mem: Delay deleting of incoming packets by one call.

This patch is a temporary fix until Andreas' four-phase patches
get reviewed and committed. Removing FastAlloc seems to have exposed
an issue which previously was reasonable rare in which packets are freed
before the sending cache is done with them. This change puts incoming packets
no a pendingDelete queue which are deleted at the start of the next call and
thus breaks the dependency between when the caller returns true and when the
packet is actually used by the sending cache.

Running valgrind on a multi-core linux boot and the memtester results in no
valgrind warnings.

1 files changed, 7 insertions, 0 deletions

diff --git a/src/mem/cache/cache.hh b/src/mem/cache/cache.hh
index 04421b1e5..beb3903da 100644
--- a/src/mem/cache/cache.hh
+++ b/src/mem/cache/cache.hh
@@ -191,6 +191,13 @@ class Cache : public BaseCache
     const bool prefetchOnAccess;
 
     /**
+     * @todo this is a temporary workaround until the 4-phase code is committed.
+     * upstream caches need this packet until true is returned, so hold it for
+     * deletion until a subsequent call
+     */
+    std::vector<PacketPtr> pendingDelete;
+
+    /**
      * Does all the processing necessary to perform the provided request.
      * @param pkt The memory request to perform.
      * @param lat The latency of the access.