2020-04-03 02:54:05 +08:00
|
|
|
//===- Writer.cpp ---------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// 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
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "Writer.h"
|
|
|
|
#include "Config.h"
|
|
|
|
#include "InputFiles.h"
|
|
|
|
#include "InputSection.h"
|
2020-05-06 07:37:34 +08:00
|
|
|
#include "MergedOutputSection.h"
|
|
|
|
#include "OutputSection.h"
|
2020-04-03 02:54:05 +08:00
|
|
|
#include "OutputSegment.h"
|
|
|
|
#include "SymbolTable.h"
|
|
|
|
#include "Symbols.h"
|
2020-04-22 04:37:57 +08:00
|
|
|
#include "SyntheticSections.h"
|
2020-04-03 02:54:05 +08:00
|
|
|
#include "Target.h"
|
2020-08-21 04:05:13 +08:00
|
|
|
#include "UnwindInfoSection.h"
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
#include "lld/Common/ErrorHandler.h"
|
|
|
|
#include "lld/Common/Memory.h"
|
|
|
|
#include "llvm/BinaryFormat/MachO.h"
|
2020-08-15 03:35:31 +08:00
|
|
|
#include "llvm/Config/llvm-config.h"
|
2020-04-29 07:58:22 +08:00
|
|
|
#include "llvm/Support/LEB128.h"
|
2020-10-15 02:03:34 +08:00
|
|
|
#include "llvm/Support/MD5.h"
|
2020-04-03 02:54:05 +08:00
|
|
|
#include "llvm/Support/MathExtras.h"
|
2020-05-06 07:37:34 +08:00
|
|
|
#include "llvm/Support/Path.h"
|
2020-04-03 02:54:05 +08:00
|
|
|
|
2020-09-22 02:04:13 +08:00
|
|
|
#include <algorithm>
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
using namespace llvm;
|
|
|
|
using namespace llvm::MachO;
|
|
|
|
using namespace lld;
|
|
|
|
using namespace lld::macho;
|
|
|
|
|
|
|
|
namespace {
|
2020-10-15 02:03:34 +08:00
|
|
|
class LCUuid;
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
class Writer {
|
|
|
|
public:
|
|
|
|
Writer() : buffer(errorHandler().outputBuffer) {}
|
|
|
|
|
2020-04-22 04:37:57 +08:00
|
|
|
void scanRelocations();
|
2020-05-02 07:29:06 +08:00
|
|
|
void createOutputSections();
|
2020-04-28 03:50:59 +08:00
|
|
|
void createLoadCommands();
|
|
|
|
void assignAddresses(OutputSegment *);
|
|
|
|
void createSymtabContents();
|
2020-04-22 04:37:57 +08:00
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
void openFile();
|
|
|
|
void writeSections();
|
2020-10-15 02:03:34 +08:00
|
|
|
void writeUuid();
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
void run();
|
|
|
|
|
|
|
|
std::unique_ptr<FileOutputBuffer> &buffer;
|
2020-04-22 04:37:57 +08:00
|
|
|
uint64_t addr = 0;
|
2020-04-28 03:50:59 +08:00
|
|
|
uint64_t fileOff = 0;
|
2020-07-31 05:28:41 +08:00
|
|
|
MachHeaderSection *header = nullptr;
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
StringTableSection *stringTableSection = nullptr;
|
2020-04-29 07:58:22 +08:00
|
|
|
SymtabSection *symtabSection = nullptr;
|
2020-09-05 09:02:07 +08:00
|
|
|
IndirectSymtabSection *indirectSymtabSection = nullptr;
|
2020-08-21 04:05:13 +08:00
|
|
|
UnwindInfoSection *unwindInfoSection = nullptr;
|
2020-10-15 02:03:34 +08:00
|
|
|
LCUuid *uuidCommand = nullptr;
|
2020-04-03 02:54:05 +08:00
|
|
|
};
|
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
// LC_DYLD_INFO_ONLY stores the offsets of symbol import/export information.
|
2020-04-03 02:54:05 +08:00
|
|
|
class LCDyldInfo : public LoadCommand {
|
|
|
|
public:
|
2020-09-06 01:55:33 +08:00
|
|
|
LCDyldInfo(RebaseSection *rebaseSection, BindingSection *bindingSection,
|
2020-08-25 12:57:59 +08:00
|
|
|
WeakBindingSection *weakBindingSection,
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
LazyBindingSection *lazyBindingSection,
|
|
|
|
ExportSection *exportSection)
|
2020-09-06 01:55:33 +08:00
|
|
|
: rebaseSection(rebaseSection), bindingSection(bindingSection),
|
|
|
|
weakBindingSection(weakBindingSection),
|
2020-08-25 12:57:59 +08:00
|
|
|
lazyBindingSection(lazyBindingSection), exportSection(exportSection) {}
|
2020-04-28 03:50:59 +08:00
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
uint32_t getSize() const override { return sizeof(dyld_info_command); }
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<dyld_info_command *>(buf);
|
|
|
|
c->cmd = LC_DYLD_INFO_ONLY;
|
|
|
|
c->cmdsize = getSize();
|
2020-09-06 01:55:33 +08:00
|
|
|
if (rebaseSection->isNeeded()) {
|
|
|
|
c->rebase_off = rebaseSection->fileOff;
|
|
|
|
c->rebase_size = rebaseSection->getFileSize();
|
|
|
|
}
|
2020-04-28 03:50:59 +08:00
|
|
|
if (bindingSection->isNeeded()) {
|
2020-05-02 07:29:06 +08:00
|
|
|
c->bind_off = bindingSection->fileOff;
|
2020-04-28 03:50:59 +08:00
|
|
|
c->bind_size = bindingSection->getFileSize();
|
|
|
|
}
|
2020-08-25 12:57:59 +08:00
|
|
|
if (weakBindingSection->isNeeded()) {
|
|
|
|
c->weak_bind_off = weakBindingSection->fileOff;
|
|
|
|
c->weak_bind_size = weakBindingSection->getFileSize();
|
|
|
|
}
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
if (lazyBindingSection->isNeeded()) {
|
|
|
|
c->lazy_bind_off = lazyBindingSection->fileOff;
|
|
|
|
c->lazy_bind_size = lazyBindingSection->getFileSize();
|
|
|
|
}
|
2020-04-29 07:58:22 +08:00
|
|
|
if (exportSection->isNeeded()) {
|
2020-05-02 07:29:06 +08:00
|
|
|
c->export_off = exportSection->fileOff;
|
2020-04-29 07:58:22 +08:00
|
|
|
