1 files changed, 43 insertions, 94 deletions

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 472932b9e..7898983c9 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -58,28 +58,6 @@ static inline void __buffer_unlink(struct journal_head *jh)
 }
 
 /*
- * Move a buffer from the checkpoint list to the checkpoint io list
- *
- * Called with j_list_lock held
- */
-static inline void __buffer_relink_io(struct journal_head *jh)
-{
-	transaction_t *transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-
-	if (!transaction->t_checkpoint_io_list) {
-		jh->b_cpnext = jh->b_cpprev = jh;
-	} else {
-		jh->b_cpnext = transaction->t_checkpoint_io_list;
-		jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
-		jh->b_cpprev->b_cpnext = jh;
-		jh->b_cpnext->b_cpprev = jh;
-	}
-	transaction->t_checkpoint_io_list = jh;
-}
-
-/*
  * Try to release a checkpointed buffer from its transaction.
  * Returns 1 if we released it and 2 if we also released the
  * whole transaction.
@@ -91,8 +69,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 	int ret = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (jh->b_transaction == NULL && !buffer_locked(bh) &&
-	    !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
+	if (!jh->b_transaction && !buffer_locked(bh) && !buffer_dirty(bh)) {
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		ret = __jbd2_journal_remove_checkpoint(jh) + 1;
 	}
@@ -191,6 +168,7 @@ __flush_batch(journal_t *journal, int *batch_count)
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
+		journal->j_chkpt_bhs[i] = NULL;
 	}
 	*batch_count = 0;
 }
@@ -228,7 +206,6 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 	 * OK, we need to start writing disk blocks.  Take one transaction
 	 * and write it.
 	 */
-	result = 0;
 	spin_lock(&journal->j_list_lock);
 	if (!journal->j_checkpoint_transactions)
 		goto out;
@@ -251,15 +228,6 @@ restart:
 		jh = transaction->t_checkpoint_list;
 		bh = jh2bh(jh);
 
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			goto retry;
-		}
 		if (jh->b_transaction != NULL) {
 			transaction_t *t = jh->b_transaction;
 			tid_t tid = t->t_tid;
@@ -294,32 +262,50 @@ restart:
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
-		if (!buffer_dirty(bh)) {
-			if (unlikely(buffer_write_io_error(bh)) && !result)
-				result = -EIO;
+		if (!trylock_buffer(bh)) {
+			/*
+			 * The buffer is locked, it may be writing back, or
+			 * flushing out in the last couple of cycles, or
+			 * re-adding into a new transaction, need to check
+			 * it again until it's unlocked.
+			 */
+			get_bh(bh);
+			spin_unlock(&journal->j_list_lock);
+			wait_on_buffer(bh);
+			/* the journal_head may have gone by now */
+			BUFFER_TRACE(bh, "brelse");
+			__brelse(bh);
+			goto retry;
+		} else if (!buffer_dirty(bh)) {
+			unlock_buffer(bh);
 			BUFFER_TRACE(bh, "remove from checkpoint");
-			if (__jbd2_journal_remove_checkpoint(jh))
-				/* The transaction was released; we're done */
+			/*
+			 * If the transaction was released or the checkpoint
+			 * list was empty, we're done.
+			 */
+			if (__jbd2_journal_remove_checkpoint(jh) ||
+			    !transaction->t_checkpoint_list)
 				goto out;
-			continue;
+		} else {
+			unlock_buffer(bh);
+			/*
+			 * We are about to write the buffer, it could be
+			 * raced by some other transaction shrink or buffer
+			 * re-log logic once we release the j_list_lock,
+			 * leave it on the checkpoint list and check status
+			 * again to make sure it's clean.
+			 */
+			BUFFER_TRACE(bh, "queue");
+			get_bh(bh);
+			J_ASSERT_BH(bh, !buffer_jwrite(bh));
+			journal->j_chkpt_bhs[batch_count++] = bh;
+			transaction->t_chp_stats.cs_written++;
+			transaction->t_checkpoint_list = jh->b_cpnext;
 		}
-		/*
-		 * Important: we are about to write the buffer, and
-		 * possibly block, while still holding the journal
-		 * lock.  We cannot afford to let the transaction
-		 * logic start messing around with this buffer before
-		 * we write it to disk, as that would break
-		 * recoverability.
-		 */
-		BUFFER_TRACE(bh, "queue");
-		get_bh(bh);
-		J_ASSERT_BH(bh, !buffer_jwrite(bh));
-		journal->j_chkpt_bhs[batch_count++] = bh;
-		__buffer_relink_io(jh);
-		transaction->t_chp_stats.cs_written++;
+
 		if ((batch_count == JBD2_NR_BATCH) ||
-		    need_resched() ||
-		    spin_needbreak(&journal->j_list_lock))
+		    need_resched() || spin_needbreak(&journal->j_list_lock) ||
+		    jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0])
 			goto unlock_and_flush;
 	}
 
@@ -333,46 +319,9 @@ restart:
 			goto restart;
 	}
 
-	/*
-	 * Now we issued all of the transaction's buffers, let's deal
-	 * with the buffers that are out for I/O.
-	 */
-restart2:
-	/* Did somebody clean up the transaction in the meanwhile? */
-	if (journal->j_checkpoint_transactions != transaction ||
-	    transaction->t_tid != this_tid)
-		goto out;
-
-	while (transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
-		bh = jh2bh(jh);
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart2;
-		}
-		if (unlikely(buffer_write_io_error(bh)) && !result)
-			result = -EIO;
-
-		/*
-		 * Now in whatever state the buffer currently is, we
-		 * know that it has been written out and so we can
-		 * drop it from the list
-		 */
-		if (__jbd2_journal_remove_checkpoint(jh))
-			break;
-	}
 out:
 	spin_unlock(&journal->j_list_lock);
-	if (result < 0)
-		jbd2_journal_abort(journal, result);
-	else
-		result = jbd2_cleanup_journal_tail(journal);
+	result = jbd2_cleanup_journal_tail(journal);
 
 	return (result < 0) ? result : 0;
 }