summaryrefslogtreecommitdiff
path: root/src/arch/riscv
AgeCommit message (Collapse)Author
2019-12-10sim,arch: Collapse the ISA specific versions of m5Syscall.Gabe Black
The x86 version doesn't do anything x86 specific, and so can be used generically in sim/pseudo_inst.(hh|cc) Jira Issue: https://gem5.atlassian.net/browse/GEM5-187 Change-Id: I46c2a7d326bd7a95daa8611888051c180e92e446 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23177 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-12-10arch,cpu,sim: Push syscall number determination up to processes.Gabe Black
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>
2019-12-10arch: Get rid of the now unused setSyscallArg.Gabe Black
Setting syscall args isn't really something we need to do in gem5, since that will be taken care of by the code actually calling the syscall. We just need to be able to retrieve the value it put there. Jira Issue: https://gem5.atlassian.net/browse/GEM5-187 Change-Id: I0bb6d5d0207a7892414a722b3788cb70ee509582 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23174 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-12-10arch: Use ignoreWarnOnceFunc instead of the WarnOnce flag.Gabe Black
Jira Issue: https://gem5.atlassian.net/browse/GEM5-187 Change-Id: I9bbffcc74ec4f3df4effa5c50f0a4a688c5b6016 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23169 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-12-08arch-riscv: set MaxMiscDestRegs to 2Alec Roelke
In an earlier patch, the FCSR was split into its two components, FRM and FFLAGS, causing explicit writes to FCSR to incur two CSR writes. With the O3 CPU model, which defers them both to later, this creates a bug where an assertion that the number of CSR writes must be less than MaxMiscDestRegs fails because that constant is 1. This patch sets it to 2 so the O3 CPU is compatible with this scheme. Change-Id: Ic3413738c4eebe9f127980d0d0af5033d18468e7 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/23220 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-12-01arch-riscv: Fix disassembling of immediate for c.lui instructionIan Jiang
For compressed instruction c.lui, the 6-bit immediate is left-shifted by 12 bits in decoding. While the original Gem5 gives the left-shifted value directly in disassembly. This patch fixes the problem by adding a new template CILuiExecute to resume the immediate before outputting it in disassembly. Note: The immediate is sign-extended to 20-bit to be compatible with GCC. Change-Id: If73f72d3e8f85a8b10ce7a323379d8ad6c4c3085 Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22567 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-11-26arch-riscv: Fix immediate decoding for integer shift immediate instructionsIan Jiang
The "shamt" in integer shift immediate instructions is an unsigned immediate encoded in bits[25:20]. While the original Gem5 uses bits[31:20] as an int64_t. This patch fixes the problem by: - Adding a new parameter "imm_code" for format IOp and use the correct bitfields SHAMT5 or SHAMT6 to assign "imm_code" for each instruction. - Use uint64_t instead of default int64_t to assign parameter "imm_type" of format IOp. The instructions affected include: - Shift Left Logical Immediate, slli - Shift Right Logical Immediate, srli - Shift Right Arithmetic Immediate, srai - Shift Left Logical Word Immediate, slliw - Shift Right Logical Word Immediate, srliw - Shift Right Arithmetic Word Immediate, sraiw Change-Id: Iad34ccd036c11630409f84f6de2b939224e100e6 Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22563 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-11-26arch-riscv: Fix disassembling for fence and fence.iIan Jiang
The original Gem5 does not give correct disassembly for instruction fence and fence.i. This patch fixes the problem by adding two bitfields PRED and SUCC and a new format FenceOp and a template FenceExecute, in which operands are generated based on PRED and SUCC in the disassembling function. Change-Id: I78dbf125fef86ce40785c498a318ffb1569da46c Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22569 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-11-25arch-riscv: Fix disassembling for atomic instructionsIan Jiang
The original Gem5 does not give correct disassembly for atomic instructions, which are implemented with one or two micro instructions. The correct register indices are not decoded until subsequent micro instruction is processed. This patch fixes the problem by getting the register indices and other properties (aq and rl) from certain bitfields of the machine code in the disassembling function. Change-Id: I2cdaf0b3c48ff266f19ca707a5de48c9050b3897 Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22568 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-11-25arch-riscv: Fix disassembling of operand list for compressed instructionsIan Jiang
