Information about what kernel to load and how to load it was built
into the System object and its subclasses. That overloaded the System
object and made it responsible for too many things, and also was
somewhat awkward when working with SE mode which doesn't have a kernel.
This change extracts the kernel and information related to it from the
System object and puts into into a OsKernel or Workload object.
Currently the idea of a "Workload" to run and a kernel are a bit
muddled, an unfortunate carry-over from the original code. It's also an
implication of trying not to make too sweeping of a change, and to
minimize the number of times configs need to change, ie avoiding
creating a "kernel" parameter which would shortly thereafter be
renamed to "workload".
In future changes, the ideas of a kernel and a workload will be
disentangled, and workloads will be expanded to include emulated
operating systems which shephard and contain Process-es for syscall
emulation.
This change was originally split into pieces to make reviewing it
easier. Those reviews are here:
https: //gem5-review.googlesource.com/c/public/gem5/+/22243
https: //gem5-review.googlesource.com/c/public/gem5/+/24144
https: //gem5-review.googlesource.com/c/public/gem5/+/24145
https: //gem5-review.googlesource.com/c/public/gem5/+/24146
https: //gem5-review.googlesource.com/c/public/gem5/+/24147
https: //gem5-review.googlesource.com/c/public/gem5/+/24286
Change-Id: Ia3d863db276a023b6a2c7ee7a656d8142ff75589
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/26466
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The requirement to have an environment variable exported to run a program
is not common, and many new users trip up on it.
Before this commit, M5_PATH was a requirement to run those scripts, or
else simulation would fail with:
IOError: Can't find a path to system files.
After this patch, as long as users indicate all required files with
command line options, M5_PATH is not needed.
This patch changes the M5_PATH semantics slightly to more closely match
PATH and so be more intuitive to users: after this commit, if the
given path contains a slash /, then the path is not searched for inside
M5_PATH, which is exactly how PATH works. Users can then select images
in the CWD with a leading ./ just as done for executables.
This is backwards incompatible if users were already specifying their paths
as ./, but this interface feels saner, because otherwise writing on the CLI
e.g.:
--disk-image path/to/my.disk
would previously fail to find the disk, even if it existed, which is very
counter-intuitive. The following will still fail however:
--disk-image my.disk
which is not ideal, but for now is a comprise between backwards
compatibility of having an M5_PATH and what users expect from CLI
interfaces.
Change-Id: Ic91e1cc20557b35b69490b6dc420e7d324fae1fc
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23672
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
All ISAs except SPARC can now take multiple disk images by passing
the --disk-image option multiple times.
Before this patch, several ISAs automatically mounted a secondary disk
called "linux-bigswap2.img", which had to be in M5_PATH even if the end
user did not want more than one disk. This was the case for for example
for X86 but not ARM.
This change was done to:
* allow ARM to have a second disk image in fs.py, which was not possible,
and allow other ISAs like X86 and ARM to take any number of disk images
* provide a simpler, more intuitive CLI interface that does not require
magic disk images to be present in M5_PATH to work for ISAs such as X86.
Linux does not need that secondary image to boot correctly, so it is
more friendly to support a minimal setup that requires the least amount
of binaries to boot, and let supply the second image manually only if
they need it.
* make fs.py --disk-image work more similarly across all ISAs
SPARC was left with a single disk only because its setup was a bit more
complex and would require further testing.
Change-Id: I8b6e08ae6daf0a5b6cd1d57d285a9677f01eb7ad
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23671
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Other scripts (like se.py) blindly try to apply the indirect predictor
if one is set. Because this option defaults to something, there's no
way (as far as I know) to purposefully select nothing, and so the
simulator crashes. Users shouldn't have to proactively prevent gem5
from killing itself regardless, so the default was changed to "None".
Change-Id: Ic3382b8065442d6705b1c6a656646598d9d5c322
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23360
Reviewed-by: Ciro Santilli <ciro.santilli@arm.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
9p allows the guest Linux kernel to mount a host directory into the guest.
This allows to very easily modify test programs after a run at the end of
boot, without the need to re-insert the changes into a disk image.
It is enabled on both fs.py and fs_bigLITTLE.py with the --vio-9p
option.
Adapted from code originally present on the wiki: http://gem5.org/WA-gem5
As documented in the CLI option help, the current setup requires the guest
to know the full path to the host share, which is annoying, but overcoming
that would require actually parsing a bit of the protocol rather than just
forwarding everything to diod.
Change-Id: Iaeb1ed185dccfa8332fe6657a54e7550f64230eb
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22831
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This is the second step towards being able to run dynamically linked
applications when the guest ISA != than host ISA.
Once the guest interpreter is loaded to memory, we are able to redirect
shared object loads through the redirectPath interface.
How do we load the guest interpreter?
The elf file is for example asking for the /lib/ld-linux-aarch64.so
interpreter.
That would point to a valid dynamic linker/loader if guest ISA == host
ISA, but if we are running on X86 we should point to the guest
(aarch64 in the example) toolchain wherever it is installed.
This patch is adding the --interp-dir option to point to the parent
folder of the guest /lib in the host fs.
Change-Id: Id27b97c060008d2e847776a49323d45c8809a27f
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23066
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This is the first step towards being able to run dynamically linked
applications when the guest ISA != than host ISA.
(Like running a arm application on x86)
By using the --redirects command line option it is possible to specify
via CLI a set of path redirections to be used in SE mode.
