Commit graph

52 commits

Author SHA1 Message Date
Andreas Hansson
13ef7a5647 MEM: Differentiate functional cache accesses from CPU and memory
This patch changes the functionalAccess member function in the cache
model such that it is aware of what port the access came from, i.e. if
it came from the CPU side or from the memory side. By adding this
information, it is possible to respect the 'forwardSnoops' flag for
snooping requests coming from the memory side and not forward
them. This fixes an outstanding issue with the IO bus getting accesses
that have no valid destination port and also cleans up future changes
to the bus model.
2012-01-17 12:55:07 -06:00
Nathan Binkert
39a055645f includes: sort all includes 2011-04-15 10:44:06 -07:00
Steve Reinhardt
71aca6d29e cache: coherence protocol enhancements & bug fixes
Allow lower-level caches (e.g., L2 or L3) to pass exclusive
copies to higher levels (e.g., L1).  This eliminates a lot
of unnecessary upgrade transactions on read-write sequences
to non-shared data.

Also some cleanup of MSHR coherence handling and multiple
bug fixes.
2010-09-09 14:40:18 -04:00
Steve Reinhardt
6629d9b2bc mem: use single BadAddr responder per system.
Previously there was one per bus, which caused some coherence problems
when more than one decided to respond.  Now there is just one on
the main memory bus.  The default bus responder on all other buses
is now the downstream cache's cpu_side port.  Caches no longer need
to do address range filtering; instead, we just have a simple flag
to prevent snoops from propagating to the I/O bus.
2008-07-16 11:10:33 -07:00
Steve Reinhardt
89a7fb0393 Fixes to get prefetching working again.
Apparently we broke it with the cache rewrite and never noticed.
Thanks to Bao Yungang <baoyungang@gmail.com> for a significant part
of these changes (and for inspiring me to work on the rest).
Some other overdue cleanup on the prefetch code too.
2009-02-16 08:56:40 -08:00
Lisa Hsu
8788d703f8 s/cpu_id/cpuId in o3 (to be consistent and match style), also fix some typos in
comments.
2008-10-23 16:49:17 -04:00
Lisa Hsu
546a6c0c1b probe function no longer used anywhere. 2008-10-23 16:49:13 -04:00
Lisa Hsu
90e40ca982 This function declaration isn't used anywhere.
HG: user: Lisa Hsu <hsul@eecs.umich.edu> HG: branch default HG: changed
src/mem/cache/cache.hh
2008-10-14 17:22:03 -04:00
Steve Reinhardt
caaac16803 Backed out changeset 94a7bb476fca: caused memory leak. 2008-06-28 13:19:38 -04:00
Steve Reinhardt
6b45238316 Generate more useful error messages for unconnected ports.
Force all non-default ports to provide a name and an
owner in the constructor.
2008-06-21 01:04:43 -04:00
Steve Reinhardt
29be31ce31 Fix handling of writeback-induced writebacks in atomic mode.
--HG--
extra : convert_revision : 4fa64f8a929f1aa36a9d5a71b8d1816b497aca4c
2008-03-25 10:01:21 -04:00
Steve Reinhardt
bdf3323915 Cache: better comments particularly regarding writeback situation.
--HG--
extra : convert_revision : 59ff9ee63ee0fec5a7dfc27b485b737455ccf362
2008-02-26 20:17:26 -08:00
Steve Reinhardt
4597a71cef Make L2+ caches allocate new block for writeback misses
instead of forwarding down the line.

--HG--
extra : convert_revision : b0d6e7862c92ea7a2d21f817d30398735e7bb8ba
2008-02-16 14:58:03 -05:00
Steve Reinhardt
9d7a69c582 Fix #include lines for renamed cache files.
--HG--
extra : convert_revision : b5008115dc5b34958246608757e69a3fa43b85c5
2008-02-10 14:45:25 -08:00
Steve Reinhardt
6c5a3ab8b2 Add ReadRespWithInvalidate to handle multi-level coherence situation
where we defer a response to a read from a far-away cache A, then later
defer a ReadExcl from a cache B on the same bus as us.  We'll assert
MemInhibit in both cases, but in the latter case MemInhibit will keep
the invalidation from reaching cache A.  This special response tells
cache A that it gets the block to satisfy its read, but must immediately
invalidate it.

