summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2017-03-13dev, arm: Add draining to the GIC modelAndreas Sandberg
The GIC model currently adds a delay to interrupts when posting them to a target CPU. This means that an interrupt signal will be represented by an event for a short period of time. We currently ignore this when draining and serialize the tick when the interrupt will fire. Upon loading the checkpoint, the simulated GIC reschedules the pending events. This behaviour is undesirable when we implement support for switching between in-kernel GIC emulation and gem5 GIC emulation. In that case, the (kernel) GIC model gets a lot simpler if we don't need to worry about in-flight interrupts from the gem5 GIC. This changeset adds a draining check to force the GIC into a state where all interrupts have been delivered prior to checkpointing/CPU switching. It also removes the now redundant serialization of interrupt events. Change-Id: I8b8b080aa291ca029a3a7bdd1777f1fcd5b01179 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2331 Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-03-13arm: Clean up the GIC implementationAndreas Sandberg
Lots of minor cleaups: * Make cached params const * Don't serialize params * Use AddrRange to represent the distributor and CPU address spaces * Store a const AddrRangeList of all PIO ranges Change-Id: I40a17bc3a38868fb3b8af247790e852cf99ddf1d Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2330 Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-03-09style: change NULL to nullptr in syscall filesBrandon Potter
Change-Id: I02719f3572f6665cace1eb5681f297dcde9e71ce Reviewed-on: https://gem5-review.googlesource.com/2271 Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-09syscall-emul: Ignore unimplemented system callsBrandon Potter
This changeset sets the implementation policy for a subset of system calls to the ignoreFunc implementation (for x86 only). The ignored system calls likely will never be implemented and this allows a warning to be issued instead of the simulation exiting with a fatal. Change-Id: I8d9741ad683151e88cc71156d3602e2d0ccb0acf Reviewed-on: https://gem5-review.googlesource.com/2270 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-03-09syscall-emul: Rewrite system call exit codeBrandon Potter
The changeset does a major refactor on the exit, exit_group, and futex system calls regarding exit functionality. A FutexMap class and related structures are added into a new file. This increases code clarity by encapsulating the futex operations and the futex state into an object. Several exit conditions were added to allow the simulator to end processes under certain conditions. Also, the simulation only exits now when all processes have finished executing. Change-Id: I1ee244caa9b5586fe7375e5b9b50fd3959b9655e Reviewed-on: https://gem5-review.googlesource.com/2269 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-03-09syscall-emul: Add the tgkill system callBrandon Potter
This changeset adds support to kill a thread group by calling the tgkill system call. The functionality is needed in some pthread applications. Change-Id: I0413a3331be69b74dfab30de95384113ec4efb63 Reviewed-on: https://gem5-review.googlesource.com/2268 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com>
2017-03-09syscall-emul: Adds SE mode signal featureBrandon Potter
This changeset adds a simple class definition and a member in the System object to track signals sent between processes. The implementation cannot support all signals that might be sent between processes, but it can support some of the simple use cases like SIGCHLD. Change-Id: Id5f95aa60e7f49da1c5b5596fbfa26e729453ac7 Reviewed-on: https://gem5-review.googlesource.com/2267 Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-09syscall-emul: Add or extend dup, dup2, and pipeBrandon Potter
This changeset extends the pipe system call to work with architectures other than Alpha (and enables the syscall for x86). For the dup system call, it sets the clone-on-exec flag by default. For the dup2 system call, the changeset adds an implementation (and enables it for x86). Change-Id: I00ddb416744ee7dd61a5cd02c4c3d97f30543878 Reviewed-on: https://gem5-review.googlesource.com/2266 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com>
2017-03-09syscall-emul: Add functionality to open syscallsBrandon Potter
This changeset adds refactors the existing open system call, adds the openat variant (enabled for x86 builds), and adds additional "special file" test cases for /proc/meminfo and /etc/passwd. Change-Id: I6f429db65bbf2a28ffa3fd12df518c2d0de49663 Reviewed-on: https://gem5-review.googlesource.com/2265 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com>
2017-03-09style: Correct some style issuesBrandon Potter
This changeset fixes line alignment issues, spacing, spelling, etc. for files that are used during SE Mode. Change-Id: Ie61b8d0eb4ebb5af554d72f1297808027833616e Reviewed-on: https://gem5-review.googlesource.com/2264 Maintainer: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr>