c->export_size = exportSection->getFileSize();
|
|
|
|
}
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
|
2020-09-06 01:55:33 +08:00
|
|
|
RebaseSection *rebaseSection;
|
2020-04-28 03:50:59 +08:00
|
|
|
BindingSection *bindingSection;
|
2020-08-25 12:57:59 +08:00
|
|
|
WeakBindingSection *weakBindingSection;
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
LazyBindingSection *lazyBindingSection;
|
2020-04-29 07:58:22 +08:00
|
|
|
ExportSection *exportSection;
|
2020-04-03 02:54:05 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
class LCDysymtab : public LoadCommand {
|
|
|
|
public:
|
2020-09-05 09:02:07 +08:00
|
|
|
LCDysymtab(IndirectSymtabSection *indirectSymtabSection)
|
|
|
|
: indirectSymtabSection(indirectSymtabSection) {}
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
uint32_t getSize() const override { return sizeof(dysymtab_command); }
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<dysymtab_command *>(buf);
|
|
|
|
c->cmd = LC_DYSYMTAB;
|
|
|
|
c->cmdsize = getSize();
|
2020-09-05 09:02:07 +08:00
|
|
|
c->indirectsymoff = indirectSymtabSection->fileOff;
|
|
|
|
c->nindirectsyms = indirectSymtabSection->getNumSymbols();
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
2020-09-05 09:02:07 +08:00
|
|
|
|
|
|
|
IndirectSymtabSection *indirectSymtabSection = nullptr;
|
2020-04-03 02:54:05 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
class LCSegment : public LoadCommand {
|
|
|
|
public:
|
|
|
|
LCSegment(StringRef name, OutputSegment *seg) : name(name), seg(seg) {}
|
|
|
|
|
|
|
|
uint32_t getSize() const override {
|
|
|
|
return sizeof(segment_command_64) +
|
2020-05-02 07:29:06 +08:00
|
|
|
seg->numNonHiddenSections() * sizeof(section_64);
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<segment_command_64 *>(buf);
|
|
|
|
buf += sizeof(segment_command_64);
|
|
|
|
|
|
|
|
c->cmd = LC_SEGMENT_64;
|
|
|
|
c->cmdsize = getSize();
|
|
|
|
memcpy(c->segname, name.data(), name.size());
|
2020-04-28 03:50:59 +08:00
|
|
|
c->fileoff = seg->fileOff;
|
|
|
|
c->maxprot = seg->maxProt;
|
|
|
|
c->initprot = seg->initProt;
|
|
|
|
|
2020-05-06 08:25:58 +08:00
|
|
|
if (seg->getSections().empty())
|
2020-04-28 03:50:59 +08:00
|
|
|
return;
|
2020-04-03 02:54:05 +08:00
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
c->vmaddr = seg->firstSection()->addr;
|
|
|
|
c->vmsize =
|
2020-04-22 04:37:57 +08:00
|
|
|
seg->lastSection()->addr + seg->lastSection()->getSize() - c->vmaddr;
|
2020-05-02 07:29:06 +08:00
|
|
|
c->nsects = seg->numNonHiddenSections();
|
2020-04-03 02:54:05 +08:00
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
for (OutputSection *osec : seg->getSections()) {
|
2020-07-29 00:56:55 +08:00
|
|
|
if (!isZeroFill(osec->flags)) {
|
|
|
|
assert(osec->fileOff >= seg->fileOff);
|
|
|
|
c->filesize = std::max(
|
|
|
|
c->filesize, osec->fileOff + osec->getFileSize() - seg->fileOff);
|
|
|
|
}
|
2020-05-06 08:25:58 +08:00
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
if (osec->isHidden())
|
2020-04-28 03:50:59 +08:00
|
|
|
continue;
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
auto *sectHdr = reinterpret_cast<section_64 *>(buf);
|
|
|
|
buf += sizeof(section_64);
|
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
memcpy(sectHdr->sectname, osec->name.data(), osec->name.size());
|
2020-04-03 02:54:05 +08:00
|
|
|
memcpy(sectHdr->segname, name.data(), name.size());
|
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
sectHdr->addr = osec->addr;
|
|
|
|
sectHdr->offset = osec->fileOff;
|
|
|
|
sectHdr->align = Log2_32(osec->align);
|
|
|
|
sectHdr->flags = osec->flags;
|
|
|
|
sectHdr->size = osec->getSize();
|
2020-09-05 09:02:07 +08:00
|
|
|
sectHdr->reserved1 = osec->reserved1;
|
|
|
|
sectHdr->reserved2 = osec->reserved2;
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
StringRef name;
|
|
|
|
OutputSegment *seg;
|
|
|
|
};
|
|
|
|
|
|
|
|
class LCMain : public LoadCommand {
|
|
|
|
uint32_t getSize() const override { return sizeof(entry_point_command); }
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<entry_point_command *>(buf);
|
|
|
|
c->cmd = LC_MAIN;
|
|
|
|
c->cmdsize = getSize();
|
2020-09-18 01:20:16 +08:00
|
|
|
|
|
|
|
if (config->entry->isInStubs())
|
|
|
|
c->entryoff =
|
|
|
|
in.stubs->fileOff + config->entry->stubsIndex * target->stubSize;
|
|
|
|
else
|
|
|
|
c->entryoff = config->entry->getFileOffset();
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
c->stacksize = 0;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
class LCSymtab : public LoadCommand {
|
|
|
|
public:
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
LCSymtab(SymtabSection *symtabSection, StringTableSection *stringTableSection)
|
|
|
|
: symtabSection(symtabSection), stringTableSection(stringTableSection) {}
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
uint32_t getSize() const override { return sizeof(symtab_command); }
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<symtab_command *>(buf);
|
|
|
|
c->cmd = LC_SYMTAB;
|
|
|
|
c->cmdsize = getSize();
|
2020-05-02 07:29:06 +08:00
|
|
|
