llvm-project/lld/COFF/Symbols.h

445 lines
14 KiB
C
Raw Normal View History

//===- Symbols.h ------------------------------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef LLD_COFF_SYMBOLS_H
#define LLD_COFF_SYMBOLS_H
#include "Chunks.h"
#include "Config.h"
#include "lld/Common/LLVM.h"
#include "lld/Common/Memory.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Object/Archive.h"
#include "llvm/Object/COFF.h"
#include <atomic>
#include <memory>
#include <vector>
namespace lld {
std::string toString(coff::Symbol &b);
// There are two different ways to convert an Archive::Symbol to a string:
// One for Microsoft name mangling and one for Itanium name mangling.
// Call the functions toCOFFString and toELFString, not just toString.
std::string toCOFFString(const coff::Archive::Symbol &b);
namespace coff {
using llvm::object::Archive;
using llvm::object::COFFSymbolRef;
using llvm::object::coff_import_header;
using llvm::object::coff_symbol_generic;
class ArchiveFile;
class InputFile;
class ObjFile;
class SymbolTable;
// The base class for real symbol classes.
class Symbol {
public:
enum Kind {
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
// The order of these is significant. We start with the regular defined
// symbols as those are the most prevalent and the zero tag is the cheapest
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
// to set. Among the defined kinds, the lower the kind is preferred over
2018-08-27 22:22:25 +08:00
// the higher kind when testing whether one symbol should take precedence
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
// over another.
DefinedRegularKind = 0,
DefinedCommonKind,
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
DefinedLocalImportKind,
DefinedImportThunkKind,
DefinedImportDataKind,
DefinedAbsoluteKind,
DefinedSyntheticKind,
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
UndefinedKind,
COFF: Change the order of adding symbols to the symbol table. Previously, the order of adding symbols to the symbol table was simple. We have a list of all input files. We read each file from beginning of the list and add all symbols in it to the symbol table. This patch changes that order. Now all archive files are added to the symbol table first, and then all the other object files are added. This shouldn't change the behavior in single-threading, and make room to parallelize in multi-threading. In the first step, only lazy symbols are added to the symbol table because archives contain only Lazy symbols. Member object files found to be necessary are queued. In the second step, defined and undefined symbols are added from object files. Adding an undefined symbol to the symbol table may cause more member files to be added to the queue. We simply continue reading all object files until the queue is empty. Finally, new archive or object files may be added to the queues by object files' directive sections (which contain new command line options). The above process is repeated until we get no new files. Symbols defined both in object files and in archives can make results undeterministic. If an archive is read before an object, a new member file gets linked, while in the other way, no new file would be added. That is the most popular cause of an undeterministic result or linking failure as I observed. Separating phases of adding lazy symbols and undefined symbols makes that deterministic. Adding symbols in each phase should be parallelizable. llvm-svn: 241107
2015-07-01 03:35:21 +08:00
LazyKind,
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
LastDefinedCOFFKind = DefinedCommonKind,
LastDefinedKind = DefinedSyntheticKind,
};
Kind kind() const { return static_cast<Kind>(symbolKind); }
// Returns the symbol name.
