summaryrefslogtreecommitdiff
path: root/src/mem/bus.cc
AgeCommit message (Collapse)Author
2007-02-06More DPRINTF cleanup.Steve Reinhardt
--HG-- extra : convert_revision : db89cea42b46476d19333038522a6c144eafdab1
2007-02-06Minor DPRINTF fixes.Steve Reinhardt
--HG-- extra : convert_revision : 41956c9a480163ecac7807982215027e8ff1a4a9
2006-12-15Use my range_map to speed up findPort() in the bus. The snoop code could ↵Ali Saidi
still use some work. --HG-- extra : convert_revision : ba0a68bd378d68e4ebd80a101b965d36c8be1db9
2006-11-22Do a functional access to levels above on a read as a temporary solution for ↵Ron Dreslinski
L2's in FS Fix a small writeback bug when missing in the L2 in atomic mode src/mem/bus.cc: Fix a comment to make sense src/mem/cache/cache_impl.hh: Do a functional access to levels above on a read as a temporary solution for L2's in FS Also fix a small writeback miss in L2 issue src/mem/cache/coherence/simple_coherence.hh: src/mem/cache/coherence/uni_coherence.cc: src/mem/cache/coherence/uni_coherence.hh: Do a functional access to levels above on a read as a temporary solution for L2's in FS tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt: tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt: tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt: Update ref's for writeback changes --HG-- extra : convert_revision : 937febd577b16b7fd97a5a68acaf53541828a251
2006-11-14Fix bugs around uni-coherence invalidates being propogated properly.Ron Dreslinski
src/mem/bus.cc: Make it so that invalidates being sent from the responder up don't call the responder but they should also not Panic. src/mem/packet.hh: If we don't have data in the packet, don't call deleteData: Example: InvalidateRequests never have data. --HG-- extra : convert_revision : 18766bc9f3bb4d852ac651d094254d347abd1634
2006-11-14Update atomic and functional paths for snoops as wellRon Dreslinski
--HG-- extra : convert_revision : 566d73438efb87ca683e4dee23454d880db3dfc7
2006-11-14Update bus bridges now that snoop ranges are passed properlyRon Dreslinski
src/mem/bridge.cc: Update brdiges, now that snoop addresses are properly forwarded. Bus bridge should only handle snoops on the second phase (SNOOP_COMMIT) src/mem/bus.cc: src/mem/bus.hh: Make sure if a busBridge has access to both things that snoop and things that respond it only takes the request once --HG-- extra : convert_revision : 26cc9ee4429be45d4476fa435e0e9a54843c2509
2006-11-13Fix some errors related to snooping and functional access in the busRon Dreslinski
src/mem/bus.cc: Only call snoop once per port, need to fix it so snoop ranges that overlap aren't added to list Functional accesses that call snoop and it goes to a higher bus may change the src, reset it after each snoop. --HG-- extra : convert_revision : 7276059c798a85cb9d138ccc5531298ecd055c13
2006-11-13Fix problems with snoop ranges not working properly on functional accessesRon Dreslinski
src/mem/bus.cc: Actually return the snoop list when asked for it. Don't get stuck in infinite functional loops --HG-- extra : convert_revision : 8e6dafbd10b30d48d28b6b5d4b464e8e8f6a3ddc
2006-11-09Be sure to populate the packet's finishTime field in the atomic timing case.Kevin Lim
--HG-- extra : convert_revision : ef34818eb2dea5b3a8e754bf56745a7cd2497bf0
2006-11-09Draining fixes.Kevin Lim
src/cpu/o3/cpu.cc: Handle draining properly when CPU isn't actually being used. src/cpu/simple/atomic.cc: Be sure to set status properly when draining. src/mem/bus.cc: Fix for draining. --HG-- extra : convert_revision : d9796e6693e974f022159029fc9743c49a970c8f
2006-11-07Fix up bus draining and add draining to the caches.Kevin Lim
src/mem/bus.cc: Fix up draining to work properly. src/mem/bus.hh: Initialize drainEvent to NULL. src/mem/cache/base_cache.cc: src/mem/cache/base_cache.hh: Add draining to the caches. --HG-- extra : convert_revision : 3082220a75d50876f10909f9f99bec535889f818
2006-11-02Merge ktlim@zizzer:/bk/newmemKevin Lim
into zamp.eecs.umich.edu:/z/ktlim2/clean/newmem-busfix --HG-- extra : convert_revision : a9a41e2c292bd95aa148e1cf4d9a77c0622a462b