c->symoff = symtabSection->fileOff;
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
c->nsyms = symtabSection->getNumSymbols();
|
2020-05-02 07:29:06 +08:00
|
|
|
c->stroff = stringTableSection->fileOff;
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
c->strsize = stringTableSection->getFileSize();
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
|
|
|
|
SymtabSection *symtabSection = nullptr;
|
|
|
|
StringTableSection *stringTableSection = nullptr;
|
2020-04-03 02:54:05 +08:00
|
|
|
};
|
|
|
|
|
2020-04-24 11:16:49 +08:00
|
|
|
// There are several dylib load commands that share the same structure:
|
|
|
|
// * LC_LOAD_DYLIB
|
|
|
|
// * LC_ID_DYLIB
|
|
|
|
// * LC_REEXPORT_DYLIB
|
|
|
|
class LCDylib : public LoadCommand {
|
2020-04-03 02:54:05 +08:00
|
|
|
public:
|
2020-09-22 02:04:13 +08:00
|
|
|
LCDylib(LoadCommandType type, StringRef path) : type(type), path(path) {
|
|
|
|
instanceCount++;
|
|
|
|
}
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
uint32_t getSize() const override {
|
|
|
|
return alignTo(sizeof(dylib_command) + path.size() + 1, 8);
|
|
|
|
}
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<dylib_command *>(buf);
|
|
|
|
buf += sizeof(dylib_command);
|
|
|
|
|
2020-04-24 11:16:49 +08:00
|
|
|
c->cmd = type;
|
2020-04-03 02:54:05 +08:00
|
|
|
c->cmdsize = getSize();
|
|
|
|
c->dylib.name = sizeof(dylib_command);
|
|
|
|
|
|
|
|
memcpy(buf, path.data(), path.size());
|
|
|
|
buf[path.size()] = '\0';
|
|
|
|
}
|
|
|
|
|
2020-09-22 02:04:13 +08:00
|
|
|
static uint32_t getInstanceCount() { return instanceCount; }
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
private:
|
2020-04-24 11:16:49 +08:00
|
|
|
LoadCommandType type;
|
2020-04-03 02:54:05 +08:00
|
|
|
StringRef path;
|
2020-09-22 02:04:13 +08:00
|
|
|
static uint32_t instanceCount;
|
2020-04-03 02:54:05 +08:00
|
|
|
};
|
|
|
|
|
2020-09-22 02:04:13 +08:00
|
|
|
uint32_t LCDylib::instanceCount = 0;
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
class LCLoadDylinker : public LoadCommand {
|
|
|
|
public:
|
|
|
|
uint32_t getSize() const override {
|
|
|
|
return alignTo(sizeof(dylinker_command) + path.size() + 1, 8);
|
|
|
|
}
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<dylinker_command *>(buf);
|
|
|
|
buf += sizeof(dylinker_command);
|
|
|
|
|
|
|
|
c->cmd = LC_LOAD_DYLINKER;
|
|
|
|
c->cmdsize = getSize();
|
|
|
|
c->name = sizeof(dylinker_command);
|
|
|
|
|
|
|
|
memcpy(buf, path.data(), path.size());
|
|
|
|
buf[path.size()] = '\0';
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
// Recent versions of Darwin won't run any binary that has dyld at a
|
|
|
|
// different location.
|
|
|
|
const StringRef path = "/usr/lib/dyld";
|
|
|
|
};
|
2020-08-13 10:50:28 +08:00
|
|
|
|
|
|
|
class LCRPath : public LoadCommand {
|
|
|
|
public:
|
|
|
|
LCRPath(StringRef path) : path(path) {}
|
|
|
|
|
|
|
|
uint32_t getSize() const override {
|
|
|
|
return alignTo(sizeof(rpath_command) + path.size() + 1, WordSize);
|
|
|
|
}
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<rpath_command *>(buf);
|
|
|
|
buf += sizeof(rpath_command);
|
|
|
|
|
|
|
|
c->cmd = LC_RPATH;
|
|
|
|
c->cmdsize = getSize();
|
|
|
|
c->path = sizeof(rpath_command);
|
|
|
|
|
|
|
|
memcpy(buf, path.data(), path.size());
|
|
|
|
buf[path.size()] = '\0';
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
StringRef path;
|
|
|
|
};
|
2020-08-15 03:35:31 +08:00
|
|
|
|
|
|
|
class LCBuildVersion : public LoadCommand {
|
|
|
|
public:
|
|
|
|
LCBuildVersion(const PlatformInfo &platform) : platform(platform) {}
|
|
|
|
|
|
|
|
const int ntools = 1;
|
|
|
|
|
|
|
|
uint32_t getSize() const override {
|
|
|
|
return sizeof(build_version_command) + ntools * sizeof(build_tool_version);
|
|
|
|
}
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<build_version_command *>(buf);
|
|
|
|
c->cmd = LC_BUILD_VERSION;
|
|
|
|
c->cmdsize = getSize();
|
|
|
|
c->platform = static_cast<uint32_t>(platform.kind);
|
|
|
|
c->minos = ((platform.minimum.getMajor() << 020) |
|
|
|
|
(platform.minimum.getMinor().getValueOr(0) << 010) |
|
|
|
|
platform.minimum.getSubminor().getValueOr(0));
|
|
|
|
c->sdk = ((platform.sdk.getMajor() << 020) |
|
|
|
|
(platform.sdk.getMinor().getValueOr(0) << 010) |
|
|
|
|
platform.sdk.getSubminor().getValueOr(0));
|
|
|
|
c->ntools = ntools;
|
|
|
|
auto *t = reinterpret_cast<build_tool_version *>(&c[1]);
|
|
|
|
t->tool = TOOL_LD;
|
|
|
|
t->version = (LLVM_VERSION_MAJOR << 020) | (LLVM_VERSION_MINOR << 010) |
|
|
|
|
LLVM_VERSION_PATCH;
|
|
|
|
}
|
|
|
|
|
|
|
|
const PlatformInfo &platform;
|
|
|
|
};
|
|
|
|
|
2020-10-15 02:03:34 +08:00
|
|
|
// Stores a unique identifier for the output file based on an MD5 hash of its
|
|
|
|
// contents. In order to hash the contents, we must first write them, but
|
|
|
|
// LC_UUID itself must be part of the written contents in order for all the
|
|
|
|
// offsets to be calculated correctly. We resolve this circular paradox by
|
|
|
|
// first writing an LC_UUID with an all-zero UUID, then updating the UUID with
|
|
|
|
// its real value later.
