jbd2: avoid mount failed when commit block is partial submitted

[ Upstream commit 0bab8db4152c4a2185a1367db09cc402bdc62d5e ]

We encountered a problem that the file system could not be mounted in
the power-off scenario. The analysis of the file system mirror shows that
only part of the data is written to the last commit block.
The valid data of the commit block is concentrated in the first sector.
However, the data of the entire block is involved in the checksum calculation.
For different hardware, the minimum atomic unit may be different.
If the checksum of a committed block is incorrect, clear the data except the
'commit_header' and then calculate the checksum. If the checkusm is correct,
it is considered that the block is partially committed, Then continue to replay
journal.

Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20240620072405.3533701-1-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 5b771a3d8d9aeb7d561a51a735b89fd75d025e00..421c0d360836e0de02b2ea226e3f2b3bb46f87d8 100644 (file)
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -448,6 +448,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
        return provided == cpu_to_be32(calculated);
 }
 
+static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf)
+{
+       struct commit_header *h;
+       __be32 provided;
+       __u32 calculated;
+       void *tmpbuf;
+
+       tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL);
+       if (!tmpbuf)
+               return false;
+
+       memcpy(tmpbuf, buf, sizeof(struct commit_header));
+       h = tmpbuf;
+       provided = h->h_chksum[0];
+       h->h_chksum[0] = 0;
+       calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize);
+       kfree(tmpbuf);
+
+       return provided == cpu_to_be32(calculated);
+}
+
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
                                      journal_block_tag3_t *tag3,
                                      void *buf, __u32 sequence)
@@ -814,6 +835,13 @@ static int do_one_pass(journal_t *journal,
                        if (pass == PASS_SCAN &&
                            !jbd2_commit_block_csum_verify(journal,
                                                           bh->b_data)) {
+                               if (jbd2_commit_block_csum_verify_partial(
+                                                                 journal,
+                                                                 bh->b_data)) {
+                                       pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+                                                 next_commit_ID, next_log_block);
+                                       goto chksum_ok;
+                               }
                        chksum_error:
                                if (commit_time < last_trans_commit_time)
                                        goto ignore_crc_mismatch;
@@ -828,6 +856,7 @@ static int do_one_pass(journal_t *journal,
                                }
                        }
                        if (pass == PASS_SCAN) {
+                       chksum_ok:
                                last_trans_commit_time = commit_time;
                                head_block = next_log_block;
                        }
@@ -847,6 +876,7 @@ static int do_one_pass(journal_t *journal,
                                          next_log_block);
                                need_check_commit_time = true;
                        }
+
                        /* If we aren't in the REVOKE pass, then we can
                         * just skip over this block. */
                        if (pass != PASS_REVOKE) {