O3: Fix issue w/wbOutstading being decremented multiple times on blocked cache.

If a split load fails on a blocked cache wbOutstanding can be decremented
twice if the first part of the split load succeeds and the second part fails.
Condition the decrementing on not having completed the first part of the load.

src/cpu/o3/iew.hh

@@ -228,7 +228,7 @@ class DefaultIEW
     {
         if (++wbOutstanding == wbMax)
             ableToIssue = false;
-        DPRINTF(IEW, "wbOutstanding: %i\n", wbOutstanding);
+        DPRINTF(IEW, "wbOutstanding: %i [sn:%lli]\n", wbOutstanding, sn);
         assert(wbOutstanding <= wbMax);
 #ifdef DEBUG
         wbList.insert(sn);

src/cpu/o3/iew_impl.hh

@@ -1221,7 +1221,9 @@ DefaultIEW<Impl>::executeInsts()
 
         // Check if the instruction is squashed; if so then skip it
         if (inst->isSquashed()) {
-            DPRINTF(IEW, "Execute: Instruction was squashed.\n");
+            DPRINTF(IEW, "Execute: Instruction was squashed. PC: %s, [tid:%i]"
+                         " [sn:%i]\n", inst->pcState(), inst->threadNumber,
+                         inst->seqNum);
 
             // Consider this instruction executed so that commit can go
             // ahead and retire the instruction.

src/cpu/o3/lsq_unit.hh

@@ -804,7 +804,12 @@ LSQUnit<Impl>::read(Request *req, Request *sreqLow, Request *sreqHigh,
 
         ++lsqCacheBlocked;
 
+        // If the first part of a split access succeeds, then let the LSQ
+        // handle the decrWb when completeDataAccess is called upon return
+        // of the requested first part of data
+        if (!completedFirst)
             iewStage->decrWb(load_inst->seqNum);
+
         // There's an older load that's already going to squash.
         if (isLoadBlocked && blockedLoadSeqNum < load_inst->seqNum)
             return NoFault;