|
|
|
|
class LCUuid : public LoadCommand {
|
|
|
|
public:
|
|
|
|
uint32_t getSize() const override { return sizeof(uuid_command); }
|
|
|
|
|
|
|
|
void writeTo(uint8_t *buf) const override {
|
|
|
|
auto *c = reinterpret_cast<uuid_command *>(buf);
|
|
|
|
c->cmd = LC_UUID;
|
|
|
|
c->cmdsize = getSize();
|
|
|
|
uuidBuf = c->uuid;
|
|
|
|
}
|
|
|
|
|
|
|
|
void writeUuid(const std::array<uint8_t, 16> &uuid) const {
|
|
|
|
memcpy(uuidBuf, uuid.data(), uuid.size());
|
|
|
|
}
|
|
|
|
|
|
|
|
mutable uint8_t *uuidBuf;
|
|
|
|
};
|
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
} // namespace
|
|
|
|
|
2020-04-22 04:37:57 +08:00
|
|
|
void Writer::scanRelocations() {
|
2020-05-19 06:46:33 +08:00
|
|
|
for (InputSection *isec : inputSections) {
|
2020-09-06 01:55:33 +08:00
|
|
|
// We do not wish to add rebase opcodes for __LD,__compact_unwind, because
|
|
|
|
// it doesn't actually end up in the final binary. TODO: filtering it out
|
|
|
|
// before Writer runs might be cleaner...
|
|
|
|
if (isec->segname == segment_names::ld)
|
|
|
|
continue;
|
|
|
|
|
2020-05-19 06:46:33 +08:00
|
|
|
for (Reloc &r : isec->relocs) {
|
2020-09-23 11:42:12 +08:00
|
|
|
if (auto *s = r.referent.dyn_cast<lld::macho::Symbol *>()) {
|
2020-05-19 06:46:33 +08:00
|
|
|
if (isa<Undefined>(s))
|
clang+lld: Improve clang+ld.darwinnew.lld interaction, pass -demangle
This patch:
- adds an ld64.lld.darwinnew symlink for lld, to go with f2710d4b576,
so that `clang -fuse-ld=lld.darwinnew` can be used to test new
Mach-O lld while it's in bring-up. (The expectation is that we'll
remove this again once new Mach-O lld is the defauld and only Mach-O
lld.)
- lets the clang driver know if the linker is lld (currently
only triggered if `-fuse-ld=lld` or `-fuse-ld=lld.darwinnew` is
passed). Currently only used for the next point, but could be used
to implement other features that need close coordination between
compiler and linker, e.g. having a diag for calling `clang++` instead
of `clang` when link errors are caused by a missing C++ stdlib.
- lets the clang driver pass `-demangle` to Mach-O lld (both old and
new), in addition to ld64
- implements -demangle for new Mach-O lld
- changes demangleItanium() to accept _Z, __Z, ___Z, ____Z prefixes
(and updates one test added in D68014). Mach-O has an extra
underscore for symbols, and the three (or, on Mach-O, four)
underscores are used for block names.
Differential Revision: https://reviews.llvm.org/D91884
2020-11-21 02:57:44 +08:00
|
|
|
error("undefined symbol " + toString(*s) + ", referenced from " +
|
2020-05-19 06:46:33 +08:00
|
|
|
sys::path::filename(isec->file->getName()));
|
2020-06-14 11:00:06 +08:00
|
|
|
else
|
2020-08-21 05:45:51 +08:00
|
|
|
target->prepareSymbolRelocation(s, isec, r);
|
2020-09-06 01:55:33 +08:00
|
|
|
} else {
|
|
|
|
assert(r.referent.is<InputSection *>());
|
|
|
|
if (!r.pcrel)
|
|
|
|
in.rebase->addEntry(isec, r.offset);
|
2020-05-19 06:46:33 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
void Writer::createLoadCommands() {
|
2020-09-06 01:55:33 +08:00
|
|
|
in.header->addLoadCommand(make<LCDyldInfo>(
|
|
|
|
in.rebase, in.binding, in.weakBinding, in.lazyBinding, in.exports));
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header->addLoadCommand(make<LCSymtab>(symtabSection, stringTableSection));
|
2020-09-05 09:02:07 +08:00
|
|
|
in.header->addLoadCommand(make<LCDysymtab>(indirectSymtabSection));
|
2020-08-13 10:50:28 +08:00
|
|
|
for (StringRef path : config->runtimePaths)
|
|
|
|
in.header->addLoadCommand(make<LCRPath>(path));
|
2020-04-29 07:58:22 +08:00
|
|
|
|
|
|
|
switch (config->outputType) {
|
|
|
|
case MH_EXECUTE:
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header->addLoadCommand(make<LCMain>());
|
|
|
|
in.header->addLoadCommand(make<LCLoadDylinker>());
|
2020-04-29 07:58:22 +08:00
|
|
|
break;
|
|
|
|
case MH_DYLIB:
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header->addLoadCommand(make<LCDylib>(LC_ID_DYLIB, config->installName));
|
2020-04-29 07:58:22 +08:00
|
|
|
break;
|
2020-09-01 14:23:37 +08:00
|
|
|
case MH_BUNDLE:
|
|
|
|
break;
|
2020-04-29 07:58:22 +08:00
|
|
|
default:
|
|
|
|
llvm_unreachable("unhandled output file type");
|
|
|
|
}
|
2020-04-03 02:54:05 +08:00
|
|
|
|
2020-08-15 03:35:31 +08:00
|
|
|
in.header->addLoadCommand(make<LCBuildVersion>(config->platform));
|
|
|
|
|
2020-10-15 02:03:34 +08:00
|
|
|
uuidCommand = make<LCUuid>();
|
|
|
|
in.header->addLoadCommand(uuidCommand);
|
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
uint8_t segIndex = 0;
|
2020-04-03 02:54:05 +08:00
|
|
|
for (OutputSegment *seg : outputSegments) {
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header->addLoadCommand(make<LCSegment>(seg->name, seg));
|
2020-05-06 08:25:58 +08:00
|
|
|
seg->index = segIndex++;
|
2020-04-28 03:50:59 +08:00
|
|
|
}
|
2020-04-03 02:54:05 +08:00
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
uint64_t dylibOrdinal = 1;
|
|
|
|
for (InputFile *file : inputFiles) {
|
|
|
|
if (auto *dylibFile = dyn_cast<DylibFile>(file)) {
|
2020-09-19 02:38:15 +08:00
|
|
|
// TODO: dylibs that are only referenced by weak refs should also be
|
|
|
|
// loaded via LC_LOAD_WEAK_DYLIB.
