gem5/src/cpu/thread_context.hh
Gabe Black 6f4bd2c1da ISA,CPU,etc: Create an ISA defined PC type that abstracts out ISA behaviors.
This change is a low level and pervasive reorganization of how PCs are managed
in M5. Back when Alpha was the only ISA, there were only 2 PCs to worry about,
the PC and the NPC, and the lsb of the PC signaled whether or not you were in
PAL mode. As other ISAs were added, we had to add an NNPC, micro PC and next
micropc, x86 and ARM introduced variable length instruction sets, and ARM
started to keep track of mode bits in the PC. Each CPU model handled PCs in
its own custom way that needed to be updated individually to handle the new
dimensions of variability, or, in the case of ARMs mode-bit-in-the-pc hack,
the complexity could be hidden in the ISA at the ISA implementation's expense.
Areas like the branch predictor hadn't been updated to handle branch delay
slots or micropcs, and it turns out that had introduced a significant (10s of
percent) performance bug in SPARC and to a lesser extend MIPS. Rather than
perpetuate the problem by reworking O3 again to handle the PC features needed
by x86, this change was introduced to rework PC handling in a more modular,
transparent, and hopefully efficient way.


PC type:

Rather than having the superset of all possible elements of PC state declared
in each of the CPU models, each ISA defines its own PCState type which has
exactly the elements it needs. A cross product of canned PCState classes are
defined in the new "generic" ISA directory for ISAs with/without delay slots
and microcode. These are either typedef-ed or subclassed by each ISA. To read
or write this structure through a *Context, you use the new pcState() accessor
which reads or writes depending on whether it has an argument. If you just
want the address of the current or next instruction or the current micro PC,
you can get those through read-only accessors on either the PCState type or
the *Contexts. These are instAddr(), nextInstAddr(), and microPC(). Note the
move away from readPC. That name is ambiguous since it's not clear whether or
not it should be the actual address to fetch from, or if it should have extra
bits in it like the PAL mode bit. Each class is free to define its own
functions to get at whatever values it needs however it needs to to be used in
ISA specific code. Eventually Alpha's PAL mode bit could be moved out of the
PC and into a separate field like ARM.

These types can be reset to a particular pc (where npc = pc +
sizeof(MachInst), nnpc = npc + sizeof(MachInst), upc = 0, nupc = 1 as
appropriate), printed, serialized, and compared. There is a branching()
function which encapsulates code in the CPU models that checked if an
instruction branched or not. Exactly what that means in the context of branch
delay slots which can skip an instruction when not taken is ambiguous, and
ideally this function and its uses can be eliminated. PCStates also generally
know how to advance themselves in various ways depending on if they point at
an instruction, a microop, or the last microop of a macroop. More on that
later.

Ideally, accessing all the PCs at once when setting them will improve
performance of M5 even though more data needs to be moved around. This is
because often all the PCs need to be manipulated together, and by getting them
all at once you avoid multiple function calls. Also, the PCs of a particular
thread will have spatial locality in the cache. Previously they were grouped
by element in arrays which spread out accesses.


Advancing the PC:

The PCs were previously managed entirely by the CPU which had to know about PC
semantics, try to figure out which dimension to increment the PC in, what to
set NPC/NNPC, etc. These decisions are best left to the ISA in conjunction
with the PC type itself. Because most of the information about how to
increment the PC (mainly what type of instruction it refers to) is contained
in the instruction object, a new advancePC virtual function was added to the
StaticInst class. Subclasses provide an implementation that moves around the
right element of the PC with a minimal amount of decision making. In ISAs like
Alpha, the instructions always simply assign NPC to PC without having to worry
about micropcs, nnpcs, etc. The added cost of a virtual function call should
be outweighed by not having to figure out as much about what to do with the
PCs and mucking around with the extra elements.

One drawback of making the StaticInsts advance the PC is that you have to
actually have one to advance the PC. This would, superficially, seem to
require decoding an instruction before fetch could advance. This is, as far as
I can tell, realistic. fetch would advance through memory addresses, not PCs,
perhaps predicting new memory addresses using existing ones. More
sophisticated decisions about control flow would be made later on, after the
instruction was decoded, and handed back to fetch. If branching needs to
happen, some amount of decoding needs to happen to see that it's a branch,
what the target is, etc. This could get a little more complicated if that gets
done by the predecoder, but I'm choosing to ignore that for now.


Variable length instructions:

To handle variable length instructions in x86 and ARM, the predecoder now
takes in the current PC by reference to the getExtMachInst function. It can
modify the PC however it needs to (by setting NPC to be the PC + instruction
length, for instance). This could be improved since the CPU doesn't know if
the PC was modified and always has to write it back.


