);
void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end);
int btrfs_split_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
const struct btrfs_key *new_key,
unsigned long split_offset);
int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
const struct btrfs_key *new_key);
int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key);
int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
const struct btrfs_key *key, struct btrfs_path *p,
int ins_len, int cow);
int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
struct btrfs_path *p, u64 time_seq);
int btrfs_search_slot_for_read(struct btrfs_root *root,
const struct btrfs_key *key,
struct btrfs_path *p, int find_higher,
int return_any);
int btrfs_realloc_node(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *parent,
int start_slot, u64 *last_ret,
struct btrfs_key *progress);
void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int slot, int nr);
static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path)
{
return btrfs_del_items(trans, root, path, path->slots[0], 1);
}
void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
const struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr);
int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
const struct btrfs_key *key, void *data, u32 data_size);
int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
const struct btrfs_key *cpu_key, u32 *data_size,
int nr);
static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
const struct btrfs_key *key,
u32 data_size)
{
return btrfs_insert_empty_items(trans, root, path, key, &data_size, 1);
}
int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
u64 time_seq);
static inline int btrfs_next_old_item(struct btrfs_root *root,
struct btrfs_path *p, u64 time_seq)
{
++p->slots[0];
if (p->slots[0] >= btrfs_header_nritems(p->nodes[0]))
return btrfs_next_old_leaf(root, p, time_seq);
return 0;
}
static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
{
return btrfs_next_old_item(root, p, 0);
}
int btrfs_leaf_free_space(struct extent_buffer *leaf);
int __must_check btrfs_drop_snapshot(struct btrfs_root *root,
struct btrfs_block_rsv *block_rsv,
int update_ref, int for_reloc);
int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *node,
struct extent_buffer *parent);
static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
{
/*
* Do it this way so we only ever do one test_bit in the normal case.
*/
if (test_bit(BTRFS_FS_CLOSING_START, &fs_info->flags)) {
if (test_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags))
return 2;
return 1;
}
return 0;
}
/*
* If we remount the fs to be R/O or umount the fs, the cleaner needn't do
* anything except sleeping. This function is used to check the status of
* the fs.
*/
static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
{
return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
}
static inline void free_fs_info(struct btrfs_fs_info *fs_info)
{
kfree(fs_info->balance_ctl);
kfree(fs_info->delayed_root);
kfree(fs_info->extent_root);
kfree(fs_info->tree_root);
kfree(fs_info->chunk_root);
kfree(fs_info->dev_root);
kfree(fs_info->csum_root);
kfree(fs_info->quota_root);
kfree(fs_info->uuid_root);
kfree(fs_info->free_space_root);
kfree(fs_info->super_copy);
kfree(fs_info->super_for_commit);
kvfree(fs_info);
}
/* tree mod log functions from ctree.c */
u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem);
void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem);
int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
/* root-item.c */
int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
u64 ref_id, u64 dirid, u64 sequence, const char *name,
int name_len);
int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
u64 ref_id, u64 dirid, u64 *sequence, const char *name,
int name_len);
int btrfs_del_root(struct btrfs_trans_handle *trans,
const struct btrfs_key *key);
int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
const struct btrfs_key *key,
struct btrfs_root_item *item);
int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_key *key,
struct btrfs_root_item *item);
int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
struct btrfs_path *path, struct btrfs_root_item *root_item,
struct btrfs_key *root_key);
int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info);
void btrfs_set_root_node(struct btrfs_root_item *item,
struct extent_buffer *node);
void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
void btrfs_update_root_times(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
/* uuid-tree.c */
int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid);
int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid);
int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
u64));
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name,
int name_len, struct btrfs_inode *dir,
struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 dir,
const char *name, int name_len,
int mod);
struct btrfs_dir_item *
btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 dir,
u64 objectid, const char *name, int name_len,
int mod);
struct btrfs_dir_item *
btrfs_search_dir_index_item(struct btrfs_root *root,
struct btrfs_path *path, u64 dirid,
const char *name, int name_len);
int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct btrfs_dir_item *di);
int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid,
const char *name, u16 name_len,
const void *data, u16 data_len);
struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 dir,
const char *name, u16 name_len,
int mod);
struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
struct btrfs_path *path,
const char *name,
int name_len);
/* orphan.c */
int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 offset);
int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 offset);
int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset);
/* inode-item.c */
int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const char *name, int name_len,
u64 inode_objectid, u64 ref_objectid, u64 index);
int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const char *name, int name_len,
