Even though the default value for the license count is 1, it seems that
if fast model is disabled, kconfig will set it to 0. When creating a
cycle using itertools over a list with zero elements, it will raise a
StopIteration.
Even though we don't actually try to build any fast model components
in that case, we do still set them up with a license slot. If the
cycle iterator is essentially broken, that will prevent that from
working and break the build.
This change forces the license count to be at least 1, even if fast
model is disabled and the license count may be set to 0 in the config.
Change-Id: Ia8df256a8f292deb6fb6fa3c5f9a7d58c2b7f782
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58490
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Add logic to collect pointers to all GPU TLBs in full system. Implement
the invalid TLBs PM4 packet. The invalidate is done functionally since
there is really no benefit to simulate it with timing and there is no
support in the TLB to do so. This allow application with much larger
data sets which may reuse device memory pages to work in gem5 without
possibly crashing due to a stale translation being leftover in the TLB.
Change-Id: Ia30cce02154d482d8f75b2280409abb8f8375c24
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58470
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This helper extracts config variables and sets them up for use in
fast model tools. Rework this function for two purposes. First, ensure
that the ['CONF'] subdict is used consistently. It was used in one spot
in that function, but not anywhere else. Avoid those mistakes by
accessing the configuration dict only once, and then reusing the value.
Second, only print the values of those variables if they aren't empty.
That avoids extra log output for values which aren't set up and aren't
being used, while still exposing those values if they are set up. This
will print them even if they aren't being actively used, but are set up
and could be with other changes in the config.
Change-Id: Ia3ea76e6cb6b3347fd082112a1eaa8d594e06ca2
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58354
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
If a fast model static library can't be found, we should treat that as
a warning instead of an error, and pass back the original library name
so that it can at least be added and potentially come from somewhere
else.
In practice, this is important because gem5 will be configured by SCons
indirectly in the future, using kconfig based tools that SCons runs on
the user's behalf. If SCons is misconfigured or not configured, this
error can trip, preventing those tools from starting. That creates a
catch 22, since you'd need SCons to fix the config, and SCons can't
run because of the config.
We can avoid that problem by making SCons more lenient, so that it can
still run even if it doesn't find static libraries where it might have
expected to.
Change-Id: Iadfd823b61fe96b937c2650250487d290492f265
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58352
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Yu-hsin Wang <yuhsingw@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This held the location of the license file, assuming it actually was a
license file and not a license server URL. If this variable was unset
because the fast model configuration parameters hadn't been set, then
the "File" would resolve to the local directory, and SCons would get
upset that you'd called the same path a directory and a file.
We can avoid this problem by just getting rid of this variable, since
it isn't used anyway.
Change-Id: I2ccda90b85f2c83c73816967d145e6bf45733f89
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58351
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Yu-hsin Wang <yuhsingw@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This makes what are configuration and what are internal SCons variables
explicit and separate, and makes it unnecessary to call out what
variables to export to C++.
These variables will also be plumbed into and out of kconfiglib in later
changes.
Change-Id: Iaf5e098d7404af06285c421dbdf8ef4171b3f001
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/56892
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
For instructions which simply require CPL0 (vs. requiring CPL is < IOPL,
or something else more complicated), this change either switches their
format so that they check that value before being returned, or adds a
comment marking them as privileged if they aren't yet implemented.
This change also makes the mov to/from CR and DR instructions more
particular, and returns an undefined instruction if the CR or DR index
is invalid.
Change-Id: I367d87a380a47428d458bda2ceecc1b983644704
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/55891
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This value is already floating around, and there is essentially no
overhead for exposing it to the decoder. With that value, we can handle
instructions which generically need to run at CPL0.
Some instructions have other more complicated permissions checks, like
that the CPL needs to have some relation to the IOPL. Those checks will
have to be implemented by the instructions themselves, since the decoder
can't factor in all possible state values.
Change-Id: Ie93f4f13aae002f69330606c515f369c5706c655
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/55889
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Currently if a Ruby functional access fails to find an address in the
caches, it gives up. For functional page table walks we need to be able
to go all the way to memory. This adds a pointer to the system object
which allows the walker to get a pointer to device memory which can be
used to do a functional access directly to memory bypassing Ruby.
Change-Id: I0ead6e5e130a0d53021c44ae9221b167c6316ab2
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57529
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The classes defined by the ISA description are actually just descriptors
which are used to make more specialized Operand classes, and then those
classes are instantiated to represent actual operands in a given
instruction. There they encode the actual index of the register, any
extensions used, etc.
To make defining operand types in the ISA more flexible and to take less
explicit machinery, this change defines a mechanism to allow overriding
individual methods of the operand class. This should for instance make
the read_code and write_code members of those classes unnecessary.
Change-Id: I1a1f787970ba56bd2884a80df4618a77eb454605
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/49740
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
This patch is fixing the redirectRegVHE method in the following
ways:
* Redirect AArch32 version of timer/counter registers
* Redirect _EL12 registers to _EL1
* Redirect _EL02 registers to _EL0
* Redirect CNTV_*_EL0 and CNTP_*_EL0 registers to
the Secure/Non-secure _EL2
* Redirect CNTVCT_EL0 to CNTPCT_EL0
Change-Id: I34eb317045b2d5a304a29ccf6e6440df68b2a279
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58117
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
At the moment those operands are using uint32_t (uw) variables,
therefore losing the content of the 32 most significant bits
This is not a problem for some of them (like CPTR_EL2, CPTR_EL3)
as [63:32] bits are RES0 for now.
HCR_EL2 on the other hand holds meaningful bits in [63:32],
HCR_EL.E2H being a notable example. With this patch we
are then fixing a bug in VHE (which relies on E2H)
Change-Id: I3e31009ad3dec8d8ea1c1057a189f7dcc2c3a54c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58113
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Create a VM class to reduce clutter in the amdgpu_device.* files. This
new file is in charge of reading/writting MMIOs related to VM contexts
and apertures. It also provides ranges checks for various apertures and
breaks out the MMIO interface so that there are not overloaded macro
definitions in the device MMIO methods.
The new translation generator classes for the various apertures are also
added to this class.
Change-Id: Ic224c1aa485685685b1136a46eed50bcf99d2350
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53066
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This was defined in the Micro_Container base class, and then again in
each subclass. The base definition was different and less complete than
the others, but the others were identical. Replace the base class
definition with the definition in the subclasses, and delete the ones in
the subclasses.
Change-Id: Ib2d1ce72958ec299115efb6efced2bd14c08467c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/56330
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The executed_as field is currently not set for global memory
instructions. This results in the default of SC_NONE, causing the status
vector to be all zeros. The GM pipe sees this and completes the
instruction immediately rather than issuing memory requests. This is
fixed by marking the instruction as executed as SC_GLOBAL always. Flat
instructions use resolvedFlatSegment for this, however since global
instructions are known to be global we can set this field directly. This
results in the expected issuing of memory requests to GPU memory.
Change-Id: Ic23102853ccd49a41e2f083b7bb24f033dfed18a
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57829
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
