#
14090:a2fea3b370b5 |
|
11-Jun-2019 |
Gabor Dozsa <gabor.dozsa@arm.com> |
sim: Add getter to fault virtual address
Change-Id: Ifd493aee9e78b0b4ddcc71e90f48679543acb861 Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19176 Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
|
#
13475:5189e2334f1a |
|
28-Nov-2018 |
Nikos Nikoleris <nikos.nikoleris@arm.com> |
base, sim: Add missing destructors
Derived classes with virtual functions need to define a virtual destructor or a protected destructor otherwise calling the base class destructor has undefined behavior. This change adds a virtual distructor in the base class.
Change-Id: I1c855aa56dff6585ff99b9147bdb4eb9729a0a53 Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/14815 Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
#
11877:5ea85692a53e |
|
20-Jul-2015 |
Brandon Potter <brandon.potter@amd.com> |
syscall_emul: [patch 13/22] add system call retry capability
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.
|
#
11876:39bff8406c3b |
|
20-Jul-2015 |
Brandon Potter <brandon.potter@amd.com> |
style: [patch 12/22] fix preliminary style issues for subsequent fault patch
This changeset add spaces in a few spots and removes an unnecessary comment.
|
#
10474:799c8ee4ecba |
|
16-Oct-2014 |
Andreas Hansson <andreas.hansson@arm.com> |
arch: Use shared_ptr for all Faults
This patch takes quite a large step in transitioning from the ad-hoc RefCountingPtr to the c++11 shared_ptr by adopting its use for all Faults. There are no changes in behaviour, and the code modifications are mostly just replacing "new" with "make_shared".
|
#
10417:710ee116eb68 |
|
27-Sep-2014 |
Andreas Hansson <andreas.hansson@arm.com> |
arch: Use const StaticInstPtr references where possible
This patch optimises the passing of StaticInstPtr by avoiding copying the reference-counting pointer. This avoids first incrementing and then decrementing the reference-counting pointer.
|
#
8794:e2ac2b7164dd |
|
18-Nov-2011 |
Gabe Black <gblack@eecs.umich.edu> |
SE/FS: Get rid of includes of config/full_system.hh.
|
#
8589:d0772caaeacd |
|
27-Sep-2011 |
Gabe Black <gblack@eecs.umich.edu> |
Faults: Make the generic faults more consistent between SE and FS.
All of the classes will now be available in both modes, and only GenericPageTableFault will continue to check the mode for conditional compilation. It uses a process object to handle the fault in SE mode, and for now those aren't available in FS mode.
|
#
8569:498d3aacd292 |
|
19-Sep-2011 |
Gabe Black <gblack@eecs.umich.edu> |
Faults: Get rid of the unused isAlignmentFault and isMachineCheckFault.
These functions aren't called anywhere and are probably only theoretically useful.
|
#
8545:a3992291e230 |
|
13-Sep-2011 |
Ali Saidi <saidi@eecs.umich.edu> |
LSQ: Only trigger a memory violation with a load/load if the value changes.
Only create a memory ordering violation when the value could have changed between two subsequent loads, instead of just when loads go out-of-order to the same address. While not very common in the case of Alpha, with an architecture with a hardware table walker this can happen reasonably frequently beacuse a translation will miss and start a table walk and before the CPU re-schedules the faulting instruction another one will pass it to the same address (or cache block depending on the dendency checking).
This patch has been tested with a couple of self-checking hand crafted programs to stress ordering between two cores.
The performance improvement on SPEC benchmarks can be substantial (2-10%).
|
#
8229:78bf55f23338 |
|
15-Apr-2011 |
Nathan Binkert <nate@binkert.org> |
includes: sort all includes
|
#
7878:d3e6ebcccabf |
|
04-Feb-2011 |
Gabe Black <gblack@eecs.umich.edu> |
Fault: Rename sim/fault.hh to fault_fwd.hh to distinguish it from faults.hh.
|
#
7867:3ee9e6c2e8f7 |
|
31-Jan-2011 |
Gabe Black <gblack@eecs.umich.edu> |
Fault: Move the definition of NoFault from faults.hh to fault.hh.
