Nathan Binkert [Fri, 11 Jul 2008 15:52:50 +0000 (08:52 -0700)]
m5ops: clean up the m5ops stuff.
- insert warnings for deprecated m5ops
- reserve opcodes for Ali's stuff
- remove code for stuff that has been deprecated forever
- simplify m5op_alpha
Nathan Binkert [Fri, 11 Jul 2008 15:52:50 +0000 (08:52 -0700)]
style: fix indentation and formatting of the pseudo insts.
Nathan Binkert [Fri, 11 Jul 2008 15:48:50 +0000 (08:48 -0700)]
eventq: change the event datastructure back to LIFO.
The status quo is preferred since it is less likely that people will
rely on LIFO than FIFO, and when we move to a parallelized M5, no
ordering between events of the same time/priority will be guaranteed.
Nathan Binkert [Fri, 11 Jul 2008 15:38:31 +0000 (08:38 -0700)]
eventq: new eventq data structure. The new data structure is singly
linked list sorted by time and priority. For things of the same time
and priority, a second, circularly linked list maintains the data
structure. Events of the same time and priority are now inserted in
FIFO order instead of LIFO order. This dramatically improves the
performance of systems that schedule multiple events at the same time.
The FIFO order version is not preferred to LIFO (because it may cause
people to rely on it), but I'm going to commit it anyway and
immediately commit the preferred LIFO version on top.
Nathan Binkert [Fri, 11 Jul 2008 04:35:42 +0000 (21:35 -0700)]
eventq: Clean up the Event class so that it uses fewer bytes. This
will hopefullly allow it to fit in a cache line.
Ali Saidi [Tue, 1 Jul 2008 14:30:08 +0000 (10:30 -0400)]
Fix cases where RADV interrupt timer is used and make ITR interrupt moderation not always delay if no interrupts have been posted for the ITR value.
Ali Saidi [Tue, 1 Jul 2008 14:25:07 +0000 (10:25 -0400)]
Remove delVirtPort() and make getVirtPort() only return cached version.
Ali Saidi [Tue, 1 Jul 2008 14:24:19 +0000 (10:24 -0400)]
Change everything to use the cached virtPort rather than created their own each time.
This appears to work, but I don't want to commit it until it gets tested a lot more.
I haven't deleted the functionality in this patch that will come later, but one question
is how to enforce encourage objects that call getVirtPort() to not cache the virtual port
since if the CPU changes out from under them it will be worse than useless. Perhaps a null
function like delVirtPort() is still useful in that case.
Ali Saidi [Tue, 1 Jul 2008 14:24:16 +0000 (10:24 -0400)]
Make the cached virtPort have a thread context so it can do everything that a newly created one can.
Ali Saidi [Tue, 1 Jul 2008 14:24:09 +0000 (10:24 -0400)]
After a checkpoint (and thus a stats reset), the not_idle_fraction/notIdleFraction statistic is really wrong.
The notIdleFraction statistic isn't updated when the statistics reset, probably because the cpu Status information
was pulled into the atomic and timing cpus. This changeset pulls Status back into the BaseSimpleCPU object. Anyone
care to comment on the odd naming of the Status instance? It shouldn't just be status because that is confusing
with Port::Status, but _status seems a bit strage too.
Steve Reinhardt [Sat, 28 Jun 2008 17:20:00 +0000 (13:20 -0400)]
Automated merge after backout.
Steve Reinhardt [Sat, 28 Jun 2008 17:19:38 +0000 (13:19 -0400)]
Backed out changeset
94a7bb476fca: caused memory leak.
Ali Saidi [Tue, 24 Jun 2008 19:51:12 +0000 (15:51 -0400)]
Automated merge with repo.m5sim.org/m5-stable
Ali Saidi [Tue, 24 Jun 2008 19:48:45 +0000 (15:48 -0400)]
Checkpoinging/SWIG: Undo part of changeset 5464 since it broke checkpointing.
