| Age | Commit message (Collapse) | Author |
|---|
|
This commit fixes the target exception Level EL2 for alignmemt fault, it
is based on HCR_EL2.tge bit.
Change-Id: Ief78b2aa0c86f1c3d9a5d3ca00121d163a9d6a86
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/24303
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
The logic that determines which syscall to call was built into the
implementation of faults/exceptions or even into the instruction
decoder, but that logic can depend on what OS is being used, and
sometimes even what version, for example 32bit vs. 64bit.
This change pushes that logic up into the Process objects since those
already handle a lot of the aspects of emulating the guest OS. Instead,
the ISA or fault implementations just notify the rest of the system
that a nebulous syscall has happened, and that gets propogated upward
until the process does something with it. That's very analogous to how
a system call would work on a real machine.
When a system call happens, the low level component which detects that
should call tc->syscall(&fault), where tc is the relevant thread (or
execution) context, and fault is a Fault which can ultimately be set
by the system call implementation.
The TC implementor (probably a CPU) will then have a chance to do
whatever it needs to to handle a system call. Currently only O3 does
anything special here. That implementor will end up calling the
Process's syscall() method.
Once in Process::syscall, the process object will use it's contextual
knowledge to determine what system call is being requested. It then
calls Process::doSyscall with the right syscall number, where doSyscall
centralizes the common mechanism for actually retrieving and calling
into the system call implementation.
Jira Issue: https://gem5.atlassian.net/browse/GEM5-187
Change-Id: I937ec1ef0576142c2a182ff33ca508d77ad0e7a1
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23176
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
|
|
This patch fixes several bugs in Fault classes "routeToHyp" member
function by which mode checking was not taking into account AArch64
execution state. For the particular case of SVC calls from NS EL0, this
prevented a correct routing to EL2 when HCR_EL2.TGE was set.
Change-Id: I5815fe6dcf4501f52bf92f61687ef6d6ef950e52
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22725
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Ciro Santilli <ciro.santilli@arm.com>
|
|
This is needed when a CMO triggers an exception (e.g. DataAbort) In that
case the faulting address should be the one encoded in the instruction
rather than the cacheline address:
According to armarm:
If a memory fault that sets FAR_EL1 is generated from a data cache
maintenance or other DC instruction, FAR_EL1[63:0] holds the address
specified in the register argument of the instruction.
Change-Id: I6d0dadbef6e70db57438b01a76c5def3bdd2d974
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22443
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
The CM bit in a DataAbort ISS indicates whether the Data Abort came from
a cache maintenance or address translation instruction.
Change-Id: I8888520446550581c8dd0507a8989935db7047be
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21305
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
According to the ESR spec, the ISV bit is set to 1 only for stage 2
aborts.
Change-Id: Id524ef36e82184f741e968ddba04ca8ccdd4ad58
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20980
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
The patch is replacing it in places where the current EL could be using
AArch32, hence leading to an incorrect ExceptionLevel.
Change-Id: I99b75af2668f2c38fd88bec62e985ab7dbea80dc
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20251
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
ARMv8.1-PAN adds a new bit to PSTATE. When the value of this PAN state
bit is 1, any privileged data access from EL1 or EL2 to a virtual memory
address that is accessible at EL0 generates a Permission fault.
This feature is mandatory in ARMv8.1 implementations.
This feature is supported in AArch64 and AArch32 states.
The ID_AA64MMFR1_EL1.PAN, ID_MMFR3_EL1.PAN, and ID_MMFR3.PAN fields
identify the support for ARMv8.1-PAN.
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Change-Id: I94a76311711739dd2394c72944d88ba9321fd159
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19729
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
First-/non-faulting loads are part of Arm SVE.
Change-Id: I93dfd6d1d74791653927e99098ddb651150a8ef7
Signed-off-by: Gabor Dozsa <gabor.dozsa@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19177
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
This makes it easier to debug unimplemented instructions.
