diff options
author | dim <dim@FreeBSD.org> | 2017-09-26 19:56:36 +0000 |
---|---|---|
committer | Luiz Souza <luiz@netgate.com> | 2018-02-21 15:12:19 -0300 |
commit | 1dcd2e8d24b295bc73e513acec2ed1514bb66be4 (patch) | |
tree | 4bd13a34c251e980e1a6b13584ca1f63b0dfe670 /contrib/llvm/tools/llvm-objdump | |
parent | f45541ca2a56a1ba1202f94c080b04e96c1fa239 (diff) | |
download | FreeBSD-src-1dcd2e8d24b295bc73e513acec2ed1514bb66be4.zip FreeBSD-src-1dcd2e8d24b295bc73e513acec2ed1514bb66be4.tar.gz |
Merge clang, llvm, lld, lldb, compiler-rt and libc++ 5.0.0 release.
MFC r309126 (by emaste):
Correct lld llvm-tblgen dependency file name
MFC r309169:
Get rid of separate Subversion mergeinfo properties for llvm-dwarfdump
and llvm-lto. The mergeinfo confuses Subversion enormously, and these
directories will just use the mergeinfo for llvm itself.
MFC r312765:
Pull in r276136 from upstream llvm trunk (by Wei Mi):
Use ValueOffsetPair to enhance value reuse during SCEV expansion.
In D12090, the ExprValueMap was added to reuse existing value during
SCEV expansion. However, const folding and sext/zext distribution can
make the reuse still difficult.
A simplified case is: suppose we know S1 expands to V1 in
ExprValueMap, and
S1 = S2 + C_a
S3 = S2 + C_b
where C_a and C_b are different SCEVConstants. Then we'd like to
expand S3 as V1 - C_a + C_b instead of expanding S2 literally. It is
helpful when S2 is a complex SCEV expr and S2 has no entry in
ExprValueMap, which is usually caused by the fact that S3 is
generated from S1 after const folding.
In order to do that, we represent ExprValueMap as a mapping from SCEV
to ValueOffsetPair. We will save both S1->{V1, 0} and S2->{V1, C_a}
into the ExprValueMap when we create SCEV for V1. When S3 is
expanded, it will first expand S2 to V1 - C_a because of S2->{V1,
C_a} in the map, then expand S3 to V1 - C_a + C_b.
Differential Revision: https://reviews.llvm.org/D21313
This should fix assertion failures when building OpenCV >= 3.1.
PR: 215649
MFC r312831:
Revert r312765 for now, since it causes assertions when building
lang/spidermonkey24.
Reported by: antoine
PR: 215649
MFC r316511 (by jhb):
Add an implementation of __ffssi2() derived from __ffsdi2().
Newer versions of GCC include an __ffssi2() symbol in libgcc and the
compiler can emit calls to it in generated code. This is true for at
least GCC 6.2 when compiling world for mips and mips64.
Reviewed by: jmallett, dim
Sponsored by: DARPA / AFRL
Differential Revision: https://reviews.freebsd.org/D10086
MFC r318601 (by adrian):
[libcompiler-rt] add bswapdi2/bswapsi2
This is required for mips gcc 6.3 userland to build/run.
Reviewed by: emaste, dim
Approved by: emaste
Differential Revision: https://reviews.freebsd.org/D10838
MFC r318884 (by emaste):
lldb: map TRAP_CAP to a trace trap
In the absense of a more specific handler for TRAP_CAP (generated by
ENOTCAPABLE or ECAPMODE while in capability mode) treat it as a trace
trap.
Example usage (testing the bug in PR219173):
% proccontrol -m trapcap lldb usr.bin/hexdump/obj/hexdump -- -Cv -s 1 /bin/ls
...
(lldb) run
Process 12980 launching
Process 12980 launched: '.../usr.bin/hexdump/obj/hexdump' (x86_64)
Process 12980 stopped
* thread #1, stop reason = trace
frame #0: 0x0000004b80c65f1a libc.so.7`__sys_lseek + 10
...
In the future we should have LLDB control the trapcap procctl itself
(as it does with ASLR), as well as report a specific stop reason.
This change eliminates an assertion failure from LLDB for now.
MFC r319796:
Remove a few unneeded files from libllvm, libclang and liblldb.
MFC r319885 (by emaste):
lld: ELF: Fix ICF crash on absolute symbol relocations.
If two sections contained relocations to absolute symbols with the same
value we would crash when trying to access their sections. Add a check that
both symbols point to sections before accessing their sections, and treat
absolute symbols as equal if their values are equal.
Obtained from: LLD commit r292578
MFC r319918:
Revert r319796 for now, it can cause undefined references when linking
in some circumstances.
Reported by: Shawn Webb <shawn.webb@hardenedbsd.org>
MFC r319957 (by emaste):
lld: Add armelf emulation mode
Obtained from: LLD r305375
MFC r321369:
Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ to
5.0.0 (trunk r308421). Upstream has branched for the 5.0.0 release,
which should be in about a month. Please report bugs and regressions,
so we can get them into the release.
Please note that from 3.5.0 onwards, clang, llvm and lldb require C++11
support to build; see UPDATING for more information.
MFC r321420:
Add a few more object files to liblldb, which should solve errors when
linking the lldb executable in some cases. In particular, when the
-ffunction-sections -fdata-sections options are turned off, or
ineffective.
Reported by: Shawn Webb, Mark Millard
MFC r321433:
Cleanup stale Options.inc files from the previous libllvm build for
clang 4.0.0. Otherwise, these can get included before the two newly
generated ones (which are different) for clang 5.0.0.
Reported by: Mark Millard
MFC r321439 (by bdrewery):
Move llvm Options.inc hack from r321433 for NO_CLEAN to lib/clang/libllvm.
The files are only ever generated to .OBJDIR, not to WORLDTMP (as a
sysroot) and are only ever included from a compilation. So using
a beforebuild target here removes the file before the compilation
tries to include it.
MFC r321664:
Pull in r308891 from upstream llvm trunk (by Benjamin Kramer):
[CodeGenPrepare] Cut off FindAllMemoryUses if there are too many uses.
This avoids excessive compile time. The case I'm looking at is
Function.cpp from an old version of LLVM that still had the giant
memcmp string matcher in it. Before r308322 this compiled in about 2
minutes, after it, clang takes infinite* time to compile it. With
this patch we're at 5 min, which is still bad but this is a
pathological case.