Gabe Black [Sat, 21 Jun 2008 18:23:58 +0000 (14:23 -0400)]
SimObject: Add in missing includes of <string> and fix minor style problem.
Steve Reinhardt [Sat, 21 Jun 2008 05:06:27 +0000 (01:06 -0400)]
Make bus address conflict error more informative
Steve Reinhardt [Sat, 21 Jun 2008 05:04:43 +0000 (01:04 -0400)]
Generate more useful error messages for unconnected ports.
Force all non-default ports to provide a name and an
owner in the constructor.
Nathan Binkert [Wed, 18 Jun 2008 19:07:15 +0000 (12:07 -0700)]
imported patch sim_object_params.diff
Nathan Binkert [Wed, 18 Jun 2008 17:15:21 +0000 (10:15 -0700)]
AtomicSimpleCPU: Separate data stalls from instruction stalls.
Separate simulation of icache stalls and dat stalls.
Nathan Binkert [Wed, 18 Jun 2008 15:00:53 +0000 (11:00 -0400)]
tests: update tests for slight changes in nsgige posted interrupts
Nathan Binkert [Wed, 18 Jun 2008 05:22:44 +0000 (22:22 -0700)]
Ethernet: share statistics between all ethernet devices and apply some
of those statistics to the e1000 model.
Nathan Binkert [Wed, 18 Jun 2008 05:14:12 +0000 (22:14 -0700)]
inet: initialization fixes.
Make sure variables are properly initialized and also make sure that
truth testing works properly.
Nathan Binkert [Wed, 18 Jun 2008 04:34:27 +0000 (21:34 -0700)]
PacketFifo: Get slack out of the EthPacketData structure. This allows
a packet to exist in multiple FIFOs if desired.
Nathan Binkert [Wed, 18 Jun 2008 04:11:20 +0000 (21:11 -0700)]
ThreadState: Ensure that kernelStats is properly initialized
Nathan Binkert [Wed, 18 Jun 2008 03:39:51 +0000 (20:39 -0700)]
rename MipsConsole to MipsBackdoor
--HG--
rename : src/dev/mips/MipsConsole.py => src/dev/mips/MipsBackdoor.py
rename : src/dev/mips/console.cc => src/dev/mips/backdoor.cc
rename : src/dev/mips/console.hh => src/dev/mips/backdoor.hh
Nathan Binkert [Wed, 18 Jun 2008 03:36:39 +0000 (20:36 -0700)]
rename AlphaConsole to AlphaBackdoor
--HG--
rename : src/dev/alpha/AlphaConsole.py => src/dev/alpha/AlphaBackdoor.py
rename : src/dev/alpha/console.cc => src/dev/alpha/backdoor.cc
rename : src/dev/alpha/console.hh => src/dev/alpha/backdoor.hh
Nathan Binkert [Wed, 18 Jun 2008 03:30:37 +0000 (20:30 -0700)]
Change the default output filename for the terminal so it's more obvious.
--HG--
rename : tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/console.system.sim_console => tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/system.terminal
rename : tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/console.system.sim_console => tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/system.terminal
rename : tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/console.system.sim_console => tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/system.terminal
rename : tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/console.system.sim_console => tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/system.terminal
rename : tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.drivesys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/drivesys.terminal
rename : tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.testsys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/testsys.terminal
Nathan Binkert [Wed, 18 Jun 2008 03:29:06 +0000 (20:29 -0700)]
Rename SimConsole to Terminal since it makes more sense
--HG--
rename : src/dev/SimConsole.py => src/dev/Terminal.py
rename : src/dev/simconsole.cc => src/dev/terminal.cc
rename : src/dev/simconsole.hh => src/dev/terminal.hh
Nathan Binkert [Mon, 16 Jun 2008 04:39:29 +0000 (21:39 -0700)]
physmem: Add a null option to physical memory so it doesn't store data.
Nathan Binkert [Mon, 16 Jun 2008 04:34:32 +0000 (21:34 -0700)]
port: Clean up default port setup and port switchover code.