2006-11-02Have bus use the BadAddress device to handle bad addresses. The O3 CPU ↵Kevin Lim
should be able to boot into Linux with caches on after this change. src/mem/bus.cc: src/mem/bus.hh: Bus now will be setup with a default responder, unless the user overrides it. This default responder should return BadAddress if no matching port is found. src/python/m5/objects/Bus.py: Bus now has a default responder for FS mode if the user doesn't override it. It returns BadAddress if no matching port is found. src/python/m5/objects/Tsunami.py: Add bad address device. Also record when the user has specified their own default responder. --HG-- extra : convert_revision : 59070477ae313ee711b2d59baa2369c9a91c5b85
2006-11-01Added code to handle draining.Gabe Black
--HG-- extra : convert_revision : 3861f553bde5865cd21a8a58a4c410896726f0a3
2006-10-20Use PacketPtr everywhereNathan Binkert
--HG-- extra : convert_revision : d9eb83ab77ffd2d725961f295b1733137e187711
2006-10-19Fix compile of m5.fastNathan Binkert
--HG-- extra : convert_revision : a8a37c318e55e48e697e4aaba339328f000b3f60
2006-10-12small bus updates for functional accessesAli Saidi
--HG-- extra : convert_revision : c7a6b199c74ed4b4ffab14bbffb51e72d75b7742
2006-10-11Make default ID unique (not broadcast)Ron Dreslinski
Fix a segfault associated with DefaultId src/mem/bus.cc: Handle a segfault in the bus when DefaultPort was being used src/mem/bus.hh: Make the Default ID more unique (it overlapped with Broadcast ID) --HG-- extra : convert_revision : 9182805c5cf4d9fe004e6c5be8547a8f41ed7bfe
2006-10-11Fix bus in FS mode.Ron Dreslinski
src/mem/bus.cc: Add debugging statement src/mem/bus.hh: Fix implementation of bus for subsequent recvTimings while handling a retry request. src/mem/tport.cc: Rework timing port to retry properly --HG-- extra : convert_revision : fbfb5e8b4a625e49c6cd764da1df46a4f336b1b2
2006-10-11More cache fixes. Atomic coherence now works as well.Ron Dreslinski
src/cpu/memtest/memtest.cc: src/cpu/memtest/memtest.hh: Make Memtester able to test atomic as well src/mem/bus.cc: src/mem/bus.hh: Handle atomic snoops properly for cache->cache transfers src/mem/cache/cache_impl.hh: Debug output. Clean up memleak in atomic mode. Set hitLatency. Still need to send back reasonable number for atomic return value. src/mem/packet.cc: Add command strings for new commands src/python/m5/objects/MemTest.py: Add param to test atomic memory. --HG-- extra : convert_revision : 43f880e29215776167c16ea90793ebf8122c785b
2006-10-11Don't call recvRetry if the bus is busy anyway. This takes care of a corner ↵Gabe Black
case as well when dealing with grants that aren't used. --HG-- extra : convert_revision : 38f7ef1b41477fb2a2438387ef3a81cccd3e7a8a
2006-10-11Make the bus work if the other sides recvRetry doesn't call sendTiming for ↵Gabe Black
some reason. --HG-- extra : convert_revision : e722ddb0354a5c021dc7c44a3e2f0a64e962442b
2006-10-10Merge zizzer:/n/wexford/x/gblack/m5/newmem_busRon Dreslinski
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest src/mem/bus.cc: SCCS merged --HG-- extra : convert_revision : 18608114350c466a56ab499ae523b01fcb2f6ef2
2006-10-10Make the bus is occupied for none broadcast packets as well.Gabe Black
--HG-- extra : convert_revision : aef3c625172e92be8f29c4c57077fefee43046bb
2006-10-10Merge zizzer:/n/wexford/x/gblack/m5/newmem_busRon Dreslinski
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest src/mem/bus.cc: SCCS merged --HG-- extra : convert_revision : eaae105025635c37af06cf72bb061ce82def9dc9
2006-10-10Debugging infoRon Dreslinski
src/base/traceflags.py: Add new flags for cacheport src/mem/bus.cc: Add debugging info src/mem/cache/base_cache.cc: Add debuggin info --HG-- extra : convert_revision : a6c4b452466a8e0b50a86e886833cb6e29edc748
2006-10-10Put in an accounting mechanism and an assert to make sure something doesn't ↵Gabe Black
try to send another packet while it's still waiting for the bus. --HG-- extra : convert_revision : 4a2b83111e49f71ca27e05c98b55bc3bac8d9f53