In disassembling compressed instructions, the original Gem5 gives needless operands, such as register or immediate. This patch fixes the problem. - Existing formats fixed: CIOp, CJOp, CBOp and Jump. - New formats added: CIAddi4spnOp (for c.addi4spn only) and CompressedROp (with templates CBasicDeclare and CBasicExecute) Change-Id: Ic293836983256a59d3a7aca091c8184b410516a4 Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22566 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com>
2019-11-25arch-riscv: Fix disassembling of immediate for U-type instructionsIan Jiang
For U-type instructions auipc and lui, the 20-bit immediate is left-shifted by 12 bits in decoding. While the original Gem5 gives the left-shifted value directly in disassembly. This patch fixes the problem by - Assign the original 20-bit immediate to internal variable "imm". - Output "imm" directly in disassembly, as how the original Gem5 does. - Do the left-shift to "imm" later in the function defining of each instruction, rather than in decoding. Change-Id: I300e26fd9c79478783c39fcd6ff70ea06db88884 Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22564 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-11-22arch-riscv: Fix bug in serialize and unserialize of InterrutpsIanJiangICT
When serialize and unserialize an variable, the parameters passed to SERIALIZE_SCALAR() and UNSERIALIZE_SCALAR() must be the same and should be a general variable name. If not, the expected item would not be found with UNSERIALIZE_SCALAR() and a fatal error would be introduced. This patch fix the bug in class Interrupts of RISCV. Change-Id: I7dd7ab6805651149304959bdf7ee9f3be9d9eaff Signed-off-by: Ian Jiang <ianjiang.ict@gmail.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22643 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com>
2019-11-18arch: Get rid of the (Big|Little)EndianGuest namespaces.Gabe Black
These namespaces were used to set up an environment/context where there was an implicit guest namespace. This is an issue when there may be multiple guest endiannesses which might be different. In cases where we don't know what the guest endianness is, we can't rely on it being an implicit part of our context since that would be ambiguous. In cases where we do know, for instance in ISA specific code, we can just use the endianness specific version that's appropriate for that context. This also (somewhat) removes the assumption that there is a single endianness that applies for a particular ISA. Practically speaking this assumption will probably still stand though, since there would likely be a non-trivial performance penalty to apply a configurable endianness instead of a fixed one the compiler can optomize/remove. Change-Id: I2dff338b58726d724f387388efe32d9233885680 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22374 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-11-18arch: Make and use endian specific versions of the mem helpers.Gabe Black
Rather than using TheISA to pick an endian conversion function, we can have a version defined for big and little endian and call the right one from the ISA code. Change-Id: I5014504968952e21abff3c5f6cbe58ca24233f33 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22373 Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-11-02arch,cpu: Move endianness conversion of inst bytes into the ISA.Gabe Black
It doesn't matter if the bytes are converted before or after they're fed into the decoder. The ISA already knows what endianness to use implicitly, and this frees the CPU which doesn't from having to worry about it. Change-Id: Id6574ee81bbf4f032c1d7b2901a664f2bd014fbc Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22343 Maintainer: Gabe Black <gabeblack@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-30arch: Make endianness a property of the OS class syscalls can consume.Gabe Black
That way the syscall implementations won't have to find the right endianness to use on their own, typically by referring to TheISA. Change-Id: I186b2f419d5dbee72cc9b5abce7356f3143f0c83 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22363 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-25mips,riscv: Get rid of some Alpha cruft in these System classes.Gabe Black
The consolePanicEvent pointer and addConsoleFuncEvent template were inherited from Alpha and were not used (and probably make no sense) for MIPS or RISCV which (to my knowledge) don't have the idea of a "console" binary. Change-Id: I109b866a65f69c7334062f7304c7b18acc51d99d Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21782 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-10-25cpu: Create a PCEventScope class to abstract the scope of PCEvents.Gabe Black