ISA parser:

To support the new API, all PC related operand types were removed from the
parser and replaced with a PCState type. There are two warts on this
implementation. First, as with all the other operand types, the PCState still
has to have a valid operand type even though it doesn't use it. Second, using
syntax like PCS.npc(target) doesn't work for two reasons, this looks like the
syntax for operand type overriding, and the parser can't figure out if you're
reading or writing. Instructions that use the PCS operand (which I've
consistently called it) need to first read it into a local variable,
manipulate it, and then write it back out.


Return address stack:

The return address stack needed a little extra help because, in the presence
of branch delay slots, it has to merge together elements of the return PC and
the call PC. To handle that, a buildRetPC utility function was added. There
are basically only two versions in all the ISAs, but it didn't seem short
enough to put into the generic ISA directory. Also, the branch predictor code
in O3 and InOrder were adjusted so that they always store the PC of the actual
call instruction in the RAS, not the next PC. If the call instruction is a
microop, the next PC refers to the next microop in the same macroop which is
probably not desirable. The buildRetPC function advances the PC intelligently
to the next macroop (in an ISA specific way) so that that case works.


Change in stats:

There were no change in stats except in MIPS and SPARC in the O3 model. MIPS
runs in about 9% fewer ticks. SPARC runs with 30%-50% fewer ticks, which could
likely be improved further by setting call/return instruction flags and taking
advantage of the RAS.


TODO:

Add != operators to the PCState classes, defined trivially to be !(a==b).
Smooth out places where PCs are split apart, passed around, and put back
together later. I think this might happen in SPARC's fault code. Add ISA
specific constructors that allow setting PC elements without calling a bunch
of accessors. Try to eliminate the need for the branching() function. Factor
out Alpha's PAL mode pc bit into a separate flag field, and eliminate places
where it's blindly masked out or tested in the PC.
2010-10-31 00:07:20 -07:00

