While FastAlloc provides a small performance increase (~1.5%) over regular malloc it isn't thread safe.
After removing FastAlloc and using tcmalloc I've seen a performance increase of 12% over libc malloc
when running twolf for ARM.
The CPUID instruction was implemented so that it would only write its results
if the instruction was successful. This works fine on the simple CPU where
unwritten registers retain their old values, but on a CPU like O3 with
renaming this is broken. The instruction needs to write the old values back
into the registers explicitly if they aren't being changed.
There are some bits of some fields of the ExtMachInst which are not actually
used for anything but are included in the hash of an ExtMachInst for
simplicity and efficiency. This change makes sure the decoder's internal
working ExtMachInst is completely initialized, even these unused bits, so that
there isn't any nondeterministic behavior, no valgrind messages about
uninitialized variables, and no potential false misses/redundant entries in
the decode cache.
The GDT can be accessed by user level software running in compatibility mode
by moving segment selectors into segment registers. The GDT needs to be set up
at an address accessible in this mode.
A small change was added a while ago to keep addresses from overflowing 32
bits when larger addresses shouldn't be accessible to software. That change
truncated when not in long mode, but really it should have truncated when not
in 64 bit mode. The difference is whether compatibility mode is included, a
mode that's supposed to act like a legacy 32 bit mode.
This will allow it to be specialized by the ISAs. The existing caching scheme
is provided by the BasicDecodeCache in the GenericISA namespace and is built
from the generalized components.
--HG--
rename : src/cpu/decode_cache.cc => src/arch/generic/decode_cache.cc
These classes are always used together, and merging them will give the ISAs
more flexibility in how they cache things and manage the process.
--HG--
rename : src/arch/x86/predecoder_tables.cc => src/arch/x86/decoder_tables.cc
This patch moves the ECF and EZF bits to individual registers (ecfBit and
ezfBit) and the CF and OF bits to cfofFlag registers. This is being done
so as to lower the read after write dependencies on the the condition code
register. Ultimately we will have the following registers [ZAPS], [OF],
[CF], [ECF], [EZF] and [DF]. Note that this is only one part of the
solution for lowering the dependencies. The other part will check whether
or not the condition code register needs to be actually read. This would
be done through a separate patch.
This patch moves send/recvTiming and send/recvTimingSnoop from the
Port base class to the MasterPort and SlavePort, and also splits them
into separate member functions for requests and responses:
send/recvTimingReq, send/recvTimingResp, and send/recvTimingSnoopReq,
send/recvTimingSnoopResp. A master port sends requests and receives
responses, and also receives snoop requests and sends snoop
responses. A slave port has the reciprocal behaviour as it receives
requests and sends responses, and sends snoop requests and receives
snoop responses.
For all MemObjects that have only master ports or slave ports (but not
both), e.g. a CPU, or a PIO device, this patch merely adds more
clarity to what kind of access is taking place. For example, a CPU
port used to call sendTiming, and will now call
sendTimingReq. Similarly, a response previously came back through
recvTiming, which is now recvTimingResp. For the modules that have
both master and slave ports, e.g. the bus, the behaviour was
previously relying on branches based on pkt->isRequest(), and this is
now replaced with a direct call to the apprioriate member function
depending on the type of access. Please note that send/recvRetry is
still shared by all the timing accessors and remains in the Port base
class for now (to maintain the current bus functionality and avoid
changing the statistics of all regressions).
The packet queue is split into a MasterPort and SlavePort version to
facilitate the use of the new timing accessors. All uses of the
PacketQueue are updated accordingly.
With this patch, the type of packet (request or response) is now well
defined for each type of access, and asserts on pkt->isRequest() and
pkt->isResponse() are now moved to the appropriate send member
functions. It is also worth noting that sendTimingSnoopReq no longer
returns a boolean, as the semantics do not alow snoop requests to be
rejected or stalled. All these assumptions are now excplicitly part of
the port interface itself.
