An ARM big.LITTLE system consists of two cpu clusters: the big
CPUs are typically complex out-of-order cores and the little
CPUs are simpler in-order ones. The fs_bigLITTLE.py script
can run a full system simulation with various number of big
and little cores and cache hierarchy. The commit also includes
two example device tree files for booting Linux on the
bigLITTLE system.
Change-Id: I6396fb3b2d8f27049ccae49d8666d643b66c088b
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
The dts files in system/arm/dt currently assume that an (unreleased)
gem5-specific virtual encoder is used as a remote endpoint for the
HDLCD. This driver won't be released as a more general virtual encoder
is about to be posted on the Linux DRI devel list and this encoder has
now been merged with gem5's kernel tree. This changeset updates gem5's
dts files to use that encoder.
Change-Id: Ic1a1be728efd31603752fdfba005b6dbdea42e7e
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Rene De Jong <rene.dejong@arm.com>
Ship aarch32 and aarch64 device trees with gem5. We currently ship
device trees as a part of the gem5 Linux kernel repository. This makes
tracking hard since device trees are supposed to be platform dependent
rather than kernel dependent (Linux considers device trees to be a
stable kernel ABI). It also makes code sharing between aarch32 and
aarch64 impossible.
This changeset implements a set of device trees for the new
VExpress_GEM5_V1 platform. The platform is described in a shared file
that is separate from the memory/CPU description. Due to differences
in how secondary CPUs are initialized, aarch32 and aarch64 use
different base files describing CPU nodes and the machine's
compatibility property.
Note: AArch64 and AArch32 interworking is not supported. If you use an AArch64
kernel you are restricted to AArch64 user-mode binaries. This will be addressed
in a later patch.
Note: Virtualization is only supported in AArch32 mode. This will also be fixed
in a later patch.
Contributors:
Giacomo Gabrielli (TrustZone, LPAE, system-level AArch64, AArch64 NEON, validation)
Thomas Grocutt (AArch32 Virtualization, AArch64 FP, validation)
Mbou Eyole (AArch64 NEON, validation)
Ali Saidi (AArch64 Linux support, code integration, validation)
Edmund Grimley-Evans (AArch64 FP)
William Wang (AArch64 Linux support)
Rene De Jong (AArch64 Linux support, performance opt.)
Matt Horsnell (AArch64 MP, validation)
Matt Evans (device models, code integration, validation)
Chris Adeniyi-Jones (AArch64 syscall-emulation)
Prakash Ramrakhyani (validation)
Dam Sunwoo (validation)
Chander Sudanthi (validation)
Stephan Diestelhorst (validation)
Andreas Hansson (code integration, performance opt.)
Eric Van Hensbergen (performance opt.)
Gabe Black
The simple_bootloader checks for CPU0 in a manner incompatible with systems
actually using affinity levels -- just looking at MPIDR[7:0]. However, in
future we may wish to use real affinity levels and this method will be in danger
of matching several CPUs with affinity0 = 0.
Match affinity2 == affinity1 == affinity0 == 0 instead.
use quiesceNs on other CPUs
panic rather than spin on an error
console/Makefile:
Add m5op to the build process
console/dbmentry.S:
use quiesceNs on other CPUs
console/printf.c:
panic rather than spin on an error.
console/console.c:
the go parameter to unixBoot is never used, so get rid of it.
just panic if we return from unixBoot since it's never supposed
to happen.
remove the MAX_CPUS parameter and the bootStrapImpure variable
and just allocate memory as needed. (Can in theory support many
more CPUs.)
only compile one console
console/Makefile:
Now that the location of the m5 backdoor is passed into the
console via the m5AlphaAccess variable, we only need to
compile one console, and don't need to define TLASER or TSUNAMI
console/console.c:
Don't hardcode the location of the AlphaAccess structure, but
rely on m5 to pass in the correct value.
Setup "volatile struct AlphaAccess *m5AlphaAccess" for use and
get rid of the hardcoded usage.
I steped on while doing it
console/console.c:
Allocate more HWRPB pages so we have room for 64 percpu_rpbs
Fix writing of Console Relocation Block virtual addresses so that
if they are outside of the first page, which they will be with more
than 8 processors, the correct adress is written
palcode/Makefile:
Update makefile for tsunami with 64 processors
palcode/platform_m5.S:
Add support for tsunami with 64 processors
console/console.c:
Remove Printed SimOS references and replace with M5
Rework the SMP stuff, so we don't trash any stacks, or what we
thought were stacks, but are actually other ppls memory.
console/dbmentry.s:
add a carefully crafted piece of assembly that doesn't use the stack,
so we don't clobber anthing in the time between when we are spinning
and when the OS tells us to go.
palcode/platform_m5.s:
add/fix code for IPI, multiprocessor interrupts (DIR), and initial
bootstrapping of the cpu
addresses so the uncachable bit is set for tsunami.
console/Makefile:
console/console.c:
changed to generate tlaser and tsunami console code at different addresses
measure. The rest of the registers I used are touched by the tlaser
platform code so I would guess their are fair game.
Random memory troubles hopefully over.
console/Makefile:
palcode/Makefile:
moved header files to /h so updated make file for that
console/dbmentry.s:
console/paljtokern.s:
console/paljtoslave.s:
upadated to use osf file that the palcode uses, one less file
console/Makefile:
Updated to build on linux and removed
lots of crud that compiled, disassembled, and then reassembled
console/dbmentry.s:
the assembler didn't like they comments, so I removed them
console/printf.c:
Gcc was very unhappy, so I fixed this line
h/lib.h:
time_t is defined in a std header, and this was causing some problems
deleted and then upon realizing we needed them undeleted a bunch of
header files in the palcode dir
console/Makefile:
fixed so it will work with tru64... still haven't got the console to build under linux
palcode/platform_m5.s:
fixed code to "fake" srm console interrupt handling correctly
include serial interrupts
console/console.c:
0 the system type, let m5 overwrite
palcode/platform_m5.s:
add some comments and make the timer interrupt actually care what CPU it happened on
Gabor Dozsa
Andreas Sandberg
Steve Reinhardt
Karthik Sangaiah
ARM gem5 Developers
Matt Evans
Ali Saidi
Prakash Ramrakhyani
Nathan Binkert
Geoffrey Blake
Ali Saidi
Nathan Binkert
Benjamin Nash
Miguel Serrano
Erik Hallnor