This abstraction will allow scheduling PCEvents for a particular ThreadContext, all contexts on a CPU, all contexts in a system, etc., and delegates scheduling and removing events to each particular scope. Right now the PCEventQueue is the only implementor of the PCEventSCope interface. Change-Id: I8fb62931511136229915c2e19d36aae7ffdec9df Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22099 Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-19arch: Make a base class for Interrupts.Gabe Black
That abstracts the ISA further from the CPU, getting us a small step closer to being able to build in more than one ISA at a time. Change-Id: Ibf7e26a3df411ffe994ac1e11d2a53b656863223 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20831 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2019-10-16arch,base,sim: Move Process loader hooks into the Process class.Gabe Black
This code was originally in the ObjectFile class, but not all object files will become Processes. All Processes will ultimately come from ObjectFiles though, so it makes more sense to put that class there. Change-Id: Ie73e4cdecbb51ce53d24cf68911a6cfc0685d771 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21468 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-10-12arch,base: Separate the idea of a memory image and object file.Gabe Black
A memory image can be described by an object file, but an object file is more than a memory image. Also, it makes sense to manipulate a memory image to, for instance, change how it's loaded into memory. That takes on larger implications (relocations, the entry point, symbols, etc.) when talking about the whole object file, and also modifies aspects which may not need to change. For instance if an image needs to be loaded into memory at addresses different from what's in the object file, but other things like symbols need to stay unmodified. Change-Id: Ia360405ffb2c1c48e0cc201ac0a0764357996a54 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21466 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-10-10arch,base: Stop loading the interpreter in ElfObject.Gabe Black
The interpreter is a separate object file, and while it's convenient to hide loading it in the code which loads the main object file, it breaks the conceptual abstraction since you only asked it to load the main object file. Also, this makes every object file format reimplement the idea of loading the interpreter. Admittedly only ELF recognizes and sets up an interpreter, but other formats conceptually could too. This does move that limitted hypothetical redundancy out of the object file formats and moves it into the process objects, but I think conceptually that's where it belongs. It would also probably be pretty easy to add a method to the base Process class that would handle loading an image and also the interpreter image. This change does not (yet) separate reading symbol tables. Change-Id: I4a165eac599a9bcd30371a162379e833c4cc89b4 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21465 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-10-10arch, base: Stop assuming object files have three segments.Gabe Black
The ObjectFile class has hardcoded assumptions that there are three segments, text, bss and data. There are some files which have one "segment" like raw files, where the entire file's contents are considered a single segment. There are also ELF files which can have an arbitrary number of segments, and those segments can hold any number of sections, including the text, data and/or bss sections. Removing this assumption frees up some object file formats from having to twist themselves to fit in that structure, possibly introducing ambiguities when some segments may fulfill multiple roles. Change-Id: I976e06a3a90ef852b17a6485e2595b006b2090d5 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21463 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-10-09arch-mips,arch-riscv,base: Get rid of the unused HexFile class.Gabe Black
A pointer to it was set up in the MIPS and RISCV system classes, but nothing ever set that pointer. The class was put in base/loader, but didn't have anything to do (as far as I can see) with loading anything it had a loadSegments method, but was not a subclass of ObjectFile. Change-Id: I4b711a31df20e20ffc306709227f60aa020fca15 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21464 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2019-10-09base: Rename Section to Segment, and some of its members.Gabe Black