It's possible for two page table walks to overlap which will go in the same
place in the TLB's trie. They would land on top of each other, so this change
adds some code which detects if an address already matches an entry and if so
throws away the new one.
The parameter is _machInst, which is very similar to the member machInst. If
machInst is used to pass the parameter to a lower level constructor, what
really happens is that machInst is set to whatever it already happened to be,
effectively leaving it uninitialized.
This change also adjusts the TlbEntry class so that it stores the number of
address bits wide a page is rather than its size in bytes. In other words,
instead of storing 4K for a 4K page, it stores 12. 12 is easy to turn into 4K,
but it's a little harder going the other way.
This patch simplifies the packet by removing the broadcast flag and
instead more firmly relying on (and enforcing) the semantics of
transactions in the classic memory system, i.e. request packets are
routed from a master to a slave based on the address, and when they
are created they have neither a valid source, nor destination. On
their way to the slave, the request packet is updated with a source
field for all modules that multiplex packets from multiple master
(e.g. a bus). When a request packet is turned into a response packet
(at the final slave), it moves the potentially populated source field
to the destination field, and the response packet is routed through
any multiplexing components back to the master based on the
destination field.
Modules that connect multiplexing components, such as caches and
bridges store any existing source and destination field in the sender
state as a stack (just as before).
The packet constructor is simplified in that there is no longer a need
to pass the Packet::Broadcast as the destination (this was always the
case for the classic memory system). In the case of Ruby, rather than
using the parameter to the constructor we now rely on setDest, as
there is already another three-argument constructor in the packet
class.
In many places where the packet information was printed as part of
DPRINTFs, request packets would be printed with a numeric "dest" that
would always be -1 (Broadcast) and that field is now removed from the
printing.
This patch introduces port access methods that separates snoop
request/responses from normal memory request/responses. The
differentiation is made for functional, atomic and timing accesses and
builds on the introduction of master and slave ports.
Before the introduction of this patch, the packets belonging to the
different phases of the protocol (request -> [forwarded snoop request
-> snoop response]* -> response) all use the same port access
functions, even though the snoop packets flow in the opposite
direction to the normal packet. That is, a coherent master sends
normal request and receives responses, but receives snoop requests and
sends snoop responses (vice versa for the slave). These two distinct
phases now use different access functions, as described below.
Starting with the functional access, a master sends a request to a
slave through sendFunctional, and the request packet is turned into a
response before the call returns. In a system without cache coherence,
this is all that is needed from the functional interface. For the
cache-coherent scenario, a slave also sends snoop requests to coherent
masters through sendFunctionalSnoop, with responses returned within
the same packet pointer. This is currently used by the bus and caches,
and the LSQ of the O3 CPU. The send/recvFunctional and
send/recvFunctionalSnoop are moved from the Port super class to the
appropriate subclass.
Atomic accesses follow the same flow as functional accesses, with
request being sent from master to slave through sendAtomic. In the
case of cache-coherent ports, a slave can send snoop requests to a
master through sendAtomicSnoop. Just as for the functional access
methods, the atomic send and receive member functions are moved to the
appropriate subclasses.
The timing access methods are different from the functional and atomic
in that requests and responses are separated in time and
send/recvTiming are used for both directions. Hence, a master uses
sendTiming to send a request to a slave, and a slave uses sendTiming
to send a response back to a master, at a later point in time. Snoop
requests and responses travel in the opposite direction, similar to
what happens in functional and atomic accesses. With the introduction
of this patch, it is possible to determine the direction of packets in
the bus, and no longer necessary to look for both a master and a slave
port with the requested port id.
In contrast to the normal recvFunctional, recvAtomic and recvTiming
that are pure virtual functions, the recvFunctionalSnoop,
recvAtomicSnoop and recvTimingSnoop have a default implementation that
calls panic. This is to allow non-coherent master and slave ports to
not implement these functions.
