1 files changed, 31 insertions, 25 deletions

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f3ad1598b201..7f21cf3aaf92 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -105,6 +105,8 @@ static int journal_submit_commit_record(journal_t *journal,
         int ret;
         struct timespec now = current_kernel_time();
 
+        *cbh = NULL;
+
         if (is_journal_aborted(journal))
                 return 0;
 
@@ -137,9 +139,9 @@ static int journal_submit_commit_record(journal_t *journal,
         if (journal->j_flags & JBD2_BARRIER &&
             !JBD2_HAS_INCOMPAT_FEATURE(journal,
                                        JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
-                ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh);
+                ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh);
         else
-                ret = submit_bh(WRITE_SYNC_PLUG, bh);
+                ret = submit_bh(WRITE_SYNC, bh);
 
         *cbh = bh;
         return ret;
@@ -217,7 +219,6 @@ static int journal_submit_data_buffers(journal_t *journal,
                         ret = err;
                 spin_lock(&journal->j_list_lock);
                 J_ASSERT(jinode->i_transaction == commit_transaction);
-                commit_transaction->t_flushed_data_blocks = 1;
                 clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
                 smp_mb__after_clear_bit();
                 wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
@@ -329,19 +330,13 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         int tag_bytes = journal_tag_bytes(journal);
         struct buffer_head *cbh = NULL; /* For transactional checksums */
         __u32 crc32_sum = ~0;
-        int write_op = WRITE_SYNC;
+        struct blk_plug plug;
 
         /*
          * First job: lock down the current transaction and wait for
          * all outstanding updates to complete.
          */
 
-#ifdef COMMIT_STATS
-        spin_lock(&journal->j_list_lock);
-        summarise_journal_usage(journal);
-        spin_unlock(&journal->j_list_lock);
-#endif
-
         /* Do we need to erase the effects of a prior jbd2_journal_flush? */
         if (journal->j_flags & JBD2_FLUSHED) {
                 jbd_debug(3, "super block updated\n");
@@ -363,13 +358,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         write_lock(&journal->j_state_lock);
         commit_transaction->t_state = T_LOCKED;
 
-        /*
-         * Use plugged writes here, since we want to submit several before
-         * we unplug the device. We don't do explicit unplugging in here,
-         * instead we rely on sync_buffer() doing the unplug for us.
-         */
-        if (commit_transaction->t_synchronous_commit)
-                write_op = WRITE_SYNC_PLUG;
         trace_jbd2_commit_locking(journal, commit_transaction);
         stats.run.rs_wait = commit_transaction->t_max_wait;
         stats.run.rs_locked = jiffies;
@@ -410,7 +398,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
          * we do not require it to remember exactly which old buffers it
          * has reserved.  This is consistent with the existing behaviour
          * that multiple jbd2_journal_get_write_access() calls to the same
-         * buffer are perfectly permissable.
+         * buffer are perfectly permissible.
          */
         while (commit_transaction->t_reserved_list) {
                 jh = commit_transaction->t_reserved_list;
@@ -469,8 +457,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         if (err)
                 jbd2_journal_abort(journal, err);
 
+        blk_start_plug(&plug);
         jbd2_journal_write_revoke_records(journal, commit_transaction,
-                                          write_op);
+                                          WRITE_SYNC);
+        blk_finish_plug(&plug);
 
         jbd_debug(3, "JBD: commit phase 2\n");
 
@@ -497,6 +487,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         err = 0;
         descriptor = NULL;
         bufs = 0;
+        blk_start_plug(&plug);
         while (commit_transaction->t_buffers) {
 
                 /* Find the next buffer to be journaled... */
@@ -658,7 +649,7 @@ start_journal_io:
                                 clear_buffer_dirty(bh);
                                 set_buffer_uptodate(bh);
                                 bh->b_end_io = journal_end_buffer_io_sync;
-                                submit_bh(write_op, bh);
+                                submit_bh(WRITE_SYNC, bh);
                         }
                         cond_resched();
                         stats.run.rs_blocks_logged += bufs;
@@ -680,12 +671,16 @@ start_journal_io:
                 err = 0;
         }
 
+        write_lock(&journal->j_state_lock);
+        J_ASSERT(commit_transaction->t_state == T_COMMIT);
+        commit_transaction->t_state = T_COMMIT_DFLUSH;
+        write_unlock(&journal->j_state_lock);
         /* 
          * If the journal is not located on the file system device,
          * then we must flush the file system device before we issue
          * the commit record
          */
-        if (commit_transaction->t_flushed_data_blocks &&
+        if (commit_transaction->t_need_data_flush &&
             (journal->j_fs_dev != journal->j_dev) &&
             (journal->j_flags & JBD2_BARRIER))
                 blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
@@ -699,6 +694,8 @@ start_journal_io:
                         __jbd2_journal_abort_hard(journal);
         }
 
+        blk_finish_plug(&plug);
+
         /* Lo and behold: we have just managed to send a transaction to
            the log.  Before we can commit it, wait for the IO so far to
            complete.  Control buffers being written are on the
@@ -760,8 +757,13 @@ wait_for_iobuf:
                    required. */
                 JBUFFER_TRACE(jh, "file as BJ_Forget");
                 jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
-                /* Wake up any transactions which were waiting for this
-                   IO to complete */
+                /*
+                 * Wake up any transactions which were waiting for this IO to
+                 * complete. The barrier must be here so that changes by
+                 * jbd2_journal_file_buffer() take effect before wake_up_bit()
+                 * does the waitqueue check.
+                 */
+                smp_mb();
                 wake_up_bit(&bh->b_state, BH_Unshadow);
                 JBUFFER_TRACE(jh, "brelse shadowed buffer");
                 __brelse(bh);
@@ -800,6 +802,10 @@ wait_for_iobuf:
                 jbd2_journal_abort(journal, err);
 
         jbd_debug(3, "JBD: commit phase 5\n");
+        write_lock(&journal->j_state_lock);
+        J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH);
+        commit_transaction->t_state = T_COMMIT_JFLUSH;
+        write_unlock(&journal->j_state_lock);
 
         if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
                                        JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
@@ -808,7 +814,7 @@ wait_for_iobuf:
                 if (err)
                         __jbd2_journal_abort_hard(journal);
         }
-        if (!err && !is_journal_aborted(journal))
+        if (cbh)
                 err = journal_wait_on_commit_record(journal, cbh);
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
                                       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
@@ -955,7 +961,7 @@ restart_loop:
 
         jbd_debug(3, "JBD: commit phase 7\n");
 
-        J_ASSERT(commit_transaction->t_state == T_COMMIT);
+        J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH);
 
         commit_transaction->t_start = jiffies;
         stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,