The cut off at 20 uses was chosen by looking at other cut-offs in LLVM
for user scanning. It's probably too high, but does the job and is
very unlikely to regress anything.
Fixes PR33900.
* I'm impatient and aborted after 15 minutes, on the bug report it was
killed after 2h.
Pull in r308986 from upstream llvm trunk (by Simon Pilgrim):
[X86][CGP] Reduce memcmp() expansion to 2 load pairs (PR33914)
D35067/rL308322 attempted to support up to 4 load pairs for memcmp
inlining which resulted in regressions for some optimized libc memcmp
implementations (PR33914).
Until we can match these more optimal cases, this patch reduces the
memcmp expansion to a maximum of 2 load pairs (which matches what we
do for -Os).
This patch should be considered for the 5.0.0 release branch as well
Differential Revision: https://reviews.llvm.org/D35830
These fix a hang (or extremely long compile time) when building older
LLVM ports.
Reported by: antoine
PR: 219139
MFC r321719:
Pull in r309503 from upstream clang trunk (by Richard Smith):
PR33902: Invalidate line number cache when adding more text to
existing buffer.
This led to crashes as the line number cache would report a bogus
line number for a line of code, and we'd try to find a nonexistent
column within the line when printing diagnostics.
This fixes an assertion when building the graphics/champlain port.
Reported by: antoine, kwm
PR: 219139
MFC r321723:
Upgrade our copies of clang, llvm, lld and lldb to r309439 from the
upstream release_50 branch. This is just after upstream's 5.0.0-rc1.
MFC r322320:
Upgrade our copies of clang, llvm and libc++ to r310316 from the
upstream release_50 branch.
MFC r322326 (by emaste):
lldb: Make i386-*-freebsd expression work on JIT path
* Enable i386 ABI creation for freebsd
* Added an extra argument in ABISysV_i386::PrepareTrivialCall for mmap
syscall
* Unlike linux, the last argument of mmap is actually 64-bit(off_t).
This requires us to push an additional word for the higher order bits.
* Prior to this change, ktrace dump will show mmap failures due to
invalid argument coming from the 6th mmap argument.
Submitted by: Karnajit Wangkhem
Differential Revision: https://reviews.llvm.org/D34776
MFC r322360 (by emaste):
lldb: Report inferior signals as signals, not exceptions, on FreeBSD
This is the FreeBSD equivalent of LLVM r238549.
This serves 2 purposes:
* LLDB should handle inferior process signals SIGSEGV/SIGILL/SIGBUS/
SIGFPE the way it is suppose to be handled. Prior to this fix these
signals will neither create a coredump, nor exit from the debugger
or work for signal handling scenario.
* eInvalidCrashReason need not report "unknown crash reason" if we have
a valid si_signo
llvm.org/pr23699
Patch by Karnajit Wangkhem
Differential Revision: https://reviews.llvm.org/D35223
Submitted by: Karnajit Wangkhem
Obtained from: LLVM r310591
MFC r322474 (by emaste):
lld: Add `-z muldefs` option.
Obtained from: LLVM r310757
MFC r322740:
Upgrade our copies of clang, llvm, lld and libc++ to r311219 from the
upstream release_50 branch.
MFC r322855:
Upgrade our copies of clang, llvm, lldb and compiler-rt to r311606 from
the upstream release_50 branch.
As of this version, lib/msun's trig test should also work correctly
again (see bug 220989 for more information).
PR: 220989
MFC r323112:
Upgrade our copies of clang, llvm, lldb and compiler-rt to r312293 from
the upstream release_50 branch. This corresponds to 5.0.0 rc4.
As of this version, the cad/stepcode port should now compile in a more
reasonable time on i386 (see bug 221836 for more information).
PR: 221836
MFC r323245:
Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ to
5.0.0 release (upstream r312559).
Release notes for llvm, clang and lld will be available here soon:
<http://releases.llvm.org/5.0.0/docs/ReleaseNotes.html>
<http://releases.llvm.org/5.0.0/tools/clang/docs/ReleaseNotes.html>
<http://releases.llvm.org/5.0.0/tools/lld/docs/ReleaseNotes.html>
Relnotes: yes
(cherry picked from commit 12cd91cf4c6b96a24427c0de5374916f2808d263)
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MachODump.cpp | 626 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp | 141 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.h | 17 |
3 files changed, 530 insertions, 254 deletions
diff --git a/contrib/llvm/tools/llvm-objdump/MachODump.cpp b/contrib/llvm/tools/llvm-objdump/MachODump.cpp index 5630848..05c2c3f 100644 --- a/contrib/llvm/tools/llvm-objdump/MachODump.cpp +++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp @@ -11,12 +11,12 @@ // //===----------------------------------------------------------------------===// -#include "llvm/Object/MachO.h" #include "llvm-objdump.h" #include "llvm-c/Disassembler.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringExtras.h" #include "llvm/ADT/Triple.h" +#include "llvm/BinaryFormat/MachO.h" #include "llvm/Config/config.h" #include "llvm/DebugInfo/DIContext.h" #include "llvm/DebugInfo/DWARF/DWARFContext.h" @@ -30,6 +30,7 @@ #include "llvm/MC/MCInstrInfo.h" #include "llvm/MC/MCRegisterInfo.h" #include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Object/MachO.h" #include "llvm/Object/MachOUniversal.h" #include "llvm/Support/Casting.h" #include "llvm/Support/CommandLine.h" @@ -39,7 +40,6 @@ #include "llvm/Support/FormattedStream.h" #include "llvm/Support/GraphWriter.h" #include "llvm/Support/LEB128.h" -#include "llvm/Support/MachO.