ELF is, in my opinion, the most important object file format gem5 currently understands, and in ELF terminolgy the blob of data that needs to be loaded into memory to a particular location is called a segment. A section is a software level view of what's in a region of memory, and a single segment may contain multiple sections which happen to follow each other in memory. Change-Id: Ib810c5050723d5a96bd7550515b08ac695fb1b02 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21462 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-08-23arch-riscv: fix GDB register cacheAlec Roelke
Fixes the definition of the RISC-V GDB register cache. The latest version, of RISC-V gdb, commit c3eb4078520dad8234ffd7fbf893ac0da23ad3c8, appears to only accept the 32 integer registers + the PC in the 'g' packet. This functions with the Linux toolchain (riscv64-unknown-linux-gnu-*), but works best with the Newlib toolchain (riscv64-unknown-elf-*). Change-Id: Ie35ea89a45870fb634e6c68236261bde27c86e41 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20028 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-21arch-riscv: Update register fileYifei Liu
This patch adds mcounteren, scounteren according to Risc-V Privileged Architectures V1.10. Change-Id: I6e138a50710bc0a1e9d9c38a11fc7fcc09ed500e Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20128 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-05-30arch, base, cpu, gpu, sim: Merge getMemProxy and getVirtProxy.Gabe Black
These two functions were performing the same function but had two different names for historical reasons. This change merges them together, keeping the getVirtProxy name to be consistent with the getPhysProxy method used to get a non-translating proxy port. Change-Id: Idd83c6b899f9343795075b030ccbc723a79e52a4 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18581 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2019-05-29sim-se: add a release parameter to Process.pyCiro Santilli
Set the default release to that single value for all ISAs. glibc has checks for the kernel version based on uname, and refuses to start any syscall emulation programs if those checks don't pass with error: FATAL: kernel too old The ideal solution to this problem is to actually implement all missing system calls for the required kernel version and bumping the release accordingly. However, it is very hard to implement all missing syscalls and verify compliance. Previously, we have simply bumped the version manually from time to time when major glibc versions started breaking. This commit alleviates the problem in two ways. Firstly, having a single kernel version for all versions means that it is easier to bump all versions at once. Secondly, it makes it is possible to set the release with a parameter, which in turn can be set from the command line with: se.py --param 'system.cpu[:].workload[:].release = "4.18.0"' Change-Id: I9e3c31073bfe68735f7b0775c8e299aa62b98222 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/17849 Maintainer: Brandon Potter <Brandon.Potter@amd.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-05-21sim-se: change syscall function signatureBrandon Potter
The system calls had four parameters. One of the parameters is ThreadContext and another is Process. The ThreadContext holds the value of the current process so the Process parameter is redundant since the system call functions already have indirect access. With the old API, it is possible to call into the functions with the wrong supplied Process which could end up being a confusing error. This patch removes the redundancy by forcing access through the ThreadContext field within each system call. Change-Id: Ib43d3f65824f6d425260dfd9f67de1892b6e8b7c Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/12299 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Maintainer: Brandon Potter <Brandon.Potter@amd.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-05-20riscv: Add an object file loader for linux.Gabe Black
Change-Id: I3accca91cc4e02fa8e3a1169590cbe6696cf05e2 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18628 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com>
2019-05-04arch-riscv: Implement MHARTID CSRAlec Roelke
This patch implements the MHARTID CSR by intercepting attempts to access it, similar to the way accesses to the performance counters are intercepted, to return the thread's context ID. Change-Id: Ie14a31036fbe0e49fb3347ac0c3c508d9427a10d Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/16988 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Alec Roelke <alec.roelke@gmail.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-05-03arch-riscv,isa: Fix for compressed jump (c_j) immAvishai Tvila