Nathan Binkert [Mon, 16 Jun 2008 04:26:33 +0000 (21:26 -0700)]
params: Prevent people from setting attributes on vector params.
Nathan Binkert [Mon, 16 Jun 2008 03:56:35 +0000 (20:56 -0700)]
add compile flags to m5
Nathan Binkert [Sun, 15 Jun 2008 04:51:08 +0000 (21:51 -0700)]
Command line option to print out List of SimObjects and their parameters
Nathan Binkert [Sun, 15 Jun 2008 04:16:00 +0000 (21:16 -0700)]
main: add .m5/options.py processing. This file is processed before
arguments are parsed so that they can change the default options for
various config parameters.
Nathan Binkert [Sun, 15 Jun 2008 04:15:59 +0000 (21:15 -0700)]
Add .m5 configuration directory
Nathan Binkert [Sun, 15 Jun 2008 04:15:58 +0000 (21:15 -0700)]
python: Separate the options parsing stuff. Remove options parsing stuff from
main.py so things are a bit more obvious.
Nathan Binkert [Sun, 15 Jun 2008 03:42:45 +0000 (20:42 -0700)]
params: Fix the memory bandwidth parameter
Nathan Binkert [Sun, 15 Jun 2008 03:39:31 +0000 (20:39 -0700)]
params: Fix floating point parameters
Nathan Binkert [Sun, 15 Jun 2008 03:19:49 +0000 (20:19 -0700)]
python: Move various utility classes into a new m5.util package so
they're all in the same place. This also involves having just one
jobfile.py and moving it into the utils directory to avoid
duplication. Lots of improvements to the utility as well.
--HG--
rename : src/python/m5/attrdict.py => src/python/m5/util/attrdict.py
rename : util/pbs/jobfile.py => src/python/m5/util/jobfile.py
rename : src/python/m5/util.py => src/python/m5/util/misc.py
rename : src/python/m5/multidict.py => src/python/m5/util/multidict.py
rename : util/stats/orderdict.py => src/python/m5/util/orderdict.py
Nathan Binkert [Sun, 15 Jun 2008 02:39:01 +0000 (19:39 -0700)]
MemReq: Add option to reset the time on a request.
Nathan Binkert [Sun, 15 Jun 2008 02:37:26 +0000 (19:37 -0700)]
Add hg commands for style check so you can check at times other than commit
Nathan Binkert [Sat, 14 Jun 2008 19:57:21 +0000 (12:57 -0700)]
Fix various SWIG warnings
Nathan Binkert [Sat, 14 Jun 2008 19:10:50 +0000 (12:10 -0700)]
Add missing dependencies on .i files
Nathan Binkert [Sat, 14 Jun 2008 17:30:18 +0000 (10:30 -0700)]
scons: proper fix for hg version stuff
Nathan Binkert [Sat, 14 Jun 2008 00:34:22 +0000 (17:34 -0700)]
scons: fix program_info.cc generation
Steve Reinhardt [Fri, 13 Jun 2008 05:59:10 +0000 (01:59 -0400)]
Automated merge with ssh://m5sim.org//repo/m5
Steve Reinhardt [Fri, 13 Jun 2008 05:33:49 +0000 (01:33 -0400)]
Get rid of bogus bus assertion.
It runs out that if a MemObject turns around and does a send in its
receive callback, and there are other sends already scheduled, then
it could observe a state where it's not at the head of the list but
the bus's sendEvent is not scheduled (because we're still in the
middle of processing the prior sendEvent).
Steve Reinhardt [Fri, 13 Jun 2008 05:29:20 +0000 (01:29 -0400)]
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.
Ali Saidi [Fri, 13 Jun 2008 05:09:06 +0000 (01:09 -0400)]
Scripts: Check for the appropriate build type as soon as possible.
Ali Saidi [Fri, 13 Jun 2008 05:09:04 +0000 (01:09 -0400)]
HG: Add compiled hg revision and date to the standard M5 output.
Gabe Black [Thu, 12 Jun 2008 05:54:21 +0000 (01:54 -0400)]
Alpha: Get rid of an old include of a non-existant file.