|
|
|
|
LoadCommandType lcType =
|
|
|
|
dylibFile->forceWeakImport ? LC_LOAD_WEAK_DYLIB : LC_LOAD_DYLIB;
|
|
|
|
in.header->addLoadCommand(make<LCDylib>(lcType, dylibFile->dylibName));
|
2020-04-28 03:50:59 +08:00
|
|
|
dylibFile->ordinal = dylibOrdinal++;
|
2020-04-24 11:16:49 +08:00
|
|
|
|
|
|
|
if (dylibFile->reexport)
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header->addLoadCommand(
|
2020-04-24 11:16:49 +08:00
|
|
|
make<LCDylib>(LC_REEXPORT_DYLIB, dylibFile->dylibName));
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
}
|
2020-09-22 02:04:13 +08:00
|
|
|
|
|
|
|
const uint32_t MACOS_MAXPATHLEN = 1024;
|
|
|
|
config->headerPad = std::max(
|
|
|
|
config->headerPad, (config->headerPadMaxInstallNames
|
|
|
|
? LCDylib::getInstanceCount() * MACOS_MAXPATHLEN
|
|
|
|
: 0));
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
|
2020-05-06 07:37:34 +08:00
|
|
|
static size_t getSymbolPriority(const SymbolPriorityEntry &entry,
|
|
|
|
const InputFile &file) {
|
|
|
|
return std::max(entry.objectFiles.lookup(sys::path::filename(file.getName())),
|
|
|
|
entry.anyObjectFile);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Each section gets assigned the priority of the highest-priority symbol it
|
|
|
|
// contains.
|
|
|
|
static DenseMap<const InputSection *, size_t> buildInputSectionPriorities() {
|
|
|
|
DenseMap<const InputSection *, size_t> sectionPriorities;
|
|
|
|
|
|
|
|
if (config->priorities.empty())
|
|
|
|
return sectionPriorities;
|
|
|
|
|
|
|
|
auto addSym = [&](Defined &sym) {
|
|
|
|
auto it = config->priorities.find(sym.getName());
|
|
|
|
if (it == config->priorities.end())
|
|
|
|
return;
|
|
|
|
|
|
|
|
SymbolPriorityEntry &entry = it->second;
|
|
|
|
size_t &priority = sectionPriorities[sym.isec];
|
|
|
|
priority = std::max(priority, getSymbolPriority(entry, *sym.isec->file));
|
|
|
|
};
|
|
|
|
|
|
|
|
// TODO: Make sure this handles weak symbols correctly.
|
|
|
|
for (InputFile *file : inputFiles)
|
|
|
|
if (isa<ObjFile>(file) || isa<ArchiveFile>(file))
|
2020-06-06 02:18:33 +08:00
|
|
|
for (lld::macho::Symbol *sym : file->symbols)
|
2020-05-06 07:37:34 +08:00
|
|
|
if (auto *d = dyn_cast<Defined>(sym))
|
|
|
|
addSym(*d);
|
|
|
|
|
|
|
|
return sectionPriorities;
|
|
|
|
}
|
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
static int segmentOrder(OutputSegment *seg) {
|
|
|
|
return StringSwitch<int>(seg->name)
|
|
|
|
.Case(segment_names::pageZero, -2)
|
|
|
|
.Case(segment_names::text, -1)
|
|
|
|
// Make sure __LINKEDIT is the last segment (i.e. all its hidden
|
|
|
|
// sections must be ordered after other sections).
|
|
|
|
.Case(segment_names::linkEdit, std::numeric_limits<int>::max())
|
|
|
|
.Default(0);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int sectionOrder(OutputSection *osec) {
|
|
|
|
StringRef segname = osec->parent->name;
|
|
|
|
// Sections are uniquely identified by their segment + section name.
|
|
|
|
if (segname == segment_names::text) {
|
2020-08-21 04:05:13 +08:00
|
|
|
return StringSwitch<int>(osec->name)
|
|
|
|
.Case(section_names::header, -1)
|
|
|
|
.Case(section_names::unwindInfo, std::numeric_limits<int>::max() - 1)
|
|
|
|
.Case(section_names::ehFrame, std::numeric_limits<int>::max())
|
|
|
|
.Default(0);
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
} else if (segname == segment_names::linkEdit) {
|
|
|
|
return StringSwitch<int>(osec->name)
|
2020-09-06 01:55:33 +08:00
|
|
|
.Case(section_names::rebase, -8)
|
2020-09-05 09:02:07 +08:00
|
|
|
.Case(section_names::binding, -7)
|
|
|
|
.Case(section_names::weakBinding, -6)
|
|
|
|
.Case(section_names::lazyBinding, -5)
|
|
|
|
.Case(section_names::export_, -4)
|
|
|
|
.Case(section_names::symbolTable, -3)
|
|
|
|
.Case(section_names::indirectSymbolTable, -2)
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
.Case(section_names::stringTable, -1)
|
|
|
|
.Default(0);
|
|
|
|
}
|
2020-06-16 06:00:27 +08:00
|
|
|
// ZeroFill sections must always be the at the end of their segments,
|
|
|
|
// otherwise subsequent sections may get overwritten with zeroes at runtime.
