There were accessors for reading these indexes, but they were not
consistently used. This change makes them private to StaticInst, and
changes places that were accessing them directly to instead use the
accessors. New accessors are added for code generated by the ISA parser
and some ARM code to set the indexes without accessing them directly.
By forcing these values to be behind accessors, it will be much simpler
to change how those values are stored and retrieved.
Change-Id: Icca80023d7f89e29504fac6b194881f88aedeec2
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/36875
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Several TLB invalidation instructions rely on VMID matching. This is
only applicable is EL2 is implemented and enabled in the current state.
The code prior to this patch was making the now invalid assumption that
we shouldn't consider the VMID if we are doing a secure lookup. This is
because in the past if we were in secure mode we were sure EL2 was not
enabled.
This is fishy and not valid anymore anyway after the introduction of
secure EL2.
Change-Id: I9a1368f8ed19279ed3c4b2da9fcdf0db799bc514
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/35242
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Modern libraries such as ROCm, MPI, and libnuma use files in Linux'
sysfs to determine the system topology such as number of CPUs, cache
size, cache associativity, etc. If Linux does not recognize the vendor
string returned by CPUID in x86 it will do a generic initialization
which does not include creating these files. In the case of ROCm
(specifically ROCt) this causes failures when getting device properties.
This can be solved by setting the vendor string to, for example,
AuthenticAMD (as qemu does) so that Linux will create the relevant sysfs
files. Unfortunately, simply changing the string in cpuid.cc to
AuthenticAMD causes simulation slowdown and may not be desirable to all
users. This change creates a parameter, defaulting to M5 Simulator as it
currently is, which can be set in python configuration files to change
the vendor string. Example of how to configure this is:
for i in range(len(self.cpus)):
for j in range(len(self.cpus[i].isa)):
self.cpus[i].isa[j].vendor_string = "AuthenticAMD"
Change-Id: I8de26d5a145867fa23518718a799dd96b5b9bffa
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/36156
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The event in KVM x86 SE mode plays double duty, triggering a system call
or a page fault depending on where it's called from (the system call
handler vs page fault handler).
This means we can eliminate the page fault gem5 op and the
pseudo_inst.hh switching header file.
This change touches a lot of things, but there wasn't really a good
place to split it up which still made sense and was consistent and
functional.
Change-Id: Ic414829917bcbd421893aa6c89d78273e4926b78
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/34165
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Alexandru Duțu <alexandru.dutu@amd.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
These tables take up a lot of space and obscure what's going on in the
file around them. This change moves them into their own files (one for
32 bit and one for 64 bit). It also moves the x86 local definitions of
some system calls into their own file, and creates a SConscript file for
the linux subdirectory.
Change-Id: Ib0978005783b41789ea59695ad95b0336f6353eb
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/34160
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
In SPARC and SE mode, system calls are triggered by a trap exception
with the appropriate trap number, and then a handler within the Workload
(formerly the Process) object recognizes the trap number and triggers
the system call.
For Linux, this special handling happens in the Linux specific Workload,
and other types of traps are passed through to the base SPARC SE
Workload class. For Solaris however, no special handling is implemented.
That means that it's actually impossible for a Solaris SE mode program
to actually trigger a system call, and so while there is some code
written for Solaris SE mode, this feature does not actually work at all.
Also, while it's relatively easy to build binaries for Linux on various
architectures using, for instance, the crosstool-ng configs in util/,
there is no ready made option that I could find for building a SPARC
Solaris cross compiler which would run on x86 linux.
Given that the support that exists isn't actually hooked up properly,
SPARC is not one of the most popular ISAs within gem5, Solaris is not a
widely used operating system, we have (to my knowledge) no test binary
to run, and setting up a cross compiler would be non-trivial, it makes
the most sense to me to remove this support.
Change-Id: I896b5abc4bf337bd4e4c06c49de7111a3b2b784c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/33996
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This is still triggered by the generic mechanism that tries out all
paths to go from an object file to a process. That's not entirely
necessary since the only loader that should be used when using the
X86ISA::EmuLinux workload is the one it provides, but the rest of gem5
isn't ready for that change yet.
This removes the last lingering reason to keep around the
arch/x86/linux/process.(hh|cc) files, so they have been deleted.
Change-Id: I425b95c9c730f31291790d63bc842e2c0092960d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/33904
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Alexandru Duțu <alexandru.dutu@amd.com>
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The TLBIALL op in gem5 was designed after the AArch32 TLBIALL instruction.
and was reused by the TLBI ALLEL1, ALLE2, ALLE3 logic.
This is not correct for the following reasons:
- TLBI ALLEx invalidates regardless of the VMID
- TLBI ALLEx (AArch64) is "target regime" oriented, whereas TLBIALL
(AArch32) is "current regime" oriented
TLBIALL has a different behaviour depending on the current exception
level: if issued at EL1 it will invalidate stage1 translations only; if
at EL2, it will invalidate stage2 translations as well.
TLBI ALLEx is more standard; every TLBI ALLE1 will invalidate stage1 and
stage2 translations. This is because the instruction is not executable
from the guest (EL1)
So for TLBIALL the condition for stage2 forwarding will be:
if (!isStage2 && isHyp) {
Whereas for TLBI ALLEx will be:
if (!isStage2 && target_el == EL1) {
Change-Id: I282f2cfaecbfc883e173770e5d2578b41055bb7a
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/35241
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The create() method on Params structs usually instantiate SimObjects
using a constructor which takes the Params struct as a parameter
somehow. There has been a lot of needless variation in how that was
done, making it annoying to pass Params down to base classes. Some of
the different forms were:
const Params &
Params &
Params *
const Params *
Params const*
This change goes through and fixes up every constructor and every
create() method to use the const Params & form. We use a reference
because the Params struct should never be null. We use const because
neither the create method nor the consuming object should modify the
record of the parameters as they came in from the config. That would
make consuming them not idempotent, and make it impossible to tell what
the actual simulation configuration was since it would change from any
user visible form (config script, config.ini, dot pdf output).
Change-Id: I77453cba52fdcfd5f4eec92dfb0bddb5a9945f31
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/35938
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