Moving the definition of NoFault into fault.hh doesn't bring any new dependencies with it, and allows some files to include just fault.hh which has less baggage. NoFault will still be available to everything that includes faults.hh because it includes fault.hh.
|
#
7678:f19b6a3a8cec |
|
13-Sep-2010 |
Gabe Black <gblack@eecs.umich.edu> |
Faults: Pass the StaticInst involved, if any, to a Fault's invoke method.
Also move the "Fault" reference counted pointer type into a separate file, sim/fault.hh. It would be better to name this less similarly to sim/faults.hh to reduce confusion, but fault.hh matches the name of the type. We could change Fault to FaultPtr to match other pointer types, and then changing the name of the file would make more sense.
|
#
7630:ffea4f79784f |
|
23-Aug-2010 |
Gabe Black <gblack@eecs.umich.edu> |
Faults: Get rid of some commented out code in sim/faults.hh.
|
#
5999:3cf8e71257e0 |
|
05-Mar-2009 |
Nathan Binkert <nate@binkert.org> |
stats: Fix all stats usages to deal with template fixes
|
#
5004:7d94cedab264 |
|
26-Aug-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Address translation: Make the page table more flexible. The page table now stores actual page table entries. It is still a templated class here, but this will be corrected in the near future.
|
#
4695:a63378aed062 |
|
18-Jul-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Make name, isMachineCheckFault, and isAlignmentFault const.
|
#
4183:3d19c1d46946 |
|
07-Mar-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Move the magic m5 PageTableFault into sim/faults.[hh,cc] since it's the same across all architectures.
|
#
2800:18a615ca6e19 |
|
26-Jun-2006 |
Ali Saidi <saidi@eecs.umich.edu> |
add syscall emulation page table fault so we can allocate more stack pages
src/cpu/simple/base.cc: add syscall emulation page table fault so we can allocate more stack pages FaultBase::invoke will do this, we don't need to do it here src/sim/faults.hh: I have no idea why this #if was there... gone src/sim/process.cc: make stack_min actually be the current minimum
|
#
2680:246e7104f744 |
|
06-Jun-2006 |
Kevin Lim <ktlim@umich.edu> |
Change ExecContext to ThreadContext. This is being renamed to differentiate between the interface used objects outside of the CPU, and the interface used by the ISA. ThreadContext is used by objects outside of the CPU and is specifically defined in thread_context.hh. ExecContext is more implicit, and is defined by files such as base_dyn_inst.hh or cpu/simple/base.hh.
Further renames/reorganization will be coming shortly; what is currently CPUExecContext (the old ExecContext from m5) will be renamed to SimpleThread or something similar.
src/arch/alpha/arguments.cc: src/arch/alpha/arguments.hh: src/arch/alpha/ev5.cc: src/arch/alpha/faults.cc: src/arch/alpha/faults.hh: src/arch/alpha/freebsd/system.cc: src/arch/alpha/freebsd/system.hh: src/arch/alpha/isa/branch.isa: src/arch/alpha/isa/decoder.isa: src/arch/alpha/isa/main.isa: src/arch/alpha/linux/process.cc: src/arch/alpha/linux/system.cc: src/arch/alpha/linux/system.hh: src/arch/alpha/linux/threadinfo.hh: src/arch/alpha/process.cc: src/arch/alpha/regfile.hh: src/arch/alpha/stacktrace.cc: src/arch/alpha/stacktrace.hh: src/arch/alpha/tlb.cc: src/arch/alpha/tlb.hh: src/arch/alpha/tru64/process.cc: src/arch/alpha/tru64/system.cc: src/arch/alpha/tru64/system.hh: src/arch/alpha/utility.hh: src/arch/alpha/vtophys.cc: src/arch/alpha/vtophys.hh: src/arch/mips/faults.cc: src/arch/mips/faults.hh: src/arch/mips/isa_traits.cc: src/arch/mips/isa_traits.hh: src/arch/mips/linux/process.cc: src/arch/mips/process.cc: src/arch/mips/regfile/float_regfile.hh: src/arch/mips/regfile/int_regfile.hh: src/arch/mips/regfile/misc_regfile.hh: src/arch/mips/regfile/regfile.hh: src/arch/mips/stacktrace.hh: src/arch/sparc/faults.cc: src/arch/sparc/faults.hh: src/arch/sparc/isa_traits.hh: src/arch/sparc/linux/process.cc: src/arch/sparc/linux/process.hh: src/arch/sparc/process.cc: src/arch/sparc/regfile.hh: src/arch/sparc/solaris/process.cc: src/arch/sparc/stacktrace.hh: src/arch/sparc/ua2005.cc: src/arch/sparc/utility.hh: src/arch/sparc/vtophys.cc: src/arch/sparc/vtophys.hh: src/base/remote_gdb.cc: src/base/remote_gdb.hh: src/cpu/base.cc: src/cpu/base.hh: src/cpu/base_dyn_inst.hh: src/cpu/checker/cpu.cc: src/cpu/checker/cpu.hh: src/cpu/checker/exec_context.hh: src/cpu/cpu_exec_context.cc: src/cpu/cpu_exec_context.hh: src/cpu/cpuevent.cc: src/cpu/cpuevent.hh: src/cpu/exetrace.hh: src/cpu/intr_control.cc: src/cpu/memtest/memtest.hh: src/cpu/o3/alpha_cpu.hh: src/cpu/o3/alpha_cpu_impl.hh: src/cpu/o3/alpha_dyn_inst_impl.hh: src/cpu/o3/commit.hh: src/cpu/o3/commit_impl.hh: src/cpu/o3/cpu.cc: src/cpu/o3/cpu.hh: src/cpu/o3/fetch_impl.hh: src/cpu/o3/regfile.hh: src/cpu/o3/thread_state.hh: src/cpu/ozone/back_end.hh: src/cpu/ozone/cpu.hh: src/cpu/ozone/cpu_impl.hh: src/cpu/ozone/front_end.hh: src/cpu/ozone/front_end_impl.hh: src/cpu/ozone/inorder_back_end.hh: src/cpu/ozone/lw_back_end.hh: src/cpu/ozone/lw_back_end_impl.hh: src/cpu/ozone/lw_lsq.hh: src/cpu/ozone/lw_lsq_impl.hh: src/cpu/ozone/thread_state.hh: src/cpu/pc_event.cc: src/cpu/pc_event.hh: src/cpu/profile.cc: src/cpu/profile.hh: src/cpu/quiesce_event.cc: src/cpu/quiesce_event.hh: src/cpu/simple/atomic.cc: src/cpu/simple/base.cc: src/cpu/simple/base.hh: src/cpu/simple/timing.cc: src/cpu/static_inst.cc: src/cpu/static_inst.hh: src/cpu/thread_state.hh: src/dev/alpha_console.cc: src/dev/ns_gige.cc: src/dev/sinic.cc: src/dev/tsunami_cchip.cc: src/kern/kernel_stats.cc: src/kern/kernel_stats.hh: src/kern/linux/events.cc: src/kern/linux/events.hh: src/kern/system_events.cc: src/kern/system_events.hh: src/kern/tru64/dump_mbuf.cc: src/kern/tru64/tru64.hh: src/kern/tru64/tru64_events.cc: src/kern/tru64/tru64_events.hh: src/mem/vport.cc: src/mem/vport.hh: src/sim/faults.cc: src/sim/faults.hh: src/sim/process.cc: src/sim/process.hh: src/sim/pseudo_inst.cc: src/sim/pseudo_inst.hh: src/sim/syscall_emul.cc: src/sim/syscall_emul.hh: src/sim/system.cc: src/cpu/thread_context.hh: src/sim/system.hh: src/sim/vptr.hh: Change ExecContext to ThreadContext.
|
#
2665:a124942bacb8 |
|
31-May-2006 |
Ali Saidi <saidi@eecs.umich.edu> |
Updated Authors from bk prs info
|
#
2632:1bb2f91485ea |
|
22-May-2006 |
Steve Reinhardt <stever@eecs.umich.edu> |
New directory structure: - simulator source now in 'src' subdirectory - imported files from 'ext' repository - support building in arbitrary places, including outside of the source tree. See comment at top of SConstruct file for more details. Regression tests are temporarily disabled; that syetem needs more extensive revisions.
SConstruct: Update for new directory structure. Modify to support build trees that are not subdirectories of the source tree. See comment at top of file for more details. Regression tests are temporarily disabled. src/arch/SConscript: src/arch/isa_parser.py: src/python/SConscript: Update for new directory structure.
|