|
|
|
|
if (isZeroFill(osec->flags))
|
|
|
|
return std::numeric_limits<int>::max();
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename T, typename F>
|
|
|
|
static std::function<bool(T, T)> compareByOrder(F ord) {
|
|
|
|
return [=](T a, T b) { return ord(a) < ord(b); };
|
|
|
|
}
|
|
|
|
|
2020-05-06 07:37:34 +08:00
|
|
|
// Sorting only can happen once all outputs have been collected. Here we sort
|
|
|
|
// segments, output sections within each segment, and input sections within each
|
|
|
|
// output segment.
|
|
|
|
static void sortSegmentsAndSections() {
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
llvm::stable_sort(outputSegments,
|
|
|
|
compareByOrder<OutputSegment *>(segmentOrder));
|
2020-05-06 07:37:34 +08:00
|
|
|
|
|
|
|
DenseMap<const InputSection *, size_t> isecPriorities =
|
|
|
|
buildInputSectionPriorities();
|
|
|
|
|
|
|
|
uint32_t sectionIndex = 0;
|
|
|
|
for (OutputSegment *seg : outputSegments) {
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
seg->sortOutputSections(compareByOrder<OutputSection *>(sectionOrder));
|
|
|
|
for (auto *osec : seg->getSections()) {
|
2020-05-06 07:37:34 +08:00
|
|
|
// Now that the output sections are sorted, assign the final
|
|
|
|
// output section indices.
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
if (!osec->isHidden())
|
|
|
|
osec->index = ++sectionIndex;
|
2020-05-06 07:37:34 +08:00
|
|
|
|
|
|
|
if (!isecPriorities.empty()) {
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
if (auto *merged = dyn_cast<MergedOutputSection>(osec)) {
|
2020-05-06 07:37:34 +08:00
|
|
|
llvm::stable_sort(merged->inputs,
|
|
|
|
[&](InputSection *a, InputSection *b) {
|
|
|
|
return isecPriorities[a] > isecPriorities[b];
|
|
|
|
});
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-05-02 07:29:06 +08:00
|
|
|
void Writer::createOutputSections() {
|
|
|
|
// First, create hidden sections
|
|
|
|
stringTableSection = make<StringTableSection>();
|
2020-08-21 04:05:13 +08:00
|
|
|
unwindInfoSection = make<UnwindInfoSection>(); // TODO(gkm): only when no -r
|
2020-05-02 07:29:06 +08:00
|
|
|
symtabSection = make<SymtabSection>(*stringTableSection);
|
2020-09-05 09:02:07 +08:00
|
|
|
indirectSymtabSection = make<IndirectSymtabSection>();
|
2020-04-29 07:58:22 +08:00
|
|
|
|
|
|
|
switch (config->outputType) {
|
|
|
|
case MH_EXECUTE:
|
2020-05-02 07:29:06 +08:00
|
|
|
make<PageZeroSection>();
|
2020-04-29 07:58:22 +08:00
|
|
|
break;
|
|
|
|
case MH_DYLIB:
|
2020-09-01 14:23:37 +08:00
|
|
|
case MH_BUNDLE:
|
2020-04-29 07:58:22 +08:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unhandled output file type");
|
|
|
|
}
|
2020-04-28 03:50:59 +08:00
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
// Then merge input sections into output sections.
|
|
|
|
MapVector<std::pair<StringRef, StringRef>, MergedOutputSection *>
|
|
|
|
mergedOutputSections;
|
2020-04-28 03:50:59 +08:00
|
|
|
for (InputSection *isec : inputSections) {
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
MergedOutputSection *&osec =
|
|
|
|
mergedOutputSections[{isec->segname, isec->name}];
|
|
|
|
if (osec == nullptr)
|
|
|
|
osec = make<MergedOutputSection>(isec->name);
|
|
|
|
osec->mergeInput(isec);
|
2020-04-22 04:37:57 +08:00
|
|
|
}
|
2020-05-06 08:25:58 +08:00
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
for (const auto &it : mergedOutputSections) {
|
|
|
|
StringRef segname = it.first.first;
|
|
|
|
MergedOutputSection *osec = it.second;
|
2020-08-21 04:05:13 +08:00
|
|
|
if (unwindInfoSection && segname == segment_names::ld) {
|
|
|
|
assert(osec->name == section_names::compactUnwind);
|
|
|
|
unwindInfoSection->setCompactUnwindSection(osec);
|
|
|
|
} else
|
|
|
|
getOrCreateOutputSegment(segname)->addOutputSection(osec);
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
for (SyntheticSection *ssec : syntheticSections) {
|
|
|
|
auto it = mergedOutputSections.find({ssec->segname, ssec->name});
|
|
|
|
if (it == mergedOutputSections.end()) {
|
|
|
|
if (ssec->isNeeded())
|
|
|
|
getOrCreateOutputSegment(ssec->segname)->addOutputSection(ssec);
|
|
|
|
} else {
|
|
|
|
error("section from " + it->second->firstSection()->file->getName() +
|
|
|
|
" conflicts with synthetic section " + ssec->segname + "," +
|
|
|
|
ssec->name);
|
|
|
|
}
|
2020-05-06 08:25:58 +08:00
|
|
|
}
|
2020-04-28 03:50:59 +08:00
|
|
|
}
|
2020-04-22 04:37:57 +08:00
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
void Writer::assignAddresses(OutputSegment *seg) {
|
|
|
|
addr = alignTo(addr, PageSize);
|
|
|
|
fileOff = alignTo(fileOff, PageSize);
|
|
|
|
seg->fileOff = fileOff;
|
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
for (auto *osec : seg->getSections()) {
|
2020-07-29 00:56:55 +08:00
|
|
|
if (!osec->isNeeded())
|
|
|
|
continue;
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
addr = alignTo(addr, osec->align);
|
|
|
|
fileOff = alignTo(fileOff, osec->align);
|
|
|
|
osec->addr = addr;
|
|
|
|
osec->fileOff = isZeroFill(osec->flags) ? 0 : fileOff;
|
|
|
|
osec->finalize();
|
2020-05-02 07:29:06 +08:00
|
|
|
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
addr += osec->getSize();
|
|
|
|
fileOff += osec->getFileSize();
|
2020-04-28 03:50:59 +08:00
|
|
|
}
|
2020-04-22 04:37:57 +08:00
|
|
|
}
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
void Writer::openFile() {
|
|
|
|
Expected<std::unique_ptr<FileOutputBuffer>> bufferOrErr =
|
2020-04-28 03:50:59 +08:00
|
|
|
FileOutputBuffer::create(config->outputFile, fileOff,
|
2020-04-03 02:54:05 +08:00
|
|
|
FileOutputBuffer::F_executable);
|
|
|
|
|
|
|
|
if (!bufferOrErr)
|
|
|
|
error("failed to open " + config->outputFile + ": " +
|
|
|
|
llvm::toString(bufferOrErr.takeError()));
|
|
|
|
else
|
|
|
|
buffer = std::move(*bufferOrErr);
|
|
|
|
}
|
|
|
|
|
|
|
|
void Writer::writeSections() {
|
|
|
|
uint8_t *buf = buffer->getBufferStart();
|
[lld-macho] Refactor segment/section creation, sorting, and merging
Summary:
There were a few issues with the previous setup:
1. The section sorting comparator used a declarative map of section names to
determine the correct order, but it turns out we need to match on more than
just names -- in particular, an upcoming diff will sort based on whether the
S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but
flexible form.
