[PATCH v2] f2fs: fix potential deadlock in f2fs_balance_fs()

[ruipengqi <ruipengqi3@gmail.com>]

From: Ruipeng Qi <ruipengqi3@gmail.com>

When the f2fs filesystem space is nearly exhausted, we encounter deadlock
issues as below:

INFO: task A:1890 blocked for more than 120 seconds.
      Tainted: G           O       6.12.41-g3fe07ddf05ab #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:A    state:D stack:0     pid:1890  tgid:1626  ppid:1153   flags:0x00000204
Call trace:
 __switch_to+0xf4/0x158
 __schedule+0x27c/0x908
 schedule+0x3c/0x118
 io_schedule+0x44/0x68
 folio_wait_bit_common+0x174/0x370
 folio_wait_bit+0x20/0x38
 folio_wait_writeback+0x54/0xc8
 truncate_inode_partial_folio+0x70/0x1e0
 truncate_inode_pages_range+0x1b0/0x450
 truncate_pagecache+0x54/0x88
 f2fs_file_write_iter+0x3e8/0xb80
 do_iter_readv_writev+0xf0/0x1e0
 vfs_writev+0x138/0x2c8
 do_writev+0x88/0x130
 __arm64_sys_writev+0x28/0x40
 invoke_syscall+0x50/0x120
 el0_svc_common.constprop.0+0xc8/0xf0
 do_el0_svc+0x24/0x38
 el0_svc+0x30/0xf8
 el0t_64_sync_handler+0x120/0x130
 el0t_64_sync+0x190/0x198

INFO: task kworker/u8:11:2680853 blocked for more than 120 seconds.
      Tainted: G           O       6.12.41-g3fe07ddf05ab #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/u8:11   state:D stack:0     pid:2680853 tgid:2680853 ppid:2      flags:0x00000208
Workqueue: writeback wb_workfn (flush-254:0)
Call trace:
 __switch_to+0xf4/0x158
 __schedule+0x27c/0x908
 schedule+0x3c/0x118
 io_schedule+0x44/0x68
 folio_wait_bit_common+0x174/0x370
 __filemap_get_folio+0x214/0x348
 pagecache_get_page+0x20/0x70
 f2fs_get_read_data_page+0x150/0x3e8
 f2fs_get_lock_data_page+0x2c/0x160
 move_data_page+0x50/0x478
 do_garbage_collect+0xd38/0x1528
 f2fs_gc+0x240/0x7e0
 f2fs_balance_fs+0x1a0/0x208
 f2fs_write_single_data_page+0x6e4/0x730  //0xfffffe0d6ca08300
 f2fs_write_cache_pages+0x378/0x9b0
 f2fs_write_data_pages+0x2e4/0x388
 do_writepages+0x8c/0x2c8
 __writeback_single_inode+0x4c/0x498
 writeback_sb_inodes+0x234/0x4a8
 __writeback_inodes_wb+0x58/0x118
 wb_writeback+0x2f8/0x3c0
 wb_workfn+0x2c4/0x508
 process_one_work+0x180/0x408
 worker_thread+0x258/0x368
 kthread+0x118/0x128
 ret_from_fork+0x10/0x200

INFO: task kworker/u8:8:2641297 blocked for more than 120 seconds.
      Tainted: G           O       6.12.41-g3fe07ddf05ab #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/u8:8    state:D stack:0     pid:2641297 tgid:2641297 ppid:2      flags:0x00000208
Workqueue: writeback wb_workfn (flush-254:0)
Call trace:
 __switch_to+0xf4/0x158
 __schedule+0x27c/0x908
 rt_mutex_schedule+0x30/0x60
 __rt_mutex_slowlock_locked.constprop.0+0x460/0x8a8
 rwbase_write_lock+0x24c/0x378
 down_write+0x1c/0x30
 f2fs_balance_fs+0x184/0x208
 f2fs_write_inode+0xf4/0x328
 __writeback_single_inode+0x370/0x498
 writeback_sb_inodes+0x234/0x4a8
 __writeback_inodes_wb+0x58/0x118
 wb_writeback+0x2f8/0x3c0
 wb_workfn+0x2c4/0x508
 process_one_work+0x180/0x408
 worker_thread+0x258/0x368
 kthread+0x118/0x128
 ret_from_fork+0x10/0x20

INFO: task B:1902 blocked for more than 120 seconds.
      Tainted: G           O       6.12.41-g3fe07ddf05ab #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:B     state:D stack:0     pid:1902  tgid:1626  ppid:1153   flags:0x0000020c
Call trace:
 __switch_to+0xf4/0x158
 __schedule+0x27c/0x908
 rt_mutex_schedule+0x30/0x60
 __rt_mutex_slowlock_locked.constprop.0+0x460/0x8a8
 rwbase_write_lock+0x24c/0x378
 down_write+0x1c/0x30
 f2fs_balance_fs+0x184/0x208
 f2fs_map_blocks+0x94c/0x1110
 f2fs_file_write_iter+0x228/0xb80
 do_iter_readv_writev+0xf0/0x1e0
 vfs_writev+0x138/0x2c8
 do_writev+0x88/0x130
 __arm64_sys_writev+0x28/0x40
 invoke_syscall+0x50/0x120
 el0_svc_common.constprop.0+0xc8/0xf0
 do_el0_svc+0x24/0x38
 el0_svc+0x30/0xf8
 el0t_64_sync_handler+0x120/0x130
 el0t_64_sync+0x190/0x198