This is needed when running a dynamically linked binary in
SE mode in a guest ISA different than the host. The linker will look
for SOs (e.g. libc.so) in /lib/, but will only find the host libraries.
With this option we can redirect to the guest toolchain/file system.
Usage:
gem5.opt [example script]
--redirects /dir1=/path/to/host/dir1 \
--redirects /dir2=/path/to/host/dir2
Change-Id: I558838be2ad6802891707e9a1cc454786859db15
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23065
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Typically, a memory controller is assigned an address range of the
form [start, end). This address range might be interleaved and
therefore only a non-continuous subset of the addresses in the address
range is handed by this controller.
Prior to this patch, the DRAM controller was unaware of the
interleaving and as a result the address range could affect the
mapping of addresses to DRAM ranks, rows and columns. This patch
changes the DRAM controller, to transform the input address to a
continuous range of the form [0, size). As a result the DRAM
controller always operates on a dense and continuous address range
regardlesss of the system configuration.
Change-Id: I7d273a630928421d1854658c9bb0ab34e9360851
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19328
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Wendy Elsasser <wendy.elsasser@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This patch is pulling the on-chip memory outside of the on_chip_devices
list.
The external interface will be more or less the same: configuration
scripts will still use the attachOnChipIO method; a new kw argument has
been added in order to store mem_ports.
We want to provide to on-chip memory the same mechanism used when
collecting on-chip dma ports. This is needed when using Ruby, since
we need to pass a non None mem_ports to prevent the bootmem to be
wired to the bus.
Change-Id: Ifc519c3072dc5de1530772c70c80dc2094e2c54c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22000
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Adding an option to enable DRAM low-power states. The low power
states can have a significant impact on application performance
(sim_ticks) on the order of 2-3x, especially for compute-gpu apps.
The options allows for it to easily be enabled/disabled to compare
performance numbers. The option is disabled by default.
Change-Id: Ib9bddbb792a1a6a4afb5339003472ff8f00a5859
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18548
Reviewed-by: Wendy Elsasser <wendy.elsasser@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This patch updates the FileSystemConfig so it works with more kinds of
config scripts (e.g., the Learning gem5 scripts).
There are 4 main changes:
- Added system as a parameter to the config_filesystem function so the
function can search the system for the number of CPUs instead of relying
on options from Options.py
- Instead of calling redirect_paths everywhere config_filesystem is
used, now it is implicitly called.
- Cleaned up the Ruby scripts a bit to remove redundant calls to
config_filesystem
- Added a config_filesystem call to the Ruby Learning gem5 script
(currently the only Learning gem5 script that requires it).
In the future, I think it would be better to move the config_filesystem
call into simulate.py, probably into the instantiate function. I tried to
use the per-CPU configuration parameters instead of options from
Options.py, but that's not possible until after the SimObject params
have been finalized in instantiate.
Change-Id: Ie6501a7435cfb3ac9d2b45be3722388b34063b1e
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18848
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Tested-by: kokoro <noreply+kokoro@google.com>
This change introduces the concept of a faux-filesystem.
The faux-filesystem creates a directory structure in m5out
(or whatever output dir the user specifies) where system calls
may be redirected.
This is useful to avoid non-determinism when reading files
with varying path names (e.g., variations from run-to-run if
the simulation is scheduled on a cluster where paths may change).
Also, this changeset allows circumventing host pseudofiles which
have information specific to the host processor (such as cache
hierarchy or processor information). Bypassing host pseudofiles
can be useful when executing runtimes in the absence of an
operating system kernel since runtimes may try to query standard
files (i.e. /proc or /sys) which are not relevant to an
application executing in syscall emulation mode.
Change-Id: I90821b3b403168b904a662fa98b85def1628621c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/12119
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Kernel was being set using a placeholder and then assigned the
correct value. This would generate the following error if the
placeholder file did not exist:
'IOError: Can't find file <placeholder> on path'
This patch follows the same directions of commit
12eca7ac04 and removes the default
values, forcing the user to properly configure the kernel.
Change-Id: I0eb45d12eda6b6efe9a3fe118996b640844a7b34
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/11850
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Python 2.7 used to return lists for operations such as map and range,
this has changed in Python 3. To make the configs Python 3 compliant,
add explicit conversions from iterators to lists where needed, replace
xrange with range, and fix changes to exec syntax.
This change doesn't fix import paths since that might require us to
restructure the configs slightly.
Change-Id: Idcea8482b286779fc98b4e144ca8f54069c08024
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/16002
Reviewed-by: Gabe Black <gabeblack@google.com>
Before this commit, there were default magic DTB and kernel filenames
for some platforms.
This was inelegant and error prone, as it refered to out-of-tree files,
and set defaults which users almost always want to customize with
explicit command line options.
One result of this is that a wrong exception could be thrown if --kernel
was given but not --machine-type, since the default machine type
VExpress_EMM had a default kernel, and the code would always search for
the default filename even though --kernel was given:
IOError: Can't find file 'vmlinux.aarch32.ll_20131205.0-gem5' on path.
The defaults existed only for older machine types, and not for the
usually recommended VExpress_GEM5_V1, which suggests that this
deprecation should not affect many users.
Change-Id: Ia49298304f658701ea0800bd79e08db404a655c3
Reviewed-on: https://gem5-review.googlesource.com/c/15898
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