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/TargetRegistry.h" #include "llvm/Support/TargetSelect.h" @@ -68,9 +68,6 @@ static cl::opt<std::string> DSYMFile("dsym", static cl::opt<bool> FullLeadingAddr("full-leading-addr", cl::desc("Print full leading address")); -static cl::opt<bool> NoLeadingAddr("no-leading-addr", - cl::desc("Print no leading address")); - static cl::opt<bool> NoLeadingHeaders("no-leading-headers", cl::desc("Print no leading headers")); @@ -1138,11 +1135,12 @@ static void DumpInfoPlistSectionContents(StringRef Filename, DataRefImpl Ref = Section.getRawDataRefImpl(); StringRef SegName = O->getSectionFinalSegmentName(Ref); if (SegName == "__TEXT" && SectName == "__info_plist") { - outs() << "Contents of (" << SegName << "," << SectName << ") section\n"; + if (!NoLeadingHeaders) + outs() << "Contents of (" << SegName << "," << SectName << ") section\n"; StringRef BytesStr; Section.getContents(BytesStr); const char *sect = reinterpret_cast<const char *>(BytesStr.data()); - outs() << sect; + outs() << format("%.*s", BytesStr.size(), sect) << "\n"; return; } } @@ -1226,8 +1224,13 @@ static void ProcessMachO(StringRef Name, MachOObjectFile *MachOOF, if (Error Err = MachOOF->checkSymbolTable()) report_error(ArchiveName, FileName, std::move(Err), ArchitectureName); - if (Disassemble) - DisassembleMachO(FileName, MachOOF, "__TEXT", "__text"); + if (Disassemble) { + if (MachOOF->getHeader().filetype == MachO::MH_KEXT_BUNDLE && + MachOOF->getHeader().cputype == MachO::CPU_TYPE_ARM64) + DisassembleMachO(FileName, MachOOF, "__TEXT_EXEC", "__text"); + else + DisassembleMachO(FileName, MachOOF, "__TEXT", "__text"); + } if (IndirectSymbols) PrintIndirectSymbols(MachOOF, !NonVerbose); if (DataInCode) @@ -1274,7 +1277,10 @@ static void ProcessMachO(StringRef Name, MachOObjectFile *MachOOF, if (DwarfDumpType != DIDT_Null) { std::unique_ptr<DIContext> DICtx(new DWARFContextInMemory(*MachOOF)); // Dump the complete DWARF structure. - DICtx->dump(outs(), DwarfDumpType, true /* DumpEH */); + DIDumpOptions DumpOpts; + DumpOpts.DumpType = DwarfDumpType; + DumpOpts.DumpEH = true; + DICtx->dump(outs(), DumpOpts); } } @@ -1566,8 +1572,13 @@ void llvm::ParseInputMachO(StringRef Filename) { // Attempt to open the binary. Expected<OwningBinary<Binary>> BinaryOrErr = createBinary(Filename); - if (!BinaryOrErr) - report_error(Filename, BinaryOrErr.takeError()); + if (!BinaryOrErr) { + if (auto E = isNotObjectErrorInvalidFileType(BinaryOrErr.takeError())) + report_error(Filename, std::move(E)); + else + outs() << Filename << ": is not an object file\n"; + return; + } Binary &Bin = *BinaryOrErr.get().getBinary(); if (Archive *A = dyn_cast<Archive>(&Bin)) { @@ -1915,11 +1926,45 @@ static int SymbolizerGetOpInfo(void *DisInfo, uint64_t Pc, uint64_t Offset, if (Arch == Triple::x86_64) { if (Size != 1 && Size != 2 && Size != 4 && Size != 0) return 0; + // For non MH_OBJECT types, like MH_KEXT_BUNDLE, Search the external + // relocation entries of a linked image (if any) for an entry that matches + // this segment offset. if (info->O->getHeader().filetype != MachO::MH_OBJECT) { - // TODO: - // Search the external relocation entries of a fully linked image - // (if any) for an entry that matches this segment offset. - // uint64_t seg_offset = (Pc + Offset); + uint64_t seg_offset = Pc + Offset; + bool reloc_found = false; + DataRefImpl Rel; + MachO::any_relocation_info RE; + bool isExtern = false; + SymbolRef Symbol; + for (const RelocationRef &Reloc : info->O->external_relocations()) { + uint64_t RelocOffset = Reloc.getOffset(); + if (RelocOffset == seg_offset) { + Rel = Reloc.getRawDataRefImpl(); + RE = info->O->getRelocation(Rel); + // external relocation entries should always be external. + isExtern = info->O->getPlainRelocationExternal(RE); + if (isExtern) { + symbol_iterator RelocSym = Reloc.getSymbol(); + Symbol = *RelocSym; + } + reloc_found = true; + break; + } + } + if (reloc_found && isExtern) { + // The Value passed in will be adjusted by the Pc if the instruction + // adds the Pc. But for x86_64 external relocation entries the Value + // is the offset from the external symbol. + if (info->O->getAnyRelocationPCRel(RE)) + op_info->Value -= Pc + Offset + Size; + Expected<StringRef> SymName = Symbol.getName(); + if (!SymName) + report_error(info->O->getFileName(), SymName.takeError()); + const char *name = SymName->data(); + op_info->AddSymbol.Present = 1; + op_info->AddSymbol.Name = name; + return 1; + } return 0; } // In MH_OBJECT filetypes search the section's relocation entries (if any) @@ -2589,7 +2634,8 @@ static const char *get_symbol_32(uint32_t sect_offset, SectionRef S, // These are structs in the Objective-C meta data and read to produce the // comments for disassembly. While these are part of the ABI they are no -// public defintions. So the are here not in include/llvm/Support/MachO.h . +// public defintions. So the are here not in include/llvm/BinaryFormat/MachO.h +// . // The cfstring object in a 64-bit Mach-O file. struct cfstring64_t { @@ -4566,6 +4612,12 @@ static void print_class64_t(uint64_t p, struct DisassembleInfo *info) { n_value, c.superclass); if (name != nullptr) outs() << " " << name; + else { + name = get_dyld_bind_info_symbolname(S.getAddress() + + offset + offsetof(struct class64_t, superclass), info); + if (name != nullptr) + outs() << " " << name; + } outs() << "\n"; outs() << " cache " << format("0x%" PRIx64, c.cache); @@ -5269,42 +5321,70 @@ static void printObjc2_64bit_MetaData(MachOObjectFile *O, bool verbose) { SectionRef CL = get_section(O, "__OBJC2", "__class_list"); if (CL == SectionRef()) CL = get_section(O, "__DATA", "__objc_classlist"); + if (CL == SectionRef()) + CL = get_section(O, "__DATA_CONST", "__objc_classlist"); + if (CL == SectionRef()) + CL = get_section(O, "__DATA_DIRTY", "__objc_classlist"); info.S = CL; walk_pointer_list_64("class", CL, O, &info, print_class64_t); SectionRef CR = get_section(O, "__OBJC2", "__class_refs"); if (CR == SectionRef()) CR = get_section(O, "__DATA", "__objc_classrefs"); + if (CR == SectionRef()) + CR = get_section(O, "__DATA_CONST", "__objc_classrefs"); + if (CR == SectionRef()) + CR = get_section(O, "__DATA_DIRTY", "__objc_classrefs"); info.S = CR; walk_pointer_list_64("class refs", CR, O, &info, nullptr); SectionRef SR = get_section(O, "__OBJC2", "__super_refs"); if (SR == SectionRef()) SR = get_section(O, "__DATA", "__objc_superrefs"); + if (SR == SectionRef()) + SR = get_section(O, "__DATA_CONST", "__objc_superrefs"); + if (SR == SectionRef()) + SR = get_section(O, "__DATA_DIRTY", "__objc_superrefs"); info.S = SR; walk_pointer_list_64("super refs", SR, O, &info, nullptr); SectionRef CA = get_section(O, "__OBJC2", "__category_list"); if (CA == SectionRef()) CA = get_section(O, "__DATA", "__objc_catlist"); + if (CA == SectionRef()) + CA = get_section(O, "__DATA_CONST", "__objc_catlist"); + if (CA == SectionRef()) + CA = get_section(O, "__DATA_DIRTY", "__objc_catlist"); info.S = CA; walk_pointer_list_64("category", CA, O, &info, print_category64_t); SectionRef PL = get_section(O, "__OBJC2", "__protocol_list"); if (PL == SectionRef()) PL = get_section(O, "__DATA", "__objc_protolist"); + if (PL == SectionRef()) + PL = get_section(O, "__DATA_CONST", "__objc_protolist"); + if (PL == SectionRef()) + PL = get_section(O, "__DATA_DIRTY", "__objc_protolist"); info.S = PL; walk_pointer_list_64("protocol", PL, O, &info, nullptr); SectionRef MR = get_section(O, "__OBJC2", "__message_refs"); if (MR == SectionRef()) MR = get_section(O, "__DATA", "__objc_msgrefs"); + if (MR == SectionRef()) + MR = get_section(O, "__DATA_CONST", "__objc_msgrefs"); + if (MR == SectionRef()) + MR = get_section(O, "__DATA_DIRTY", "__objc_msgrefs"); info.S = MR; print_message_refs64(MR, &info); SectionRef II = get_section(O, "__OBJC2", "__image_info"); if (II == SectionRef()) II = get_section(O, "__DATA", "__objc_imageinfo"); + if (II == SectionRef()) + II = get_section(O, "__DATA_CONST", "__objc_imageinfo"); + if (II == SectionRef()) + II = get_section(O, "__DATA_DIRTY", "__objc_imageinfo"); info.S = II; print_image_info64(II, &info); } @@ -5335,75 +5415,75 @@ static void printObjc2_32bit_MetaData(MachOObjectFile *O, bool verbose) { info.adrp_addr = 0; info.adrp_inst = 0; - const SectionRef CL = get_section(O, "__OBJC2", "__class_list"); - if (CL != SectionRef()) { - info.S = CL; - walk_pointer_list_32("class", CL, O, &info, print_class32_t); - } else { - const SectionRef CL = get_section(O, "__DATA", "__objc_classlist"); - info.S = CL; - walk_pointer_list_32("class", CL, O, &info, print_class32_t); - } + SectionRef CL = get_section(O, "__OBJC2", "__class_list"); + if (CL == SectionRef()) + CL = get_section(O, "__DATA", "__objc_classlist"); + if (CL == SectionRef()) + CL = get_section(O, "__DATA_CONST", "__objc_classlist"); + if (CL == SectionRef()) + CL = get_section(O, "__DATA_DIRTY", "__objc_classlist"); + info.S = CL; + walk_pointer_list_32("class", CL, O, &info, print_class32_t); - const SectionRef CR = get_section(O, "__OBJC2", "__class_refs"); - if (CR != SectionRef()) { - info.S = CR; - walk_pointer_list_32("class refs", CR, O, &info, nullptr); - } else { - const SectionRef CR = get_section(O, "__DATA", "__objc_classrefs"); - info.S = CR; - walk_pointer_list_32("class refs", CR, O, &info, nullptr); - } + SectionRef CR = get_section(O, "__OBJC2", "__class_refs"); + if (CR == SectionRef()) + CR = get_section(O, "__DATA", "__objc_classrefs"); + if (CR == SectionRef()) + CR = get_section(O, "__DATA_CONST", "__objc_classrefs"); + if (CR == SectionRef()) + CR = get_section(O, "__DATA_DIRTY", "__objc_classrefs"); + info.S = CR; + walk_pointer_list_32("class refs", CR, O, &info, nullptr); - const SectionRef SR = get_section(O, "__OBJC2", "__super_refs"); - if (SR != SectionRef()) { - info.S = SR; - walk_pointer_list_32("super refs", SR, O, &info, nullptr); - } else { - const SectionRef SR = get_section(O, "__DATA", "__objc_superrefs"); - info.S = SR; - walk_pointer_list_32("super refs", SR, O, &info, nullptr); - } + SectionRef SR = get_section(O, "__OBJC2", "__super_refs"); + if (SR == SectionRef()) + SR = get_section(O, "__DATA", "__objc_superrefs"); + if (SR == SectionRef()) + SR = get_section(O, "__DATA_CONST", "__objc_superrefs"); + if (SR == SectionRef()) + SR = get_section(O, "__DATA_DIRTY", "__objc_superrefs"); + info.S = SR; + walk_pointer_list_32("super refs", SR, O, &info, nullptr); - const SectionRef CA = get_section(O, "__OBJC2", "__category_list"); - if (CA != SectionRef()) { - info.S = CA; - walk_pointer_list_32("category", CA, O, &info, print_category32_t); - } else { - const SectionRef CA = get_section(O, "__DATA", "__objc_catlist"); - info.S = CA; - walk_pointer_list_32("category", CA, O, &info, print_category32_t); - } + SectionRef CA = get_section(O, "__OBJC2", "__category_list"); + if (CA == SectionRef()) + CA = get_section(O, "__DATA", "__objc_catlist"); + if (CA == SectionRef()) + CA = get_section(O, "__DATA_CONST", "__objc_catlist"); + if (CA == SectionRef()) + CA = get_section(O, "__DATA_DIRTY", "__objc_catlist"); + info.S = CA; + walk_pointer_list_32("category", CA, O, &info, print_category32_t); - const SectionRef PL = get_section(O, "__OBJC2", "__protocol_list"); - if (PL != SectionRef()) { - info.S = PL; - walk_pointer_list_32("protocol", PL, O, &info, nullptr); - } else { - const SectionRef PL = get_section(O, "__DATA", "__objc_protolist"); - info.S = PL; - walk_pointer_list_32("protocol", PL, O, &info, nullptr); - } + SectionRef PL = get_section(O, "__OBJC2", "__protocol_list"); + if (PL == SectionRef()) + PL = get_section(O, "__DATA", "__objc_protolist"); + if (PL == SectionRef()) + PL = get_section(O, "__DATA_CONST", "__objc_protolist"); + if (PL == SectionRef()) + PL = get_section(O, "__DATA_DIRTY", "__objc_protolist"); + info.S = PL; + walk_pointer_list_32("protocol", PL, O, &info, nullptr); - const SectionRef MR = get_section(O, "__OBJC2", "__message_refs"); - if (MR != SectionRef()) { - info.S = MR; - print_message_refs32(MR, &info); - } else { - const SectionRef MR = get_section(O, "__DATA", "__objc_msgrefs"); - info.S = MR; - print_message_refs32(MR, &info); - } + SectionRef MR = get_section(O, "__OBJC2", "__message_refs"); + if (MR == SectionRef()) + MR = get_section(O, "__DATA", "__objc_msgrefs"); + if (MR == SectionRef()) + MR = get_section(O, "__DATA_CONST", "__objc_msgrefs"); + if (MR == SectionRef()) + MR = get_section(O, "__DATA_DIRTY", "__objc_msgrefs"); + info.S = MR; + print_message_refs32(MR, &info); - const SectionRef II = get_section(O, "__OBJC2", "__image_info"); - if (II != SectionRef()) { - info.S = II; - print_image_info32(II, &info); - } else { - const SectionRef II = get_section(O, "__DATA", "__objc_imageinfo"); - info.S = II; - print_image_info32(II, &info); - } + SectionRef II = get_section(O, "__OBJC2", "__image_info"); + if (II == SectionRef()) + II = get_section(O, "__DATA", "__objc_imageinfo"); + if (II == SectionRef()) + II = get_section(O, "__DATA_CONST", "__objc_imageinfo"); + if (II == SectionRef()) + II = get_section(O, "__DATA_DIRTY", "__objc_imageinfo"); + info.S = II; + print_image_info32(II, &info); } static bool printObjc1_32bit_MetaData(MachOObjectFile *O, bool verbose) { @@ -6597,6 +6677,12 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, if (Bytes.size() == 0) return; + // If the section has symbols but no symbol at the start of the section + // these are used to make sure the bytes before the first symbol are + // disassembled. + bool FirstSymbol = true; + bool FirstSymbolAtSectionStart = true; + // Disassemble symbol by symbol. for (unsigned SymIdx = 0; SymIdx != Symbols.size(); SymIdx++) { Expected<StringRef> SymNameOrErr = Symbols[SymIdx].getName(); @@ -6686,11 +6772,29 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, // (i.e. we're not targeting M-class) and the function is Thumb. bool UseThumbTarget = IsThumb && ThumbTarget; - outs() << SymName << ":\n"; + // If we are not specifying a symbol to start disassembly with and this + // is the first symbol in the section but not at the start of the section + // then move the disassembly index to the start of the section and + // don't print the symbol name just yet. This is so the bytes before the + // first symbol are disassembled. + uint64_t SymbolStart = Start; + if (DisSymName.empty() && FirstSymbol && Start != 0) { + FirstSymbolAtSectionStart = false; + Start = 0; + } + else + outs() << SymName << ":\n"; + DILineInfo lastLine; for (uint64_t Index = Start; Index < End; Index += Size) { MCInst Inst; + // If this is the first symbol in the section and it was not at the + // start of the section, see if we are at its Index now and if so print + // the symbol name. + if (FirstSymbol && !FirstSymbolAtSectionStart && Index == SymbolStart) + outs() << SymName << ":\n"; + uint64_t PC = SectAddress + Index; if (!NoLeadingAddr) { if (FullLeadingAddr) { @@ -6783,6 +6887,9 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, } } } + // Now that we are done disassembled the first symbol set the bool that + // were doing this to false. + FirstSymbol = false; } if (!symbolTableWorked) { // Reading the symbol table didn't work, disassemble the whole section. @@ -6793,8 +6900,10 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, MCInst Inst; uint64_t PC = SectAddress + Index; + SmallVector<char, 64> AnnotationsBytes; + raw_svector_ostream Annotations(AnnotationsBytes); if (DisAsm->getInstruction(Inst, InstSize, Bytes.slice(Index), PC, - DebugOut, nulls())) { + DebugOut, Annotations)) { if (!NoLeadingAddr) { if (FullLeadingAddr) { if (MachOOF->is64Bit()) @@ -6809,7 +6918,8 @@ static void DisassembleMachO(StringRef Filename, MachOObjectFile *MachOOF, outs() << "\t"; dumpBytes(makeArrayRef(Bytes.data() + Index, InstSize), outs()); } - IP->printInst(&Inst, outs(), "", *STI); + StringRef AnnotationsStr = Annotations.str(); + IP->printInst(&Inst, outs(), AnnotationsStr, *STI); outs() << "\n"; } else { unsigned int Arch = MachOOF->getArch(); @@ -7570,6 +7680,10 @@ static void PrintMachHeader(uint32_t magic, uint32_t cputype, outs() << " APP_EXTENSION_SAFE"; f &= ~MachO::MH_APP_EXTENSION_SAFE; } + if (f & MachO::MH_NLIST_OUTOFSYNC_WITH_DYLDINFO) { + outs() << " NLIST_OUTOFSYNC_WITH_DYLDINFO"; + f &= ~MachO::MH_NLIST_OUTOFSYNC_WITH_DYLDINFO; + } if (f != 0 || flags == 0) outs() << format(" 0x%08" PRIx32, f); } else { @@ -8169,6 +8283,51 @@ static void PrintVersionMinLoadCommand(MachO::version_min_command vd) { outs() << "\n"; } +static