This patch addresses a number of minor issues that cause problems when
compiling with clang >= 3.0 and gcc >= 4.6. Most importantly, it
avoids using the deprecated ext/hash_map and instead uses
unordered_map (and similarly so for the hash_set). To make use of the
new STL containers, g++ and clang has to be invoked with "-std=c++0x",
and this is now added for all gcc versions >= 4.6, and for clang >=
3.0. For gcc >= 4.3 and <= 4.5 and clang <= 3.0 we use the tr1
unordered_map to avoid the deprecation warning.
The addition of c++0x in turn causes a few problems, as the
compiler is more stringent and adds a number of new warnings. Below,
the most important issues are enumerated:
1) the use of namespaces is more strict, e.g. for isnan, and all
headers opening the entire namespace std are now fixed.
2) another other issue caused by the more stringent compiler is the
narrowing of the embedded python, which used to be a char array,
and is now unsigned char since there were values larger than 128.
3) a particularly odd issue that arose with the new c++0x behaviour is
found in range.hh, where the operator< causes gcc to complain about
the template type parsing (the "<" is interpreted as the beginning
of a template argument), and the problem seems to be related to the
begin/end members introduced for the range-type iteration, which is
a new feature in c++11.
As a minor update, this patch also fixes the build flags for the clang
debug target that used to be shared with gcc and incorrectly use
"-ggdb".
Virtual (pre-segmentation) addresses are truncated based on address size, and
any non-64 bit linear address is truncated to 32 bits. This means that real
mode addresses aren't truncated down to 16 bits after their segment bases are
added in.
This patch introduces the notion of a master and slave port in the C++
code, thus bringing the previous classification from the Python
classes into the corresponding simulation objects and memory objects.
The patch enables us to classify behaviours into the two bins and add
assumptions and enfore compliance, also simplifying the two
interfaces. As a starting point, isSnooping is confined to a master
port, and getAddrRanges to slave ports. More of these specilisations
are to come in later patches.
The getPort function is not getMasterPort and getSlavePort, and
returns a port reference rather than a pointer as NULL would never be
a valid return value. The default implementation of these two
functions is placed in MemObject, and calls fatal.
The one drawback with this specific patch is that it requires some
code duplication, e.g. QueuedPort becomes QueuedMasterPort and
QueuedSlavePort, and BusPort becomes BusMasterPort and BusSlavePort
(avoiding multiple inheritance). With the later introduction of the
port interfaces, moving the functionality outside the port itself, a
lot of the duplicated code will disappear again.
This patch cleans up a number of minor issues aiming to get closer to
compliance with the C++0x standard as interpreted by gcc and clang
(compile with std=c++0x and -pedantic-errors). In particular, the
patch cleans up enums where the last item was succeded by a comma,
namespaces closed by a curcly brace followed by a semi-colon, and the
use of the GNU-extension typeof (replaced by templated functions). It
does not address variable-length arrays, zero-size arrays, anonymous
structs, range expressions in switch statements, and the use of long
long. The generated CPU code also has a large number of issues that
remain to be fixed, mainly related to overflows in implicit constant
conversion (due to shifts).
This patch makes the code compile with clang 2.9 and 3.0 again by
making two very minor changes. Firt, it maintains a strict typing in
the forward declaration of the BaseCPUParams. Second, it adds a
FullSystemInt flag of the type unsigned int next to the boolean
FullSystem flag. The FullSystemInt variable can be used in
decode-statements (expands to switch statements) in the instruction
decoder.
Making the CheckerCPU a runtime time option requires the code to be compatible
with ISAs other than ARM. This patch adds the appropriate function
stubs to allow compilation.
This patch adds a function to X86 tlb that returns the
walker port. This port is required for correctly connecting
the walker ports for the cpu just switched in
If an instruction is executed speculatively and hits a situation where it
wants to panic, it should return a fault instead. If the instruction was
misspeculated, the fault can be thrown away. If the instruction wasn't
misspeculated, the fault will be invoked and the panic will still happen.
