Ali Saidi [Tue, 4 Jun 2013 20:17:04 +0000 (15:17 -0500)]
scons: ammend swig warning error to version 2.0.10 as well
Andreas Sandberg [Tue, 4 Jun 2013 08:08:21 +0000 (10:08 +0200)]
dev: Clarify why updates are delayed when the MC14818 is activated
Andreas Sandberg [Mon, 3 Jun 2013 11:55:41 +0000 (13:55 +0200)]
arch: Create a method to finalize physical addresses
in the TLB
Some architectures (currently only x86) require some fixing-up of
physical addresses after a normal address translation. This is usually
to remap devices such as the APIC, but could be used for other memory
mapped devices as well. When running the CPU in a using hardware
virtualization, we still need to do these address fix-ups before
inserting the request into the memory system. This patch moves this
patch allows that code to be used by such CPUs without doing full
address translations.
Andreas Sandberg [Mon, 3 Jun 2013 11:51:03 +0000 (13:51 +0200)]
base: Make the Python module loader PEP302 compliant
The custom Python loader didn't comply with PEP302 for two reasons:
* Previously, we would overwrite old modules on name
conflicts. PEP302 explicitly states that: "If there is an existing
module object named 'fullname' in sys.modules, the loader must use
that existing module".
* The "__package__" attribute wasn't set. PEP302: "The __package__
attribute must be set."
This changeset addresses both of these issues.
Andreas Sandberg [Mon, 3 Jun 2013 11:40:05 +0000 (13:40 +0200)]
config: Add missing CPUs to --restore-with-cpu
The --restore-with-cpu option didn't use CpuConfig.cpu_names() to
determine which CPU names are valid, instead it used a static list of
known CPU names. This changeset makes the option parsing code use the
CPU list from the CpuConfig module instead.
Andreas Sandberg [Mon, 3 Jun 2013 11:39:11 +0000 (13:39 +0200)]
kvm: Allow architectures to override the cycle accounting mechanism
Some architectures have special registers in the guest that can be
used to do cycle accounting. This is generally preferrable since the
prevents the guest from seeing a non-monotonic clock. This changeset
adds a virtual method, getHostCycles(), that the architecture-specific
code can override to implement this functionallity. The default
implementation uses the hwCycles counter.
Andreas Sandberg [Mon, 3 Jun 2013 11:38:59 +0000 (13:38 +0200)]
kvm: Add handling of EAGAIN when creating timers
timer_create can apparently return -1 and set errno to EAGAIN if the
kernel suffered a temporary failure when allocating a timer. This
happens from time to time, so we need to handle it.
Andreas Sandberg [Mon, 3 Jun 2013 11:21:21 +0000 (13:21 +0200)]
sim: Add debug output when executing pseudo-instructions
Andreas Sandberg [Mon, 3 Jun 2013 10:36:56 +0000 (12:36 +0200)]
kvm: Add a call to thread->startup() in startup()
It is now required to initialize the thread context by calling
startup() on it. Failing to do so currently causes decoder in
x86-based CPUs to get very confused when restoring from checkpoints.
Andreas Sandberg [Mon, 3 Jun 2013 10:28:52 +0000 (12:28 +0200)]
dev: Add support for disabling ticking and the divider in MC146818
Some Linux versions disable updates (regB.set = 1) to prevent the chip
from updating its internal state while the OS is updating it. Support
for this was already there, this patch merely disables the check in
writeReg that prevented it from being enabled. The patch also includes
support for disabling the divider, which is used to control when clock
updates should start after setting the internal RTC state.
These changes are required to boot most vanilla Linux distributions
that update the RTC settings at boot.
Andreas Sandberg [Mon, 3 Jun 2013 10:28:41 +0000 (12:28 +0200)]
dev: Clean up MC146818 register (A & B) handling
Rewrite reg A & B handling to use the bitunion stuff instead of bit
masking. Add better error messages when the kernel tries to enable
unsupported stuff.
Andreas Hansson [Thu, 30 May 2013 16:54:18 +0000 (12:54 -0400)]
stats: Update the stats to reflect bus and memory changes
This patch updates the stats to reflect the addition of the bus stats,
and changes to the bus layers. In addition it updates the stats to
match the addition of the static pipeline latency of the memory
conotroller and the addition of a stat tracking the bytes per
activate.
Andreas Hansson [Thu, 30 May 2013 16:54:14 +0000 (12:54 -0400)]
mem: More descriptive DRAM config names
This patch changes the class names of the variuos DRAM configurations
to better reflect what memory they are based on. The speed and
interface width is now part of the name, and also the alias that is
used to select them on the command line.
Some minor changes are done to the actual parameters, to better
reflect the named configurations. As a result of these changes the
regressions change slightly and the stats will be bumped in a separate
patch.