void PrintNoteLoadCommand(MachO::note_command Nt) { + outs() << " cmd LC_NOTE\n"; + outs() << " cmdsize " << Nt.cmdsize; + if (Nt.cmdsize != sizeof(struct MachO::note_command)) + outs() << " Incorrect size\n"; + else + outs() << "\n"; + const char *d = Nt.data_owner; + outs() << "data_owner " << format("%.16s\n", d); + outs() << " offset " << Nt.offset << "\n"; + outs() << " size " << Nt.size << "\n"; +} + +static void PrintBuildToolVersion(MachO::build_tool_version bv) { + outs() << " tool " << MachOObjectFile::getBuildTool(bv.tool) << "\n"; + outs() << " version " << MachOObjectFile::getVersionString(bv.version) + << "\n"; +} + +static void PrintBuildVersionLoadCommand(const MachOObjectFile *obj, + MachO::build_version_command bd) { + outs() << " cmd LC_BUILD_VERSION\n"; + outs() << " cmdsize " << bd.cmdsize; + if (bd.cmdsize != + sizeof(struct MachO::build_version_command) + + bd.ntools * sizeof(struct MachO::build_tool_version)) + outs() << " Incorrect size\n"; + else + outs() << "\n"; + outs() << " platform " << MachOObjectFile::getBuildPlatform(bd.platform) + << "\n"; + if (bd.sdk) + outs() << " sdk " << MachOObjectFile::getVersionString(bd.sdk) + << "\n"; + else + outs() << " sdk n/a\n"; + outs() << " minos " << MachOObjectFile::getVersionString(bd.minos) + << "\n"; + outs() << " ntools " << bd.ntools << "\n"; + for (unsigned i = 0; i < bd.ntools; ++i) { + MachO::build_tool_version bv = obj->getBuildToolVersion(i); + PrintBuildToolVersion(bv); + } +} + static void PrintSourceVersionCommand(MachO::source_version_command sd) { outs() << " cmd LC_SOURCE_VERSION\n"; outs() << " cmdsize " << sd.cmdsize; @@ -8374,6 +8533,25 @@ static void PrintRoutinesCommand64(MachO::routines_command_64 r) { outs() << " reserved6 " << r.reserved6 << "\n"; } +static void Print_x86_thread_state32_t(MachO::x86_thread_state32_t &cpu32) { + outs() << "\t eax " << format("0x%08" PRIx32, cpu32.eax); + outs() << " ebx " << format("0x%08" PRIx32, cpu32.ebx); + outs() << " ecx " << format("0x%08" PRIx32, cpu32.ecx); + outs() << " edx " << format("0x%08" PRIx32, cpu32.edx) << "\n"; + outs() << "\t edi " << format("0x%08" PRIx32, cpu32.edi); + outs() << " esi " << format("0x%08" PRIx32, cpu32.esi); + outs() << " ebp " << format("0x%08" PRIx32, cpu32.ebp); + outs() << " esp " << format("0x%08" PRIx32, cpu32.esp) << "\n"; + outs() << "\t ss " << format("0x%08" PRIx32, cpu32.ss); + outs() << " eflags " << format("0x%08" PRIx32, cpu32.eflags); + outs() << " eip " << format("0x%08" PRIx32, cpu32.eip); + outs() << " cs " << format("0x%08" PRIx32, cpu32.cs) << "\n"; + outs() << "\t ds " << format("0x%08" PRIx32, cpu32.ds); + outs() << " es " << format("0x%08" PRIx32, cpu32.es); + outs() << " fs " << format("0x%08" PRIx32, cpu32.fs); + outs() << " gs " << format("0x%08" PRIx32, cpu32.gs) << "\n"; +} + static void Print_x86_thread_state64_t(MachO::x86_thread_state64_t &cpu64) { outs() << " rax " << format("0x%016" PRIx64, cpu64.rax); outs() << " rbx " << format("0x%016" PRIx64, cpu64.rbx); @@ -8611,7 +8789,85 @@ static void PrintThreadCommand(MachO::thread_command t, const char *Ptr, const char *begin = Ptr + sizeof(struct MachO::thread_command); const char *end = Ptr + t.cmdsize; uint32_t flavor, count, left; - if (cputype == MachO::CPU_TYPE_X86_64) { + if (cputype == MachO::CPU_TYPE_I386) { + while (begin < end) { + if (end - begin > (ptrdiff_t)sizeof(uint32_t)) { + memcpy((char *)&flavor, begin, sizeof(uint32_t)); + begin += sizeof(uint32_t); + } else { + flavor = 0; + begin = end; + } + if (isLittleEndian != sys::IsLittleEndianHost) + sys::swapByteOrder(flavor); + if (end - begin > (ptrdiff_t)sizeof(uint32_t)) { + memcpy((char *)&count, begin, sizeof(uint32_t)); + begin += sizeof(uint32_t); + } else { + count = 0; + begin = end; + } + if (isLittleEndian != sys::IsLittleEndianHost) + sys::swapByteOrder(count); + if (flavor == MachO::x86_THREAD_STATE32) { + outs() << " flavor i386_THREAD_STATE\n"; + if (count == MachO::x86_THREAD_STATE32_COUNT) + outs() << " count i386_THREAD_STATE_COUNT\n"; + else + outs() << " count " << count + << " (not x86_THREAD_STATE32_COUNT)\n"; + MachO::x86_thread_state32_t cpu32; + left = end - begin; + if (left >= sizeof(MachO::x86_thread_state32_t)) { + memcpy(&cpu32, begin, sizeof(MachO::x86_thread_state32_t)); + begin += sizeof(MachO::x86_thread_state32_t); + } else { + memset(&cpu32, '\0', sizeof(MachO::x86_thread_state32_t)); + memcpy(&cpu32, begin, left); + begin += left; + } + if (isLittleEndian != sys::IsLittleEndianHost) + swapStruct(cpu32); + Print_x86_thread_state32_t(cpu32); + } else if (flavor == MachO::x86_THREAD_STATE) { + outs() << " flavor x86_THREAD_STATE\n"; + if (count == MachO::x86_THREAD_STATE_COUNT) + outs() << " count x86_THREAD_STATE_COUNT\n"; + else + outs() << " count " << count + << " (not x86_THREAD_STATE_COUNT)\n"; + struct MachO::x86_thread_state_t ts; + left = end - begin; + if (left >= sizeof(MachO::x86_thread_state_t)) { + memcpy(&ts, begin, sizeof(MachO::x86_thread_state_t)); + begin += sizeof(MachO::x86_thread_state_t); + } else { + memset(&ts, '\0', sizeof(MachO::x86_thread_state_t)); + memcpy(&ts, begin, left); + begin += left; + } + if (isLittleEndian != sys::IsLittleEndianHost) + swapStruct(ts); + if (ts.tsh.flavor == MachO::x86_THREAD_STATE32) { + outs() << "\t tsh.flavor x86_THREAD_STATE32 "; + if (ts.tsh.count == MachO::x86_THREAD_STATE32_COUNT) + outs() << "tsh.count x86_THREAD_STATE32_COUNT\n"; + else + outs() << "tsh.count " << ts.tsh.count + << " (not x86_THREAD_STATE32_COUNT\n"; + Print_x86_thread_state32_t(ts.uts.ts32); + } else { + outs() << "\t tsh.flavor " << ts.tsh.flavor << " tsh.count " + << ts.tsh.count << "\n"; + } + } else { + outs() << " flavor " << flavor << " (unknown)\n"; + outs() << " count " << count << "\n"; + outs() << " state (unknown)\n"; + begin += count * sizeof(uint32_t); + } + } + } else if (cputype == MachO::CPU_TYPE_X86_64) { while (begin < end) { if (end - begin > (ptrdiff_t)sizeof(uint32_t)) { memcpy((char *)&flavor, begin, sizeof(uint32_t)); @@ -9014,6 +9270,13 @@ static void PrintLoadCommands(const MachOObjectFile *Obj, uint32_t filetype, Command.C.cmd == MachO::LC_VERSION_MIN_WATCHOS) { MachO::version_min_command Vd = Obj->getVersionMinLoadCommand(Command); PrintVersionMinLoadCommand(Vd); + } else if (Command.C.cmd == MachO::LC_NOTE) { + MachO::note_command Nt = Obj->getNoteLoadCommand(Command); + PrintNoteLoadCommand(Nt); + } else if (Command.C.cmd == MachO::LC_BUILD_VERSION) { + MachO::build_version_command Bv = + Obj->getBuildVersionLoadCommand(Command); + PrintBuildVersionLoadCommand(Obj, Bv); } else if (Command.C.cmd == MachO::LC_SOURCE_VERSION) { MachO::source_version_command Sd = Obj->getSourceVersionCommand(Command); PrintSourceVersionCommand(Sd); @@ -9123,6 +9386,22 @@ void llvm::printMachOLoadCommands(const object::ObjectFile *Obj) { //===----------------------------------------------------------------------===// void llvm::printMachOExportsTrie(const object::MachOObjectFile *Obj) { + uint64_t BaseSegmentAddress = 0; + for (const auto &Command : Obj->load_commands()) { + if (Command.C.cmd == MachO::LC_SEGMENT) { + MachO::segment_command Seg = Obj->getSegmentLoadCommand(Command); + if (Seg.fileoff == 0 && Seg.filesize != 0) { + BaseSegmentAddress = Seg.vmaddr; + break; + } + } else if (Command.C.cmd == MachO::LC_SEGMENT_64) { + MachO::segment_command_64 Seg = Obj->getSegment64LoadCommand(Command); + if (Seg.fileoff == 0 && Seg.filesize != 0) { + BaseSegmentAddress = Seg.vmaddr; + break; + } + } + } for (const llvm::object::ExportEntry &Entry : Obj->exports()) { uint64_t Flags = Entry.flags(); bool ReExport = (Flags & MachO::EXPORT_SYMBOL_FLAGS_REEXPORT); @@ -9136,7 +9415,7 @@ void llvm::printMachOExportsTrie(const object::MachOObjectFile *Obj) { outs() << "[re-export] "; else outs() << format("0x%08llX ", - Entry.address()); // FIXME:add in base address + Entry.address() + BaseSegmentAddress); outs() << Entry.name(); if (WeakDef || ThreadLocal || Resolver || Abs) { bool NeedsComma = false; @@ -9182,117 +9461,21 @@ void llvm::printMachOExportsTrie(const object::MachOObjectFile *Obj) { // rebase table dumping //===----------------------------------------------------------------------===// -namespace { -class SegInfo { -public: - SegInfo(const object::MachOObjectFile *Obj); - - StringRef segmentName(uint32_t SegIndex); - StringRef sectionName(uint32_t SegIndex, uint64_t SegOffset); - uint64_t address(uint32_t SegIndex, uint64_t SegOffset); - bool isValidSegIndexAndOffset(uint32_t SegIndex, uint64_t SegOffset); - -private: - struct SectionInfo { - uint64_t Address; - uint64_t Size; - StringRef SectionName; - StringRef SegmentName; - uint64_t OffsetInSegment; - uint64_t SegmentStartAddress; - uint32_t SegmentIndex; - }; - const SectionInfo &findSection(uint32_t SegIndex, uint64_t SegOffset); - SmallVector<SectionInfo, 32> Sections; -}; -} - -SegInfo::SegInfo(const object::MachOObjectFile *Obj) { - // Build table of sections so segIndex/offset pairs can be translated. - uint32_t CurSegIndex = Obj->hasPageZeroSegment() ? 1 : 0; - StringRef CurSegName; - uint64_t CurSegAddress; - for (const SectionRef &Section : Obj->sections()) { - SectionInfo Info; - error(Section.getName(Info.SectionName)); - Info.Address = Section.getAddress(); - Info.Size = Section.getSize(); - Info.SegmentName = - Obj->getSectionFinalSegmentName(Section.getRawDataRefImpl()); - if (!Info.SegmentName.equals(CurSegName)) { - ++CurSegIndex; - CurSegName = Info.SegmentName; - CurSegAddress = Info.Address; - } - Info.SegmentIndex = CurSegIndex - 1; - Info.OffsetInSegment = Info.Address - CurSegAddress; - Info.SegmentStartAddress = CurSegAddress; - Sections.push_back(Info); - } -} - -StringRef SegInfo::segmentName(uint32_t SegIndex) { - for (const SectionInfo &SI : Sections) { - if (SI.SegmentIndex == SegIndex) - return SI.SegmentName; - } - llvm_unreachable("invalid segIndex"); -} - -bool SegInfo::isValidSegIndexAndOffset(uint32_t SegIndex, - uint64_t OffsetInSeg) { - for (const SectionInfo &SI : Sections) { - if (SI.SegmentIndex != SegIndex) - continue; - if (SI.OffsetInSegment > OffsetInSeg) - continue; - if (OffsetInSeg >= (SI.OffsetInSegment + SI.Size)) - continue; - return true; - } - return false; -} - -const SegInfo::SectionInfo &SegInfo::findSection(uint32_t SegIndex, - uint64_t OffsetInSeg) { - for (const SectionInfo &SI : Sections) { - if (SI.SegmentIndex != SegIndex) - continue; - if (SI.OffsetInSegment > OffsetInSeg) - continue; - if (OffsetInSeg >= (SI.OffsetInSegment + SI.Size)) - continue; - return SI; - } - llvm_unreachable("segIndex and offset not in any section"); -} - -StringRef SegInfo::sectionName(uint32_t SegIndex, uint64_t OffsetInSeg) { - return findSection(SegIndex, OffsetInSeg).SectionName; -} - -uint64_t SegInfo::address(uint32_t SegIndex, uint64_t OffsetInSeg) { - const SectionInfo &SI = findSection(SegIndex, OffsetInSeg); - return SI.SegmentStartAddress + OffsetInSeg; -} - -void