2017-03-09syscall-emul: Move memState into its own fileBrandon Potter
The Process class is full of implementation details and structures related to SE Mode. This changeset factors out an internal class from Process and moves it into a separate file. The purpose behind doing this is to clean up the code and make it a bit more modular. Change-Id: Ic6941a1657751e8d51d5b6b1dcc04f1195884280 Reviewed-on: https://gem5-review.googlesource.com/2263 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2017-03-09misc: add missing copyright/author information in previous commitPierre-Yves Péneau
See a06a46f and a854373. Change-Id: Id66427db22b7d7764c218b9cd78d95db929f4127 Signed-off-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr> Reviewed-on: https://gem5-review.googlesource.com/2224 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-09ruby: fix MOESI_hammer directory to work with > 3GB memoryLena Olson
The MOESI_hammer directory assumes a contiguous address space, but X86 has an IO gap from 3-4GB. This patch allows the directory to work with more than 3GB of memory on X86. Assumptions: the physical address space (range of possible physical addresses) is 0-XGB when X <= 3GB, and 0-(X+1)GB when X > 3GB. If there is no IO gap this patch should still work. Change-Id: I5453a09e953643cada2c096a91d339a3676f55ee Reviewed-on: https://gem5-review.googlesource.com/2169 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-09ruby: fix and/or precedence in sliccLena Olson
The slicc compiler currently treats && and || with the same precedence. This is highly non-intuitive to people used to C, and was probably an error. This patch makes && bind tighter than ||. For example, previously: if (A || B && C) compiled to: if ((A || B) && C) With this patch, it compiles to: if (A || (B && C)) Change-Id: Idbbd5b50cc86a8d6601045adc14a253284d7b791 Signed-off-by: Lena Olson (leolson@google.com) Reviewed-on: https://gem5-review.googlesource.com/2168 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Joe Gross <criusx@gmail.com> Reviewed-by: Sooraj Puthoor <puthoorsooraj@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Conflicts: COPYING
2017-03-09misc: Add a CONTRIBUTING documentJason Lowe-Power
This document details how to contribute to gem5 based on our new contribution flow with git and gerrit. Change-Id: I0a7e15fd83a3ee3ab6c85c1192f46f1e1d33b7c2 Signed-off-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-on: http://reviews.gem5.org/r/3814/ Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Pierre-Yves Peneau <pierre-yves.peneau@lirmm.fr> Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Reviewed-by: Brad Beckmann <brad.beckmann@amd.com> Reviewed-by: Ali Saidi <Ali.Saidi@ARM.com>
2017-03-07gpu-compute: Fix Python/C++ object hierarchy discrepanciesAndreas Sandberg
The GPUCoalescer and the Shader classes have different base classes in C++ and Python. This causes subtle bugs in SWIG and compilation errors for PyBind. Change-Id: I1ddd2a8ea43f083470538ddfea891347b21d14d8 Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2228 Maintainer: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr> Reviewed-by: Bradford Beckmann <brad.beckmann@amd.com>
2017-03-07power: Avoid forward declarations that confuse wrappersAndreas Sandberg
The Python wrappers get confused by the forward declarations in the power framework. This changeset restructures the code slightly to avoid the troublesome forward declarations. Change-Id: Id8c93224f1988edb5fdf9d3abc6237f2f688c02d Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-by: Sascha Bischoff <sascha.bischoff@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2227 Reviewed-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-07dev, arm: Render HDLCD frames at a fixed rate in KVMSudhanshu Jha
Use the new fast scan-out API in the PixelPump to render frames at a fixed frame rate in KVM mode. The refresh rate when running in KVM can be controlled by the virt_refresh_rate parameter. Change-Id: Ib3c78f174e3f8f4ca8a9b723c4e5d311a433b8aa Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2242 Reviewed-by: Rahul Thakur <rjthakur@google.com>
2017-03-07dev: Add support for single-pass scan out in the PixelPumpSudhanshu Jha
Add a helper function to scan out an entire frame in one time step. This requires the public PixelPump to be changed somewhat to separate timing updates from general PixelPump control. Instead of calling PixelPump::start(timings), timings now need to be updated using a separate call to PixelPump::updateTimings(timings) before calling PixelPump::start(). Display controllers that don't need accurate timing (e.g., in KVM mode), can use the new PixelPump::renderFrame() API to render an entire frame in one step. This call results in the same callbacks (e.g., calls to nextPixel()) as the timing calls, but they all happen in immediately. Unlike the timing counterpart, renderFrame() doesn't support buffer underruns and will panic if nextPixle() indicates an underrun. Change-Id: I76c84db04249b02d4207c5281d82aa693d0881be Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2241 Reviewed-by: Rahul Thakur <rjthakur@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-03-07dev, kvm: Add a fast KVM-aware mode in DmaReadFifoSudhanshu Jha