Andreas Hansson [Thu, 30 May 2013 16:54:13 +0000 (12:54 -0400)]
mem: Add bytes per activate DRAM controller stat
This patch adds a histogram to track how many bytes are accessed in an
open row before it is closed. This metric is useful in characterising
a workload and the efficiency of the DRAM scheduler. For example, a
DDR3-1600 device requires 44 cycles (tRC) before it can activate
another row in the same bank. For a x32 interface (8 bytes per cycle)
that means 8 x 44 = 352 bytes must be transferred to hide the
preparation time.
Andreas Hansson [Thu, 30 May 2013 16:54:12 +0000 (12:54 -0400)]
mem: Add static latency to the DRAM controller
This patch adds a frontend and backend static latency to the DRAM
controller by delaying the responses. Two parameters expressing the
frontend and backend contributions in absolute time are added to the
controller, and the appropriate latency is added to the responses when
adding them to the (infinite) queued port for sending.
For writes and reads that hit in the write buffer, only the frontend
latency is added. For reads that are serviced by the DRAM, the static
latency is the sum of the pipeline latencies of the entire frontend,
backend and PHY. The default values are chosen based on having roughly
10 pipeline stages in total at 500 MHz.
In the future, it would be sensible to make the controller use its
clock and convert these latencies (and a few of the DRAM timings) to
cycles.
Andreas Hansson [Thu, 30 May 2013 16:54:11 +0000 (12:54 -0400)]
mem: Spring cleaning of MSHR and MSHRQueue
This patch does some minor tidying up of the MSHR and MSHRQueue. The
clean up started as part of some ad-hoc tracing and debugging, but
seems worthwhile enough to go in as a separate patch.
The highlights of the changes are reduced scoping (private) members
where possible, avoiding redundant new/delete, and constructor
initialisation to please static code analyzers.
Andreas Hansson [Thu, 30 May 2013 16:54:09 +0000 (12:54 -0400)]
mem: Fix MSHR print format
This patch fixes an incorrect print format string by adding an
additional string element.
Andreas Hansson [Thu, 30 May 2013 16:54:09 +0000 (12:54 -0400)]
cpu: Prune the stale TraceCPU
This patch prunes the TraceCPU as the code is stale and the
functionality that it provided can now be achieved with the TrafficGen
using its trace playback mode.
The TraceCPU was able to play back pre-recorded memory traces of a few
different formats, and to achieve this level of flexibility with the
TrafficGen, use the util/encode_packet_trace (with suitable
modifications) to create a protobuf trace off-line.
Sascha Bischoff [Thu, 30 May 2013 16:54:08 +0000 (12:54 -0400)]
cpu: Check that minimum TrafficGen period is less than max period
Add a check which ensures that the minumum period for the LINEAR and
RANDOM traffic generator states is less than or equal to the maximum
period. If the minimum period is greater than the maximum period a
fatal is triggered.
Sascha Bischoff [Thu, 30 May 2013 16:54:07 +0000 (12:54 -0400)]
cpu: Fix bug when reading in TrafficGen state transitions
This patch fixes a bug with the traffic generator which occured when
reading in the state transitions from the configuration
file. Previously, the size of the vector which stored the transitions
was used to get the size of the transitions matrix, rather than using
the number of states. Therefore, if there were more transitions than
states, i.e. some transitions has a probability of less than 1, then
the traffic generator would fatal when trying to check the
transitions.
This issue has been addressed by using the number of input states,
rather then the number of transitions.
Andreas Hansson [Thu, 30 May 2013 16:54:06 +0000 (12:54 -0400)]
cpu: Add request elasticity to the traffic generator
This patch adds an optional request elasticity to the traffic
generator, effectievly compensating for it in the case of the linear
and random generators, and adding it in the case of the trace
generator. The accounting is left with the top-level traffic
generator, and the individual generators do the necessary math as part
of determining the next packet tick.
Note that in the linear and random generators we have to compensate
for the blocked time to not be elastic, i.e. without this patch the
aforementioned generators will slow down in the case of back-pressure.
Andreas Hansson [Thu, 30 May 2013 16:54:05 +0000 (12:54 -0400)]
cpu: Block traffic generator when requests have to retry
This patch changes the queued port for a conventional master port and
stalls the traffic generator when requests are not immediately
accepted. This is a first step to allowing elasticity in the injection
of requests.
The patch also adds stats for the sent packets and retries, and
slightly changes how the nextPacketTick and getNextPacket
interact. The advancing of the trace is now moved to getNextPacket and
nextPacketTick is only responsible for answering the question when the
next packet should be sent.