u64 inode_objectid, u64 ref_objectid, u64 *index);
int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid);
int btrfs_lookup_inode(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_path *path,
struct btrfs_key *location, int mod);
struct btrfs_inode_extref *
btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
const char *name, int name_len,
u64 inode_objectid, u64 ref_objectid, int ins_len,
int cow);
struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf,
int slot, const char *name,
int name_len);
struct btrfs_inode_extref *btrfs_find_name_in_ext_backref(
struct extent_buffer *leaf, int slot, u64 ref_objectid,
const char *name, int name_len);
/* file-item.c */
struct btrfs_dio_private;
int btrfs_del_csums(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 len);
blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
u8 *dst);
blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio,
u64 logical_offset);
int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 objectid, u64 pos,
u64 disk_offset, u64 disk_num_bytes,
u64 num_bytes, u64 offset, u64 ram_bytes,
u8 compression, u8 encryption, u16 other_encoding);
int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid,
u64 bytenr, int mod);
int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_ordered_sum *sums);
blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
u64 file_start, int contig);
int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
struct list_head *list, int search_commit);
void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
const struct btrfs_path *path,
struct btrfs_file_extent_item *fi,
const bool new_inline,
struct extent_map *em);
/* inode.c */
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
u64 start, u64 len);
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes, bool strict);
void __btrfs_del_delalloc_inode(struct btrfs_root *root,
struct btrfs_inode *inode);
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_inode *dir, struct btrfs_inode *inode,
const char *name, int name_len);
int btrfs_add_link(struct btrfs_trans_handle *trans,
struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
const char *name, int name_len, int add_backref, u64 index);
int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front);
int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode, u64 new_size,
u32 min_type);
int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
unsigned int extra_bits,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root,
struct btrfs_root *parent_root,
u64 new_dirid);
void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
unsigned *bits);
void btrfs_clear_delalloc_extent(struct inode *inode,
struct extent_state *state, unsigned *bits);
void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
struct extent_state *other);
void btrfs_split_delalloc_extent(struct inode *inode,
struct extent_state *orig, u64 split);
int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio,
unsigned long bio_flags);
void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
void btrfs_free_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
int __init btrfs_init_cachep(void);
void __cold btrfs_destroy_cachep(void);
struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *new,
struct btrfs_path *path);
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *was_new);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 end, int create);
int btrfs_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode);
int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode);
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode);
int btrfs_orphan_cleanup(struct btrfs_root *root);
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
int btrfs_prealloc_file_range_trans(struct inode *inode,
struct btrfs_trans_handle *trans, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started, unsigned long *nr_written,
struct writeback_control *wbc);
int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
u64 end, int uptodate);
extern const struct dentry_operations btrfs_dentry_operations;
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
int btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file *file,
struct btrfs_ioctl_defrag_range_args *range,
u64 newer_than, unsigned long max_pages);
void btrfs_get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space);
void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs);
/* file.c */
int __init btrfs_auto_defrag_init(void);
void __cold btrfs_auto_defrag_exit(void);
int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode);
int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
int skip_pinned);
extern const struct file_operations btrfs_file_operations;
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
struct btrfs_path *path, u64 start, u64 end,
u64 *drop_end, int drop_cache,
int replace_extent,
u32 extent_item_size,
int *key_inserted);
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode, u64 start,
u64 end, int drop_cache);
int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path,
const u64 start, const u64 end,
struct btrfs_clone_extent_info *clone_info,
struct btrfs_trans_handle **trans_out);
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode, u64 start, u64 end);
int btrfs_release_file(struct inode *inode, struct file *file);
int btrfs_dirty_pages(struct inode *inode, struct page **pages,
size_t num_pages, loff_t pos, size_t write_bytes,
struct extent_state **cached);
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos,
size_t *write_bytes);
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
/* super.c */
int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
unsigned long new_flags);
int btrfs_sync_fs(struct super_block *sb, int wait);
char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
u64 subvol_objectid);
static inline __printf(2, 3) __cold
void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
{
}
#ifdef CONFIG_PRINTK
__printf(2, 3)
__cold
void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...);
#else
#define btrfs_printk(fs_info, fmt, args...) \
