cpu: Fix LLSC atomic CPU wakeup

Writes to locked memory addresses (LLSC) did not wake up the locking
CPU. This can lead to deadlocks on multi-core runs. In AtomicSimpleCPU,
recvAtomicSnoop was checking if the incoming packet was an invalidation
(isInvalidate) and only then handled a locked snoop. But, writes are
seen instead of invalidates when running without caches (fast-forward
configurations). As as simple fix, now handleLockedSnoop is also called
even if the incoming snoop packet are from writes.

src/cpu/simple/atomic.cc

@@ -292,7 +292,10 @@ AtomicSimpleCPU::AtomicCPUDPort::recvAtomicSnoop(PacketPtr pkt)
     }
 
     // if snoop invalidates, release any associated locks
-    if (pkt->isInvalidate()) {
+    // When run without caches, Invalidation packets will not be received
+    // hence we must check if the incoming packets are writes and wakeup
+    // the processor accordingly
+    if (pkt->isInvalidate() || pkt->isWrite()) {
         DPRINTF(SimpleCPU, "received invalidation for addr:%#x\n",
                 pkt->getAddr());
         for (auto &t_info : cpu->threadInfo) {

src/cpu/simple/timing.cc

@@ -876,8 +876,14 @@ TimingSimpleCPU::DcachePort::recvTimingSnoopReq(PacketPtr pkt)
         }
     }
 
-    for (auto &t_info : cpu->threadInfo) {
-        TheISA::handleLockedSnoop(t_info->thread, pkt, cacheBlockMask);
+    // Making it uniform across all CPUs:
+    // The CPUs need to be woken up only on an invalidation packet (when using caches)
+    // or on an incoming write packet (when not using caches)
+    // It is not necessary to wake up the processor on all incoming packets
+    if (pkt->isInvalidate() || pkt->isWrite()) {
+        for (auto &t_info : cpu->threadInfo) {
+            TheISA::handleLockedSnoop(t_info->thread, pkt, cacheBlockMask);
+        }
     }
 }