diff --git a/src/mem/cache/base.cc b/src/mem/cache/base.cc
index 08cd09f..6049ca6 100644
--- a/src/mem/cache/base.cc
+++ b/src/mem/cache/base.cc
@@ -69,7 +69,8 @@
 BaseCache::CacheSlavePort::CacheSlavePort(const std::string &_name,
                                           BaseCache *_cache,
                                           const std::string &_label)
-    : QueuedSlavePort(_name, _cache, queue), queue(*_cache, *this, _label),
+    : QueuedSlavePort(_name, _cache, queue),
+      queue(*_cache, *this, true, _label),
       blocked(false), mustSendRetry(false),
       sendRetryEvent([this]{ processSendRetry(); }, _name)
 {
@@ -228,7 +229,7 @@
         // lat, neglecting responseLatency, modelling hit latency
         // just as the value of lat overriden by access(), which calls
         // the calculateAccessLatency() function.
-        cpuSidePort.schedTimingResp(pkt, request_time, true);
+        cpuSidePort.schedTimingResp(pkt, request_time);
     } else {
         DPRINTF(Cache, "%s satisfied %s, no response needed\n", __func__,
                 pkt->print());
@@ -400,7 +401,7 @@
     // Reset the bus additional time as it is now accounted for
     pkt->headerDelay = pkt->payloadDelay = 0;
 
-    cpuSidePort.schedTimingResp(pkt, completion_time, true);
+    cpuSidePort.schedTimingResp(pkt, completion_time);
 }
 
 void
@@ -2400,7 +2401,7 @@
                                     const std::string &_label)
     : CacheMasterPort(_name, _cache, _reqQueue, _snoopRespQueue),
       _reqQueue(*_cache, *this, _snoopRespQueue, _label),
-      _snoopRespQueue(*_cache, *this, _label), cache(_cache)
+      _snoopRespQueue(*_cache, *this, true, _label), cache(_cache)
 {
 }
 
diff --git a/src/mem/cache/cache.cc b/src/mem/cache/cache.cc
index 90c4b9b..e23c4ef 100644
--- a/src/mem/cache/cache.cc
+++ b/src/mem/cache/cache.cc
@@ -391,7 +391,7 @@
 
         // request_time is used here, taking into account lat and the delay
         // charged if the packet comes from the xbar.
-        cpuSidePort.schedTimingResp(pkt, request_time, true);
+        cpuSidePort.schedTimingResp(pkt, request_time);
 
         // If an outstanding request is in progress (we found an
         // MSHR) this is set to null
@@ -802,7 +802,7 @@
             }
             // Reset the bus additional time as it is now accounted for
             tgt_pkt->headerDelay = tgt_pkt->payloadDelay = 0;
-            cpuSidePort.schedTimingResp(tgt_pkt, completion_time, true);
+            cpuSidePort.schedTimingResp(tgt_pkt, completion_time);
             break;
 
           case MSHR::Target::FromPrefetcher:
@@ -932,7 +932,7 @@
     pkt->headerDelay = pkt->payloadDelay = 0;
     DPRINTF(CacheVerbose, "%s: created response: %s tick: %lu\n", __func__,
             pkt->print(), forward_time);
-    memSidePort.schedTimingSnoopResp(pkt, forward_time, true);
+    memSidePort.schedTimingSnoopResp(pkt, forward_time);
 }
 
 uint32_t
diff --git a/src/mem/cache/noncoherent_cache.cc b/src/mem/cache/noncoherent_cache.cc
index ca282a3..08cfdd6 100644
--- a/src/mem/cache/noncoherent_cache.cc
+++ b/src/mem/cache/noncoherent_cache.cc
@@ -288,7 +288,7 @@
 
             // Reset the bus additional time as it is now accounted for
             tgt_pkt->headerDelay = tgt_pkt->payloadDelay = 0;
-            cpuSidePort.schedTimingResp(tgt_pkt, completion_time, true);
+            cpuSidePort.schedTimingResp(tgt_pkt, completion_time);
             break;
 
           case MSHR::Target::FromPrefetcher:
diff --git a/src/mem/dram_ctrl.cc b/src/mem/dram_ctrl.cc
index e7af75b..b6ec465 100644
--- a/src/mem/dram_ctrl.cc
+++ b/src/mem/dram_ctrl.cc
@@ -938,7 +938,7 @@
 
         // queue the packet in the response queue to be sent out after
         // the static latency has passed
-        port.schedTimingResp(pkt, response_time, true);
+        port.schedTimingResp(pkt, response_time);
     } else {
         // @todo the packet is going to be deleted, and the DRAMPacket
         // is still having a pointer to it
@@ -2924,7 +2924,7 @@
 }
 