Gabe Black [Thu, 12 Jun 2008 05:00:29 +0000 (01:00 -0400)]
Params: Allow nested namespaces in cxx_namespace
Gabe Black [Thu, 12 Jun 2008 05:00:19 +0000 (01:00 -0400)]
X86: Make the cpuid processor identifier return a real string.
Gabe Black [Thu, 12 Jun 2008 05:00:05 +0000 (01:00 -0400)]
X86: Make the code compile as 32 bit.
Gabe Black [Thu, 12 Jun 2008 04:59:58 +0000 (00:59 -0400)]
Params: Remove an unnecessary include.
Gabe Black [Thu, 12 Jun 2008 04:58:36 +0000 (00:58 -0400)]
X86: Make the e820 table manually or automatically configurable from python.
Gabe Black [Thu, 12 Jun 2008 04:58:27 +0000 (00:58 -0400)]
X86: Make the disassembly for halt conform with the other microops.
Gabe Black [Thu, 12 Jun 2008 04:58:19 +0000 (00:58 -0400)]
X86: Implement and hook up STI and CLI instructions.
Gabe Black [Thu, 12 Jun 2008 04:58:13 +0000 (00:58 -0400)]
X86: Make sure there's something to catch when the kernel messes with ports "behind" the pci config magic ports.
Gabe Black [Thu, 12 Jun 2008 04:56:54 +0000 (00:56 -0400)]
X86: Make the platform object initialize channel 0 of the PIT.
Gabe Black [Thu, 12 Jun 2008 04:56:17 +0000 (00:56 -0400)]
X86: Hook the speaker device to the pit device.
Gabe Black [Thu, 12 Jun 2008 04:56:07 +0000 (00:56 -0400)]
Timer: Fill out the periodic modes a little.
Gabe Black [Thu, 12 Jun 2008 04:54:48 +0000 (00:54 -0400)]
Dev: Seperate the 8254 timer from tsunami and use it in that and the PC.
Gabe Black [Thu, 12 Jun 2008 04:54:32 +0000 (00:54 -0400)]
BitUnion: Take out namespace declaration so bitunions can be declared inside classes.
Gabe Black [Thu, 12 Jun 2008 04:54:19 +0000 (00:54 -0400)]
X86: Add an event for the apic timer timeout. It doesn't get used yet.
Gabe Black [Thu, 12 Jun 2008 04:54:12 +0000 (00:54 -0400)]
X86: Rename the divide count register to divide configuration.
Gabe Black [Thu, 12 Jun 2008 04:54:05 +0000 (00:54 -0400)]
X86: Make the apic isr and irr work.
Gabe Black [Thu, 12 Jun 2008 04:54:01 +0000 (00:54 -0400)]
X86: Make the apic task priority register work.
Gabe Black [Thu, 12 Jun 2008 04:53:50 +0000 (00:53 -0400)]
X86: Make the logical destination and destination format work.
Gabe Black [Thu, 12 Jun 2008 04:53:43 +0000 (00:53 -0400)]
X86: Make the apic ID register work.
Gabe Black [Thu, 12 Jun 2008 04:53:37 +0000 (00:53 -0400)]
X86: Make the apic version register work.
Gabe Black [Thu, 12 Jun 2008 04:53:01 +0000 (00:53 -0400)]
X86: Implement a partial, sort of correct version of the protected mode variant of iret.
Gabe Black [Thu, 12 Jun 2008 04:52:12 +0000 (00:52 -0400)]
X86: Change how segment loading is performed.
Gabe Black [Thu, 12 Jun 2008 04:51:57 +0000 (00:51 -0400)]
X86: Make pushes and pops use the stack size instead of the data size.
Gabe Black [Thu, 12 Jun 2008 04:51:50 +0000 (00:51 -0400)]
X86: In non 64bit mode, throw a fault when a NULL segment is accessed.
Gabe Black [Thu, 12 Jun 2008 04:51:14 +0000 (00:51 -0400)]
X86: Take advantage of the new meta register.