419 lines
13 KiB
C++

/*
* Copyright (c) 2006 The Regents of The University of Michigan
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met: redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer;
* redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution;
* neither the name of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* Authors: Kevin Lim
*/
#ifndef __CPU_THREAD_CONTEXT_HH__
#define __CPU_THREAD_CONTEXT_HH__
#include <string>
#include <iostream>
#include "arch/registers.hh"
#include "arch/types.hh"
#include "base/types.hh"
#include "config/full_system.hh"
#include "config/the_isa.hh"
// @todo: Figure out a more architecture independent way to obtain the ITB and
// DTB pointers.
namespace TheISA
{
class TLB;
}
class BaseCPU;
class Checkpoint;
class EndQuiesceEvent;
class TranslatingPort;
class FunctionalPort;
class VirtualPort;
class Process;
class System;
namespace TheISA {
namespace Kernel {
class Statistics;
};
};
/**
* ThreadContext is the external interface to all thread state for
* anything outside of the CPU. It provides all accessor methods to
* state that might be needed by external objects, ranging from
* register values to things such as kernel stats. It is an abstract
* base class; the CPU can create its own ThreadContext by either
* deriving from it, or using the templated ProxyThreadContext.
*
* The ThreadContext is slightly different than the ExecContext. The
* ThreadContext provides access to an individual thread's state; an
* ExecContext provides ISA access to the CPU (meaning it is
* implicitly multithreaded on SMT systems). Additionally the
* ThreadState is an abstract class that exactly defines the
* interface; the ExecContext is a more implicit interface that must
* be implemented so that the ISA can access whatever state it needs.
*/
class ThreadContext
{
protected:
typedef TheISA::MachInst MachInst;
typedef TheISA::IntReg IntReg;
typedef TheISA::FloatReg FloatReg;
typedef TheISA::FloatRegBits FloatRegBits;
typedef TheISA::MiscReg MiscReg;
public:
enum Status
{
/// Running. Instructions should be executed only when
/// the context is in this state.
Active,
/// Temporarily inactive. Entered while waiting for
/// synchronization, etc.
Suspended,
/// Permanently shut down. Entered when target executes
/// m5exit pseudo-instruction. When all contexts enter
/// this state, the simulation will terminate.
Halted
};
virtual ~ThreadContext() { };
virtual BaseCPU *getCpuPtr() = 0;
virtual int cpuId() = 0;
virtual int threadId() = 0;
virtual void setThreadId(int id) = 0;
virtual int contextId() = 0;
virtual void setContextId(int id) = 0;
virtual TheISA::TLB *getITBPtr() = 0;
virtual TheISA::TLB *getDTBPtr() = 0;
virtual System *getSystemPtr() = 0;
#if FULL_SYSTEM
virtual TheISA::Kernel::Statistics *getKernelStats() = 0;
virtual FunctionalPort *getPhysPort() = 0;
virtual VirtualPort *getVirtPort() = 0;
virtual void connectMemPorts(ThreadContext *tc) = 0;
#else
virtual TranslatingPort *getMemPort() = 0;
virtual Process *getProcessPtr() = 0;
#endif
virtual Status status() const = 0;
virtual void setStatus(Status new_status) = 0;
/// Set the status to Active. Optional delay indicates number of
/// cycles to wait before beginning execution.
virtual void activate(int delay = 1) = 0;
/// Set the status to Suspended.
virtual void suspend(int delay = 0) = 0;
/// Set the status to Halted.
virtual void halt(int delay = 0) = 0;
#if FULL_SYSTEM
virtual void dumpFuncProfile() = 0;
#endif
virtual void takeOverFrom(ThreadContext *old_context) = 0;
virtual void regStats(const std::string &name) = 0;
virtual void serialize(std::ostream &os) = 0;
virtual void unserialize(Checkpoint *cp, const std::string &section) = 0;
#if FULL_SYSTEM
virtual EndQuiesceEvent *getQuiesceEvent() = 0;
// Not necessarily the best location for these...
// Having an extra function just to read these is obnoxious
virtual Tick readLastActivate() = 0;
virtual Tick readLastSuspend() = 0;
virtual void profileClear() = 0;
virtual void profileSample() = 0;
#endif
virtual void copyArchRegs(ThreadContext *tc) = 0;
virtual void clearArchRegs() = 0;
//
// New accessors for new decoder.
//
virtual uint64_t readIntReg(int reg_idx) = 0;
virtual FloatReg readFloatReg(int reg_idx) = 0;
virtual FloatRegBits readFloatRegBits(int reg_idx) = 0;
virtual void setIntReg(int reg_idx, uint64_t val) = 0;
virtual void setFloatReg(int reg_idx, FloatReg val) = 0;
virtual void setFloatRegBits(int reg_idx, FloatRegBits val) = 0;
virtual TheISA::PCState pcState() = 0;
virtual void pcState(const TheISA::PCState &val) = 0;
virtual Addr instAddr() = 0;
virtual Addr nextInstAddr() = 0;
virtual MicroPC microPC() = 0;
virtual MiscReg readMiscRegNoEffect(int misc_reg) = 0;
virtual MiscReg readMiscReg(int misc_reg) = 0;
virtual void setMiscRegNoEffect(int misc_reg, const MiscReg &val) = 0;
virtual void setMiscReg(int misc_reg, const MiscReg &val) = 0;
virtual int flattenIntIndex(int reg) = 0;
virtual int flattenFloatIndex(int reg) = 0;
virtual uint64_t
readRegOtherThread(int misc_reg, ThreadID tid)
{
return 0;
}
virtual void
setRegOtherThread(int misc_reg, const MiscReg &val, ThreadID tid)
{
}
// Also not necessarily the best location for these two. Hopefully will go
// away once we decide upon where st cond failures goes.
virtual unsigned readStCondFailures() = 0;
virtual void setStCondFailures(unsigned sc_failures) = 0;
// Only really makes sense for old CPU model. Still could be useful though.
