5 files changed, 40 insertions, 32 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd2f2b4..b7d7bd0f066e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
  */
 #define EXT4_IO_END_UNWRITTEN   0x0001
 #define EXT4_IO_END_ERROR       0x0002
+#define EXT4_IO_END_QUEUED      0x0004
 
 struct ext4_io_page {
         struct page     *p_page;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c4da98a959ae..18d2558b7624 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -121,9 +121,6 @@ void ext4_evict_inode(struct inode *inode)
 
         trace_ext4_evict_inode(inode);
 
-        mutex_lock(&inode->i_mutex);
-        ext4_flush_completed_IO(inode);
-        mutex_unlock(&inode->i_mutex);
         ext4_ioend_wait(inode);
 
         if (inode->i_nlink) {
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 78839af7ce29..92f38ee13f8a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
         unsigned long           flags;
         int                     ret;
 
-        mutex_lock(&inode->i_mutex);
+        if (!mutex_trylock(&inode->i_mutex)) {
+                /*
+                 * Requeue the work instead of waiting so that the work
+                 * items queued after this can be processed.
+                 */
+                queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+                /*
+                 * To prevent the ext4-dio-unwritten thread from keeping
+                 * requeueing end_io requests and occupying cpu for too long,
+                 * yield the cpu if it sees an end_io request that has already
+                 * been requeued.
+                 */
+                if (io->flag & EXT4_IO_END_QUEUED)
+                        yield();
+                io->flag |= EXT4_IO_END_QUEUED;
+                return;
+        }
         ret = ext4_end_io_nolock(io);
         if (ret < 0) {
                 mutex_unlock(&inode->i_mutex);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index b9c172b3fbbe..673704fab748 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -70,9 +70,8 @@ xfs_synchronize_times(
 }
 
 /*
- * If the linux inode is valid, mark it dirty.
- * Used when committing a dirty inode into a transaction so that
- * the inode will get written back by the linux code
+ * If the linux inode is valid, mark it dirty, else mark the dirty state
+ * in the XFS inode to make sure we pick it up when reclaiming the inode.
  */
 void
 xfs_mark_inode_dirty_sync(
@@ -82,6 +81,10 @@ xfs_mark_inode_dirty_sync(
 
         if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
                 mark_inode_dirty_sync(inode);
+        else {
+                barrier();
+                ip->i_update_core = 1;
+        }
 }
 
 void
@@ -92,6 +95,11 @@ xfs_mark_inode_dirty(
 
         if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
                 mark_inode_dirty(inode);
+        else {
+                barrier();
+                ip->i_update_core = 1;
+        }
+
 }
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9a72dda58bd0..2366c54cc4fa 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -356,6 +356,8 @@ xfs_parseargs(
                         mp->m_flags |= XFS_MOUNT_DELAYLOG;
                 } else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
                         mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
+                        xfs_warn(mp,
+        "nodelaylog is deprecated and will be removed in Linux 3.3");
                 } else if (!strcmp(this_char, MNTOPT_DISCARD)) {
                         mp->m_flags |= XFS_MOUNT_DISCARD;
                 } else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
@@ -877,33 +879,17 @@ xfs_log_inode(
         struct xfs_trans        *tp;
         int                     error;
 
-        xfs_iunlock(ip, XFS_ILOCK_SHARED);
         tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
         error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-
         if (error) {
                 xfs_trans_cancel(tp, 0);
-                /* we need to return with the lock hold shared */
-                xfs_ilock(ip, XFS_ILOCK_SHARED);
                 return error;
         }
 
         xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-        /*
-         * Note - it's possible that we might have pushed ourselves out of the
-         * way during trans_reserve which would flush the inode.  But there's
-         * no guarantee that the inode buffer has actually gone out yet (it's
-         * delwri).  Plus the buffer could be pinned anyway if it's part of
-         * an inode in another recent transaction.  So we play it safe and
-         * fire off the transaction anyway.
-         */
-        xfs_trans_ijoin(tp, ip);
+        xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
         xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-        error = xfs_trans_commit(tp, 0);
-        xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
-
-        return error;
+        return xfs_trans_commit(tp, 0);
 }
 
 STATIC int
@@ -918,7 +904,9 @@ xfs_fs_write_inode(
         trace_xfs_write_inode(ip);
 
         if (XFS_FORCED_SHUTDOWN(mp))
-                return XFS_ERROR(EIO);
+                return -XFS_ERROR(EIO);
+        if (!ip->i_update_core)
+                return 0;
 
         if (wbc->sync_mode == WB_SYNC_ALL) {
                 /*
@@ -929,12 +917,10 @@ xfs_fs_write_inode(
                  * of synchronous log foces dramatically.
                  */
                 xfs_ioend_wait(ip);
-                xfs_ilock(ip, XFS_ILOCK_SHARED);
-                if (ip->i_update_core) {
-                        error = xfs_log_inode(ip);
-                        if (error)
-                                goto out_unlock;
-                }
+                error = xfs_log_inode(ip);
+                if (error)
+                        goto out;
+                return 0;
         } else {
                 /*
                  * We make this non-blocking if the inode is contended, return