This patch is adding a clearer design intent to all objects that would
not be complete without a port proxy by making the proxies members
rathen than dynamically allocated. In essence, if NULL would not be a
valid value for the proxy, then we avoid using a pointer to make this
clear.
The same approach is used for the methods using these proxies, such as
loadSections, that now use references rather than pointers to better
reflect the fact that NULL would not be an acceptable value (in fact
the code would break and that is how this patch started out).
Overall the concept of "using a reference to express unconditional
composition where a NULL pointer is never valid" could be done on a
much broader scale throughout the code base, but for now it is only
done in the locations affected by the proxies.
This patch moves all port creation from the getPort method to be
consistently done in the MemObject's constructor. This is possible
thanks to the Swig interface passing the length of the vector ports.
Previously there was a mix of: 1) creating the ports as members (at
object construction time) and using getPort for the name resolution,
or 2) dynamically creating the ports in the getPort call. This is now
uniform. Furthermore, objects that would not be complete without a
port have these ports as members rather than having pointers to
dynamically allocated ports.
This patch also enables an elaboration-time enumeration of all the
ports in the system which can be used to determine the masterId.
This patch classifies all ports in Python as either Master or Slave
and enforces a binding of master to slave. Conceptually, a master (such
as a CPU or DMA port) issues requests, and receives responses, and
conversely, a slave (such as a memory or a PIO device) receives
requests and sends back responses. Currently there is no
differentiation between coherent and non-coherent masters and slaves.
The classification as master/slave also involves splitting the dual
role port of the bus into a master and slave port and updating all the
system assembly scripts to use the appropriate port. Similarly, the
interrupt devices have to have their int_port split into a master and
slave port. The intdev and its children have minimal changes to
facilitate the extra port.
Note that this patch does not enforce any port typing in the C++
world, it merely ensures that the Python objects have a notion of the
port roles and are connected in an appropriate manner. This check is
carried when two ports are connected, e.g. bus.master =
memory.port. The following patches will make use of the
classifications and specialise the C++ ports into masters and slaves.
This change adds a master id to each request object which can be
used identify every device in the system that is capable of issuing a request.
This is part of the way to removing the numCpus+1 stats in the cache and
replacing them with the master ids. This is one of a series of changes
that make way for the stats output to be changed to python.
This patch adds the necessary flags to the SConstruct and SConscript
files for compiling using clang 2.9 and later (on Ubuntu et al and OSX
XCode 4.2), and also cleans up a bunch of compiler warnings found by
clang. Most of the warnings are related to hidden virtual functions,
comparisons with unsigneds >= 0, and if-statements with empty
bodies. A number of mismatches between struct and class are also
fixed. clang 2.8 is not working as it has problems with class names
that occur in multiple namespaces (e.g. Statistics in
kernel_stats.hh).
clang has a bug (http://llvm.org/bugs/show_bug.cgi?id=7247) which
causes confusion between the container std::set and the function
Packet::set, and this is currently addressed by not including the
entire namespace std, but rather selecting e.g. "using std::vector" in
the appropriate places.
This patch simplifies the address-range determination mechanism and
also unifies the naming across ports and devices. It further splits
the queries for determining if a port is snooping and what address
ranges it responds to (aiming towards a separation of
cache-maintenance ports and pure memory-mapped ports). Default
behaviours are such that most ports do not have to define isSnooping,
and master ports need not implement getAddrRanges.
Port proxies are used to replace non-structural ports, and thus enable
all ports in the system to correspond to a structural entity. This has
the advantage of accessing memory through the normal memory subsystem
and thus allowing any constellation of distributed memories, address
maps, etc. Most accesses are done through the "system port" that is
used for loading binaries, debugging etc. For the entities that belong
to the CPU, e.g. threads and thread contexts, they wrap the CPU data
port in a port proxy.
