dm zoned: avoid triggering reclaim from inside dmz_map()

commit 2d0b2d64d325e22939d9db3ba784f1236459ed98 upstream.

This patch avoids that lockdep reports the following:

======================================================
WARNING: possible circular locking dependency detected
4.18.0-rc1 #62 Not tainted
------------------------------------------------------
kswapd0/84 is trying to acquire lock:
00000000c313516d (&xfs_nondir_ilock_class){++++}, at: xfs_free_eofblocks+0xa2/0x1e0

but task is already holding lock:
00000000591c83ae (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x5/0x30

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (fs_reclaim){+.+.}:
  kmem_cache_alloc+0x2c/0x2b0
  radix_tree_node_alloc.constprop.19+0x3d/0xc0
  __radix_tree_create+0x161/0x1c0
  __radix_tree_insert+0x45/0x210
  dmz_map+0x245/0x2d0 [dm_zoned]
  __map_bio+0x40/0x260
  __split_and_process_non_flush+0x116/0x220
  __split_and_process_bio+0x81/0x180
  __dm_make_request.isra.32+0x5a/0x100
  generic_make_request+0x36e/0x690
  submit_bio+0x6c/0x140
  mpage_readpages+0x19e/0x1f0
  read_pages+0x6d/0x1b0
  __do_page_cache_readahead+0x21b/0x2d0
  force_page_cache_readahead+0xc4/0x100
  generic_file_read_iter+0x7c6/0xd20
  __vfs_read+0x102/0x180
  vfs_read+0x9b/0x140
  ksys_read+0x55/0xc0
  do_syscall_64+0x5a/0x1f0
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

-> #1 (&dmz->chunk_lock){+.+.}:
  dmz_map+0x133/0x2d0 [dm_zoned]
  __map_bio+0x40/0x260
  __split_and_process_non_flush+0x116/0x220
  __split_and_process_bio+0x81/0x180
  __dm_make_request.isra.32+0x5a/0x100
  generic_make_request+0x36e/0x690
  submit_bio+0x6c/0x140
  _xfs_buf_ioapply+0x31c/0x590
  xfs_buf_submit_wait+0x73/0x520
  xfs_buf_read_map+0x134/0x2f0
  xfs_trans_read_buf_map+0xc3/0x580
  xfs_read_agf+0xa5/0x1e0
  xfs_alloc_read_agf+0x59/0x2b0
  xfs_alloc_pagf_init+0x27/0x60
  xfs_bmap_longest_free_extent+0x43/0xb0
  xfs_bmap_btalloc_nullfb+0x7f/0xf0
  xfs_bmap_btalloc+0x428/0x7c0
  xfs_bmapi_write+0x598/0xcc0
  xfs_iomap_write_allocate+0x15a/0x330
  xfs_map_blocks+0x1cf/0x3f0
  xfs_do_writepage+0x15f/0x7b0
  write_cache_pages+0x1ca/0x540
  xfs_vm_writepages+0x65/0xa0
  do_writepages+0x48/0xf0
  __writeback_single_inode+0x58/0x730
  writeback_sb_inodes+0x249/0x5c0
  wb_writeback+0x11e/0x550
  wb_workfn+0xa3/0x670
  process_one_work+0x228/0x670
  worker_thread+0x3c/0x390
  kthread+0x11c/0x140
  ret_from_fork+0x3a/0x50

-> #0 (&xfs_nondir_ilock_class){++++}:
  down_read_nested+0x43/0x70
  xfs_free_eofblocks+0xa2/0x1e0
  xfs_fs_destroy_inode+0xac/0x270
  dispose_list+0x51/0x80
  prune_icache_sb+0x52/0x70
  super_cache_scan+0x127/0x1a0
  shrink_slab.part.47+0x1bd/0x590
  shrink_node+0x3b5/0x470
  balance_pgdat+0x158/0x3b0
  kswapd+0x1ba/0x600
  kthread+0x11c/0x140
  ret_from_fork+0x3a/0x50

other info that might help us debug this:

Chain exists of:
  &xfs_nondir_ilock_class --> &dmz->chunk_lock --> fs_reclaim

Possible unsafe locking scenario:

     CPU0                    CPU1
     ----                    ----
lock(fs_reclaim);
                             lock(&dmz->chunk_lock);
                             lock(fs_reclaim);
lock(&xfs_nondir_ilock_class);

diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 6d7bda6f8190583136608898d778a0ec161c7aee..ba6b0a90ecfb1647e7dcbaff72533af1e24cc91e 100644 (file)
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -788,7 +788,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
        /* Chunk BIO work */
        mutex_init(&dmz->chunk_lock);
-       INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_KERNEL);
+       INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
        dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
                                        0, dev->name);
        if (!dmz->chunk_wq) {