2. We were sorting OutputSections stored in a MapVector, which left the
MapVector in an inconsistent state -- the wrong keys map to the wrong values!
In practice, we weren't doing key lookups (only container iteration) after the
sort, so this was fine, but it was still a dubious state of affairs. This diff
copies the OutputSections to a vector before sorting them.
3. We were adding unneeded OutputSections to OutputSegments and then filtering
them out later, which meant that we had to remember whether an OutputSegment
was in a pre- or post-filtered state. This diff only adds the sections to the
segments if they are needed.
In addition to those major changes, two minor ones worth noting:
1. I renamed all OutputSection variable names to `osec`, to parallel `isec`.
Previously we were using some inconsistent combination of `osec`, `os`, and
`section`.
2. I added a check (and a test) for InputSections with names that clashed with
those of our synthetic OutputSections.
Reviewers: #lld-macho
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81887
2020-06-15 15:03:24 +08:00
|
|
|
for (OutputSegment *seg : outputSegments)
|
|
|
|
for (OutputSection *osec : seg->getSections())
|
|
|
|
osec->writeTo(buf + osec->fileOff);
|
2020-04-03 02:54:05 +08:00
|
|
|
}
|
|
|
|
|
2020-10-15 02:03:34 +08:00
|
|
|
void Writer::writeUuid() {
|
|
|
|
MD5 hash;
|
|
|
|
const auto *bufStart = reinterpret_cast<char *>(buffer->getBufferStart());
|
|
|
|
const auto *bufEnd = reinterpret_cast<char *>(buffer->getBufferEnd());
|
|
|
|
hash.update(StringRef(bufStart, bufEnd - bufStart));
|
|
|
|
MD5::MD5Result result;
|
|
|
|
hash.final(result);
|
|
|
|
// Conform to UUID version 4 & 5 as specified in RFC 4122:
|
|
|
|
// 1. Set the version field to indicate that this is an MD5-based UUID.
|
|
|
|
result.Bytes[6] = (result.Bytes[6] & 0xf) | 0x30;
|
|
|
|
// 2. Set the two MSBs of uuid_t::clock_seq_hi_and_reserved to zero and one.
|
|
|
|
result.Bytes[8] = (result.Bytes[8] & 0x3f) | 0x80;
|
|
|
|
uuidCommand->writeUuid(result.Bytes);
|
|
|
|
}
|
|
|
|
|
2020-04-03 02:54:05 +08:00
|
|
|
void Writer::run() {
|
2020-04-28 03:50:59 +08:00
|
|
|
// dyld requires __LINKEDIT segment to always exist (even if empty).
|
2020-05-02 07:29:06 +08:00
|
|
|
OutputSegment *linkEditSegment =
|
|
|
|
getOrCreateOutputSegment(segment_names::linkEdit);
|
|
|
|
|
2020-09-18 01:20:16 +08:00
|
|
|
prepareBranchTarget(config->entry);
|
2020-05-02 07:29:06 +08:00
|
|
|
scanRelocations();
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
if (in.stubHelper->isNeeded())
|
|
|
|
in.stubHelper->setup();
|
2020-05-02 07:29:06 +08:00
|
|
|
|
2020-08-28 06:59:30 +08:00
|
|
|
for (const macho::Symbol *sym : symtab->getSymbols())
|
|
|
|
if (const auto *defined = dyn_cast<Defined>(sym))
|
|
|
|
if (defined->overridesWeakDef)
|
|
|
|
in.weakBinding->addNonWeakDefinition(defined);
|
|
|
|
|
2020-05-02 07:29:06 +08:00
|
|
|
// Sort and assign sections to their respective segments. No more sections nor
|
2020-05-06 07:37:34 +08:00
|
|
|
// segments may be created after these methods run.
|
2020-05-02 07:29:06 +08:00
|
|
|
createOutputSections();
|
2020-05-06 07:37:34 +08:00
|
|
|
sortSegmentsAndSections();
|
2020-05-02 07:29:06 +08:00
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
createLoadCommands();
|
|
|
|
|
|
|
|
// Ensure that segments (and the sections they contain) are allocated
|
|
|
|
// addresses in ascending order, which dyld requires.
|
|
|
|
//
|
|
|
|
// Note that at this point, __LINKEDIT sections are empty, but we need to
|
|
|
|
// determine addresses of other segments/sections before generating its
|
|
|
|
// contents.
|
|
|
|
for (OutputSegment *seg : outputSegments)
|
2020-05-02 07:29:06 +08:00
|
|
|
if (seg != linkEditSegment)
|
|
|
|
assignAddresses(seg);
|
2020-04-28 03:50:59 +08:00
|
|
|
|
|
|
|
// Fill __LINKEDIT contents.
|
2020-09-06 01:55:33 +08:00
|
|
|
in.rebase->finalizeContents();
|
2020-07-03 12:19:55 +08:00
|
|
|
in.binding->finalizeContents();
|
2020-08-25 12:57:59 +08:00
|
|
|
in.weakBinding->finalizeContents();
|
2020-08-28 06:54:42 +08:00
|
|
|
in.lazyBinding->finalizeContents();
|
2020-08-28 06:59:15 +08:00
|
|
|
in.exports->finalizeContents();
|
[lld-macho][reland] Add basic symbol table output
This diff implements basic support for writing a symbol table.