2006-10-10Changed the bus to use a bool to keep track of retries rather than a pointerGabe Black
src/mem/tport.cc: minor formatting tweak --HG-- extra : convert_revision : 7391d142815c5876fcc0f991bd053e6a1781c101
2006-10-09Fixes to the bus, and added fields to the packet.Gabe Black
src/mem/bus.cc: Put back the check to see if the bus is busy. Also, populate the fields in the packet to indicate when the first word and the entire packet will be delivered. src/mem/bus.hh: Remove the occupyBus function. src/mem/packet.hh: Added fields to the packet to indicate when the first chunk of a packet arrives, and when the entire packet arrives. --HG-- extra : convert_revision : cfc7670a33913d48a04d02c6d2448290a51f2d3c
2006-10-09Merge zizzer.eecs.umich.edu:/bk/newmemGabe Black
into zeep.eecs.umich.edu:/home/gblack/m5/newmem_bus --HG-- extra : convert_revision : 8267487b935eaf11665841ace3a5c664751b53b0
2006-10-09Potentially functional partially timed bandwidth limitted bus model.Gabe Black
src/mem/bus.cc: Fixes to the previous hand merging, and put the snooping back into recvTiming and out of it's own function. src/mem/bus.hh: Put snooping back into recvTiming and not in it's own function. --HG-- extra : convert_revision : fd031b7e6051a5be07ed6926454fde73b1739dc6
2006-10-08Fixes for functional path.Ron Dreslinski
If the cpu needs to update any state when it gets a functional write (LSQ??) then that code needs to be written. src/cpu/o3/fetch_impl.hh: src/cpu/o3/lsq_impl.hh: src/cpu/ozone/front_end_impl.hh: src/cpu/ozone/lw_lsq_impl.hh: src/cpu/simple/atomic.cc: src/cpu/simple/timing.cc: CPU's can recieve functional accesses, they need to determine if they need to do anything with them. src/mem/bus.cc: src/mem/bus.hh: Make the fuctional path do the correct tye of snoop --HG-- extra : convert_revision : 70d09f954b907a8aa9b8137579cd2b06e02ae2ff
2006-10-08Merge zizzer.eecs.umich.edu:/bk/newmemGabe Black
into zeep.eecs.umich.edu:/home/gblack/m5/newmem_bus src/mem/bus.cc: Hand merged. Needs to be fixed --HG-- extra : convert_revision : df03219ccfd18431cc726a063bd29d30554944a1
2006-10-08Move away from using the statusChange function on snoops. Clean up snooping ↵Ron Dreslinski
code in general. --HG-- extra : convert_revision : 5a57bfd7742a212047fc32e8cae0dc602fdc915c
2006-10-08bus changesGabe Black
src/mem/bus.cc: src/mem/bus.hh: minor fix and some formatting changes src/python/m5/objects/Bus.py: changed bits to bytes --HG-- extra : convert_revision : dcd22205604b7a2727eaf2094084c4858f3589c5
2006-10-08Merge zizzer.eecs.umich.edu:/bk/newmemGabe Black
into zeep.eecs.umich.edu:/home/gblack/m5/newmem_bus --HG-- extra : convert_revision : 1749397443ccb320d32f8dd23c71ed0431d30cb7
2006-10-08A possible implementation of a multiplexed bus.Gabe Black
--HG-- extra : convert_revision : 3c560eda12ffd8ca539c91024baf2770b963ede8
2006-10-05First pass at snooping stuff that compiles and doesn't break.Ron Dreslinski
Still need: -Handle NACK's on the recieve side -Distinguish top level caches -Handle repsonses from caches failing the fast path -Handle BusError and propogate it -Fix the invalidate packet associated with snooping in the cache src/mem/bus.cc: Make sure to snoop on functional accesses src/mem/cache/base_cache.cc: Wait to make a request into a response until it is ready to be issued src/mem/cache/base_cache.hh: Support range changes for snoops Set up snoop responses for cache->cache transfers src/mem/cache/cache_impl.hh: Only access the cache if it wasn't satisfied by cache->cache transfer Handle snoop phases (detect block, then snoop) Fix functional access to work properly (still need to fix snoop path for functional accesses) --HG-- extra : convert_revision : 4c25f11d7a996c1f56f4f7b55dde87a344e5fdf8
2006-10-05Partial reimplementation of the bus. The "clock" and "width" parameters have ↵Gabe Black
been added, and the HasData flag has been partially added to packets. --HG-- extra : convert_revision : abb2a259fcf843457abbc0bd36f9504fbe6d7d39
2006-08-28Make address formats consistent in DPRINTFs.Steve Reinhardt
--HG-- extra : convert_revision : 73c6616aa9228c08e21fcc134dd0e675cd57aee6