--HG--
extra : convert_revision : f85c8b47bb30232da37ac861b50a6539dc81161b
2008-01-02 15:22:38 -08:00
Steve Reinhardt
3952e41ab1 Add functional PrintReq command for memory-system debugging.
--HG--
extra : convert_revision : 73b753e57c355b7e6873f047ddc8cb371c3136b7
2008-01-02 12:20:15 -08:00
Miles Kaufmann
54cc0053f0 params: Deprecate old-style constructors; update most SimObject constructors.
SimObjects not yet updated:
- Process and subclasses
- BaseCPU and subclasses

The SimObject(const std::string &name) constructor was removed.  Subclasses
that still rely on that behavior must call the parent initializer as
  : SimObject(makeParams(name))

--HG--
extra : convert_revision : d6faddde76e7c3361ebdbd0a7b372a40941c12ed
2007-08-30 15:16:59 -04:00
Ali Saidi
06a9f58c68 DMA: Add IOCache and fix bus bridge to optionally only send requests one
way so a cache can handle partial block requests for i/o devices.

--HG--
extra : convert_revision : a68b5ae826731bc87ed93eb7ef326a2393053964
2007-08-10 16:14:01 -04:00
Steve Reinhardt
82e2a35576 Replace lowerMSHRPending flag with more robust scheme
based on following Packet senderState links.

--HG--
extra : convert_revision : 9027d59bd7242aa0e4275bf94d8b1fb27bd59d79
2007-07-22 21:43:38 -07:00
Steve Reinhardt
1c2d5f5e64 Replace DeferredSnoop flag with LowerMSHRPending flag.
Turns out DeferredSnoop isn't quite the right bit of info
we needed... see new comment in cache_impl.hh.

--HG--
extra : convert_revision : a38de8c1677a37acafb743b7074ef88b21d3b7be
2007-07-22 08:09:24 -07:00
Steve Reinhardt
9117c94f9c Get rid of coherence protocol object.
--HG--
extra : convert_revision : 4ff144342dca23af9a12a2169ca318a002654b42
2007-06-27 20:54:13 -07:00
Steve Reinhardt
c4903e0882 Revamp replacement-of-upgrade handling.
--HG--
extra : convert_revision : 9bc09d8ae6d50e6dfbb4ab21514612f9aa102a2e
2007-06-26 23:30:30 -07:00
Steve Reinhardt
1b20df5607 Handle deferred snoops better.
--HG--
extra : convert_revision : 703da6128832eb0d5cfed7724e5105f4b3fe4f90
2007-06-26 22:23:10 -07:00
Steve Reinhardt
47bce8ef78 Better handling of deferred targets.
--HG--
extra : convert_revision : 0fbc28c32c1eeb3dd672df14c1d53bd516f81d0f
2007-06-24 17:32:31 -07:00
Steve Reinhardt
bdd5fd20fb Fixes to hitLatency, blocking, buffer allocation.
Single-cpu timing mode seems to work now.

--HG--
extra : convert_revision : 720f6172df18a1c941e5bd0e8fdfbd686c13c7ad
2007-06-22 09:24:07 -07:00
Steve Reinhardt
83af0fdcf5 Getting closer...
configs/example/memtest.py:
    Add progress interval option.
src/base/traceflags.py:
    Add MemTest flag.
src/cpu/memtest/memtest.cc:
    Clean up tracing.
src/cpu/memtest/memtest.hh:
    Get rid of unused code.