Attributes are loosely supported for extern symbols and not at all for
other types.
Initial version by Kellie Medlin <kelliem@fb.com>
Originally committed in a3d95a50ee33 and reverted in fbae153ca583 due to
UBSAN erroring over unaligned writes. That has been fixed in the
current diff with the following changes:
```
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -133,6 +133,9 @@ SymtabSection::SymtabSection(StringTableSection &stringTableSection)
: stringTableSection(stringTableSection) {
segname = segment_names::linkEdit;
name = section_names::symbolTable;
+ // TODO: When we introduce the SyntheticSections superclass, we should make
+ // all synthetic sections aligned to WordSize by default.
+ align = WordSize;
}
size_t SymtabSection::getSize() const {
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -371,6 +371,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
ArrayRef<InputSection *> sections = p.second;
for (InputSection *isec : sections) {
addr = alignTo(addr, isec->align);
+ // We must align the file offsets too to avoid misaligned writes of
+ // structs.
+ fileOff = alignTo(fileOff, isec->align);
isec->addr = addr;
addr += isec->getSize();
fileOff += isec->getFileSize();
@@ -396,6 +397,7 @@ void Writer::writeSections() {
uint64_t fileOff = seg->fileOff;
for (auto § : seg->getSections()) {
for (InputSection *isec : sect.second) {
+ fileOff = alignTo(fileOff, isec->align);
isec->writeTo(buf + fileOff);
fileOff += isec->getFileSize();
}
```
I don't think it's easy to write a test for alignment (that doesn't
involve brittly hard-coding file offsets), so there isn't one... but
UBSAN builds pass now.
Differential Revision: https://reviews.llvm.org/D79050
2020-04-29 07:58:19 +08:00
|
|
|
symtabSection->finalizeContents();
|
2020-09-05 09:02:07 +08:00
|
|
|
indirectSymtabSection->finalizeContents();
|
2020-04-22 04:37:57 +08:00
|
|
|
|
2020-04-28 03:50:59 +08:00
|
|
|
// Now that __LINKEDIT is filled out, do a proper calculation of its
|
2020-05-02 07:29:06 +08:00
|
|
|
// addresses and offsets.
|
|
|
|
assignAddresses(linkEditSegment);
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
openFile();
|
|
|
|
if (errorCount())
|
|
|
|
return;
|
|
|
|
|
|
|
|
writeSections();
|
2020-10-15 02:03:34 +08:00
|
|
|
writeUuid();
|
2020-04-03 02:54:05 +08:00
|
|
|
|
|
|
|
if (auto e = buffer->commit())
|
|
|
|
error("failed to write to the output file: " + toString(std::move(e)));
|
|
|
|
}
|
|
|
|
|
|
|
|
void macho::writeResult() { Writer().run(); }
|
2020-04-22 04:37:57 +08:00
|
|
|
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
void macho::createSyntheticSections() {
|
2020-07-31 05:28:41 +08:00
|
|
|
in.header = make<MachHeaderSection>();
|
2020-09-06 01:55:33 +08:00
|
|
|
in.rebase = make<RebaseSection>();
|
2020-07-03 12:19:55 +08:00
|
|
|
in.binding = make<BindingSection>();
|
2020-08-25 12:57:59 +08:00
|
|
|
in.weakBinding = make<WeakBindingSection>();
|
2020-08-28 06:54:42 +08:00
|
|
|
in.lazyBinding = make<LazyBindingSection>();
|
2020-08-28 06:59:15 +08:00
|
|
|
in.exports = make<ExportSection>();
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
in.got = make<GotSection>();
|
2020-08-13 10:50:09 +08:00
|
|
|
in.tlvPointers = make<TlvPointerSection>();
|
[lld-macho] Support calls to functions in dylibs
Summary:
This diff implements lazy symbol binding -- very similar to the PLT
mechanism in ELF.
ELF's .plt section is broken up into two sections in Mach-O:
StubsSection and StubHelperSection. Calls to functions in dylibs will
end up calling into StubsSection, which contains indirect jumps to
addresses stored in the LazyPointerSection (the counterpart to ELF's
.plt.got).
Initially, the LazyPointerSection contains addresses that point into one
of the entry points in the middle of the StubHelperSection. The code in
StubHelperSection will push on the stack an offset into the
LazyBindingSection. The push is followed by a jump to the beginning of
the StubHelperSection (similar to PLT0), which then calls into
dyld_stub_binder. dyld_stub_binder is a non-lazily bound symbol, so this
call looks it up in the GOT.
The stub binder will look up the bind opcodes in the LazyBindingSection
at the given offset. The bind opcodes will tell the binder to update the
address in the LazyPointerSection to point to the symbol, so that
subsequent calls don't have to redo the symbol resolution. The binder
will then jump to the resolved symbol.
Depends on D78269.
Reviewers: ruiu, pcc, MaskRay, smeenai, alexshap, gkm, Ktwu, christylee
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78270
2020-05-06 08:38:10 +08:00
|
|
|
in.lazyPointers = make<LazyPointerSection>();
|
|
|
|
in.stubs = make<StubsSection>();
|
|
|
|
in.stubHelper = make<StubHelperSection>();
|
|
|
|
in.imageLoaderCache = make<ImageLoaderCacheSection>();
|
|
|
|
}
|