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
StringRef getName();
void replaceKeepingName(Symbol *other, size_t size);
[COFF] Support MinGW automatic dllimport of data Normally, in order to reference exported data symbols from a different DLL, the declarations need to have the dllimport attribute, in order to use the __imp_<var> symbol (which contains an address to the actual variable) instead of the variable itself directly. This isn't an issue in the same way for functions, since any reference to the function without the dllimport attribute will end up as a reference to a thunk which loads the actual target function from the import address table (IAT). GNU ld, in MinGW environments, supports automatically importing data symbols from DLLs, even if the references didn't have the appropriate dllimport attribute. Since the PE/COFF format doesn't support the kind of relocations that this would require, the MinGW's CRT startup code has an custom framework of their own for manually fixing the missing relocations once module is loaded and the target addresses in the IAT are known. For this to work, the linker (originall in GNU ld) creates a list of remaining references needing fixup, which the runtime processes on startup before handing over control to user code. While this feature is rather controversial, it's one of the main features allowing unix style libraries to be used on windows without any extra porting effort. Some sort of automatic fixing of data imports is also necessary for the itanium C++ ABI on windows (as clang implements it right now) for importing vtable pointers in certain cases, see D43184 for some discussion on that. The runtime pseudo relocation handler supports 8/16/32/64 bit addresses, either PC relative references (like IMAGE_REL_*_REL32*) or absolute references (IMAGE_REL_AMD64_ADDR32, IMAGE_REL_AMD64_ADDR32, IMAGE_REL_I386_DIR32). On linking, the relocation is handled as a relocation against the corresponding IAT slot. For the absolute references, a normal base relocation is created, to update the embedded address in case the image is loaded at a different address. The list of runtime pseudo relocations contains the RVA of the imported symbol (the IAT slot), the RVA of the location the relocation should be applied to, and a size of the memory location. When the relocations are fixed at runtime, the difference between the actual IAT slot value and the IAT slot address is added to the reference, doing the right thing for both absolute and relative references. With this patch alone, things work fine for i386 binaries, and mostly for x86_64 binaries, with feature parity with GNU ld. Despite this, there are a few gotchas: - References to data from within code works fine on both x86 architectures, since their relocations consist of plain 32 or 64 bit absolute/relative references. On ARM and AArch64, references to data doesn't consist of a plain 32 or 64 bit embedded address or offset in the code. On ARMNT, it's usually a MOVW+MOVT instruction pair represented by a IMAGE_REL_ARM_MOV32T relocation, each instruction containing 16 bit of the target address), on AArch64, it's usually an ADRP+ADD/LDR/STR instruction pair with an even more complex encoding, storing a PC relative address (with a range of +/- 4 GB). This could theoretically be remedied by extending the runtime pseudo relocation handler with new relocation types, to support these instruction encodings. This isn't an issue for GCC/GNU ld since they don't support windows on ARMNT/AArch64. - For x86_64, if references in code are encoded as 32 bit PC relative offsets, the runtime relocation will fail if the target turns out to be out of range for a 32 bit offset. - Fixing up the relocations at runtime requires making sections writable if necessary, with the VirtualProtect function. In Windows Store/UWP apps, this function is forbidden. These limitations are addressed by a few later patches in lld and llvm. Differential Revision: https://reviews.llvm.org/D50917 llvm-svn: 340726
2018-08-27 16:43:31 +08:00
// Returns the file from which this symbol was created.
InputFile *getFile();
// Indicates that this symbol will be included in the final image. Only valid
// after calling markLive.
bool isLive() const;
protected:
friend SymbolTable;
explicit Symbol(Kind k, StringRef n = "")
: symbolKind(k), isExternal(true), isCOMDAT(false),
writtenToSymtab(false), pendingArchiveLoad(false), isGCRoot(false),
isRuntimePseudoReloc(false), nameSize(n.size()),
nameData(n.empty() ? nullptr : n.data()) {}
const unsigned symbolKind : 8;
unsigned isExternal : 1;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
public:
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
// This bit is used by the \c DefinedRegular subclass.
unsigned isCOMDAT : 1;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
// This bit is used by Writer::createSymbolAndStringTable() to prevent
// symbols from being written to the symbol table more than once.
unsigned writtenToSymtab : 1;
// True if this symbol was referenced by a regular (non-bitcode) object.
unsigned isUsedInRegularObj : 1;
// True if we've seen both a lazy and an undefined symbol with this symbol
// name, which means that we have enqueued an archive member load and should
// not load any more archive members to resolve the same symbol.
unsigned pendingArchiveLoad : 1;
/// True if we've already added this symbol to the list of GC roots.
unsigned isGCRoot : 1;
unsigned isRuntimePseudoReloc : 1;
protected:
// Symbol name length. Assume symbol lengths fit in a 32-bit integer.
uint32_t nameSize;
const char *nameData;
};
// The base class for any defined symbols, including absolute symbols,
// etc.
class Defined : public Symbol {
public:
Defined(Kind k, StringRef n) : Symbol(k, n) {}
static bool classof(const Symbol *s) { return s->kind() <= LastDefinedKind; }
// Returns the RVA (relative virtual address) of this symbol. The
// writer sets and uses RVAs.
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
uint64_t getRVA();
// Returns the chunk containing this symbol. Absolute symbols and __ImageBase
// do not have chunks, so this may return null.