Use a fast, functional, read operations keep the DMA FIFO full when running in KVM mode. Change-Id: I5b378c2fb6a1d3e687cef15e807e63a0a53a60e2 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2226 Reviewed-by: Rahul Thakur <rjthakur@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-07arm, kmi: Clear interrupts in KMI devicesSudhanshu Jha
Added functionality to check and clear interrupts for KMI devices. This fixes a boot bug when using KVM and in-kernel GIC emulation. Change-Id: Ia3e91d07567b7faf3f82b0adfda4a165a502a339 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2225 Reviewed-by: Rahul Thakur <rjthakur@google.com>
2017-03-06syscall-emul: Remove unused class and memberBrandon Potter
The WaitRec structure in the Process class is unnecessary. There is a member declaration inside of the Process class, waitList, that uses the WaitRec definition. However, waitList is unused so they are both dead bits of code. This changeset removes both the WaitRec struct and waitList member from Process. Change-Id: Ia6ee7488b9f47fd0f0ae29c818fba6ea0710699c Reviewed-on: https://gem5-review.googlesource.com/2262 Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com> Reviewed-by: Michael LeBeane <Michael.Lebeane@amd.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2017-03-03mem: Make blkAlign a common function between all tag classesNikos Nikoleris
blkAlign was defined as a separate function in the base associative and fully-associative tags classes although both functions implemented identical functionality. This patch moves the blkAlign in the base tags class. Change-Id: I3d415d0e62bddeec7ce0d559667e40a8c5fdc2d4 Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Andreas Hansson <andreas.hansson@arm.com>
2017-03-03mem: Use pkt::getBlockAddr instead of BaseCace::blockAlignNikos Nikoleris
Change-Id: I0ed4e528cb750a323facdc811dde7f0ed1ff228e Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Andreas Hansson <andreas.hansson@arm.com>
2017-03-03arm, kvm: enable running 32-bit Guest under ARM KVM64Rahul Thakur
1) Pass KVM_ARM_VCPU_EL1_32BIT to kvmArmVCpuInit when running 32-bit OS 2) Correctly map 64-bit registers to banked 32-bit ones Change-Id: I1dec6427d6f5c3bba599ccdd804f1dfe80d3e670 Reviewed-on: https://gem5-review.googlesource.com/2261 Maintainer: Rahul Thakur <rjthakur@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-03-03arm, kvm: fix saving/restoring conditional flags in ARM KVM64Rahul Thakur
The gem5 stores flags separately from other fields CPSR, so we need to split them out and recombine on trips to/from KVM. Change-Id: I28ed00eb6f0e2a1436adfbc51b6ccf056958afeb Reviewed-on: https://gem5-review.googlesource.com/2260 Reviewed-by: Rahul Thakur <rjthakur@google.com> Maintainer: Rahul Thakur <rjthakur@google.com>
2017-03-01config: exit with fatal() if errorPierre-Yves Péneau
If output redirection is activated, the error message is printed in simout. This change ensure it will be printed in simerr. Change-Id: Ie661ac6b6978bf2e4aaaccdf23134795d764d459 Signed-off-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr> Reviewed-on: https://gem5-review.googlesource.com/2221 Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2017-03-01ruby: fix and/or precedence in sliccLena Olson
The slicc compiler currently treats && and || with the same precedence. This is highly non-intuitive to people used to C, and was probably an error. This patch makes && bind tighter than ||. For example, previously: if (A || B && C) compiled to: if ((A || B) && C) With this patch, it compiles to: if (A || (B && C)) Change-Id: Idbbd5b50cc86a8d6601045adc14a253284d7b791 Signed-off-by: Lena Olson (leolson@google.com) Reviewed-on: https://gem5-review.googlesource.com/2168 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Joe Gross <criusx@gmail.com> Reviewed-by: Sooraj Puthoor <puthoorsooraj@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> [ Rebased onto master ] Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-03-01scons: Automatically add a git commit message hookAndreas Sandberg
Gerrit requires that all commit messages have a Change-Id tag. This tag is added automatically by a commit message hook in Git. Include the default Gerrit commit message hook and add it automatically using scons to make life easier for everyone. Change-Id: I1270fbaaadf6ed151bddf14521a38e0c1a02d131 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2166 Reviewed-by: Jason Lowe-Power <power.jg@gmail.com> Maintainer: Jason Lowe-Power <power.jg@gmail.com>
2017-02-27syscall_emul: [PATCH 15/22] add clone/execve for threading and multiprocess ↵Brandon Potter
simulations Modifies the clone system call and adds execve system call. Requires allowing processes to steal thread contexts from other processes in the same system object and the ability to detach pieces of process state (such as MemState) to allow dynamic sharing.