--HG--
extra : convert_revision : 92bd8241a6c90bfb6d908e5a5132cbdb500cbb87
2007-06-21 11:59:17 -07:00
Steve Reinhardt
35cf19d441 More major reorg of cache. Seems to work for atomic mode now,
timing mode still broken.

configs/example/memtest.py:
    Revamp options.
src/cpu/memtest/memtest.cc:
    No need for memory initialization.
    No need to make atomic response... memory system should do that now.
src/cpu/memtest/memtest.hh:
    MemTest really doesn't want to snoop.
src/mem/bridge.cc:
    checkFunctional() cleanup.
src/mem/bus.cc:
src/mem/bus.hh:
src/mem/cache/base_cache.cc:
src/mem/cache/base_cache.hh:
src/mem/cache/cache.cc:
src/mem/cache/cache.hh:
src/mem/cache/cache_blk.hh:
src/mem/cache/cache_builder.cc:
src/mem/cache/cache_impl.hh:
src/mem/cache/coherence/coherence_protocol.cc:
src/mem/cache/coherence/coherence_protocol.hh:
src/mem/cache/coherence/simple_coherence.hh:
src/mem/cache/miss/SConscript:
src/mem/cache/miss/mshr.cc:
src/mem/cache/miss/mshr.hh:
src/mem/cache/miss/mshr_queue.cc:
src/mem/cache/miss/mshr_queue.hh:
src/mem/cache/prefetch/base_prefetcher.cc:
src/mem/cache/tags/fa_lru.cc:
src/mem/cache/tags/fa_lru.hh:
src/mem/cache/tags/iic.cc:
src/mem/cache/tags/iic.hh:
src/mem/cache/tags/lru.cc:
src/mem/cache/tags/lru.hh:
src/mem/cache/tags/split.cc:
src/mem/cache/tags/split.hh:
src/mem/cache/tags/split_lifo.cc:
src/mem/cache/tags/split_lifo.hh:
src/mem/cache/tags/split_lru.cc:
src/mem/cache/tags/split_lru.hh:
src/mem/packet.cc:
src/mem/packet.hh:
src/mem/physical.cc:
src/mem/physical.hh:
src/mem/tport.cc:
    More major reorg.  Seems to work for atomic mode now,
    timing mode still broken.

--HG--
extra : convert_revision : 7e70dfc4a752393b911880ff028271433855ae87
2007-06-17 17:27:53 -07:00
Steve Reinhardt
da46364b18 Fix getDeviceAddressRanges() to get snooping right.
--HG--
extra : convert_revision : 2aeab25ef955ab9db7b968786faff227239fbbe4
2007-05-22 07:30:55 -07:00
Steve Reinhardt
792d5b9e5e First set of changes for reorganized cache coherence support.
Compiles but doesn't work... committing just so I can merge
(stupid bk!).

src/mem/bridge.cc:
    Get rid of SNOOP_COMMIT.
src/mem/bus.cc:
src/mem/packet.hh:
    Get rid of SNOOP_COMMIT & two-pass snoop.
    First bits of EXPRESS_SNOOP support.
src/mem/cache/base_cache.cc:
src/mem/cache/base_cache.hh:
src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
src/mem/cache/miss/blocking_buffer.cc:
src/mem/cache/miss/miss_queue.cc:
src/mem/cache/prefetch/base_prefetcher.cc:
    Big reorg of ports and port-related functions & events.
src/mem/cache/cache.cc:
src/mem/cache/cache_builder.cc:
src/mem/cache/coherence/SConscript:
    Get rid of UniCoherence object.

--HG--
extra : convert_revision : 7672434fa3115c9b1c94686f497e57e90413b7c3
2007-05-18 22:35:04 -07:00
Ron Dreslinski
6b8cd9d06d First Pass At Cmp/Swap in caches
--HG--
extra : convert_revision : 211bfb7c6a59e9e120dae1600d4754baaf231332
2007-03-27 17:05:25 -05:00
Ali Saidi
027dfa01e6 stop m5 from leaking like a sieve
don't create a new physPort/virtPort every time activateContext() is called
add the ability to tell a memory object to delete it's reference to a port and a method to have a port call deletePortRefs()
on the port owner as well as delete it's peer
still need to stop calling connectMemoPorts() every time activateContext() is called or we'll overflow the bus id and panic

src/cpu/thread_state.cc:
    if we hav ea (phys|virt)Port don't create a new on, have it delete it's peer and then reuse it
src/mem/bus.cc:
src/mem/bus.hh:
    add ability to delete a port by usig a hash_map instead of an array to store port ids
    add a function to do deleting
src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
src/mem/mem_object.cc:
src/mem/mem_object.hh:
    adda function to delete port references from a memory object
src/mem/port.cc:
src/mem/port.hh:
    add a removeConn function that tell the owener to delete any references to the port and then deletes its peer

--HG--
extra : convert_revision : 272f0c8f80e1cf1ab1750d8be5a6c9aa110b06a4
2007-03-08 18:57:15 -05:00
Steve Reinhardt
9d7db8bb2b Streamline Cache/Tags interface: get rid of redundant functions,
don't regenerate address from block in cache so that tags can
turn around and use address to look up block again.