Andreas Hansson [Thu, 30 May 2013 16:54:04 +0000 (12:54 -0400)]
cpu: Move traffic generator sending out of generator states
This patch moves the responsibility for sending packets out of the
generator states and leaves it with the top-level traffic
generator. The main aim of this patch is to enable a transition to
non-queued ports, i.e. with send/retry flow control, and to do so it
is much more convenient to not wrap the port interactions and instead
leave it all local to the traffic generator.
The generator states now only govern when they are ready to send
something new, and the generation of the packets to send. They thus
have no knowledge of the port that is used.
Andreas Hansson [Thu, 30 May 2013 16:54:03 +0000 (12:54 -0400)]
cpu: Fold together the StateGraph and the TrafficGen
This patch simplifies the object hierarchy of the traffic generator by
getting rid of the StateGraph class and folding this functionality
into the traffic generator itself.
The main goal of this patch is to facilitate upcoming changes by
reducing the number of affected layers.
Andreas Hansson [Thu, 30 May 2013 16:54:02 +0000 (12:54 -0400)]
mem: Make returning snoop responses occupy response layer
This patch introduces a mirrored internal snoop port to facilitate
easy addition of flow control for the snoop responses that are turned
into normal responses on their return. To perform this, the slave
ports of the coherent bus are wrapped in internal master ports that
are passed as the source ports to the response layer in question.
As a result of this patch, there is more contention for the response
resources, and as such system performance will decrease slightly.
A consequence of the mirrored internal port is that the port the bus
tells to retry (the internal one) and the port actually retrying (the
mirrored) one are not the same. Thus, the existing check in tryTiming
is not longer correct. In fact, the test is redundant as the layer is
only in the retry state while calling sendRetry on the waiting port,
and if the latter does not immediately call the bus then the retry
state is left. Consequently the check is removed.
Andreas Hansson [Thu, 30 May 2013 16:54:01 +0000 (12:54 -0400)]
mem: Make the buses multi layered
This patch makes the buses multi layered, and effectively creates a
crossbar structure with distributed contention ports at the
destination ports. Before this patch, a bus could have a single
request, response and snoop response in flight at any time, and with
these changes there can be as many requests as connected slaves (bus
master ports), and as many responses as connected masters (bus slave
ports).
Together with address interleaving, this patch enables us to create
high-throughput memory interconnects, e.g. 50+ GByte/s.
Andreas Hansson [Thu, 30 May 2013 16:54:00 +0000 (12:54 -0400)]
mem: Separate the two snoop response cases in the bus
This patch makes the flow control and state updates of the coherent
bus more clear by separating the two cases, i.e. forward as a snoop
response, or turn it into a normal response.
With this change it is also more clear what resources are being
occupied, and that we effectively bypass the busy check for the second
case. As a result of the change in resource usage some stats change.
Andreas Hansson [Thu, 30 May 2013 16:53:59 +0000 (12:53 -0400)]
mem: Tidy up a few variables in the bus
This patch does some minor housekeeping on the bus code, removing
redundant code, and moving the extraction of the destination id to the
top of the functions using it.
Uri Wiener [Thu, 30 May 2013 16:53:58 +0000 (12:53 -0400)]
mem: Add basic stats to the buses
This patch adds a basic set of stats which are hard to impossible to
implement using only communication monitors, and are needed for
insight such as bus utilization, transactions through the bus etc.
Stats added include throughput and transaction distribution, and also
a two-dimensional vector capturing how many packets and how much data
is exchanged between the masters and slaves connected to the bus.
Andreas Hansson [Thu, 30 May 2013 16:53:57 +0000 (12:53 -0400)]
mem: Use unordered set in bus request tracking
This patch changes the set used to track outstanding requests to an
unordered set (part of C++11 STL). There is no need to maintain the
order, and hopefully there might even be a small performance benefit.
Andreas Hansson [Thu, 30 May 2013 16:53:57 +0000 (12:53 -0400)]
mem: Check for waiting state in bus draining
This patch fixes a bug in the bus where the bus transitions from busy
to idle and still has a port that is waiting for a retry from a peer.
Andreas Hansson [Thu, 30 May 2013 16:53:56 +0000 (12:53 -0400)]
mem: Add a LPDDR3-1600 configuration
This patch adds a typical (leaning towards fast) LPDDR3 configuration
based on publically available data. As expected, it looks very similar
to the LPDDR2-S4 configuration, only with a slightly lower burst time.
Andreas Hansson [Thu, 30 May 2013 16:53:55 +0000 (12:53 -0400)]
mem: Adapt the LPDDR2 to match a single x32 channel
This patch adapts the existing LPDDR2 configuration to make use of the
multi-channel functionality. Thus, to get a x64 interface two
controllers should be instantiated using the makeMultiChannel method.
The page size and ranks are also adapted to better suit with a typical
LPDDR2 part.