Chunk *getChunk();
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
};
// Symbols defined via a COFF object file or bitcode file. For COFF files, this
// stores a coff_symbol_generic*, and names of internal symbols are lazily
// loaded through that. For bitcode files, Sym is nullptr and the name is stored
// as a decomposed StringRef.
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
class DefinedCOFF : public Defined {
friend Symbol;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
public:
DefinedCOFF(Kind k, InputFile *f, StringRef n, const coff_symbol_generic *s)
: Defined(k, n), file(f), sym(s) {}
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
static bool classof(const Symbol *s) {
return s->kind() <= LastDefinedCOFFKind;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
}
InputFile *getFile() { return file; }
COFFSymbolRef getCOFFSymbol();
InputFile *file;
protected:
const coff_symbol_generic *sym;
};
// Regular defined symbols read from object file symbol tables.
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
class DefinedRegular : public DefinedCOFF {
public:
DefinedRegular(InputFile *f, StringRef n, bool isCOMDAT,
bool isExternal = false,
const coff_symbol_generic *s = nullptr,
SectionChunk *c = nullptr)
: DefinedCOFF(DefinedRegularKind, f, n, s), data(c ? &c->repl : nullptr) {
this->isExternal = isExternal;
this->isCOMDAT = isCOMDAT;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
}
static bool classof(const Symbol *s) {
return s->kind() == DefinedRegularKind;
}
uint64_t getRVA() const { return (*data)->getRVA() + sym->Value; }
SectionChunk *getChunk() const { return *data; }
uint32_t getValue() const { return sym->Value; }
SectionChunk **data;
};
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
class DefinedCommon : public DefinedCOFF {
public:
DefinedCommon(InputFile *f, StringRef n, uint64_t size,
const coff_symbol_generic *s = nullptr,
CommonChunk *c = nullptr)
: DefinedCOFF(DefinedCommonKind, f, n, s), data(c), size(size) {
this->isExternal = true;
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
}
static bool classof(const Symbol *s) {
return s->kind() == DefinedCommonKind;
}
uint64_t getRVA() { return data->getRVA(); }
CommonChunk *getChunk() { return data; }
private:
friend SymbolTable;
uint64_t getSize() const { return size; }
CommonChunk *data;
uint64_t size;
};
// Absolute symbols.
class DefinedAbsolute : public Defined {
public:
DefinedAbsolute(StringRef n, COFFSymbolRef s)
: Defined(DefinedAbsoluteKind, n), va(s.getValue()) {
isExternal = s.isExternal();
[opt] Devirtualize the SymbolBody type hierarchy and start compacting its members into the base class. First, to help motivate this kind of change, understand that in a self-link, LLD creates 5.5 million defined regular symbol bodies (and 6 million symbol bodies total). A significant portion of its time is spent allocating the memory for these symbols, and befor ethis patch the defined regular symbol body objects alone consumed some 420mb of memory during the self link. As a consequence, I think it is worth expending considerable effort to make these objects as memory efficient as possible. This is the first of several components of that. This change starts with the goal of removing the virtual functins from SymbolBody so that it can avoid having a vptr embedded in it when it already contains a "kind" member, and that member can be much more compact than a vptr. The primary way of doing this is to sink as much of the logic that we would have to dispatch for into data in the base class. As part of this, I made the various flags bits that will pack into a bitfield with the kind tag. I also sank the Name down to eliminate the dispatch for that, and used LLVM's RTTI-style dispatch for everything else (most of which is cold and so doesn't matter terribly if we get minutely worse lowering than a vtable dispatch). As I was doing this, I wanted to make the RTTI-dispatch (which would become much hotter than before) as efficient as possible, so I've re-organized the tags somewhat. Notably, the common case (regular defined symbols) is now zero which we can test for faster. I also needed to rewrite the comparison routine used during resolving symbols. This proved to be quite complex as the semantics of the existing one were very subtle due to the back-and-forth virtual dispatch caused by re-dispatching with reversed operands. I've consolidated it to a single function and tried to comment it quite a bit more to help explain what is going on. However, this may need more comments or other explanations. It at least passes all the regression tests. I'm not working on Windows, so I can't fully test it. With all of these changes, the size of a DefinedRegular symbol on a 64-bit build goes from 80 bytes to 64 bytes, and we save approximately 84mb or 20% of the memory consumed by these symbol bodies during the link. The link time appears marginally faster as well, and the profile hotness of the memory allocation subsystem got a bit better, but there is still a lot of allocation traffic. Differential Revision: http://reviews.llvm.org/D10792 llvm-svn: 241001
2015-06-30 05:35:48 +08:00
}
DefinedAbsolute(StringRef n, uint64_t v)
: Defined(DefinedAbsoluteKind, n), va(v) {}
static bool classof(const Symbol *s) {
return s->kind() == DefinedAbsoluteKind;
}
uint64_t getRVA() { return va - config->imageBase; }
void setVA(uint64_t v) { va = v; }
// Section index relocations against absolute symbols resolve to
// this 16 bit number, and it is the largest valid section index
// plus one. This variable keeps it.