The following replacements are made:
FunctionalPort > PortProxy
TranslatingPort > SETranslatingPortProxy
VirtualPort > FSTranslatingPortProxy
--HG--
rename : src/mem/vport.cc => src/mem/fs_translating_port_proxy.cc
rename : src/mem/vport.hh => src/mem/fs_translating_port_proxy.hh
rename : src/mem/translating_port.cc => src/mem/se_translating_port_proxy.cc
rename : src/mem/translating_port.hh => src/mem/se_translating_port_proxy.hh
The DPRINTF for doing protection checks appears after the checks have been
carried out. It is possible that the function returns while the checks are
being carried, in which case the printf is missed out. This patch moves the
DPRINTF before the checks.
--HG--
extra : rebase_source : 172896057e593022444d882ea93323a5d9f77a89
This patch adds a new microop for memory barrier. The microop itself does
nothing, but since it is marked as a memory barrier, the O3 CPU should flush
all the pending loads and stores before the fence to the memory system.
PageTable supported an allocate() call that called back
through the Process to allocate memory, but did not have
a method to map addresses without allocating new pages.
It makes more sense for Process to do the allocation, so
this method was renamed allocateMem() and moved to Process,
and uses a new map() call on PageTable.
The remaining uses of the process pointer in PageTable
were only to get the name and the PID, so by passing these
in directly in the constructor, we can make PageTable
completely independent of Process.
Not all objects need a platform pointer, and having one creates a dependence
on their being a platform object. This change removes the platform pointer to
from the base device object and moves it into subclasses that actually need
it.
By using an underscore, the "." is still available and can unambiguously be
used to refer to members of a structure if an operand is a structure, class,
etc. This change mostly just replaces the appropriate "."s with "_"s, but
there were also a few places where the ISA descriptions where handling the
extensions themselves and had their own regular expressions to update. The
regular expressions in the isa parser were updated as well. It also now
looks for one of the defined type extensions specifically after connecting "_"
where before it would look for any sequence of characters after a "."
following an operand name and try to use it as the extension. This helps to
disambiguate cases where a "_" may legitimately be part of an operand name but
not separate the name from the type suffix.
Because leaving the "_" and suffix on the variable name still leaves a valid
C++ identifier and all extensions need to be consistent in a given context, I
considered leaving them on as a breadcrumb that would show what the intended
type was for that operand. Unfortunately the operands can be referred to in
code templates, the Mem operand in particular, and since the exact type of Mem
can be different for different uses of the same template, that broke things.
Translating MSR addresses into MSR register indices took a lot of space in the
TLB source and made looking around in that file awkward. This change moves
the lookup into its own file to get it out of the way. It also changes it from
a switch statement to a hash map which should hopefully be a little more
efficient.
The decoder now checks the value of FULL_SYSTEM in a switch statement to
decide whether to return a real syscall instruction or one that triggers
syscall emulation (or a panic in FS mode). The switch statement should devolve
into an if, and also should be optimized out since it's based on constant
input.
Having two StaticInst classes, one nominally ISA dependent and the other ISA
dependent, has not been historically useful and makes the StaticInst class
more complicated that it needs to be. This change merges StaticInstBase into
StaticInst.
Do some minor cleanup of some recently added comments, a warning, and change
other instances of stack extension to be like what's now being done for x86.
The way flag bits were being set for microops in x86 ended up implicitly
calling the bitset constructor which was truncating flags beyond the width of
an unsigned long. This change sets the bits in chunks which are always small
enough to avoid being truncated. On 64 bit machines this should reduce to be
the same as before, and on 32 bit machines it should work properly and not be
unreasonably inefficient.
When an instruction is translated in the x86 TLB, a variable called
delayedResponse is passed back and forth which tracks whether a translation
could be completed immediately, or if there's going to be callback that will
finish things up. If a read was to the internal memory space, memory mapped
registers used to implement things like MSRs, the function hadn't yet gotten
to where delayedResponse was set to false, it's default. That meant that the
value was never set, and the TLB could start waiting for a callback that would
never come. This change simply moves the assignment to above where control
can divert to translateInt().