 DRAMCtrl::MemoryPort::MemoryPort(const std::string& name, DRAMCtrl& _memory)
-    : QueuedSlavePort(name, &_memory, queue), queue(_memory, *this),
+    : QueuedSlavePort(name, &_memory, queue), queue(_memory, *this, true),
       memory(_memory)
 { }
 
diff --git a/src/mem/packet_queue.cc b/src/mem/packet_queue.cc
index 7aa2fc1..45378ae 100644
--- a/src/mem/packet_queue.cc
+++ b/src/mem/packet_queue.cc
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012,2015 ARM Limited
+ * Copyright (c) 2012,2015,2018 ARM Limited
  * All rights reserved.
  *
  * The license below extends only to copyright in the software and shall
@@ -49,9 +49,11 @@
 
 PacketQueue::PacketQueue(EventManager& _em, const std::string& _label,
                          const std::string& _sendEventName,
+                         bool force_order,
                          bool disable_sanity_check)
     : em(_em), sendEvent([this]{ processSendEvent(); }, _sendEventName),
       _disableSanityCheck(disable_sanity_check),
+      forceOrder(force_order),
       label(_label), waitingOnRetry(false)
 {
 }
@@ -102,11 +104,11 @@
 }
 
 void
-PacketQueue::schedSendTiming(PacketPtr pkt, Tick when, bool force_order)
+PacketQueue::schedSendTiming(PacketPtr pkt, Tick when)
 {
     DPRINTF(PacketQueue, "%s for %s address %x size %d when %lu ord: %i\n",
             __func__, pkt->cmdString(), pkt->getAddr(), pkt->getSize(), when,
-            force_order);
+            forceOrder);
 
     // we can still send a packet before the end of this tick
     assert(when >= curTick());
@@ -137,13 +139,13 @@
     // assert(waitingOnRetry || sendEvent.scheduled());
 
     // this belongs in the middle somewhere, so search from the end to
-    // order by tick; however, if force_order is set, also make sure
+    // order by tick; however, if forceOrder is set, also make sure
     // not to re-order in front of some existing packet with the same
     // address
     auto i = transmitList.end();
     --i;
     while (i != transmitList.begin() && when < i->tick &&
-           !(force_order && i->pkt->getAddr() == pkt->getAddr()))
+           !(forceOrder && i->pkt->getAddr() == pkt->getAddr()))
         --i;
 
     // emplace inserts the element before the position pointed to by
@@ -250,8 +252,9 @@
 
 SnoopRespPacketQueue::SnoopRespPacketQueue(EventManager& _em,
                                            MasterPort& _masterPort,
+                                           bool force_order,
                                            const std::string _label)
-    : PacketQueue(_em, _label, name(_masterPort, _label)),
+    : PacketQueue(_em, _label, name(_masterPort, _label), force_order),
       masterPort(_masterPort)
 {
 }
@@ -263,8 +266,9 @@
 }
 
 RespPacketQueue::RespPacketQueue(EventManager& _em, SlavePort& _slavePort,
+                                 bool force_order,
                                  const std::string _label)
-    : PacketQueue(_em, _label, name(_slavePort, _label)),
+    : PacketQueue(_em, _label, name(_slavePort, _label), force_order),
       slavePort(_slavePort)
 {
 }
diff --git a/src/mem/packet_queue.hh b/src/mem/packet_queue.hh
index 629fca5..4ac4bf3 100644
--- a/src/mem/packet_queue.hh
+++ b/src/mem/packet_queue.hh
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012,2015 ARM Limited
+ * Copyright (c) 2012,2015,2018 ARM Limited
  * All rights reserved.
  *
  * The license below extends only to copyright in the software and shall
@@ -96,6 +96,13 @@
       */
     bool _disableSanityCheck;
 
+    /**
+     * if true, inserted packets have to be unconditionally scheduled
+     * after the last packet in the queue that references the same
+     * address
+     */
+    bool forceOrder;
+
   protected:
 
     /** Label to use for print request packets label stack. */
@@ -130,11 +137,13 @@
      *
      * @param _em Event manager used for scheduling this queue
      * @param _label Label to push on the label stack for print request packets
+     * @param force_order Force insertion order for packets with same address
      * @param disable_sanity_check Flag used to disable the sanity check
      *        on the size of the transmitList. The check is enabled by default.
      */
     PacketQueue(EventManager& _em, const std::string& _label,
                 const std::string& _sendEventName,
+                bool force_order = false,
                 bool disable_sanity_check = false);
 