2017-02-27syscall_emul: [patch 14/22] adds identifier system callsBrandon Potter
This changeset add fields to the process object and adds the following three system calls: setpgid, gettid, getpid.
2017-02-27x86: remove unnecessary parameter from functionsBrandon Potter
2017-02-27gpu-compute: remove unnecessary member from classTony Gutierrez
The clang compiler complains that the wavefront member in the GpuISA class is unused. This changeset removes the member, because it does not appear serve a purpose.
2017-02-27gpu-compute: mark functions with override if replacing virtualBrandon Potter
The clang compiler is more stringent than the recent versions of GCC when dealing with overrides. This changeset adds the specifier to the methods which need it to silence the compiler.
2017-02-27arch: Include generated decoder header after normal headersAndreas Sandberg
The generated decoder header defines macros that represent bit fields within instructions. These fields typically have short names that conflict with names in other header files. Include the generated header after all normal header to avoid this issue. Change-Id: I53d149b75432c20abdbf651e32c3c785d897973b Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-02-27base: Refactor logging to make log level selection cleanerAndreas Sandberg
It's currently possible to change the log level in gem5 by tweaking a set of global variables. These variables are currently exposed to Python using SWIG. This mechanism is far from ideal for two reasons: First, changing the log level requires that the Python world enables or disables individual levels. Ideally, this should be a single call where a log level is selected. Second, exporting global variables is poorly supported by most Python frameworks. SWIG puts variables in their own namespace and PyBind doesn't seem to support it at all. This changeset refactors the logging code to create a more abstract interface. Each log level is associated with an instance of a Logger class. This class contains common functionality, an enable flag, and a verbose flag. Available LogLevels are described by the LogLevel class. Lower log levels are used for more critical messages (PANIC being level 0) and higher levels for less critical messages. The highest log level that is printed is controlled by calling Logger:setLevel(). Change-Id: I31e44299d242d953197a8e62679250c91d6ef776 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Gabor Dozsa <gabor.dozsa@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2017-02-27tests: Disable descriptions in stat filesAndreas Sandberg
Don't output verbose text descriptions in stat files when running tests. This saves a lot of space when storing reference data. Change-Id: I2a7ead4843586e800ecf83846694b73f0c356373 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Sascha Bischoff <sascha.bischoff@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com>
2017-02-27python: Add a generalized mechanism to configure statsAndreas Sandberg
Add a mechanism to configure the stat output format using a URL-like syntax. This makes it possible to specify both an output format (currently, only text is supported) and override default parameters. On the Python-side, this is implemented using a helper function (m5.stats.addStatVisitor) that adds a visitor to the list of active stat visitors. The helper function parses a URL-like stat specification to determine the stat output type. Optional parameters can be specified to change how stat visitors behave. For example, to output stats in text format without stat descriptions: m5.stats.addStatVisitor("text://stats.txt?desc=False") From the command line: gem5.opt --stats-file="text://stats.txt?desc=False" Internally, the stat framework uses the _url_factory decorator to wrap a Python function with the fn(path, **kwargs) signature in a function that takes a parsed URL as its only argument. The path and keyword arguments are automatically derived from the URL in the wrapper function. New output formats can be registered in the m5.stats.factories dictionary. This dictionary contains a mapping between format names (URL schemes) and factory methods. To retain backwards compatibility, the code automatically assumes that the user wants text output if no format has been specified (i.e., when specifying a plain path). Change-Id: Ic4dce93ab4ead07ffdf71e55a22ba0ae5a143061 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Curtis Dunham <curtis.dunham@arm.com> Reviewed-by: Sascha Bischoff <sascha.bischoff@arm.com> Reviewed-by: Ilias Vougioukas <ilias.vougioukas@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Tony Gutierrez <anthony.gutierrez@amd.com>
2015-07-20syscall_emul: [patch 13/22] add system call retry capabilityBrandon Potter
