[PATCH v4] f2fs: fix to stop filesystem update once CP failed

From: Chao Yu
Date: Tue Aug 03 2021 - 20:38:47 EST


During f2fs_write_checkpoint(), once we failed in
f2fs_flush_nat_entries() or do_checkpoint(), metadata of filesystem
such as prefree bitmap, nat/sit version bitmap won't be recovered,
it may cause f2fs image to be inconsistent, let's just set CP error
flag to avoid further updates until we figure out a scheme to rollback
all metadatas in such condition.

Reported-by: Yangtao Li <frank.li@xxxxxxxx>
Signed-off-by: Yangtao Li <frank.li@xxxxxxxx>
Signed-off-by: Chao Yu <chao@xxxxxxxxxx>
---
- add congestion_wait() and f2fs_stop_checkpoint() in
f2fs_flush_device_cache
- use DEFAULT_RETRY_IO_COUNT
fs/f2fs/checkpoint.c | 12 +++++++++---
fs/f2fs/f2fs.h | 2 +-
fs/f2fs/segment.c | 15 +++++++++++++--
3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 6c208108d69c..7f6745f4630e 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1639,8 +1639,11 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

/* write cached NAT/SIT entries to NAT/SIT area */
err = f2fs_flush_nat_entries(sbi, cpc);
- if (err)
+ if (err) {
+ f2fs_err(sbi, "f2fs_flush_nat_entries failed err:%d, stop checkpoint", err);
+ f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
goto stop;
+ }

f2fs_flush_sit_entries(sbi, cpc);

@@ -1648,10 +1651,13 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_save_inmem_curseg(sbi);

err = do_checkpoint(sbi, cpc);
- if (err)
+ if (err) {
+ f2fs_err(sbi, "do_checkpoint failed err:%d, stop checkpoint", err);
+ f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
f2fs_release_discard_addrs(sbi);
- else
+ } else {
f2fs_clear_prefree_segments(sbi, cpc);
+ }

f2fs_restore_inmem_curseg(sbi);
stop:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c44fdad8495e..299ed8cb1bd3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -547,7 +547,7 @@ enum {
*/
};

-#define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */
+#define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO or flush count */

/* congestion wait timeout value, default: 20ms */
#define DEFAULT_IO_TIMEOUT (msecs_to_jiffies(20))
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 80f26158e304..ca9876a6d396 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -776,11 +776,22 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
return 0;

for (i = 1; i < sbi->s_ndevs; i++) {
+ int count = DEFAULT_RETRY_IO_COUNT;
+
if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
continue;
- ret = __submit_flush_wait(sbi, FDEV(i).bdev);
- if (ret)
+
+ do {
+ ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+ if (ret)
+ congestion_wait(BLK_RW_ASYNC,
+ DEFAULT_IO_TIMEOUT);
+ } while (ret && --count);
+
+ if (ret) {
+ f2fs_stop_checkpoint(sbi, false);
break;
+ }

spin_lock(&sbi->dev_lock);
f2fs_clear_bit(i, (char *)&sbi->dirty_device);
--
2.22.1