Nothing big here, but when you have an address that is not in the page table request to be allocated, if it falls outside of the maximum stack range all you get is a page fault and you don't know why. Add a little warn() to explain it a bit. Also add some comments and alter logic a little so that you don't totally ignore the return value of checkAndAllocNextPage().
Control register operands are set up so that writing to them is serialize
after, serialize before, and non-speculative. These are probably overboard,
but they should usually be safe. Unfortunately there are times when even these
aren't enough. If an instruction modifies state that affects fetch, later
serialized instructions which come after it might have already gone through
fetch and decode by the time it commits. These instructions may have been
translated incorrectly or interpretted incorrectly and need to be destroyed.
This change modifies instructions which will or may have this behavior so that
they use the IsSquashAfter flag when necessary.
This patch implements the copyRegs() function for the x86 architecture.
The patch assumes that no side effects other than TLB invalidation need
to be considered while copying the registers. This may not hold true in
future.
readBytes and writeBytes had the word "bytes" in their names because they
accessed blobs of bytes. This distinguished them from the read and write
functions which handled higher level data types. Because those functions don't
exist any more, this change renames readBytes and writeBytes to more general
names, readMem and writeMem, which reflect the fact that they are how you read
and write memory. This also makes their names more consistent with the
register reading/writing functions, although those are still read and set for
some reason.
A significant contributor to the need for adoptOrphanParams()
is the practice of appending to SimObjectVectors which have
already been assigned as children. This practice sidesteps the
assignment operation for those appended SimObjects, which is
where parent/child relationships are typically established.
This patch reworks the config scripts that use append() on
SimObjectVectors, which all happen to be in the x86 system
configuration. At some point in the future, I hope to make
SimObjectVectors immutable (by deriving from tuple rather than
list), at which time this patch will be necessary for correct
operation. For now, it just avoids some of the warning
messages that get printed in adoptOrphanParams().
Debug flags are ExecUser, ExecKernel, and ExecAsid. ExecUser and
ExecKernel are set by default when Exec is specified. Use minus
sign with ExecUser or ExecKernel to remove user or kernel tracing
respectively.
This change makes the decoder figure out if an instruction that only supports
memory is using a register encoding and decodes directly to "Unknown" which will
behave appropriately. This prevents other parts of the instruction creation
process from seeing the mismatch and asserting.
At the same time, rename the trace flags to debug flags since they
have broader usage than simply tracing. This means that
--trace-flags is now --debug-flags and --trace-help is now --debug-help
***
(1): get rid of expandForMT function
MIPS is the only ISA that cares about having a piece of ISA state integrate
multiple threads so add constants for MIPS and relieve the other ISAs from having
to define this. Also, InOrder was the only core that was actively calling
this function
* * *
(2): get rid of corespecific type
The CoreSpecific type was used as a proxy to pass in HW specific params to
a MIPS CPU, but since MIPS FS hasnt been touched for awhile, it makes sense
to not force every other ISA to use CoreSpecific as well use a special
reset function to set it. That probably should go in a PowerOn reset fault
anyway.
The internet says this instruction was created by accident when an Intel CPU
failed to decode x87 instructions properly. It's been documented on a few rare
occasions and has generally worked to ensure backwards compatability. One
source claims that the gcc toolchain is basically the only thing that emits
it, and that emulators/binary translators like qemu and bochs implement it.
We won't actually implement it here since we're hardly implementing any other
x87 instructions either. If we were to implement it, it would behave the same
as ffree but then also pop the register stack.
http://www.pagetable.com/?p=16
There may not be a formally correct spelling for the past tense of mmap, but
mmapped is the spelling Google doesn't try to autocorrect. This makes sense
because it mirrors the past tense of map->mapped and not the past tense of
cape->caped.
