mem: Allocate cache writebacks before new MSHRs

This patch changes the order of writeback allocation such that any
writebacks resulting from a tag lookup (e.g. for an uncacheable
access), are added to the writebuffer before any new MSHR entries are
allocated. This ensures that the writebacks logically precedes the new
allocations.

The patch also changes the uncacheable flush to use proper timed (or
atomic) writebacks, as opposed to functional writes.

1 files changed, 0 insertions, 12 deletions

diff --git a/src/mem/cache/cache.hh b/src/mem/cache/cache.hh
index 0ee776e92..7971c6654 100644
--- a/src/mem/cache/cache.hh
+++ b/src/mem/cache/cache.hh
@@ -332,18 +332,6 @@ class Cache : public BaseCache
     bool invalidateVisitor(BlkType &blk);
 
     /**
-     * Flush a cache line due to an uncacheable memory access to the
-     * line.
-     *
-     * @note This shouldn't normally happen, but we need to handle it
-     * since some architecture models don't implement cache
-     * maintenance operations. We won't even try to get a decent
-     * timing here since the line should have been flushed earlier by
-     * a cache maintenance operation.
-     */
-    void uncacheableFlush(PacketPtr pkt);
-
-    /**
      * Squash all requests associated with specified thread.
      * intended for use by I-cache.
      * @param threadNum The thread to squash.