Change-Id: Iaaa288037326722f07251299fd68eacb2e295376
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Ciro Santilli <ciro.santilli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18396
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
When dumping the opcode that caused an Undefined Instruction, we just
want to dump the real instruction encoding, and not the extended version
with metabits (like thumb, bigThumb etc). This was not appening when
panicking in SE mode.
The patch is also replacing custom masking in the Unknown(64) disassembler
in favour of ArmStaticInstruction::encoding() helper.
Change-Id: I9eb6fd145d02b4b07bb51f0bd89ca014d6d5a6de
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18395
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
ARMv8 differs from ARMv7 with the presence of RVBAR register, which
contains the implementation defined reset address when EL3 is not
implemented.
The entry 0x0 in the AArch32 vector table, once used for the Reset
Vector, is now marked as "Not used", stating that it is now IMPLEMENTATION
DEFINED. An implementation might still use this vector table entry to
hold the Reset vector, but having a Reset address != than the general
vector table (for any other exception) is allowed.
At the moment any Reset exception is still using 0 as a vector table
base address. This patch is extending the ArmSystem::resetAddr64 to
ArmSystem::resetAddr so that it can be used for initializing
MVBAR/RVBAR. In order to do so, we are providing a specialized behavior
for the Reset exception when evaluating the vector base address.
Change-Id: I051a730dc089e194db3b107bbed19251c661f87e
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/14000
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
ARMv8 has removed SCTLR.VE bit which is now hardcoded to 0. We are
removing it from gem5 since we were not handling it anyway.
Change-Id: Ibde2db45c7f8add4a3188f2cb8c23701a6088d03
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13998
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
AArch32 Software Breakpoint (BKPT) can trigger an AArch64 fault when
interprocessing if the trapping conditions are met.
Change-Id: I485852ed19429f9cd928a6447a95eb6f471f189c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/11197
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
The Illegal Execution fault triggered by the setting of processor state
PSTATE.IL happens in AArch32 as well and takes the form of UNDEFINED
exception fault. We are hence copying the UndefinedInstruction AArch32
fields into the IllegalInstSetStateFault.
Change-Id: Ibb7424397c2030ea5d010577c530277a27036aea
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10814
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
This patch moves the detection of the Illegal Execution flag (PSTATE.IL)
from the tlb translation stage (fetch) to the decoding stage. This is
done by adding the illegalExecution field to the PCState.
Change-Id: I9c1c4e9c6bd5ded905c1d56b3034e4e9322582fa
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10813
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
The software breakpoint exception class needs to be adjusted depending
on the source EL's execution state. This change fixes an incorrect
exception class when taking a breakpoint from aarch64.
Change-Id: I99d87a04be6bf9ce3a69f6b19969fa006cfd63a4
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Ciro Santilli <ciro.santilli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10809
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
|
|
Change-Id: Ife4a2189e140cdefcf53fa88213d8a5225067457
Reviewed-by: Jack Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/9201
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
|
|
Previous code was aborting simulation when a debug exception taken in
aarch64 mode was encountered. This because an invalid (0xff)
instruction fault status code was produced.
Change-Id: I289f93f672be70cfbdc404be536809835160bdaf
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8363
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
The fault status code generated by a Prefetch/Data Fault was containing
a wrong value when the fault was triggered in aarch32 but handled in
aarch64. This because the encoding differs between the two ISAs and the
encoder was just checking the starting ISA rather than the the ending
one. In this case the getFsr must be called after we know which is the
ending ISA, which happens only after ArmFault::invoke gets called. The
fsc update hence happens before writing into the Syndrome register.
Change-Id: I725f12b6dcc0178f608233bd3d15e466d1cd1ffc
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8362
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
There is a set of internal variables in ArmFault thats get updated once
the fault is invoked (ArmFault::invoke). Sometimes we rely on those even
if the fault is generated but not invoked (e.g. when checking if a
memory access is producing a fault). This patch is moving the update
functionalities inside a public method so that a client can make use of
it even when not invoking the fault.