c_j(al) has a special format, called CJ. The jump offset format is instbits[12:2] --> offset[11|4|9:8|10|6|7|3:1|5] Currently in decoder.isa, c_j format is JOp, the imm and branchTarget are incorrect In the execute section (decoder.isa:228), the imm fields is ignored and the offset is calculated correctlly. As a result, we get decoder flush for each c_j instance I've added CJOp format in compressed.isa, and use it in execute section. In addition, c_j is mappped to jal zero, cj_imm, and actually is neither indirect control nor a function call I fixed the flags accordently. I'll fix all IsRet, IsCall and IsIndirectControl flags for rest of (c_)jal(r) in my next commit. I ran coremark -O0 before my fix and I got 37.7% branch miss-rate, after the fix the branch miss-rate is <13% Change-Id: I608d5894a78a1ebefe36f21e21aaea68b42bccfc Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/17808 Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com>
2019-04-30arch: Stop using TheISA within the ISAs.Gabe Black
We know for sure what the ISA is, so there's no need for the indirection. Change-Id: I73ff04c50890d40a4c7f40caeee746b68b846cb3 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18488 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-04-28arch, sim: Simplify the AuxVector type.Gabe Black
The AuxVector type has a bunch of accessors which just give access to the underlying variables through references. We might as well just make those members accessible directly. Also, the AuxVector doesn't need to handle endianness flips itself. We can tell the byteswap mechanism how to flip an AuxVector, and let it handle that for us. This gets rid of the entire .cc file which was complicated by trying to both hide the ISA specific endianness translations, and instantiate templated functions in a .cc. Change-Id: I433cd61e73e0b067b6d628fba31be4a4ec1c4cf0 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18373 Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
2019-02-12python: Don't assume SimObjects live in the global namespaceAndreas Sandberg
The importer in Python 3 doesn't like the way we import SimObjects from the global namespace. Convert the existing SimObject declarations to import from m5.objects. As a side-effect, this makes these files consistent with configuration files. Change-Id: I11153502b430822130722839e1fa767b82a027aa Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/15981 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
2019-02-08riscv: fix AMO, LR and SC instructionsTuan Ta
(1) Atomic Memory Operation (AMO) This patch changes how RISC-V AMO instructions are implemented. For each AMO, instead of issuing a locking load and an unlocking store request to downstream memory system, this patch issues a single memory request that contains a corresponding AtomicOpFunctor to the memory system. Once the memory system receives the request, the atomic operation is executed in one single step. This patch also changes how AMO instructions handle acquire and release flags in AMOs (e.g., amoadd.aq and amoadd.rl). If an AMO is associated with an acquire flag, a memory fence is inserted after the AMO completes as a micro-op. If an AMO is associated with a release flag, another memory fence is inserted before the AMO executes. If both flags are specified, the AMO is broken down into a sequence of 3 micro-ops: mem fence -> atomic RMW -> mem fence. This change makes this AMO implementation comply to the release consistency model. (2) Load-Reserved (LR) and Store-Conditional (SC) Addresses locked by LR instructions are tracked in a stack data structure. LR instruction pushes its target address to the stack, and SC instruction pops the top address from the stack. As specified by RISC-V ISA, a SC fails if its target address does not match with the most recent LR. Previously, there was a single stack for all hardware thread contexts. A shared stack between thread contexts can lead to a infinite sequence of failed SCs if LRs from other threads keep pushing new addresses to this stack. This patch gives each context its private stack to address the problem. This patch also adds extra memory fence micro-ops to lr/sc to guarantee a correct execution order of memory instructions with respect to release consistency model. Change-Id: I1e95900367c89dd866ba872a5203f63359ac51ae Reviewed-on: https://gem5-review.googlesource.com/c/8189 Reviewed-by: Alec Roelke <ar4jc@virginia.edu> Maintainer: Alec Roelke <ar4jc@virginia.edu>
2019-02-08riscv: fixed syscall return valueTuan Ta
In case of failure, a syscall returns a negative value encoding the error code. This patch makes the risc-v implementation returns the encoded value instead of its absolute value upon a failure of a syscall. Change-Id: I6032b0337fe1cff5b326dbc6bb3b87a415f03300 Reviewed-on: https://gem5-review.googlesource.com/c/9627 Reviewed-by: Alec Roelke <ar4jc@virginia.edu> Maintainer: Alec Roelke <ar4jc@virginia.edu>