Gabe Black [Thu, 12 Jun 2008 04:50:25 +0000 (00:50 -0400)]
X86: Keep handy values like the operating mode in one register.
Gabe Black [Thu, 12 Jun 2008 04:50:10 +0000 (00:50 -0400)]
X86: Change what the microop chks does.
Instead of computing the segment descriptor address, this now checks if a
selector value/descriptor are legal for a particular purpose.
Gabe Black [Thu, 12 Jun 2008 04:50:05 +0000 (00:50 -0400)]
X86: Add a microop to read a segments attribute register.
Gabe Black [Thu, 12 Jun 2008 04:49:50 +0000 (00:49 -0400)]
X86: Add microops and supporting code to manipulate the whole rflags register.
Gabe Black [Thu, 12 Jun 2008 04:49:25 +0000 (00:49 -0400)]
X86: Add microops which panic, fatal, warn, and warn_once.
Gabe Black [Thu, 12 Jun 2008 04:49:16 +0000 (00:49 -0400)]
X86: Truncate descriptors to 16 bits.
Gabe Black [Thu, 12 Jun 2008 04:48:58 +0000 (00:48 -0400)]
X86: Redo BSF.
Gabe Black [Thu, 12 Jun 2008 04:48:46 +0000 (00:48 -0400)]
X86: Flesh out 3dnow instruction decoding a bit and grab the byte immediate.
Gabe Black [Thu, 12 Jun 2008 04:48:33 +0000 (00:48 -0400)]
X86: Update the regressions for the new string instructions.
Gabe Black [Thu, 12 Jun 2008 04:48:15 +0000 (00:48 -0400)]
X86: Make string instructions work when rcx=0.
Gabe Black [Thu, 12 Jun 2008 04:48:02 +0000 (00:48 -0400)]
X86: Have all 8 machine check registers since the kernel assumes they're there.
Gabe Black [Thu, 12 Jun 2008 04:47:25 +0000 (00:47 -0400)]
X86: Bypass unaligned access support for register addressed MSRs.
Gabe Black [Thu, 12 Jun 2008 04:46:22 +0000 (00:46 -0400)]
X86: Remove enforcement of APIC register access alignment. Panic if more than one register is accessed at a time.
Gabe Black [Thu, 12 Jun 2008 04:46:16 +0000 (00:46 -0400)]
X86: Force the kernel to use a certain loops per jiffy instead of calculating it.
Gabe Black [Thu, 12 Jun 2008 04:46:04 +0000 (00:46 -0400)]
X86: Fix the implementation of BSF.
Gabe Black [Thu, 12 Jun 2008 04:45:52 +0000 (00:45 -0400)]
X86: Bit scan forward/reverse were accidentally transposed.
Gabe Black [Thu, 12 Jun 2008 04:45:22 +0000 (00:45 -0400)]
X86: Fix a byte register indexing issue in the sign extending move from memory microcode.
Gabe Black [Thu, 12 Jun 2008 04:45:11 +0000 (00:45 -0400)]
X86: Make the amount of system memory match the hardcoded e820 info.
Gabe Black [Thu, 12 Jun 2008 04:45:01 +0000 (00:45 -0400)]
X86: Make the regular console use the serial port as well.
Gabe Black [Thu, 12 Jun 2008 04:42:52 +0000 (00:42 -0400)]
X86: Update the regressions for the fact that rdtsc does something now.
Gabe Black [Thu, 12 Jun 2008 04:39:10 +0000 (00:39 -0400)]
X86: Add in some support for the tsc register.
Gabe Black [Thu, 12 Jun 2008 04:35:50 +0000 (00:35 -0400)]
CPU: Make the simple cpu trace data for loads/stores.
Ali Saidi [Wed, 11 Jun 2008 14:54:12 +0000 (10:54 -0400)]
X86: Fix building on *BSD hosts
Ali Saidi [Wed, 11 Jun 2008 14:54:08 +0000 (10:54 -0400)]
SCons: Fix more SCons version issues