Change-Id: I3ac5b6835023f28ec569fe25487dffa356e1b2fd
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8361
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
This patch enables PCAlignmentFault routing to Hypervisor in case
HCR_EL2.TGE == 1, as is happening for other arm exceptions.
Change-Id: I48364ef1a0bcb5d030135221ae4bc6429e32759e
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8841
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
The stats are silently non-copy constructible. Therefore, when someone
copy-constructs any object with stats, asserts happen when registering
the stats, as they were not constructed in the intended way.
This patch solves that by explicitly deleting the copy constructor,
trading an obscure run-time assert for a compile-time somehow more
meaningful error meassage.
This triggers some compilation errors as the FaultStats in the fault
definitions of ARM and SPARC use brace-enclosed initialisations in which
one of the elements derives from DataWrap, which is not
copy-constructible anymore. To fix that, this patch also adds a
constructor for the FaultVals in both ISAs.
Change-Id: I340e203b9386609b32c66e3b8918a015afe415a4
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8082
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
This patch replaces the dummy values which were defined for the
SecureMonitorTrap thus enabling its usage in aarch32 mode. 1) It
changes the vector table offset from 0x14 to 0x4 in compliance with the
armv8 documentation. 2) When trapping in monitor mode for aarch32, the
mon_lr is updated with the pc + a non zero offset (+4/2 depending on the
current instruction set: +4 for A32, +2 for T32).
Change-Id: I01e1e52bf5ecd405e7472e31e01cf9a599153b08
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8041
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
The old code chose vector offset associated with exceptions taken
to EL3 by incorrectly using "from64", which is associated with the
exception level where the exception was taken from. However, the
offset should depends on the ISA of the lower EL and not of the
starting EL itself, as specified in ARM ARM. This patch corrects
this by implementing the method in AArch64.TakeException in ARM ARM.
Change-Id: I8f7c9aa777c5f2eef9e2d89c36e9daee23f3a822
Reviewed-by: Jack Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/8001
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
Supervisor Trap is supposed to be able to handle exceptions routed
to EL2, which is enabled by HCR_EL2.TGE. This fix adds routeToHyp()
function to Supervisor Trap to handle this, similar to that in
UndefinedFault, DataAbort, etc.
Change-Id: I1fcf9f2d445ecbc13c8f6d3b7d599728b0250ab7
Reviewed-by: Jack Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/7961
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
If undefined instruction has to be routed to EL2, the HSR register
must change the HSR.EC and HSR.ISS accordingly, which means not using
the EL1 exception syndrome, but the unknown reason one (EC=0, ISS=0)
Change-Id: I1540c713ab545bf307c1dad3ae305de4178443f4
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/6621
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
Cosmetic fix: prefer static_cast rather than reinterpret_cast in
hierarchy.
Change-Id: Ic0e5a4df9b18072a6df5ee316f674241074c349a
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/6761
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
Add support for software breakpoints as signalled by the aarch64 brk
instruction. This introduces a new SoftwareBreakpoint fault.
Change-Id: I93646c3298e09d7f7b0983108ba8937c7331297a
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/5721
Reviewed-by: Giacomo Gabrielli <Giacomo.Gabrielli@arm.com>
|
|
This Patch is removing the FlushPipe ArmFault, which was used for
flushing the pipeline in favour of the general IsSquashAfter StaticInstr
flag. Using a fault was preventing tracers from tracing barriers like
ISB and from adding them to the instruction count
Change-Id: I176e9254eca904694f2f611eb486c55e50ec61ff
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/5361
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
|
|
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.
|
|
|
|
This patch corrects IPA reporting if the translation faults in a
stage 2 lookup.
Change-Id: I0b914527f8a9f98a5e980a131cf9d03e5584b4e9
|
|
Faults that could potentially be routed to the hypervisor checked
whether or not they were in a secure state without checking if security
was enabled or not. This caused faults not to be routed correctly. This
patch causes secure state checking to first ask if security is enabled.