2006-08-22Commiting a version of the multi-phase snoop atomic bus so people can see ↵Ron Dreslinski
the framework. Doesn't work, but also doesn't break uni-processor systems. Working on pulling out the changes in the cache so that it remains working. src/mem/bus.cc: Changes for multi-phase snoop Some code for registering snoop ranges (a version that compiles and runs, but does nothing) src/mem/bus.hh: Changes for multi-phase snoop src/mem/packet.hh: Flag for multi-phase snoop src/mem/port.hh: Status for multi-phase snoop --HG-- extra : convert_revision : 4c2e5263bba16e3bcf03aabe36ff45ec36de4720
2006-08-14Fix up doxygen.Steve Reinhardt
--HG-- rename : docs/footer.html => src/doxygen/footer.html rename : docs/stl.hh => src/doxygen/stl.hh extra : convert_revision : 2b2e5637930843c1be07deaa708fd4126213cda2
2006-07-06Add default responder to busAli Saidi
Update configuration for new default responder on bus Update to devices to handle their own pci config space without pciconfigall Remove most of pciconfigall, it now is a dumbdevice which gets it's address based on the bus it's supposed to respond for Remove need for pci config space from platform, add registerPciDevice function to prevent more than one device from having same bus:dev:func and interrupt Remove pciconfigspace from pci devices, and py files Add calcConfigAddr that returns address for config space based on bus/dev/function + offset configs/test/fs.py: Update configuration for new default responder on bus src/dev/ide_ctrl.cc: src/dev/ide_ctrl.hh: src/dev/ns_gige.cc: src/dev/ns_gige.hh: src/dev/pcidev.cc: src/dev/pcidev.hh: Update to handle it's own pci config space without pciconfigall src/dev/io_device.cc: src/dev/io_device.hh: change naming for pio port break out recvTiming into two functions to reuse code src/dev/pciconfigall.cc: src/dev/pciconfigall.hh: removing most of pciconfigall, it now is a dumbdevice which gets it's address based on the bus it's supposed to respond for src/dev/pcireg.h: add a max size for PCI config space (per PCI spec) src/dev/platform.cc: src/dev/platform.hh: remove need for pci config space from platform, add registerPciDevice function to prevent more than one device from having same bus:dev:func and interrupt src/dev/sinic.cc: remove pciconfigspace as it's no longer a needed parameter src/dev/tsunami.cc: src/dev/tsunami.hh: src/dev/tsunami_pchip.cc: src/dev/tsunami_pchip.hh: add calcConfigAddr that returns address for config space based on bus/dev/function + offset (per PCI spec) src/mem/bus.cc: src/mem/bus.hh: src/python/m5/objects/Bus.py: add idea of default responder to bus src/python/m5/objects/Pci.py: add config port for pci devices add latency, bus and size parameters for pci config all (min is 8MB, max is 256MB see pci spec) --HG-- extra : convert_revision : 99db43b0a3a077f86611d6eaff6664a3885da7c9
2006-06-13Move SimObject creation and Port connection loopsSteve Reinhardt
into Python. Add Port and VectorPort objects and support for specifying port connections via assignment. The whole C++ ConfigNode hierarchy is gone now, as are C++ Connector objects. configs/test/fs.py: configs/test/test.py: Rewrite for new port connector syntax. src/SConscript: Remove unneeded files: - mem/connector.* - sim/config* src/dev/io_device.hh: src/mem/bridge.cc: src/mem/bridge.hh: src/mem/bus.cc: src/mem/bus.hh: src/mem/mem_object.hh: src/mem/physical.cc: src/mem/physical.hh: Allow getPort() to take an optional index to support vector ports (eventually). src/python/m5/__init__.py: Move SimObject construction and port connection operations into Python (with C++ calls). src/python/m5/config.py: Move SimObject construction and port connection operations into Python (with C++ calls). Add support for declaring and connecting MemObject ports in Python. src/python/m5/objects/Bus.py: src/python/m5/objects/PhysicalMemory.py: Add port declaration. src/sim/builder.cc: src/sim/builder.hh: src/sim/serialize.cc: src/sim/serialize.hh: ConfigNodes are gone; builder just gets the name of a .ini file section now. src/sim/main.cc: Move SimObject construction and port connection operations into Python (with C++ calls). Split remaining initialization operations into two parts, loadIniFile() and finalInit(). src/sim/param.cc: src/sim/param.hh: SimObject resolution done globally in Python now (not via ConfigNode hierarchy). src/sim/sim_object.cc: Remove unneeded #include. --HG-- extra : convert_revision : 2fa4001eaaec0c9a4231ef6e854f8e156d930dfe
