jbd2: fix race between write_metadata_buffer and get_write_access

The function jbd2_journal_write_metadata_buffer() calls
jbd_unlock_bh_state(bh_in) too early; this could potentially allow
another thread to call get_write_access on the buffer head, modify the
data, and dirty it, and allowing the wrong data to be written into the
journal.  Fortunately, if we lose this race, the only time this will
actually cause filesystem corruption is if there is a system crash or
other unclean shutdown of the system before the next commit can take
place.

Signed-off-by: dingdinghua <dingdinghua85@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 7b545c3b3942d0b48fb55be9dc094ed9ce298ac5..e378cb383979a3e8e54234b14aa354e890c54e26 100644 (file)
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -297,6 +297,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
        unsigned int new_offset;
        struct buffer_head *bh_in = jh2bh(jh_in);
        struct jbd2_buffer_trigger_type *triggers;
+       journal_t *journal = transaction->t_journal;
 
        /*
         * The buffer really shouldn't be locked: only the current committing
@@ -310,6 +311,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
        J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
 
        new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+       /* keep subsequent assertions sane */
+       new_bh->b_state = 0;
+       init_buffer(new_bh, NULL, NULL);
+       atomic_set(&new_bh->b_count, 1);
+       new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
 
        /*
         * If a new transaction has already done a buffer copy-out, then
@@ -388,14 +394,6 @@ repeat:
                kunmap_atomic(mapped_data, KM_USER0);
        }
 
-       /* keep subsequent assertions sane */
-       new_bh->b_state = 0;
-       init_buffer(new_bh, NULL, NULL);
-       atomic_set(&new_bh->b_count, 1);
-       jbd_unlock_bh_state(bh_in);
-
-       new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
-
        set_bh_page(new_bh, new_page, new_offset);
        new_jh->b_transaction = NULL;
        new_bh->b_size = jh2bh(jh_in)->b_size;
@@ -412,7 +410,11 @@ repeat:
         * copying is moved to the transaction's shadow queue.
         */
        JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
-       jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+       spin_lock(&journal->j_list_lock);
+       __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+       spin_unlock(&journal->j_list_lock);
+       jbd_unlock_bh_state(bh_in);
+
        JBUFFER_TRACE(new_jh, "file as BJ_IO");
        jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);