     /**
@@ -187,9 +196,8 @@
      *
      * @param pkt Packet to send
      * @param when Absolute time (in ticks) to send packet
-     * @param force_order Force insertion order for packets with same address
      */
-    void schedSendTiming(PacketPtr pkt, Tick when, bool force_order = false);
+    void schedSendTiming(PacketPtr pkt, Tick when);
 
     /**
      * Retry sending a packet from the queue. Note that this is not
@@ -267,9 +275,11 @@
      *
      * @param _em Event manager used for scheduling this queue
      * @param _masterPort Master port used to send the packets
+     * @param force_order Force insertion order for packets with same address
      * @param _label Label to push on the label stack for print request packets
      */
     SnoopRespPacketQueue(EventManager& _em, MasterPort& _masterPort,
+                         bool force_order = false,
                          const std::string _label = "SnoopRespPacketQueue");
 
     virtual ~SnoopRespPacketQueue() { }
@@ -303,10 +313,12 @@
      *
      * @param _em Event manager used for scheduling this queue
      * @param _slavePort Slave port used to send the packets
+     * @param force_order Force insertion order for packets with same address
      * @param _label Label to push on the label stack for print request packets
      */
     RespPacketQueue(EventManager& _em, SlavePort& _slavePort,
-                     const std::string _label = "RespPacketQueue");
+                    bool force_order = false,
+                    const std::string _label = "RespPacketQueue");
 
     virtual ~RespPacketQueue() { }
 
diff --git a/src/mem/qos/mem_sink.cc b/src/mem/qos/mem_sink.cc
index a951dae..77cfbaf 100644
--- a/src/mem/qos/mem_sink.cc
+++ b/src/mem/qos/mem_sink.cc
@@ -289,7 +289,7 @@
                 removed_entries, responseLatency);
 
     // Schedule the response
-    port.schedTimingResp(pkt, curTick() + responseLatency, true);
+    port.schedTimingResp(pkt, curTick() + responseLatency);
     DPRINTF(QOS,
             "%s response scheduled at time %d\n",
             __func__, curTick() + responseLatency);
@@ -344,7 +344,7 @@
 
 MemSinkCtrl::MemoryPort::MemoryPort(const std::string& n,
                                     MemSinkCtrl& m)
-  : QueuedSlavePort(n, &m, queue), memory(m), queue(memory, *this)
+  : QueuedSlavePort(n, &m, queue, true), memory(m), queue(memory, *this, true)
 {}
 
 AddrRangeList
diff --git a/src/mem/qport.hh b/src/mem/qport.hh
index 708347a..77d8dfa 100644
--- a/src/mem/qport.hh
+++ b/src/mem/qport.hh
@@ -88,8 +88,8 @@
      * @param pkt Packet to send
      * @param when Absolute time (in ticks) to send packet
      */
-    void schedTimingResp(PacketPtr pkt, Tick when, bool force_order = false)
-    { respQueue.schedSendTiming(pkt, when, force_order); }
+    void schedTimingResp(PacketPtr pkt, Tick when)
+    { respQueue.schedSendTiming(pkt, when); }
 
     /** Check the list of buffered packets against the supplied
      * functional request. */
@@ -153,9 +153,8 @@
      * @param pkt Packet to send
      * @param when Absolute time (in ticks) to send packet
      */
-    void schedTimingSnoopResp(PacketPtr pkt, Tick when, bool force_order =
-                              false)
-    { snoopRespQueue.schedSendTiming(pkt, when, force_order); }
+    void schedTimingSnoopResp(PacketPtr pkt, Tick when)
+    { snoopRespQueue.schedSendTiming(pkt, when); }
 
     /** Check the list of buffered packets against the supplied
      * functional request. */
diff --git a/src/mem/ruby/slicc_interface/AbstractController.cc b/src/mem/ruby/slicc_interface/AbstractController.cc
index 101a4ce..1327ecc 100644
--- a/src/mem/ruby/slicc_interface/AbstractController.cc
+++ b/src/mem/ruby/slicc_interface/AbstractController.cc
@@ -382,7 +382,7 @@
                                            const std::string &_label)
     : QueuedMasterPort(_name, _controller, reqQueue, snoopRespQueue),
       reqQueue(*_controller, *this, _label),
-      snoopRespQueue(*_controller, *this, _label),
+      snoopRespQueue(*_controller, *this, false, _label),
       controller(_controller)
 {
 }