2006-05-31Updated Authors from bk prs infoAli Saidi
--HG-- extra : convert_revision : 77f475b156d81c03a2811818fa23593d5615c685
2006-05-30Add a very poor implementation of dealing with retries on timing requests. ↵Ali Saidi
It is especially slow with tracing on since it ends up being O(N^2). But it's probably going to have to change for the real bus anyway, so it should be rewritten then Change recvRetry() to not accept a packet. Sendtiming should be called again (and can respond with false or true) Removed Port Blocked/Unblocked and replaced with sendRetry(). Remove possibility of packet mangling if packet is going to be refused anyway in bridge src/cpu/simple/atomic.cc: src/cpu/simple/atomic.hh: src/cpu/simple/timing.cc: src/cpu/simple/timing.hh: Change recvRetry() to not accept a packet. Sendtiming should be called again (and can respond with false or true) src/dev/io_device.cc: src/dev/io_device.hh: Make DMA Timing requests/responses work. Change recvRetry() to not accept a packet. Sendtiming should be called again (and can respond with false or true) src/mem/bridge.cc: src/mem/bridge.hh: Change recvRetry() to not accept a packet. Sendtiming should be called again (and can respond with false or true) Removed Port Blocked/Unblocked and replaced with sendRetry(). Remove posibility of packet mangling if packet is going to be refused anyway. src/mem/bus.cc: src/mem/bus.hh: Add a very poor implementation of dealing with retries on timing requests. It is especially slow with tracing on since it ends up being O(N^2). But it's probably going to have to change for the real bus anyway, so it should be rewritten then src/mem/port.hh: Change recvRetry() to not accept a packet. Sendtiming should be called again (and can respond with false or true) Removed Blocked/Unblocked port status, their functionality is really duplicated in the recvRetry() method --HG-- extra : convert_revision : fab613404be54bfa7a4c67572bae7b559169e573
2006-05-26Add a little more tracing support for Bus/Port stuff.Steve Reinhardt
src/base/traceflags.py: Sort flags so you can find things. Add BusAddrRanges flag for tracking RangeChange events separately from general bus activity. src/mem/bus.cc: Add BusAddrRanges flag for tracking RangeChange events separately from general bus activity. src/mem/port.cc: src/mem/port.hh: Print Config trace message when peers are set up. --HG-- extra : convert_revision : d7c11d5f90c8de5c8d97e473501a268a567e9e44
2006-05-26Significant rework of Packet class interface:Steve Reinhardt
- new constructor guarantees initialization of most fields - flags track status of non-guaranteed fields (addr, size, src) - accessor functions (getAddr() etc.) check status on access - Command & Result classes are nested in Packet class scope - Command now built from vector of behavior bits - string version of Command for tracing - reinitFromRequest() and makeTimingResponse() encapsulate common manipulations of existing packets src/cpu/simple/atomic.cc: src/cpu/simple/base.cc: src/cpu/simple/timing.cc: src/dev/alpha_console.cc: src/dev/ide_ctrl.cc: src/dev/io_device.cc: src/dev/io_device.hh: src/dev/isa_fake.cc: src/dev/ns_gige.cc: src/dev/pciconfigall.cc: src/dev/sinic.cc: src/dev/tsunami_cchip.cc: src/dev/tsunami_io.cc: src/dev/tsunami_pchip.cc: src/dev/uart8250.cc: src/mem/bus.cc: src/mem/bus.hh: src/mem/physical.cc: src/mem/port.cc: src/mem/port.hh: src/mem/request.hh: Update for new Packet interface. --HG-- extra : convert_revision : 9973d09ea4fa61795f23772a7d3995fa4df5c269
2006-05-26Add names to memory Port objects for tracing.Steve Reinhardt
--HG-- extra : convert_revision : ddf30084e343e8656e4812ab20356292b35507ee