summaryrefslogtreecommitdiff
path: root/src/mem
diff options
context:
space:
mode:
authorSteve Reinhardt <stever@gmail.com>2008-06-13 01:29:20 -0400
committerSteve Reinhardt <stever@gmail.com>2008-06-13 01:29:20 -0400
commit024ec4c5c310b1225a52532d41d5cc9f2633ae6c (patch)
treee2792fceab44c2fe9518fd40d2d5ad27d74de945 /src/mem
parent2b4874449ce45504a1759c593a1f9b00983fca01 (diff)
downloadgem5-024ec4c5c310b1225a52532d41d5cc9f2633ae6c.tar.xz
Get rid of bogus cache assertion.
I was asserting that the only reason you would defer targets is if a write came in while you had an outstanding read miss, but there's another case where you could get a read access after you've snooped an invalidation and buffered it because it applies to a prior outstanding miss.
Diffstat (limited to 'src/mem')
-rw-r--r--src/mem/cache/cache_impl.hh1
1 files changed, 0 insertions, 1 deletions
diff --git a/src/mem/cache/cache_impl.hh b/src/mem/cache/cache_impl.hh
index 7bab3012b..3b56c0a2e 100644
--- a/src/mem/cache/cache_impl.hh
+++ b/src/mem/cache/cache_impl.hh
@@ -823,7 +823,6 @@ Cache<TagStore>::handleResponse(PacketPtr pkt)
}
if (mshr->promoteDeferredTargets()) {
- assert(mshr->needsExclusive() && !blk->isWritable());
// avoid later read getting stale data while write miss is
// outstanding.. see comment in timingAccess()
blk->status &= ~BlkReadable;