Merge tag 'v3.3' into staging/for_v3.4

* tag 'v3.3': (1646 commits)
  Linux 3.3
  Don't limit non-nested epoll paths
  netfilter: ctnetlink: fix race between delete and timeout expiration
  ipv6: Don't dev_hold(dev) in ip6_mc_find_dev_rcu.
  nilfs2: fix NULL pointer dereference in nilfs_load_super_block()
  nilfs2: clamp ns_r_segments_percentage to [1, 99]
  afs: Remote abort can cause BUG in rxrpc code
  afs: Read of file returns EBADMSG
  C6X: remove dead code from entry.S
  wimax/i2400m: fix erroneous NETDEV_TX_BUSY use
  net/hyperv: fix erroneous NETDEV_TX_BUSY use
  net/usbnet: reserve headroom on rx skbs
  bnx2x: fix memory leak in bnx2x_init_firmware()
  bnx2x: fix a crash on corrupt firmware file
  sch_sfq: revert dont put new flow at the end of flows
  ipv6: fix icmp6_dst_alloc()
  MAINTAINERS: Add Serge as maintainer of capabilities
  drivers/video/backlight/s6e63m0.c: fix corruption storing gamma mode
  MAINTAINERS: add entry for exynos mipi display drivers
  MAINTAINERS: fix link to Gustavo Padovans tree
  ...

1 files changed, 22 insertions, 5 deletions

diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 5d1a00a5041..05f0754f2b4 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -453,8 +453,6 @@ out:
  *
  * Return <0 on error, 0 on success, 1 if there was nothing to clean up.
  *
- * Called with the journal lock held.
- *
  * This is the only part of the journaling code which really needs to be
  * aware of transaction aborts.  Checkpointing involves writing to the
  * main filesystem area rather than to the journal, so it can proceed
@@ -472,13 +470,14 @@ int cleanup_journal_tail(journal_t *journal)
 	if (is_journal_aborted(journal))
 		return 1;
 
-	/* OK, work out the oldest transaction remaining in the log, and
+	/*
+	 * OK, work out the oldest transaction remaining in the log, and
 	 * the log block it starts at.
 	 *
 	 * If the log is now empty, we need to work out which is the
 	 * next transaction ID we will write, and where it will
-	 * start. */
-
+	 * start.
+	 */
 	spin_lock(&journal->j_state_lock);
 	spin_lock(&journal->j_list_lock);
 	transaction = journal->j_checkpoint_transactions;
@@ -504,7 +503,25 @@ int cleanup_journal_tail(journal_t *journal)
 		spin_unlock(&journal->j_state_lock);
 		return 1;
 	}
+	spin_unlock(&journal->j_state_lock);
+
+	/*
+	 * We need to make sure that any blocks that were recently written out
+	 * --- perhaps by log_do_checkpoint() --- are flushed out before we
+	 * drop the transactions from the journal. It's unlikely this will be
+	 * necessary, especially with an appropriately sized journal, but we
+	 * need this to guarantee correctness.  Fortunately
+	 * cleanup_journal_tail() doesn't get called all that often.
+	 */
+	if (journal->j_flags & JFS_BARRIER)
+		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
 
+	spin_lock(&journal->j_state_lock);
+	if (!tid_gt(first_tid, journal->j_tail_sequence)) {
+		spin_unlock(&journal->j_state_lock);
+		/* Someone else cleaned up journal so return 0 */
+		return 0;
+	}
 	/* OK, update the superblock to recover the freed space.
 	 * Physical blocks come first: have we wrapped beyond the end of
 	 * the log?  */