Andreas Hansson [Thu, 30 May 2013 16:53:54 +0000 (12:53 -0400)]
mem: Avoid explicitly zeroing the memory backing store
This patch removes the explicit memset as it is redundant and causes
the simulator to touch the entire space, forcing the host system to
allocate the pages.
Anonymous pages are mapped on the first access, and the page-fault
handler is responsible for zeroing them. Thus, the pages are still
zeroed, but we avoid touching the entire allocated space which enables
us to use much larger memory sizes as long as not all the memory is
actually used.
Andreas Hansson [Thu, 30 May 2013 16:53:53 +0000 (12:53 -0400)]
util: Auto generate the packet proto definitions
This patch simplifies the usage of the packet trace encoder/decoder by
attempting to automatically generating the packet proto definitions in
case they cannot be found.
Andreas Hansson [Thu, 30 May 2013 16:53:53 +0000 (12:53 -0400)]
base: Avoid size limitation on protobuf coded streams
This patch changes how the streams are created to avoid the size
limitation on the coded streams. As we only read/write a single
message at a time, there is never any message larger than a few
bytes. However, the coded stream eventually complains that its
internal counter reaches 64+ MByte if the total file size exceeds this
value.
Based on suggestions in the protobuf discussion forums, the coded
stream is now created for every message that is read/written. The
result is that the internal byte count never goes about tens of bytes,
and we can read/write any size file that the underlying file I/O can
handle.
Andreas Hansson [Thu, 30 May 2013 16:53:52 +0000 (12:53 -0400)]
cpu: Make hash struct instead of class to please clang
This patch changes the type of the hash function for BasicBlockRanges
to match the original definition of the templatized type. Without
this, clang raises a warning and combined with the "-Werror" flag this
causes compilation to fail.
Malek Musleh [Tue, 21 May 2013 16:57:14 +0000 (11:57 -0500)]
ruby: slicc: fix error msg in TypeFieldMemberAST.py
Nilay Vaish [Tue, 21 May 2013 16:41:27 +0000 (11:41 -0500)]
x86, regressions: updates stats
This is due to op class, function call, walker patches.
Gedare Bloom [Tue, 21 May 2013 16:40:11 +0000 (11:40 -0500)]
x86: Squash outstanding walks when instructions are squashed.
This is the x86 version of the ARM changeset
baa17ba80e06. In case an
instruction has been squashed by the o3 cpu, this patch allows page
table walker to avoid carrying out a pending translation that the
instruction requested for.
Nilay Vaish [Tue, 21 May 2013 16:34:41 +0000 (11:34 -0500)]
x86: mark instructions for being function call/return
Currently call and return instructions are marked as IsCall and IsReturn. Thus, the
branch predictor does not use RAS for these instructions. Similarly, the number of
function calls that took place is recorded as 0. This patch marks these instructions
as they should be.
Nilay Vaish [Tue, 21 May 2013 16:33:57 +0000 (11:33 -0500)]
x86: add op class for int and fp microops in isa description
Currently all the integer microops are marked as IntAluOp and the floating
point microops are marked as FloatAddOp. This patch adds support for marking
different microops differently. Now IntMultOp, IntDivOp, FloatDivOp,
FloatMultOp, FloatCvtOp, FloatSqrtOp classes will be used as well. This will
help in providing different latencies for different op class.
Nilay Vaish [Tue, 21 May 2013 16:32:57 +0000 (11:32 -0500)]
stats: updates statistics for ruby regressions
Nilay Vaish [Tue, 21 May 2013 16:32:45 +0000 (11:32 -0500)]
ruby: moesi hammer: cosmetic changes
Updates copyright years, removes space at the end of lines, shortens
variable names.
Nilay Vaish [Tue, 21 May 2013 16:32:38 +0000 (11:32 -0500)]
ruby: mesi cmp directory: cosmetic changes
Updates copyright years, removes space at the end of lines, shortens
variable names.
Nilay Vaish [Tue, 21 May 2013 16:32:24 +0000 (11:32 -0500)]
ruby: moesi cmp token: cosmetic changes
Updates copyright years, removes space at the end of lines, shortens
variable names.
Nilay Vaish [Tue, 21 May 2013 16:32:15 +0000 (11:32 -0500)]
ruby: moesi cmp directory: cosmetic changes
Updates copyright years, removes space at the end of lines, shortens
variable names.
Nilay Vaish [Tue, 21 May 2013 16:32:08 +0000 (11:32 -0500)]
configs: ruby: pass the option use_map to directory controller
The option was not being passed to directory controllers for the protocols
MOESI_CMP_token and MOESI_CMP_directory. This was resulting in an error
while instantiating the directory controller as it tries to access the
wrong type of memory.
ruby: add stats to .sm files, remove cache profiler
This patch changes the way cache statistics are collected in ruby.