--HG--
extra : convert_revision : 171018aa6e331d98399c4e5ef24e173c95eaca28
2006-12-18 23:07:52 -08:00
Steve Reinhardt
f655932700 No need to template prefetcher on cache TagStore type.
--HG--
rename : src/mem/cache/prefetch/tagged_prefetcher_impl.hh => src/mem/cache/prefetch/tagged_prefetcher.cc
extra : convert_revision : 56c0b51e424a3a6590332dba4866e69a1ad19598
2006-12-18 21:53:06 -08:00
Steve Reinhardt
1428b0de7d Get rid of generic CacheTags object (fold back into Cache).
--HG--
extra : convert_revision : 8769bd8cc358ab3cbbdbbcd909b2e0f1515e09da
2006-12-18 20:47:12 -08:00
Steve Reinhardt
d172e1576a Split CachePort class into CpuSidePort and MemSidePort
and push those into derived Cache template class to
eliminate a few layers of virtual functions and
conditionals ("if (isCpuSide) { ... }" etc.).

--HG--
extra : convert_revision : cb1b88246c95b36aa0cf26d534127d3714ddb774
2006-12-13 22:04:36 -08:00
Steve Reinhardt
5fbf3aa471 Turn cache MissQueue/BlockingBuffer into virtual object
instead of template parameter.

--HG--
extra : convert_revision : fce0fbd041149b9c781eb23f480ba84fddbfd4a0
2006-12-04 09:10:53 -08:00
Nathan Binkert
a4c6f0d69e Use PacketPtr everywhere
--HG--
extra : convert_revision : d9eb83ab77ffd2d725961f295b1733137e187711
2006-10-20 00:10:12 -07:00
Steve Reinhardt
6cd187e1f0 Get rid of obsolete in-cache copy support.
--HG--
extra : convert_revision : a701ed9d078c67718a33f4284c0403a8aaac7b25
2006-10-18 08:16:22 -07:00
Ron Dreslinski
a17afb1649 Fix for DMA's in FS caches.
Fix CSHR's for flow control.
Fix for Bus Bridges reusing packets (clean flags up)

Now both timing/atomic caches with MOESI in UP fail at same point.

src/dev/io_device.hh:
    DMA's should send WriteInvalidates
src/mem/bridge.cc:
    Reusing packet, clean flags in the packet set by bus.
src/mem/cache/base_cache.cc:
src/mem/cache/base_cache.hh:
src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
src/mem/cache/coherence/simple_coherence.hh:
src/mem/cache/coherence/uni_coherence.cc:
src/mem/cache/coherence/uni_coherence.hh:
    Fix CSHR's for flow control.
src/mem/packet.hh:
    Make a writeInvalidateResp, since the DMA expects responses to it's writes

--HG--
extra : convert_revision : 59fd6658bcc0d076f4b143169caca946472a86cd
2006-10-13 15:47:05 -04:00
Ron Dreslinski
cc78d86661 Fix several bugs pertaining to upgrades/mem leaks.
src/mem/cache/base_cache.cc:
    Fix a bug about not having a request to send
src/mem/cache/base_cache.hh:
    Fix a bug with the blocking code
src/mem/cache/cache.hh:
    AFix a bug with snoop hits in WB buffer
src/mem/cache/cache_impl.hh:
    Fix a bug with snoop hits in WB buffer
    Also, add better DPRINTF's
src/mem/cache/miss/miss_queue.cc:
    Fix a bug with upgrades (Need to clean it up later)
src/mem/cache/miss/mshr.cc:
    Fix a memory leak bug, still some outstanding with writebacks not being deleted
src/mem/cache/miss/mshr_queue.cc:
    Fix a bug about upgrades (need to clean up later)
src/mem/packet.hh:
    Fix for newly added cmd attribute for upgrades
tests/configs/memtest.py:
    More interesting testcase

