#
13988:d579f9c76531 |
|
03-May-2019 |
Gabe Black <gabeblack@google.com> |
sparc: Add an object file loader for linux and solaris.
Change-Id: I76bcbc06714f7d538f03a8311994a868de3640f1 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18629 Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.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.
|
#
11851:824055fe6b30 |
|
09-Nov-2016 |
Brandon Potter <brandon.potter@amd.com> |
syscall_emul: [patch 5/22] remove LiveProcess class and use Process instead
The EIOProcess class was removed recently and it was the only other class which derived from Process. Since every Process invocation is also a LiveProcess invocation, it makes sense to simplify the organization by combining the fields from LiveProcess into Process.
|
#
11794:97eebddaae84 |
|
09-Nov-2016 |
Brandon Potter <brandon.potter@amd.com> |
syscall_emul: [patch 2/22] move SyscallDesc into its own .hh and .cc
The class was crammed into syscall_emul.hh which has tons of forward declarations and template definitions. To clean it up a bit, moved the class into separate files and commented the class with doxygen style comments. Also, provided some encapsulation by adding some accessors and a mutator.
The syscallreturn.hh file was renamed syscall_return.hh to make it consistent with other similarly named files in the src/sim directory.
The DPRINTF_SYSCALL macro was moved into its own header file with the include the Base and Verbose flags as well.
|
#
11793:ef606668d247 |
|
09-Nov-2016 |
Brandon Potter <brandon.potter@amd.com> |
style: [patch 1/22] use /r/3648/ to reorganize includes
|
#
8229:78bf55f23338 |
|
15-Apr-2011 |
Nathan Binkert <nate@binkert.org> |
includes: sort all includes
|
#
7741:340b6f01d69b |
|
11-Nov-2010 |
Gabe Black <gblack@eecs.umich.edu> |
SPARC: Clean up some historical style issues.
|
#
6329:5d8b91875859 |
|
09-Jul-2009 |
Gabe Black <gblack@eecs.umich.edu> |
Registers: Add a registers.hh file as an ISA switched header. This file is for register indices, Num* constants, and register types. copyRegs and copyMiscRegs were moved to utility.hh and utility.cc.
|
#
6075:1e1a874f9b17 |
|
19-Apr-2009 |
Gabe Black <gblack@eecs.umich.edu> |
SE mode: Make keeping track of the number of syscalls less hacky.
|
#
5981:5e7899a2692f |
|
28-Feb-2009 |
Steve Reinhardt <stever@gmail.com> |
Fix Num_Syscall_Descs check bug in non-x86 ISAs. (See cset d35d2b28df38 for x86 fix.)
|
#
5154:7e6431213487 |
|
16-Oct-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Make the process objects use the Params structs in their constructors, and use a limit to check if access are on the stack.
|
#
4188:6a9ac3b35285 |
|
09-Mar-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Split the syscall table, SPARC specific syscall implementations, and the 32 bit syscall table into it's own file. Corrected problems with the stat structure. These should be tested on 64 bit x86 and SPARC machines.
|
#
4118:ddd23e5282d7 |
|
02-Mar-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Implement the _llseek syscall. It's Linux only, so we'll actually use the lseek syscall.
|
#
4111:65fffcb4fae9 |
|
28-Feb-2007 |
Gabe Black <gblack@eecs.umich.edu> |
Make trap instructions always generate TrapInstruction Fault objects which call into the Process object to handle system calls. Refactored the Process objects, and move the handler code into it's own file, and add some syscalls which are used in a natively compiled hello world. Software traps with trap number 3 (not syscall number 3) are supposed to cause the register windows to be flushed but are ignored right now. Finally, made uname for SPARC report a 2.6.12 kernel which is what m22-018.pool happens to be running.
|
#
3669:3607aaed36b6 |
|
16-Nov-2006 |
Nathan Binkert <binkertn@umich.edu> |
Implement current working directory for LiveProcesses
|
#
3114:7a4771b9b720 |
|
17-Sep-2006 |
Gabe Black <gblack@eecs.umich.edu> |
Finished changing how stat structures are translated, fixed the handling of various ids as LiveProcess parameters.
src/arch/alpha/linux/process.cc: src/arch/alpha/linux/process.hh: src/arch/alpha/process.cc: src/arch/alpha/process.hh: src/arch/alpha/tru64/process.cc: src/arch/alpha/tru64/process.hh: src/arch/mips/linux/process.cc: src/arch/mips/linux/process.hh: src/arch/mips/process.cc: src/arch/mips/process.hh: src/arch/sparc/linux/process.cc: src/arch/sparc/linux/process.hh: src/arch/sparc/process.cc: src/arch/sparc/process.hh: src/arch/sparc/solaris/process.cc: src/arch/sparc/solaris/process.hh: src/sim/process.cc: src/sim/process.hh: src/sim/syscall_emul.cc: src/sim/syscall_emul.hh: Changed Process to LiveProcess in syscall handlers and fixed the implementation of uid, euid, gid, egid, pid and ppid as LiveProcess parameters. src/kern/tru64/tru64.hh: Changed Process to LiveProcess in syscall handlers and fixed the implementation of uid, euid, gid, egid, pid and ppid as LiveProcess parameters. Also fit tru64 in with the new way to handle stat calls.
|
#
2962:4f3ee6fa65fa |
|
26-Jul-2006 |
Gabe Black <gblack@eecs.umich.edu> |
Now ignore sigaction
src/arch/sparc/isa/operands.isa: Added the GSR register as a control register
|
#
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.
|