As of now, there is separate entity called CacheProfiler which holds
statistical variables for caches. The CacheMemory class defines different
functions for accessing the CacheProfiler. These functions are then invoked
in the .sm files. I find this approach opaque and prone to error. Secondly,
we probably should not be paying the cost of a function call for recording
statistics.
Instead, this patch allows for accessing statistical variables in the
.sm files. The collection would become transparent. Secondly, it would happen
in place, so no function calls. The patch also removes the CacheProfiler class.
--HG--
rename : src/mem/slicc/ast/InfixOperatorExprAST.py => src/mem/slicc/ast/OperatorExprAST.py
Anthony Gutierrez [Tue, 14 May 2013 22:39:47 +0000 (18:39 -0400)]
cpu: remove local/globalHistoryBits params from branch pred
having separate params for the local/globalHistoryBits and the
local/globalPredictorSize can lead to inconsistencies if they
are not carefully set. this patch dervies the number of bits
necessary to index into the local/global predictors based on
their size.
the value of the localHistoryTableSize for the ARM O3 CPU has been
increased to 1024 from 64, which is more accurate for an A15 based
on some correlation against A15 hardware.
Andreas Sandberg [Tue, 14 May 2013 14:02:45 +0000 (16:02 +0200)]
kvm: Add support for disabling coalesced MMIO
Add the option useCoalescedMMIO to the BaseKvmCPU. The default
behavior is to disable coalesced MMIO since this hasn't been heavily
tested.
Andreas Sandberg [Tue, 14 May 2013 13:59:43 +0000 (15:59 +0200)]
kvm: Dump state before panic in KVM exit handlers
Andreas Sandberg [Tue, 14 May 2013 13:56:04 +0000 (15:56 +0200)]
kvm: Fix the memory interface used by KVM
The CpuPort class was removed before the KVM patches were committed,
which means that the KVM interface currently doesn't compile. This
changeset adds the BaseKvmCPU::KVMCpuPort class which derives from
MasterPort. This class is used on the data and instruction ports
instead of the old CpuPort.
Andreas Sandberg [Tue, 14 May 2013 13:06:50 +0000 (15:06 +0200)]
arm: Add support for the m5fail pseudo-op
Andreas Sandberg [Tue, 14 May 2013 13:03:45 +0000 (15:03 +0200)]
arm: Fix compilation error in m5 utility
Changeset
5ca6098b9560 accidentally broke the m5 utility. This
changeset adds the missing co-processor call used to trigger the
pseudo-op in ARM mode and fixes an alignment issue that caused some
pseudo-ops to leave thumb mode.
Andreas Sandberg [Tue, 7 May 2013 12:47:04 +0000 (14:47 +0200)]
arm: Make libm5 a dependency of the m5 utility
The m5 utility wasn't relinked properly since libm5.a wasn't a
dependency of the utility. This changeset addresses that issue.
Andreas Sandberg [Thu, 2 May 2013 10:03:43 +0000 (12:03 +0200)]
kvm: Add a stat counting number of instructions executed
This changeset adds a 'numInsts' stat to the KVM-based CPU. It also
cleans up the variable names in kvmRun to make the distinction between
host cycles and estimated simulated cycles clearer. As a bonus
feature, it also fixes a warning (unreferenced variable) when
compiling in fast mode.
Andreas Sandberg [Thu, 2 May 2013 10:02:19 +0000 (12:02 +0200)]
kvm: Add checkpoint debug print
Add a debug print (when the Checkpoint debug flag is set) on serialize
and unserialize. Additionally, dump the KVM state before
serializing. The KVM state isn't dumped after unserializing since the
state is loaded lazily on the next KVM entry.
Andreas Sandberg [Thu, 2 May 2013 10:01:50 +0000 (12:01 +0200)]
kvm: Make MMIO requests uncacheable
Device accesses are normally uncacheable. This change probably doesn't
make any difference since we normally disable caching when KVM is
active. However, there might be devices that check this, so we'd
better enable this flag to be safe.
Andreas Sandberg [Thu, 2 May 2013 09:54:08 +0000 (11:54 +0200)]
sim: Add support for m5fail in pseudoInst()
Andreas Hansson [Sun, 28 Apr 2013 21:14:39 +0000 (17:14 -0400)]
config: Added memory type to t1000 regression
This patch adds the memory type parameter to the t1000 regression.
