xfs: Always flush caches when integrity is required

There is no reason anymore for not issuing device integrity
operations when teh filesystem requires ordering or data integrity
guarantees. We should always issue cache flushes and FUA writes
where necessary and let the underlying storage optimise them as
necessary for correct integrity operation.

Signed-Off-By: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index b5b9bffe352074806910a064ae41a941c97678c8..7d3afa0bddd3920aa167751c58b797f08121a4b6 100644 (file)
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1711,8 +1711,7 @@ xfs_free_buftarg(
        percpu_counter_destroy(&btp->bt_io_count);
        list_lru_destroy(&btp->bt_lru);
 
-       if (mp->m_flags & XFS_MOUNT_BARRIER)
-               xfs_blkdev_issue_flush(btp);
+       xfs_blkdev_issue_flush(btp);
 
        kmem_free(btp);
 }

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f5effa68e037ae59f57b1f1188dbe4e2eb40b15c..2951c483b24bb8d5658e7ff45c99f2027253492b 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -149,19 +149,16 @@ xfs_file_fsync(
 
        xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
-       if (mp->m_flags & XFS_MOUNT_BARRIER) {
-               /*
-                * If we have an RT and/or log subvolume we need to make sure
-                * to flush the write cache the device used for file data
-                * first.  This is to ensure newly written file data make
-                * it to disk before logging the new inode size in case of
-                * an extending write.
-                */
-               if (XFS_IS_REALTIME_INODE(ip))
-                       xfs_blkdev_issue_flush(mp->m_rtdev_targp);
-               else if (mp->m_logdev_targp != mp->m_ddev_targp)
-                       xfs_blkdev_issue_flush(mp->m_ddev_targp);
-       }
+       /*
+        * If we have an RT and/or log subvolume we need to make sure to flush
+        * the write cache the device used for file data first.  This is to
+        * ensure newly written file data make it to disk before logging the new
+        * inode size in case of an extending write.
+        */
+       if (XFS_IS_REALTIME_INODE(ip))
+               xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+       else if (mp->m_logdev_targp != mp->m_ddev_targp)
+               xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
        /*
         * All metadata updates are logged, which means that we just have to
@@ -196,10 +193,8 @@ xfs_file_fsync(
         * an already allocated file and thus do not have any metadata to
         * commit.
         */
-       if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
-           mp->m_logdev_targp == mp->m_ddev_targp &&
-           !XFS_IS_REALTIME_INODE(ip) &&
-           !log_flushed)
+       if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
+           mp->m_logdev_targp == mp->m_ddev_targp)
                xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
        return error;

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3b74fa011bb1566ce43dedc2fbdbc49336645d84..25fa31d973c8e3f071ef3f2e067f91ebf50f349e 100644 (file)
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1862,26 +1862,21 @@ xlog_sync(
 
        bp->b_io_length = BTOBB(count);
        bp->b_fspriv = iclog;
-       bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
-       bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
+       bp->b_flags &= ~XBF_FLUSH;
+       bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA);
 
-       if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
-               bp->b_flags |= XBF_FUA;
-
-               /*
-                * Flush the data device before flushing the log to make
-                * sure all meta data written back from the AIL actually made
-                * it to disk before stamping the new log tail LSN into the
-                * log buffer.  For an external log we need to issue the
-                * flush explicitly, and unfortunately synchronously here;
-                * for an internal log we can simply use the block layer
-                * state machine for preflushes.
-                */
-               if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp)
-                       xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp);
-               else
-                       bp->b_flags |= XBF_FLUSH;
-       }
+       /*
+        * Flush the data device before flushing the log to make sure all meta
+        * data written back from the AIL actually made it to disk before
+        * stamping the new log tail LSN into the log buffer.  For an external
+        * log we need to issue the flush explicitly, and unfortunately
+        * synchronously here; for an internal log we can simply use the block
+        * layer state machine for preflushes.
+        */
+       if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp)
+               xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp);
+       else
+               bp->b_flags |= XBF_FLUSH;
 
        ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
        ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
@@ -1906,10 +1901,8 @@ xlog_sync(
                xfs_buf_associate_memory(bp,
                                (char *)&iclog->ic_header + count, split);
                bp->b_fspriv = iclog;
-               bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
-               bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
-               if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
-                       bp->b_flags |= XBF_FUA;
+               bp->b_flags &= ~XBF_FLUSH;
+               bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA);
 
                ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
                ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);