static uint16_t numOutputSections;
private:
uint64_t va;
};
// This symbol is used for linker-synthesized symbols like __ImageBase and
// __safe_se_handler_table.
class DefinedSynthetic : public Defined {
public:
explicit DefinedSynthetic(StringRef name, Chunk *c)
: Defined(DefinedSyntheticKind, name), c(c) {}
static bool classof(const Symbol *s) {
return s->kind() == DefinedSyntheticKind;
}
// A null chunk indicates that this is __ImageBase. Otherwise, this is some
// other synthesized chunk, like SEHTableChunk.
uint32_t getRVA() { return c ? c->getRVA() : 0; }
Chunk *getChunk() { return c; }
private:
Chunk *c;
};
// This class represents a symbol defined in an archive file. It is
// created from an archive file header, and it knows how to load an
// object file from an archive to replace itself with a defined
// symbol. If the resolver finds both Undefined and Lazy for
// the same name, it will ask the Lazy to load a file.
class Lazy : public Symbol {
public:
Lazy(ArchiveFile *f, const Archive::Symbol s)
: Symbol(LazyKind, s.getName()), file(f), sym(s) {}
static bool classof(const Symbol *s) { return s->kind() == LazyKind; }
MemoryBufferRef getMemberBuffer();
ArchiveFile *file;
private:
friend SymbolTable;
private:
const Archive::Symbol sym;
};
// Undefined symbols.
class Undefined : public Symbol {
public:
explicit Undefined(StringRef n) : Symbol(UndefinedKind, n) {}
static bool classof(const Symbol *s) { return s->kind() == UndefinedKind; }
// An undefined symbol can have a fallback symbol which gives an
// undefined symbol a second chance if it would remain undefined.
// If it remains undefined, it'll be replaced with whatever the
// Alias pointer points to.
Symbol *weakAlias = nullptr;
// If this symbol is external weak, try to resolve it to a defined
// symbol by searching the chain of fallback symbols. Returns the symbol if
// successful, otherwise returns null.
Defined *getWeakAlias();
};
// Windows-specific classes.
// This class represents a symbol imported from a DLL. This has two
// names for internal use and external use. The former is used for
// name resolution, and the latter is used for the import descriptor
// table in an output. The former has "__imp_" prefix.
class DefinedImportData : public Defined {
public:
DefinedImportData(StringRef n, ImportFile *f)
: Defined(DefinedImportDataKind, n), file(f) {
}
static bool classof(const Symbol *s) {
return s->kind() == DefinedImportDataKind;
}
uint64_t getRVA() { return file->location->getRVA(); }
Chunk *getChunk() { return file->location; }
void setLocation(Chunk *addressTable) { file->location = addressTable; }
StringRef getDLLName() { return file->dllName; }
StringRef getExternalName() { return file->externalName; }
uint16_t getOrdinal() { return file->hdr->OrdinalHint; }
ImportFile *file;
};
// This class represents a symbol for a jump table entry which jumps
// to a function in a DLL. Linker are supposed to create such symbols
// without "__imp_" prefix for all function symbols exported from
// DLLs, so that you can call DLL functions as regular functions with
// a regular name. A function pointer is given as a DefinedImportData.
class DefinedImportThunk : public Defined {
public:
DefinedImportThunk(StringRef name, DefinedImportData *s, uint16_t machine);
static bool classof(const Symbol *s) {
return s->kind() == DefinedImportThunkKind;
}
uint64_t getRVA() { return data->getRVA(); }
Chunk *getChunk() { return data; }
DefinedImportData *wrappedSym;
private:
Chunk *data;
};
// If you have a symbol "foo" in your object file, a symbol name
// "__imp_foo" becomes automatically available as a pointer to "foo".