virtual bool misspeculating() = 0;
#if !FULL_SYSTEM
// Same with st cond failures.
virtual Counter readFuncExeInst() = 0;
virtual void syscall(int64_t callnum) = 0;
// This function exits the thread context in the CPU and returns
// 1 if the CPU has no more active threads (meaning it's OK to exit);
// Used in syscall-emulation mode when a thread calls the exit syscall.
virtual int exit() { return 1; };
#endif
/** function to compare two thread contexts (for debugging) */
static void compare(ThreadContext *one, ThreadContext *two);
};
/**
* ProxyThreadContext class that provides a way to implement a
* ThreadContext without having to derive from it. ThreadContext is an
* abstract class, so anything that derives from it and uses its
* interface will pay the overhead of virtual function calls. This
* class is created to enable a user-defined Thread object to be used
* wherever ThreadContexts are used, without paying the overhead of
* virtual function calls when it is used by itself. See
* simple_thread.hh for an example of this.
*/
template <class TC>
class ProxyThreadContext : public ThreadContext
{
public:
ProxyThreadContext(TC *actual_tc)
{ actualTC = actual_tc; }
private:
TC *actualTC;
public:
BaseCPU *getCpuPtr() { return actualTC->getCpuPtr(); }
int cpuId() { return actualTC->cpuId(); }
int threadId() { return actualTC->threadId(); }
void setThreadId(int id) { return actualTC->setThreadId(id); }
int contextId() { return actualTC->contextId(); }
void setContextId(int id) { actualTC->setContextId(id); }
TheISA::TLB *getITBPtr() { return actualTC->getITBPtr(); }
TheISA::TLB *getDTBPtr() { return actualTC->getDTBPtr(); }
System *getSystemPtr() { return actualTC->getSystemPtr(); }
#if FULL_SYSTEM
TheISA::Kernel::Statistics *getKernelStats()
{ return actualTC->getKernelStats(); }
FunctionalPort *getPhysPort() { return actualTC->getPhysPort(); }
VirtualPort *getVirtPort() { return actualTC->getVirtPort(); }
void connectMemPorts(ThreadContext *tc) { actualTC->connectMemPorts(tc); }
#else
TranslatingPort *getMemPort() { return actualTC->getMemPort(); }
Process *getProcessPtr() { return actualTC->getProcessPtr(); }
#endif
Status status() const { return actualTC->status(); }
void setStatus(Status new_status) { actualTC->setStatus(new_status); }
/// Set the status to Active. Optional delay indicates number of
/// cycles to wait before beginning execution.
void activate(int delay = 1) { actualTC->activate(delay); }
/// Set the status to Suspended.
void suspend(int delay = 0) { actualTC->suspend(); }
/// Set the status to Halted.
void halt(int delay = 0) { actualTC->halt(); }
#if FULL_SYSTEM
void dumpFuncProfile() { actualTC->dumpFuncProfile(); }
#endif
void takeOverFrom(ThreadContext *oldContext)
{ actualTC->takeOverFrom(oldContext); }
void regStats(const std::string &name) { actualTC->regStats(name); }
void serialize(std::ostream &os) { actualTC->serialize(os); }
void unserialize(Checkpoint *cp, const std::string &section)
{ actualTC->unserialize(cp, section); }
#if FULL_SYSTEM
EndQuiesceEvent *getQuiesceEvent() { return actualTC->getQuiesceEvent(); }
Tick readLastActivate() { return actualTC->readLastActivate(); }
Tick readLastSuspend() { return actualTC->readLastSuspend(); }
void profileClear() { return actualTC->profileClear(); }
void profileSample() { return actualTC->profileSample(); }
#endif
// @todo: Do I need this?
void copyArchRegs(ThreadContext *tc) { actualTC->copyArchRegs(tc); }
void clearArchRegs() { actualTC->clearArchRegs(); }
//
// New accessors for new decoder.
//
uint64_t readIntReg(int reg_idx)
{ return actualTC->readIntReg(reg_idx); }
FloatReg readFloatReg(int reg_idx)
{ return actualTC->readFloatReg(reg_idx); }
FloatRegBits readFloatRegBits(int reg_idx)
{ return actualTC->readFloatRegBits(reg_idx); }
void setIntReg(int reg_idx, uint64_t val)
{ actualTC->setIntReg(reg_idx, val); }
void setFloatReg(int reg_idx, FloatReg val)
{ actualTC->setFloatReg(reg_idx, val); }
void setFloatRegBits(int reg_idx, FloatRegBits val)
{ actualTC->setFloatRegBits(reg_idx, val); }
TheISA::PCState pcState() { return actualTC->pcState(); }
void pcState(const TheISA::PCState &val) { actualTC->pcState(val); }
Addr instAddr() { return actualTC->instAddr(); }
Addr nextInstAddr() { return actualTC->nextInstAddr(); }
MicroPC microPC() { return actualTC->microPC(); }
bool readPredicate() { return actualTC->readPredicate(); }
void setPredicate(bool val)
{ actualTC->setPredicate(val); }
MiscReg readMiscRegNoEffect(int misc_reg)
{ return actualTC->readMiscRegNoEffect(misc_reg); }
MiscReg readMiscReg(int misc_reg)
{ return actualTC->readMiscReg(misc_reg); }
void setMiscRegNoEffect(int misc_reg, const MiscReg &val)
{ return actualTC->setMiscRegNoEffect(misc_reg, val); }
void setMiscReg(int misc_reg, const MiscReg &val)
{ return actualTC->setMiscReg(misc_reg, val); }
int flattenIntIndex(int reg)
{ return actualTC->flattenIntIndex(reg); }
int flattenFloatIndex(int reg)
{ return actualTC->flattenFloatIndex(reg); }
unsigned readStCondFailures()
{ return actualTC->readStCondFailures(); }
void setStCondFailures(unsigned sc_failures)
{ actualTC->setStCondFailures(sc_failures); }
// @todo: Fix this!
bool misspeculating() { return actualTC->misspeculating(); }
#if !FULL_SYSTEM
void syscall(int64_t callnum)
{ actualTC->syscall(callnum); }
Counter readFuncExeInst() { return actualTC->readFuncExeInst(); }
#endif
};
#endif