--HG--
rename : src/arch/alpha/mmaped_ipr.hh => src/arch/alpha/mmapped_ipr.hh
rename : src/arch/arm/mmaped_ipr.hh => src/arch/arm/mmapped_ipr.hh
rename : src/arch/mips/mmaped_ipr.hh => src/arch/mips/mmapped_ipr.hh
rename : src/arch/power/mmaped_ipr.hh => src/arch/power/mmapped_ipr.hh
rename : src/arch/sparc/mmaped_ipr.hh => src/arch/sparc/mmapped_ipr.hh
rename : src/arch/x86/mmaped_ipr.hh => src/arch/x86/mmapped_ipr.hh
In x86, 32 and 64 bit writes to registers in which registers appear to be 32 or
64 bits wide overwrite all bits of the destination register. This change
removes false dependencies in these cases where the previous value of a
register doesn't need to be read to write a new value. New versions of most
microops are created that have a "Big" suffix which simply overwrite their
destination, and the right version to use is selected during microop
allocation based on the selected data size.
This does not change the performance of the O3 CPU model significantly, I
assume because there are other false dependencies from the condition code bits
in the flags register.
These faults can panic/warn/warn_once, etc., instead of instructions doing
that themselves directly. That way, instructions can be speculatively
executed, and only if they're actually going to commit will their fault be
invoked and the panic, etc., happen.
When redirecting fetch to handle branches, the npc of the current pc state
needs to be left alone. This change makes the pc state record whether or not
the npc already reflects a real value by making it keep track of the current
instruction size, or if no size has been set.
JMP_FAR_I was unpacking its far pointer operand using sll instead of srl like
it should, and also putting the components in the wrong registers for use by
other microcode.
During iret access LDT/GDT at CPL0 rather than after transition to user mode
(if I'm reading the Intel IA-64 architecture spec correctly, the contents of
the descriptor table are read before the CPL is updated).
Move page table walker state to its own object type, and make the
walker instantiate state for each outstanding walk. By storing the
states in a queue, the walker is able to handle multiple outstanding
timing requests. Note that functional walks use separate state
elements.
Double packet delete problem is due to an interrupt device deleting a packet that the SimpleTimingPort also deletes. Since MessagePort descends from SimpleTimingPort, simply reimplement the failing code from SimpleTimingPort: recvTiming.
Ran all the source files through 'perl -pi' with this script:
s|\s*(};?\s*)?/\*\s*(end\s*)?namespace\s*(\S+)\s*\*/(\s*})?|} // namespace $3|;
s|\s*};?\s*//\s*(end\s*)?namespace\s*(\S+)\s*|} // namespace $2\n|;
s|\s*};?\s*//\s*(\S+)\s*namespace\s*|} // namespace $1\n|;
Also did a little manual editing on some of the arch/*/isa_traits.hh files
and src/SConscript.
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.
Code in the CPUs that need a nop to carry a fault can't easily deal with a
microcoded nop. This instruction format provides for one that isn't.
--HG--
rename : src/arch/x86/isa/formats/syscall.isa => src/arch/x86/isa/formats/nop.isa
In the process make add skipFuction() to handle isa specific function skipping
instead of ifdefs and other ugliness. For almost all ABIs, 64 bit arguments can
only start in even registers. Size is now passed to getArgument() so that 32
bit systems can make decisions about register selection for 64 bit arguments.
The number argument is now passed by reference because getArgument() will need
to change it based on the size of the argument and the current argument number.
For ARM, if the argument number is odd and a 64-bit register is requested the
number must first be incremented to because all 64 bit arguments are passed
in an even argument register. Then the number will be incremented again to
access both halves of the argument.
This reduces the scope of those includes and makes it less likely for there to
be a dependency loop. This also moves the hashing functions associated with
ExtMachInst objects to be with the ExtMachInst definitions and out of
utility.hh.
Also move the "Fault" reference counted pointer type into a separate file,
sim/fault.hh. It would be better to name this less similarly to sim/faults.hh
to reduce confusion, but fault.hh matches the name of the type. We could change
Fault to FaultPtr to match other pointer types, and then changing the name of
the file would make more sense.