2019-02-08riscv: ignore nanosleep syscallTuan Ta
Change-Id: I564a09564da668a5db3e75f15b33efaca363d71a Reviewed-on: https://gem5-review.googlesource.com/c/9624 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-02-08arch-riscv: initialize RISC-V's thread pointer register in clone syscallTuan Ta
This patch initializes thread pointer register to Thread Local Storage (TLS)'s pointer given to a clone system call. Change-Id: I03e2cf4763e6a0ed31f357772a513a05e1e3461b Reviewed-on: https://gem5-review.googlesource.com/c/9622 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Maintainer: Brandon Potter <Brandon.Potter@amd.com>
2019-02-07arch-riscv: Enable support for riscv 32-bit in SE mode.Austin Harris
This patch splits up the riscv SE mode support for 32 and 64-bit. A future patch will add support for decoding rv32 instructions. Change-Id: Ia79ae19f753caf94dc7e5830a6630efb94b419d7 Signed-off-by: Austin Harris <austinharris@utexas.edu> Reviewed-on: https://gem5-review.googlesource.com/c/15355 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com>
2019-02-06riscv: remove NonSpeculative flag from fence instTuan Ta
Fence instruction origially had two flags NonSpeculative and MemBarrier. In O3 model, MemBarrier instructions are inserted into the instruction queue by the InstructionQueue::insertBarrier (at src/cpu/o3/iew_impl.hh:1083). Barrier instructions are implicitly assumed to be non-speculative. Adding NonSpeculative flag to fence instruction makes it inserted into the instruction queue twice (at src/cpu/o3/iew_impl.hh:1083 and :1111). This can lead to a deadlock if both pointers to the instruction are not cleared from the queue when the instruction retires. This patch removes NonSpeculative flag from the fence inst. Change-Id: I26573d12a0b52f43b73c0e51158286dc98d05ea4 Reviewed-on: https://gem5-review.googlesource.com/c/8183 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Alec Roelke <ar4jc@virginia.edu> Maintainer: Alec Roelke <ar4jc@virginia.edu>
2019-02-06arch-riscv: Initialize interrupt maskTuan Ta
This patch initializes RISCV interrupt mask to 0. Change-Id: I56289d9f3f319e239e305befea006a0ad4d86b75 Reviewed-on: https://gem5-review.googlesource.com/c/16162 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-02-05misc: added missing override specifierAndrea Mondelli
Added missing specifier for various virtual functions. Change-Id: I4783e92d78789a9ae182fad79aadceafb00b2458 Reviewed-on: https://gem5-review.googlesource.com/c/16103 Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-02-05riscv: Get rid of ISA specific register types in Interrupts.Austin Harris
Change-Id: I5542649c6af27a286f276a289b86c40dd7e32abc Signed-off-by: Austin Harris <austinharris@utexas.edu> Reviewed-on: https://gem5-review.googlesource.com/c/16122 Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-02-01cpu, arch: Replace the CCReg type with RegVal.Gabe Black
Most architectures weren't using the CCReg type, and in x86 and arm it was already a uint64_t. Change-Id: I0b3d5e690e6b31db6f2627f449c89bde0f6750a6 Reviewed-on: https://gem5-review.googlesource.com/c/14515 Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-01-31riscv: Get rid of some ISA specific register types.Gabe Black
Change-Id: Ie812cf1d42536094273ba2ec731c16cca38db100 Reviewed-on: https://gem5-review.googlesource.com/c/14466 Reviewed-by: Alec Roelke <alec.roelke@gmail.com> Maintainer: Alec Roelke <alec.roelke@gmail.com>
2019-01-31arch: cpu: Rename *FloatRegBits* to *FloatReg*.Gabe Black
Now that there's no plain FloatReg, there's no reason to distinguish FloatRegBits with a special suffix since it's the only way to read or write FP registers. Change-Id: I3a60168c1d4302aed55223ea8e37b421f21efded Reviewed-on: https://gem5-review.googlesource.com/c/14460 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-01-30arch,cpu: Add vector predicate registersGiacomo Gabrielli
Latest-gen. vector/SIMD extensions, including the Arm Scalable Vector Extension (SVE), introduce the notion of a predicate register file. This changeset adds this feature across architectures and CPU models. Change-Id: Iebcadbad89c0a582ff8b1b70de353305db603946 Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/13715 Maintainer: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2019-01-24base: arch: Get rid of the now unused FloatRegVal type.Gabe Black
This type is no longer used since FP registers are accessed as integer bit patterns. Change-Id: I1070f9443d6247165fd64c6bc041811c28287e9f Reviewed-on: https://gem5-review.googlesource.com/c/14459 Reviewed-by: Brandon Potter <Brandon.Potter@amd.com> Reviewed-by: Gabe Black <gabeblack@google.com> Maintainer: Gabe Black <gabeblack@google.com>
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-11 12:50:05 +0000