--HG--
extra : convert_revision : fcb4f17dd58b537bb4f67a8c835f50e455e8c688
2006-10-10 01:32:18 -04:00
Ron Dreslinski
afce51d10a Set size properly on uncache accesses
Don't use the senderState after you get a succesful sendTiming.  Not guarnteed to be correct

src/mem/cache/base_cache.cc:
src/mem/cache/base_cache.hh:
src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
src/mem/cache/miss/blocking_buffer.cc:
src/mem/cache/miss/blocking_buffer.hh:
src/mem/cache/miss/miss_queue.hh:
    Don't use the senderState after you get a succesful sendTiming.  Not guarnteed to be correct

--HG--
extra : convert_revision : 2e8e812bf7fd3ba2b4cba7f7173cb41862f761af
2006-10-09 16:37:02 -04:00
Ron Dreslinski
212c5aefb5 Fixes for functional accesses to use the snoop path.
And small other tweaks to snooping coherence.

src/mem/cache/base_cache.hh:
    Make timing response at the time of send.
src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
    Update probe interface to be bi-directional for functional accesses
src/mem/packet.hh:
    Add the function to create an atomic response to a given request

--HG--
extra : convert_revision : 04075a117cf30a7df16e6d3ce485543cc77d4ca6
2006-10-05 23:28:03 -04:00
Ron Dreslinski
d5ac1cb51f Pulled out changes to fix EIO programs with caches. Also fixes any translatingPort read/write Blob function problems with caches.
-Basically removed the ASID from places it is no longer needed due to PageTable

src/mem/cache/cache.hh:
src/mem/cache/cache_impl.hh:
src/mem/cache/miss/blocking_buffer.cc:
src/mem/cache/miss/blocking_buffer.hh:
src/mem/cache/miss/miss_queue.cc:
src/mem/cache/miss/miss_queue.hh:
src/mem/cache/miss/mshr.cc:
src/mem/cache/miss/mshr.hh:
src/mem/cache/miss/mshr_queue.cc:
src/mem/cache/miss/mshr_queue.hh:
src/mem/cache/prefetch/base_prefetcher.cc:
src/mem/cache/prefetch/base_prefetcher.hh:
src/mem/cache/tags/fa_lru.cc:
src/mem/cache/tags/fa_lru.hh:
src/mem/cache/tags/iic.cc:
src/mem/cache/tags/iic.hh:
src/mem/cache/tags/lru.cc:
src/mem/cache/tags/lru.hh:
src/mem/cache/tags/split.cc:
src/mem/cache/tags/split.hh:
src/mem/cache/tags/split_lifo.cc:
src/mem/cache/tags/split_lifo.hh:
src/mem/cache/tags/split_lru.cc:
src/mem/cache/tags/split_lru.hh:
    Remove asid where it wasn't neccesary anymore due to Page Table

--HG--
extra : convert_revision : ab8bbf4cc47b9eaefa9cdfa790881a21d0e7bf28
2006-08-15 16:21:46 -04:00
Steve Reinhardt
5bd07f98ed Fix up doxygen.
--HG--
rename : docs/footer.html => src/doxygen/footer.html
rename : docs/stl.hh => src/doxygen/stl.hh
extra : convert_revision : 2b2e5637930843c1be07deaa708fd4126213cda2
2006-08-14 19:25:07 -04:00
Ron Dreslinski
1ccfdb442f Timing cache works for hello world test.
Still need
1) detailed CPU (blocking ability in cache)
1a) Multiple outstanding requests (need to keep track of times for events)
2)Multi-level support
3)MP coherece support
4)LL/SC support
5)Functional path needs to be correctly implemented (temporarily works without multiple outstanding requests (simple cpu))

src/cpu/simple/timing.cc:
    Temp hack because timing cpu doesn't export ports properly so single I/D cache communicates only through the Icache port.
src/mem/cache/base_cache.cc:
    Handle marking MSHR's in service
    Add support for getting CSHR's
src/mem/cache/base_cache.hh:
    Make these functions visible at the base cache level
src/mem/cache/cache.hh:
    make the functions virtual
src/mem/cache/cache_impl.hh:
    Rename the function to make sense
src/mem/packet.hh:
    Accidentally clearing the needsResponse field when sending a response back.

