O3: Fix corner case squashing into the microcode ROM.

When fetching from the microcode ROM, if the PC is set so that it isn't in the
cache block that's been fetched the CPU will get stuck. The fetch stage
notices that it's in the ROM so it doesn't try to fetch from the current PC.
It then later notices that it's outside of the current cache block so it skips
generating instructions expecting to continue once the right bytes have been
fetched. This change lets the fetch stage attempt to generate instructions,
and only checks if the bytes it's going to use are valid if it's really going
to use them.

1 files changed, 14 insertions, 6 deletions

diff --git a/src/cpu/o3/fetch_impl.hh b/src/cpu/o3/fetch_impl.hh
index 832ca3767..84f2c3506 100644
--- a/src/cpu/o3/fetch_impl.hh
+++ b/src/cpu/o3/fetch_impl.hh
@@ -1238,14 +1238,22 @@ DefaultFetch<Impl>::fetch(bool &status_change)
     unsigned blkOffset = (fetchAddr - cacheDataPC[tid]) / instSize;
 
     // Loop through instruction memory from the cache.
-    // Keep issuing while we have not reached the end of the block or a
-    // macroop is active and fetchWidth is available and branch is not
+    // Keep issuing while fetchWidth is available and branch is not
     // predicted taken
-    while ((blkOffset < numInsts || curMacroop) &&
-                           numInst < fetchWidth && !predictedBranch) {
+    while (numInst < fetchWidth && !predictedBranch) {
+
+        // We need to process more memory if we aren't going to get a
+        // StaticInst from the rom, the current macroop, or what's already
+        // in the predecoder.
+        bool needMem = !inRom && !curMacroop && !predecoder.extMachInstReady();
+
+        if (needMem) {
+            if (blkOffset >= numInsts) {
+                // We need to process more memory, but we've run out of the
+                // current block.
+                break;
+            }
 
-        // If we need to process more memory, do it now.
-        if (!(curMacroop || inRom) && !predecoder.extMachInstReady()) {
             if (ISA_HAS_DELAY_SLOT && pcOffset == 0) {
                 // Walk past any annulled delay slot instructions.
                 Addr pcAddr = thisPC.instAddr() & BaseCPU::PCMask;