btrfs_no_printk(fs_info, fmt, ##args)
#endif
#define btrfs_emerg(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_EMERG fmt, ##args)
#define btrfs_alert(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_ALERT fmt, ##args)
#define btrfs_crit(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_CRIT fmt, ##args)
#define btrfs_err(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_ERR fmt, ##args)
#define btrfs_warn(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_WARNING fmt, ##args)
#define btrfs_notice(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_INFO fmt, ##args)
/*
* Wrappers that use printk_in_rcu
*/
#define btrfs_emerg_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_EMERG fmt, ##args)
#define btrfs_alert_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_ALERT fmt, ##args)
#define btrfs_crit_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_CRIT fmt, ##args)
#define btrfs_err_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_ERR fmt, ##args)
#define btrfs_warn_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_WARNING fmt, ##args)
#define btrfs_notice_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_INFO fmt, ##args)
/*
* Wrappers that use a ratelimited printk_in_rcu
*/
#define btrfs_emerg_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_EMERG fmt, ##args)
#define btrfs_alert_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_ALERT fmt, ##args)
#define btrfs_crit_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_CRIT fmt, ##args)
#define btrfs_err_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_ERR fmt, ##args)
#define btrfs_warn_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_WARNING fmt, ##args)
#define btrfs_notice_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_INFO fmt, ##args)
/*
* Wrappers that use a ratelimited printk
*/
#define btrfs_emerg_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_EMERG fmt, ##args)
#define btrfs_alert_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_ALERT fmt, ##args)
#define btrfs_crit_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_CRIT fmt, ##args)
#define btrfs_err_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_ERR fmt, ##args)
#define btrfs_warn_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_WARNING fmt, ##args)
#define btrfs_notice_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_INFO fmt, ##args)
#if defined(CONFIG_DYNAMIC_DEBUG)
#define btrfs_debug(fs_info, fmt, args...) \
_dynamic_func_call_no_desc(fmt, btrfs_printk, \
fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
_dynamic_func_call_no_desc(fmt, btrfs_printk_in_rcu, \
fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
_dynamic_func_call_no_desc(fmt, btrfs_printk_rl_in_rcu, \
fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl(fs_info, fmt, args...) \
_dynamic_func_call_no_desc(fmt, btrfs_printk_ratelimited, \
fs_info, KERN_DEBUG fmt, ##args)
#elif defined(DEBUG)
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
btrfs_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
btrfs_printk_rl_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl(fs_info, fmt, args...) \
btrfs_printk_ratelimited(fs_info, KERN_DEBUG fmt, ##args)
#else
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl(fs_info, fmt, args...) \
btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args)
#endif
#define btrfs_printk_in_rcu(fs_info, fmt, args...) \
do { \
rcu_read_lock(); \
btrfs_printk(fs_info, fmt, ##args); \
rcu_read_unlock(); \
} while (0)
#define btrfs_no_printk_in_rcu(fs_info, fmt, args...) \
do { \
rcu_read_lock(); \
btrfs_no_printk(fs_info, fmt, ##args); \
rcu_read_unlock(); \
} while (0)
#define btrfs_printk_ratelimited(fs_info, fmt, args...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
if (__ratelimit(&_rs)) \
btrfs_printk(fs_info, fmt, ##args); \
} while (0)
#define btrfs_printk_rl_in_rcu(fs_info, fmt, args...) \
do { \
rcu_read_lock(); \
btrfs_printk_ratelimited(fs_info, fmt, ##args); \
rcu_read_unlock(); \
} while (0)
#ifdef CONFIG_BTRFS_ASSERT
__cold __noreturn
static inline void assertfail(const char *expr, const char *file, int line)
{
pr_err("assertion failed: %s, in %s:%d\n", expr, file, line);
BUG();
}
#define ASSERT(expr) \
(likely(expr) ? (void)0 : assertfail(#expr, __FILE__, __LINE__))
#else
static inline void assertfail(const char *expr, const char* file, int line) { }
#define ASSERT(expr) (void)(expr)
#endif
/*
* Use that for functions that are conditionally exported for sanity tests but
* otherwise static
*/
#ifndef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
#define EXPORT_FOR_TESTS static
#else
#define EXPORT_FOR_TESTS
#endif
__cold
static inline void btrfs_print_v0_err(struct btrfs_fs_info *fs_info)
{
btrfs_err(fs_info,
"Unsupported V0 extent filesystem detected. Aborting. Please re-create your filesystem with a newer kernel");
}
__printf(5, 6)
__cold
void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
const char *btrfs_decode_error(int errno);
__cold
void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
const char *function,
unsigned int line, int errno);
/*
* Call btrfs_abort_transaction as early as possible when an error condition is
* detected, that way the exact line number is reported.
*/
#define btrfs_abort_transaction(trans, errno) \
do { \
/* Report first abort since mount */ \
if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
&((trans)->fs_info->fs_state))) { \
if ((errno) != -EIO && (errno) != -EROFS) { \
WARN(1, KERN_DEBUG \
"BTRFS: Transaction aborted (error %d)\n", \
(errno)); \
} else { \
btrfs_debug((trans)->fs_info, \
"Transaction aborted (error %d)", \
(errno)); \
} \
} \
__btrfs_abort_transaction((trans), __func__, \
__LINE__, (errno)); \
} while (0)
#define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \
do { \
__btrfs_handle_fs_error((fs_info), __func__, __LINE__, \
(errno), fmt, ##args); \
} while (0)
__printf(5, 6)
__cold
void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
/*
* If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
* will panic(). Otherwise we BUG() here.