Michael Levenhagen [Tue, 23 Apr 2013 20:21:32 +0000 (15:21 -0500)]
x86: corrects vsyscall address for gettimeofday
The vsyscall address for gettimeofday is 0xffffffffff600000ul. The offset
therefore should be 0x0 instead of 0x410. This can be cross checked with
the file sysdeps/unix/sysv/linux/x86_64/gettimeofday.c in source of glibc.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Michael Levenhagen [Tue, 23 Apr 2013 20:21:30 +0000 (15:21 -0500)]
x86: enable gettimeofday and getppid system calls
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Marco Elver [Tue, 23 Apr 2013 16:56:48 +0000 (11:56 -0500)]
config: Fix mem-type option not used in ruby_fs script
This fixes missing mem-type arguments to makeLinuxAlphaRubySystem and
makeLinuxX86System after a recent changeset allowing mem-type to be
configured via options missed fixing these calls.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Mitch Hayenga [Tue, 23 Apr 2013 13:47:52 +0000 (09:47 -0400)]
sim: Fix two bugs relating to software caching of PageTable entries.
The existing implementation can read uninitialized data or stale information
from the cached PageTable entries.
1) Add a valid bit for the cache entries. Simply using zero for the virtual
address to signify invalid entries is not sufficient. Speculative, wrong-path
accesses frequently access page zero. The current implementation would return
a uninitialized TLB entry when address zero was accessed and the PageTable
cache entry was invalid.
2) When unmapping/mapping/remaping a page, invalidate the corresponding
PageTable cache entry if one already exists.
Andreas Hansson [Tue, 23 Apr 2013 09:07:10 +0000 (05:07 -0400)]
cpu: Fix TraceGen flag initalisation
This patch ensures the flags are always initialised.
Nilay Vaish [Tue, 23 Apr 2013 05:03:09 +0000 (00:03 -0500)]
x86: regressions: add switcher full test
Nilay Vaish [Tue, 23 Apr 2013 05:03:07 +0000 (00:03 -0500)]
ruby: mesi coherence protocol: remove unused state M_MB
Nilay Vaish [Tue, 23 Apr 2013 05:03:05 +0000 (00:03 -0500)]
x86, stats: updates due to lret bugfix
Christian Menard [Tue, 23 Apr 2013 05:03:04 +0000 (00:03 -0500)]
x86: increment the stack pointer in lret inst
The 'lret' instruction reloads instruction pointer and code segment from the
stack and then pops them. But the popping part is missing from the current
implementation. This caused incorrect behavior in some code related to the
Fiasco OS. Microops are being added to rectify the behavior of the instruction.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Nilay Vaish [Tue, 23 Apr 2013 05:03:02 +0000 (00:03 -0500)]
ruby: patch checkpoint restore with garnet
Due to recent changes to clocking system in Ruby and the way Ruby restores
state from a checkpoint, garnet was failing to run from a checkpointed state.
The problem is that Ruby resets the time to zero while warming up the caches.
If any component records a local copy of the time (read calls curCycle())
before the simulation has started, then that component will not operate until
that time is reached. In the context of this particular patch, the Garnet
Network class calls curCycle() at multiple places. Any non-operational
component can block in requests in the memory system, which the system
interprets as a deadlock. This patch makes changes so that Garnet can
successfully run from checkpointed state.
It adds a globally visible time at which the actual execution started. This
time is initialized in RubySystem::startup() function. This variable is only
meant for components with in Ruby. This replaces the private variable that
was maintained within Garnet since it is not possible to figure out the
correct time when the value of this variable can be set.
The patch also does away with all cases where curCycle() is called with in
some Ruby component before the system has actually started executing. This
is required due to the quirky manner in which ruby restores from a checkpoint.
Andreas Hansson [Mon, 22 Apr 2013 17:20:34 +0000 (13:20 -0400)]
mem: Address mapping with fine-grained channel interleaving
This patch adds an address mapping scheme where the channel
interleaving takes place on a cache line granularity. It is similar to
the existing RaBaChCo that interleaves on a DRAM page, but should give
higher performance when there is less locality in the address
stream.
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
mem: More descriptive enum names for address mapping
This patch changes the slightly ambigious names used for the address
mapping scheme to be more descriptive, and actually spell out what
they do. With this patch we also open up for adding more flavours of
open- and close-type mappings, i.e. interleaving across channels with
the open map.
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
cpu: Use request flags in trace playback
This patch changes the TraceGen such that it uses the optional request
flags from the protobuf trace if they are present.
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
cpu: Make the generators usable outside the TrafficGen module
This patch enables the use of the generator behaviours outside the
TrafficGen module. This is useful e.g. to allow packet replay modes
for other devices in the system without having to replace them with a
TrafficGen in the configuration files.
This change also enables more specific behaviours to be composed as
specific modules, e.g. BaseBandModem can use a number of generators
and have application-specific parameters based around a specific set
of generators.
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
config: Add a mem-type config option to se/fs scripts
This patch enables selection of the memory controller class through a
mem-type command-line option. Behind the scenes, this option is
treated much like the cpu-type, and a similar framework is used to
resolve the valid options, and translate the short-hand description to
a valid class.