Change-Id: I179e9b181b27f552734c9bab2b18d05ac579a119
|
|
This patch adds the option for faults to be routed to the hypervisor
using the pre-existing routeToHyp() functions that are present in each
fault type.
Change-Id: I9735512c094457636b9870456a5be5432288e004
|
|
This patch adds the AArch64 instruction hvc which raises an exception
from EL1 into EL2. The host OS uses this instruction to world switch
into the guest.
Change-Id: I930ee43f4f0abd4b35a68eb2a72e44e3ea6570be
|
|
Change-Id: I59fa4fae98c33d9e5c2185382e1411911d27d341
|
|
We currently check the current state instead of the state of the
target EL when determining how we report a fault. This breaks
interprocessing since EL0 in aarch32 would report its fault status
using the aarch32 registers even if EL1 is in aarch64. Fix this to
report the fault using the format of the target EL.
Change-Id: Ic080267ac210783d1e01c722a4ddaa687dce280e
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Mitch Hayenga <mitch.hayenga@arm.com>
|
|
Adds per-thread interrupt controllers and thread/context logic
so that interrupts properly get routed in SMT systems.
|
|
This patch optimises the passing of StaticInstPtr by avoiding copying
the reference-counting pointer. This avoids first incrementing and
then decrementing the reference-counting pointer.
|
|
This patch closes a number of space gaps in debug messages caused by
the incorrect use of line continuation within strings. (There's also
one consistency change to a similar, but correct, use of line
continuation)
|
|
Analogous to ee049bf (for x86). Requires a bump of the checkpoint version
and corresponding upgrader code to move the condition code register values
to the new register file.
|
|
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
|
|
This patch adds a warning for missing field initializers for both gcc
and clang, and addresses the warnings that were generated.
|
|
Try to decrease indentation, and remove some redundant FullSystem checks.
|
|
|
|
Only create a memory ordering violation when the value could have changed
between two subsequent loads, instead of just when loads go out-of-order
to the same address. While not very common in the case of Alpha, with
an architecture with a hardware table walker this can happen reasonably
frequently beacuse a translation will miss and start a table walk and
before the CPU re-schedules the faulting instruction another one will
pass it to the same address (or cache block depending on the dendency
checking).
This patch has been tested with a couple of self-checking hand crafted
programs to stress ordering between two cores.
The performance improvement on SPEC benchmarks can be substantial (2-10%).
|
|
SEV instructions were originally implemented to cause asynchronous squashes
via the generateTCSquash() function in the O3 pipeline when updating the
SEV_MAILBOX miscReg. This caused race conditions between CPUs in an MP system
that would lead to a pipeline either going inactive indefinitely or not being
able to commit squashed instructions. Fixed SEV instructions to behave like
interrupts and cause synchronous sqaushes inside the pipeline, eliminating
the race conditions. Also fixed up the semantics of the WFE instruction to
behave as documented in the ARMv7 ISA description to not sleep if SEV_MAILBOX=1
or unmasked interrupts are pending.
|
|
This patch fixes two problems with the O3 cpu model. The first is an issue
with an instruction fetch causing a fault on the next address while the
current macro-op is being issued. This happens when the micro-ops exceed
the fetch bandwdith and then on the next cycle the fetch stage attempts
to issue a request to the next line while it still has micro-ops to issue
if the next line faults a fault is attached to a micro-op in the currently
executing macro-op rather than a "nop" from the next instruction block.
This leads to an instruction incorrectly faulting when on fetch when
it had no reason to fault.
A similar problem occurs with interrupts. When an interrupt occurs the
fetch stage nominally stops issuing instructions immediately. This is incorrect
in the case of a macro-op as the current location might not be interruptable.
|
|
Break up the condition code bits into NZ, C, V registers. These are individually
written and this removes some incorrect dependencies between instructions.
|