// This class is for such automatically-created symbols.
// Yes, this is an odd feature. We didn't intend to implement that.
// This is here just for compatibility with MSVC.
class DefinedLocalImport : public Defined {
public:
DefinedLocalImport(StringRef n, Defined *s)
: Defined(DefinedLocalImportKind, n), data(make<LocalImportChunk>(s)) {}
static bool classof(const Symbol *s) {
return s->kind() == DefinedLocalImportKind;
}
uint64_t getRVA() { return data->getRVA(); }
Chunk *getChunk() { return data; }
private:
LocalImportChunk *data;
};
inline uint64_t Defined::getRVA() {
switch (kind()) {
case DefinedAbsoluteKind:
return cast<DefinedAbsolute>(this)->getRVA();
case DefinedSyntheticKind:
return cast<DefinedSynthetic>(this)->getRVA();
case DefinedImportDataKind:
return cast<DefinedImportData>(this)->getRVA();
case DefinedImportThunkKind:
return cast<DefinedImportThunk>(this)->getRVA();
case DefinedLocalImportKind:
return cast<DefinedLocalImport>(this)->getRVA();
case DefinedCommonKind:
return cast<DefinedCommon>(this)->getRVA();
case DefinedRegularKind:
return cast<DefinedRegular>(this)->getRVA();
case LazyKind:
case UndefinedKind:
llvm_unreachable("Cannot get the address for an undefined symbol.");
}
llvm_unreachable("unknown symbol kind");
}
inline Chunk *Defined::getChunk() {
switch (kind()) {
case DefinedRegularKind:
return cast<DefinedRegular>(this)->getChunk();
case DefinedAbsoluteKind:
return nullptr;
case DefinedSyntheticKind:
return cast<DefinedSynthetic>(this)->getChunk();
case DefinedImportDataKind:
return cast<DefinedImportData>(this)->getChunk();
case DefinedImportThunkKind:
return cast<DefinedImportThunk>(this)->getChunk();
case DefinedLocalImportKind:
return cast<DefinedLocalImport>(this)->getChunk();
case DefinedCommonKind:
return cast<DefinedCommon>(this)->getChunk();
case LazyKind:
case UndefinedKind:
llvm_unreachable("Cannot get the chunk of an undefined symbol.");
}
llvm_unreachable("unknown symbol kind");
}
// A buffer class that is large enough to hold any Symbol-derived
// object. We allocate memory using this class and instantiate a symbol
// using the placement new.
union SymbolUnion {
alignas(DefinedRegular) char a[sizeof(DefinedRegular)];
alignas(DefinedCommon) char b[sizeof(DefinedCommon)];
alignas(DefinedAbsolute) char c[sizeof(DefinedAbsolute)];
alignas(DefinedSynthetic) char d[sizeof(DefinedSynthetic)];
alignas(Lazy) char e[sizeof(Lazy)];
alignas(Undefined) char f[sizeof(Undefined)];
alignas(DefinedImportData) char g[sizeof(DefinedImportData)];
alignas(DefinedImportThunk) char h[sizeof(DefinedImportThunk)];
alignas(DefinedLocalImport) char i[sizeof(DefinedLocalImport)];
};
template <typename T, typename... ArgT>
void replaceSymbol(Symbol *s, ArgT &&... arg) {
static_assert(std::is_trivially_destructible<T>(),
"Symbol types must be trivially destructible");
static_assert(sizeof(T) <= sizeof(SymbolUnion), "Symbol too small");
static_assert(alignof(T) <= alignof(SymbolUnion),
"SymbolUnion not aligned enough");
assert(static_cast<Symbol *>(static_cast<T *>(nullptr)) == nullptr &&
"Not a Symbol");
new (s) T(std::forward<ArgT>(arg)...);
}
} // namespace coff
} // namespace lld
#endif