INFO: task sync:2769849 blocked for more than 120 seconds.
      Tainted: G           O       6.12.41-g3fe07ddf05ab #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:sync            state:D stack:0     pid:2769849 tgid:2769849 ppid:736    flags:0x0000020c
Call trace:
 __switch_to+0xf4/0x158
 __schedule+0x27c/0x908
 schedule+0x3c/0x118
 wb_wait_for_completion+0xb0/0xe8
 sync_inodes_sb+0xc8/0x2b0
 sync_inodes_one_sb+0x24/0x38
 iterate_supers+0xa8/0x138
 ksys_sync+0x54/0xc8
 __arm64_sys_sync+0x18/0x30
 invoke_syscall+0x50/0x120
 el0_svc_common.constprop.0+0xc8/0xf0
 do_el0_svc+0x24/0x38
 el0_svc+0x30/0xf8
 el0t_64_sync_handler+0x120/0x130
 el0t_64_sync+0x190/0x198

The root cause is a potential deadlock between the following tasks:

kworker/u8:11				Thread A
- f2fs_write_single_data_page
 - f2fs_do_write_data_page
  - folio_start_writeback(X)
  - f2fs_outplace_write_data
   - bio_add_folio(X)
 - folio_unlock(X)
					- truncate_inode_pages_range
					 - __filemap_get_folio(X, FGP_LOCK)
					 - truncate_inode_partial_folio(X)
					  - folio_wait_writeback(X)
 - f2fs_balance_fs
  - f2fs_gc
   - do_garbage_collect
    - move_data_page
     - f2fs_get_lock_data_page
      - __filemap_get_folio(X, FGP_LOCK)

Both threads try to access folio X. Thread A holds the lock but waits
for writeback, while kworker waits for the lock. This causes a deadlock.

Other threads also enter D state, waiting for locks such as gc_lock and
writepages.

OPU/IPU DATA folio are all affected by this issue. To avoid such
potential deadlocks, always commit these cached folios before
triggering f2fs_gc() in f2fs_balance_fs().

v2:
- Commit cached OPU/IPU folios, not just OPU folios as in v1.

Suggested-by: Chao <chao@kernel.org>
Signed-off-by: Ruipeng Qi <ruipengqi3@gmail.com>
---
 fs/f2fs/data.c    | 26 ++++++++++++++++++++++++++
 fs/f2fs/f2fs.h    |  1 +
 fs/f2fs/segment.c |  9 +++++++++
 3 files changed, 36 insertions(+)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 338df7a2aea6..fd03366b3228 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -939,6 +939,32 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
 	}
 }
 
+void f2fs_submit_all_merged_ipu_writes(struct f2fs_sb_info *sbi)
+{
+	struct bio_entry *be, *tmp;
+	struct f2fs_bio_info *io;
+	enum temp_type temp;
+	LIST_HEAD(list);
+
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+		io = sbi->write_io[DATA] + temp;
+
+		if (list_empty(&io->bio_list))
+			continue;
+
+		f2fs_down_write(&io->bio_list_lock);
+		list_splice_init(&io->bio_list, &list);
+		f2fs_up_write(&io->bio_list_lock);
+
+		list_for_each_entry_safe(be, tmp, &list, list) {
+			f2fs_submit_write_bio(sbi, be->bio, DATA);
+			del_bio_entry(be);
+		}
+
+	}
+
+}
+
 int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio = *fio->bio;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bb34e864d0ef..e9038ab1b2bd 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4148,6 +4148,7 @@ void f2fs_submit_merged_write_folio(struct f2fs_sb_info *sbi,
 				struct folio *folio, enum page_type type);
 void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
 					struct bio **bio, struct folio *folio);
+void f2fs_submit_all_merged_ipu_writes(struct f2fs_sb_info *sbi);
 void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
 int f2fs_submit_page_bio(struct f2fs_io_info *fio);
 int f2fs_merge_page_bio(struct f2fs_io_info *fio);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6a97fe76712b..856ffe91b94f 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -454,6 +454,15 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 		io_schedule();
 		finish_wait(&sbi->gc_thread->fggc_wq, &wait);
 	} else {
+
+		/*
+		 * Submit all cached OPU/IPU DATA bios before triggering
+		 * foreground GC to avoid potential deadlocks.
+		 */
+
+		f2fs_submit_merged_write(sbi, DATA);
+		f2fs_submit_all_merged_ipu_writes(sbi);
+
 		struct f2fs_gc_control gc_control = {
 			.victim_segno = NULL_SEGNO,
 			.init_gc_type = f2fs_sb_has_blkzoned(sbi) ?
-- 
2.25.1