--HG--
extra : convert_revision : 2325d4e0b77e470fa9da91490317dc8ed88b17e2
2006-07-06 16:52:05 -04:00
Ron Dreslinski
329e32f8c6 Now timing reads work in single level of cache with simple cpu
src/mem/cache/base_cache.cc:
src/mem/cache/base_cache.hh:
src/mem/cache/cache.hh:
    Changes to handle timing reads in Simple CPU (blocking buffers)

--HG--
extra : convert_revision : a2e7d4287d7cdfd1bbf9c929ecbeafde499a5b9f
2006-07-06 15:15:37 -04:00
Ron Dreslinski
1bdc65b00f First pass, now compiles with current head of tree.
Compile and initialization work, still working on functionality.

src/mem/cache/base_cache.cc:
    Temp fix for cpu's use of getPort functionality.  CPU's will need to be ported to the new connector objects.
    Also, all packets have to have data or the delete fails.
src/mem/cache/cache.hh:
    Fix function prototypes so overloading works
src/mem/cache/cache_impl.hh:
    fix functions to match virtual base class
src/mem/cache/miss/miss_queue.cc:
    Packets havve to have data, or delete fails
src/python/m5/objects/BaseCache.py:
    Update for newmem

--HG--
extra : convert_revision : 2b6ad1e9d8ae07ace9294cd257e2ccc0024b7fcb
2006-06-30 16:25:35 -04:00
Ron Dreslinski
dea1a19b2d Fix the packet data allocation methods. Small fixes from changesets after my initial work.
This now compiles.

src/mem/cache/base_cache.cc:
    Fix getPort function that changed
src/mem/cache/base_cache.hh:
    Fix get port function, provide default implementations of virtual functions in the base class
src/mem/cache/cache.hh:
    Fix virtual function declerations
src/mem/cache/cache_builder.cc:
    Fix params
src/mem/cache/cache_impl.hh:
src/mem/cache/miss/blocking_buffer.cc:
src/mem/cache/miss/miss_queue.cc:
src/mem/cache/miss/mshr.cc:
src/mem/cache/prefetch/base_prefetcher.cc:
src/mem/cache/tags/iic.cc:
src/mem/cache/tags/lru.cc:
    Properly allocate data in packet

--HG--
extra : convert_revision : dedf8b0f76ab90b06b60f8fe079c0ae361f91a48
2006-06-30 11:34:27 -04:00
Ron Dreslinski
eafb5c4936 Still missing prefetch and tags directories as well as cache builder.
Some implementation details were left blank still, need to fill them in.

src/SConscript:
    Reorder build to compile all files first
src/mem/cache/cache.hh:
src/mem/cache/cache_builder.cc:
src/mem/cache/cache_impl.hh:
src/mem/cache/coherence/coherence_protocol.cc:
src/mem/cache/coherence/uni_coherence.cc:
src/mem/cache/coherence/uni_coherence.hh:
src/mem/cache/miss/blocking_buffer.cc:
src/mem/cache/miss/miss_queue.cc:
src/mem/cache/miss/mshr.cc:
src/mem/cache/miss/mshr.hh:
src/mem/cache/miss/mshr_queue.cc:
    More changesets pulled, now compiles everything in /miss directory and in the root directory
src/mem/packet.hh:
    Add some more support, need to clean some of it out once everything is working

--HG--
extra : convert_revision : ba73676165810edf2c2effaf5fbad8397d6bd800
2006-06-29 16:07:19 -04:00
Ron Dreslinski
0d323c753d More Changes, working towards cache.cc compiling. Headers cleaned up.
src/mem/cache/cache_blk.hh:
    Remove XC

--HG--
extra : convert_revision : aa2c43e4412ebb93165e12f693d5126983cfd0dc
2006-06-28 17:28:33 -04:00