*/
#define btrfs_panic(fs_info, errno, fmt, args...) \
do { \
__btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
BUG(); \
} while (0)
/* compatibility and incompatibility defines */
#define btrfs_set_fs_incompat(__fs_info, opt) \
__btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt, \
#opt)
static inline void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info,
u64 flag, const char* name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_incompat_flags(disk_super);
if (!(features & flag)) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_incompat_flags(disk_super);
if (!(features & flag)) {
features |= flag;
btrfs_set_super_incompat_flags(disk_super, features);
btrfs_info(fs_info,
"setting incompat feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_clear_fs_incompat(__fs_info, opt) \
__btrfs_clear_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt, \
#opt)
static inline void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info,
u64 flag, const char* name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_incompat_flags(disk_super);
if (features & flag) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_incompat_flags(disk_super);
if (features & flag) {
features &= ~flag;
btrfs_set_super_incompat_flags(disk_super, features);
btrfs_info(fs_info,
"clearing incompat feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_fs_incompat(fs_info, opt) \
__btrfs_fs_incompat((fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
static inline bool __btrfs_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag)
{
struct btrfs_super_block *disk_super;
disk_super = fs_info->super_copy;
return !!(btrfs_super_incompat_flags(disk_super) & flag);
}
#define btrfs_set_fs_compat_ro(__fs_info, opt) \
__btrfs_set_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt, \
#opt)
static inline void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info,
u64 flag, const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_compat_ro_flags(disk_super);
if (!(features & flag)) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_compat_ro_flags(disk_super);
if (!(features & flag)) {
features |= flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
btrfs_info(fs_info,
"setting compat-ro feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_clear_fs_compat_ro(__fs_info, opt) \
__btrfs_clear_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt, \
#opt)
static inline void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info,
u64 flag, const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
disk_super = fs_info->super_copy;
features = btrfs_super_compat_ro_flags(disk_super);
if (features & flag) {
spin_lock(&fs_info->super_lock);
features = btrfs_super_compat_ro_flags(disk_super);
if (features & flag) {
features &= ~flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
btrfs_info(fs_info,
"clearing compat-ro feature flag for %s (0x%llx)",
name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_fs_compat_ro(fs_info, opt) \
__btrfs_fs_compat_ro((fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
{
struct btrfs_super_block *disk_super;
disk_super = fs_info->super_copy;
return !!(btrfs_super_compat_ro_flags(disk_super) & flag);
}
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir);
#else
#define btrfs_get_acl NULL
#define btrfs_set_acl NULL
static inline int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir)
{
return 0;
}
#endif
/* relocation.c */
int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start);
int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_recover_relocation(struct btrfs_root *root);
int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *buf,
struct extent_buffer *cow);
void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
u64 *bytes_to_reserve);
int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
struct btrfs_pending_snapshot *pending);
/* scrub.c */
int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
u64 end, struct btrfs_scrub_progress *progress,
int readonly, int is_dev_replace);
void btrfs_scrub_pause(struct btrfs_fs_info *fs_info);
void btrfs_scrub_continue(struct btrfs_fs_info *fs_info);
int btrfs_scrub_cancel(struct btrfs_fs_info *info);
int btrfs_scrub_cancel_dev(struct btrfs_device *dev);
int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
struct btrfs_scrub_progress *progress);
static inline void btrfs_init_full_stripe_locks_tree(
struct btrfs_full_stripe_locks_tree *locks_root)
{
locks_root->root = RB_ROOT;
mutex_init(&locks_root->lock);
}
/* dev-replace.c */
void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info);
void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount);
static inline void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
{
btrfs_bio_counter_sub(fs_info, 1);
}
/* reada.c */
struct reada_control {
struct btrfs_fs_info *fs_info; /* tree to prefetch */
struct btrfs_key key_start;
struct btrfs_key key_end; /* exclusive */
atomic_t elems;
struct kref refcnt;
wait_queue_head_t wait;
};
struct reada_control *btrfs_reada_add(struct btrfs_root *root,
struct btrfs_key *start, struct btrfs_key *end);
int btrfs_reada_wait(void *handle);
void btrfs_reada_detach(void *handle);
int btree_readahead_hook(struct extent_buffer *eb, int err);
void btrfs_reada_remove_dev(struct btrfs_device *dev);
void btrfs_reada_undo_remove_dev(struct btrfs_device *dev);
static inline int is_fstree(u64 rootid)
{
if (rootid == BTRFS_FS_TREE_OBJECTID ||
((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID &&
!btrfs_qgroup_level(rootid)))
return 1;
return 0;
}
static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
{
return signal_pending(current);
}
#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_inode_set_ops(struct inode *inode);
void btrfs_test_destroy_inode(struct inode *inode);
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
}
#else
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
return 0;
}
#endif
#endif