This changeset adds functionality that allows system calls to retry without affecting thread context state such as the program counter or register values for the associated thread context (when system calls return with a retry fault). This functionality is needed to solve problems with blocking system calls in multi-process or multi-threaded simulations where information is passed between processes/threads. Blocking system calls can cause deadlock because the simulator itself is single threaded. There is only a single thread servicing the event queue which can cause deadlock if the thread hits a blocking system call instruction. To illustrate the problem, consider two processes using the producer/consumer sharing model. The processes can use file descriptors and the read and write calls to pass information to one another. If the consumer calls the blocking read system call before the producer has produced anything, the call will block the event queue (while executing the system call instruction) and deadlock the simulation. The solution implemented in this changeset is to recognize that the system calls will block and then generate a special retry fault. The fault will be sent back up through the function call chain until it is exposed to the cpu model's pipeline where the fault becomes visible. The fault will trigger the cpu model to replay the instruction at a future tick where the call has a chance to succeed without actually going into a blocking state. In subsequent patches, we recognize that a syscall will block by calling a non-blocking poll (from inside the system call implementation) and checking for events. When events show up during the poll, it signifies that the call would not have blocked and the syscall is allowed to proceed (calling an underlying host system call if necessary). If no events are returned from the poll, we generate the fault and try the instruction for the thread context at a distant tick. Note that retrying every tick is not efficient. As an aside, the simulator has some multi-threading support for the event queue, but it is not used by default and needs work. Even if the event queue was completely multi-threaded, meaning that there is a hardware thread on the host servicing a single simulator thread contexts with a 1:1 mapping between them, it's still possible to run into deadlock due to the event queue barriers on quantum boundaries. The solution of replaying at a later tick is the simplest solution and solves the problem generally.
2015-07-20style: [patch 12/22] fix preliminary style issues for subsequent fault patchBrandon Potter
This changeset add spaces in a few spots and removes an unnecessary comment.
2015-07-20syscall_emul: [patch 11/22] extend functionality of fcntlBrandon Potter
This changeset adds the ability to set a close-on-exec flag for a given file descriptor. It also reworks some of the logic surrounding setting and retrieving flags from the file description.
2017-02-23x86: remove redundant condition check in tlb codeBrandon Potter
2017-02-23base: fix small memory leak in the ELF loaderBrandon Potter
2017-02-21mem: Remove unused size field from the CacheBlk classNikos Nikoleris
Change-Id: I6149290d6d2ac1a4bd6165871c93d7b7d6a980ad Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Remove the unused asid field from the CacheBlk classNikos Nikoleris
Change-Id: I29f45733c5fad822bdd0d8dcc7939d86b2e8c97b Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Remove unused arguments (asid/contex_id) from accessBlockNikos Nikoleris
Change-Id: I79c2662fc81630ab321db8a75be6cd15fa07d372 Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Remove unused type BlkList from the cache and the tagsNikos Nikoleris
Change-Id: If9ebb8488e8db587482ecfa99d2c12cfe5734fb9 Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Remove unused functions from the tag classesNikos Nikoleris
Change-Id: I4f3c2c027b1acaaf791a4c71086f34a9b9fbf4df Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Always use the helper function to invalidate a blockNikos Nikoleris
Policies like the LRU need to be notified when a block is invalidated, the helper function does this along with invalidating the block. Change-Id: I3ed59cf07938caa7f394ee6054b0af9e00b267ea Reviewed-by: Andreas Hansson <andreas.hansson@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2017-02-21mem: Fix MSHR assert triggering for invalidated prefetchesSascha Bischoff
This changeset updates an assert in src/mem/cache/mshr.cc which was erroneously catching invalidated prefetch requests. These requests can become invalidated if another component writes (an exclusive access) to this location during the time that the read request is in flight. The original assert made the assumption that these cases can only occur for reads generated by the CPU, and hence prefetcher-generated requests would sometimes trip the assert. Change-Id: If4f043273a688c2bab8f7a641192a2b583e7b20e Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-24 14:05:47 +0000