The regression scripts are updated with a hardcoded memory class for
the moment. The best solution going forward is probably to get the
memory out of the makeSystem functions, but Ruby complicates things as
it does not connect the memory controller to the membus.
--HG--
rename : configs/common/CpuConfig.py => configs/common/MemConfig.py
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
mem: Add a WideIO DRAM configuration
This patch adds a WideIO 200 MHz configuration that can be used as a
baseline to compare with DDRx and LPDDRx. Note that it is a single
channel and that it should be replicated 4 times. It is based on
publically available information and attempts to capture an envisioned
8 Gbit single-die part (i.e. without TSVs).
Uri Wiener [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
mem: Adding verbose debug output in the memory system
This patch provides useful printouts throughut the memory system. This
includes pretty-printed cache tags and function call messages
(call-stack like).
Andreas Hansson [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
mem: Replace check with panic where inhibited should not happen
This patch changes the SimpleTimingPort and RubyPort to panic on
inhibited requests as this should never happen in either of the
cases. The SimpleTimingPort is only used for the I/O devices PIO port
and the DMA devices config port and should thus never see an inhibited
request. Similarly, the SimpleTimingPort is also used for the
MessagePort in x86, and there should also not be any cases where the
port sees an inhibited request.
Ali Saidi [Mon, 22 Apr 2013 17:20:33 +0000 (13:20 -0400)]
stats: Update stats for O3 switching fix.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Add support for pseudo-ops on ARM
This changeset adds support for m5 pseudo-ops when running in
kvm-mode. Unfortunately, we can't trap the normal gem5 co-processor
entry in KVM (it doesn't seem to be possible to trap accesses to
non-existing co-processors). We therefore use BZJ instructions to
cause a trap from virtualized mode into gem5. The BZJ instruction is
becomes a normal branch to the gem5 fallback code when running in
simulated mode, which means that this patch does not need to change
the ARM ISA-specific code.
Note: This requires a patched host kernel.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
sim: Add a helper function to execute pseudo instructions
All architectures execute m5 pseudo instructions by setting up
arguments according to the ABI and executing a magic instruction that
contains an operation number. Handling of such instructions is
currently spread across the different ISA implementations. This
changeset introduces the PseudoInst::pseudoInst function which handles
most of this in an architecture independent way. This is function is
mainly intended to be used from KVM, but can also be used from the
simulated CPUs.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Add support for state dumping on ARM
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Add basic support for ARM
Architecture specific limitations:
* LPAE is currently not supported by gem5. We therefore panic if LPAE
is enabled when returning to gem5.
* The co-processor based interface to the architected timer is
unsupported. We can't support this due to limitations in the KVM
API on ARM.
* M5 ops are currently not supported. This requires either a kernel
hack or a memory mapped device that handles the guest<->m5
interface.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
arm: Add a method to query interrupt state ignoring CPSR masks
Add the method checkRaw to ArmISA::Interrupts. This method can be used
to query the raw state (ignoring CPSR masks) of an interrupt. It is
primarily intended for hardware virtualized CPUs.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Add experimental support for a perf-based execution timer
Add support for using the CPU cycle counter instead of a normal POSIX
timer to generate timed exits to gem5. This should, in theory, provide
better resolution when requesting timer signals.
The perf-based timer requires a fairly recent kernel since it requires
a working PERF_EVENT_IOC_PERIOD ioctl. This ioctl has existed in the
kernel for a long time, but it used to be completely broken due to an
inverted match when the kernel copied things from user
space. Additionally, the ioctl does not change the sample period
correctly on all kernel versions which implement it. It is currently
only known to work reliably on kernel version 3.7 and above on ARM.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
tests: Add support for testing KVM-based CPUs
This changeset adds support for initializing a KVM VM in the
BaseSystem test class and adds the following methods in run.py:
require_file -- Test if a file exists and abort/skip if not.
require_kvm -- Test if KVM support has been compiled into gem5 (i.e.,
BaseKvmCPU exists) and the KVM device exists on the
host.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
config: Add a KVM VM to systems with KVM CPUs
KVM-based CPUs need a KVM VM object in the system to manage
system-global KVM stuff (VM creation, interrupt delivery, memory
managment, etc.). This changeset adds a VM to the system if KVM has
been enabled at compile time (the BaseKvmCPU object exists) and a
KVM-based CPU has been selected at runtime.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Avoid synchronizing the TC on every KVM exit
Reduce the number of KVM->TC synchronizations by overloading the
getContext() method and only request an update when the TC is
requested as opposed to every time KVM returns to gem5.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:32 +0000 (13:20 -0400)]
kvm: Basic support for hardware virtualized CPUs
This changeset introduces the architecture independent parts required
to support KVM-accelerated CPUs. It introduces two new simulation
objects:
KvmVM -- The KVM VM is a component shared between all CPUs in a shared
memory domain. It is typically instantiated as a child of the
system object in the simulation hierarchy. It provides access
to KVM VM specific interfaces.
