gem5/src/mem/cache
Ron Dreslinski 903a618714 Fix a bug to handle the fact that a CPU can send Functional accesses while a sendTiming has not returned in the call stack.
src/mem/cache/base_cache.cc:
    Sometimes a functional access comes while waiting on a outstanding packet being sent.
    This could be because Timing CPU does some post processing on the recvTiming which send functional access.
    Either the CPU should leave the pkt/req around (so They can be referenced in the mem system). Or the mem
    system should remove them from outstanding lists and reinsert them if they fail in the sendTiming.

    I did the later, eventually we should consider doing the former if that is the correct behavior.

--HG--
extra : convert_revision : be41e0d2632369dca9d7c15e96e5576d7583fe6a
2006-11-13 22:37:22 -05:00
..
coherence Refactor coherence state table initialization. 2006-10-21 13:43:14 -07:00
miss If we didn't satisfy all targets, reset the packet we are requesting with. 2006-11-13 21:34:25 -05:00
prefetch Use PacketPtr everywhere 2006-10-20 00:10:12 -07:00
tags s/pktuest/request/ (all in comments) 2006-10-22 20:38:34 -07:00
base_cache.cc Fix a bug to handle the fact that a CPU can send Functional accesses while a sendTiming has not returned in the call stack. 2006-11-13 22:37:22 -05:00
base_cache.hh Since cpus now send out snoop ranges, remove it from the cache. 2006-11-13 19:00:50 -05:00
cache.cc Was having difficulty with merging the cache, reverted to an early version and will add back in the patches to make it work soon. 2006-06-28 11:02:14 -04:00
cache.hh Use PacketPtr everywhere 2006-10-20 00:10:12 -07:00
cache_blk.hh First cut at LL/SC support in caches (atomic mode only). 2006-10-19 00:33:33 -07:00
cache_builder.cc Get rid of obsolete in-cache copy support. 2006-10-18 08:16:22 -07:00
cache_impl.hh Handle packets being deleted by lower level properly. 2006-11-12 09:06:15 -05:00