BaseKvmCPU -- Abstract base class for all KVM-based CPUs. Architecture
dependent CPU implementations inherit from this class
and implement the following methods:
* updateKvmState() -- Update the
architecture-dependent KVM state from the gem5
thread context associated with the CPU.
* updateThreadContext() -- Update the thread context
from the architecture-dependent KVM state.
* dump() -- Dump the KVM state using (optional).
In order to deliver interrupts to the guest, CPU
implementations typically override the tick() method and
check for, and deliver, interrupts prior to entering
KVM.
Hardware-virutalized CPU currently have the following limitations:
* SE mode is not supported.
* PC events are not supported.
* Timing statistics are currently very limited. The current approach
simply scales the host cycles with a user-configurable factor.
* The simulated system must not contain any caches.
* Since cycle counts are approximate, there is no way to request an
exact number of cycles (or instructions) to be executed by the CPU.
* Hardware virtualized CPUs and gem5 CPUs must not execute at the
same time in the same simulator instance.
* Only single-CPU systems can be simulated.
* Remote GDB connections to the guest system are not supported.
Additionally, m5ops requires an architecture specific interface and
might not be supported.
Timothy M. Jones [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
cpu: Let python scripts obtain the number of instructions executed
Andreas Sandberg [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
arm: Enable support for triggering a sim panic on kernel panics
Add the options 'panic_on_panic' and 'panic_on_oops' to the
LinuxArmSystem SimObject. When these option are enabled, the simulator
panics when the guest kernel panics or oopses. Enable panic on panic
and panic on oops in ARM-based test cases.
Dam Sunwoo [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
sim: separate nextCycle() and clockEdge() in clockedObjects
Previously, nextCycle() could return the *current* cycle if the current tick was
already aligned with the clock edge. This behavior is not only confusing (not
quite what the function name implies), but also caused problems in the
drainResume() function. When exiting/re-entering the sim loop (e.g., to take
checkpoints), the CPUs will drain and resume. Due to the previous behavior of
nextCycle(), the CPU tick events were being rescheduled in the same ticks that
were already processed before draining. This caused divergence from runs that
did not exit/re-entered the sim loop. (Initially a cycle difference, but a
significant impact later on.)
This patch separates out the two behaviors (nextCycle() and clockEdge()),
uses nextCycle() in drainResume, and uses clockEdge() everywhere else.
Nothing (other than name) should change except for the drainResume timing.
Dam Sunwoo [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
cpu: generate SimPoint basic block vector profiles
This patch is based on http://reviews.m5sim.org/r/1474/ originally written by
Mitch Hayenga. Basic block vectors are generated (simpoint.bb.gz in simout
folder) based on start and end addresses of basic blocks.
Some comments to the original patch are addressed and hooks are added to create
and resume from checkpoints based on instruction counts dictated by external
SimPoint analysis tools.
SimPoint creation/resuming options will be implemented as a separate patch.
Chris Emmons [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
ARM: Add support for HDLCD controller for TC2 and newer Versatile Express tiles.
Newer core tiles / daughterboards for the Versatile Express platform have an
HDLCD controller that supports HD-quality output. This patch adds an
implementation of the controller.
Andreas Sandberg [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
sim: Add helper functions that add PCEvents with custom arguments
This changeset adds support for forwarding arguments to the PC
event constructors to following methods:
addKernelFuncEvent
addFuncEvent
Additionally, this changeset adds the following helper method to the
System base class:
addFuncEventOrPanic - Hook a PCEvent to a symbol, panic on failure.
addKernelFuncEventOrPanic - Hook a PCEvent to a kernel symbol, panic
on failure.
System implementations have been updated to use the new functionality
where appropriate.
Ali Saidi [Mon, 22 Apr 2013 17:20:31 +0000 (13:20 -0400)]
cpu: fix a switching issue with the o3 cpu.
This change fixes the switcheroo test that broke earlier this month. The code
that was checking for the pipeline being blocked wasn't checking for a pending
translation, only for a icache access.
Andreas Hansson [Fri, 19 Apr 2013 13:04:42 +0000 (09:04 -0400)]
stats: Update stats for ldr_ret_uop (changeset
35198406dd72)
This patch merely bumps the stats to match the changes introduced in
changeset
35198406dd72.
Nilay Vaish [Wed, 17 Apr 2013 21:09:37 +0000 (16:09 -0500)]
base: load weak symbols from object file
Without loading weak symbols into gem5, some function names and the given PC
cannot correspond correctly, because the binding attributes of unction names
in an ELF file are not only STB_GLOBAL or STB_LOCAL, but also STB_WEAK. This
patch adds a function for loading weak symbols.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>