llvm::printMachORebaseTable(const object::MachOObjectFile *Obj) { - // Build table of sections so names can used in final output. - SegInfo sectionTable(Obj); - +void llvm::printMachORebaseTable(object::MachOObjectFile *Obj) { outs() << "segment section address type\n"; - for (const llvm::object::MachORebaseEntry &Entry : Obj->rebaseTable()) { - uint32_t SegIndex = Entry.segmentIndex(); - uint64_t OffsetInSeg = Entry.segmentOffset(); - StringRef SegmentName = sectionTable.segmentName(SegIndex); - StringRef SectionName = sectionTable.sectionName(SegIndex, OffsetInSeg); - uint64_t Address = sectionTable.address(SegIndex, OffsetInSeg); + Error Err = Error::success(); + for (const llvm::object::MachORebaseEntry &Entry : Obj->rebaseTable(Err)) { + StringRef SegmentName = Entry.segmentName(); + StringRef SectionName = Entry.sectionName(); + uint64_t Address = Entry.address(); // Table lines look like: __DATA __nl_symbol_ptr 0x0000F00C pointer outs() << format("%-8s %-18s 0x%08" PRIX64 " %s\n", SegmentName.str().c_str(), SectionName.str().c_str(), Address, Entry.typeName().str().c_str()); } + if (Err) + report_error(Obj->getFileName(), std::move(Err)); } static StringRef ordinalName(const object::MachOObjectFile *Obj, int Ordinal) { @@ -9320,18 +9503,15 @@ static StringRef ordinalName(const object::MachOObjectFile *Obj, int Ordinal) { // bind table dumping //===----------------------------------------------------------------------===// -void llvm::printMachOBindTable(const object::MachOObjectFile *Obj) { +void llvm::printMachOBindTable(object::MachOObjectFile *Obj) { // Build table of sections so names can used in final output. - SegInfo sectionTable(Obj); - outs() << "segment section address type " "addend dylib symbol\n"; - for (const llvm::object::MachOBindEntry &Entry : Obj->bindTable()) { - uint32_t SegIndex = Entry.segmentIndex(); - uint64_t OffsetInSeg = Entry.segmentOffset(); - StringRef SegmentName = sectionTable.segmentName(SegIndex); - StringRef SectionName = sectionTable.sectionName(SegIndex, OffsetInSeg); - uint64_t Address = sectionTable.address(SegIndex, OffsetInSeg); + Error Err = Error::success(); + for (const llvm::object::MachOBindEntry &Entry : Obj->bindTable(Err)) { + StringRef SegmentName = Entry.segmentName(); + StringRef SectionName = Entry.sectionName(); + uint64_t Address = Entry.address(); // Table lines look like: // __DATA __got 0x00012010 pointer 0 libSystem ___stack_chk_guard @@ -9346,24 +9526,22 @@ void llvm::printMachOBindTable(const object::MachOObjectFile *Obj) { << left_justify(ordinalName(Obj, Entry.ordinal()), 16) << " " << Entry.symbolName() << Attr << "\n"; } + if (Err) + report_error(Obj->getFileName(), std::move(Err)); } //===----------------------------------------------------------------------===// // lazy bind table dumping //===----------------------------------------------------------------------===// -void llvm::printMachOLazyBindTable(const object::MachOObjectFile *Obj) { - // Build table of sections so names can used in final output. - SegInfo sectionTable(Obj); - +void llvm::printMachOLazyBindTable(object::MachOObjectFile *Obj) { outs() << "segment section address " "dylib symbol\n"; - for (const llvm::object::MachOBindEntry &Entry : Obj->lazyBindTable()) { - uint32_t SegIndex = Entry.segmentIndex(); - uint64_t OffsetInSeg = Entry.segmentOffset(); - StringRef SegmentName = sectionTable.segmentName(SegIndex); - StringRef SectionName = sectionTable.sectionName(SegIndex, OffsetInSeg); - uint64_t Address = sectionTable.address(SegIndex, OffsetInSeg); + Error Err = Error::success(); + for (const llvm::object::MachOBindEntry &Entry : Obj->lazyBindTable(Err)) { + StringRef SegmentName = Entry.segmentName(); + StringRef SectionName = Entry.sectionName(); + uint64_t Address = Entry.address(); // Table lines look like: // __DATA __got 0x00012010 libSystem ___stack_chk_guard @@ -9373,30 +9551,28 @@ void llvm::printMachOLazyBindTable(const object::MachOObjectFile *Obj) { << left_justify(ordinalName(Obj, Entry.ordinal()), 16) << " " << Entry.symbolName() << "\n"; } + if (Err) + report_error(Obj->getFileName(), std::move(Err)); } //===----------------------------------------------------------------------===// // weak bind table dumping //===----------------------------------------------------------------------===// -void llvm::printMachOWeakBindTable(const object::MachOObjectFile *Obj) { - // Build table of sections so names can used in final output. - SegInfo sectionTable(Obj); - +void llvm::printMachOWeakBindTable(object::MachOObjectFile *Obj) { outs() << "segment section address " "type addend symbol\n"; - for (const llvm::object::MachOBindEntry &Entry : Obj->weakBindTable()) { + Error Err = Error::success(); + for (const llvm::object::MachOBindEntry &Entry : Obj->weakBindTable(Err)) { // Strong symbols don't have a location to update. if (Entry.flags() & MachO::BIND_SYMBOL_FLAGS_NON_WEAK_DEFINITION) { outs() << " strong " << Entry.symbolName() << "\n"; continue; } - uint32_t SegIndex = Entry.segmentIndex(); - uint64_t OffsetInSeg = Entry.segmentOffset(); - StringRef SegmentName = sectionTable.segmentName(SegIndex); - StringRef SectionName = sectionTable.sectionName(SegIndex, OffsetInSeg); - uint64_t Address = sectionTable.address(SegIndex, OffsetInSeg); + StringRef SegmentName = Entry.segmentName(); + StringRef SectionName = Entry.sectionName(); + uint64_t Address = Entry.address(); // Table lines look like: // __DATA __data 0x00001000 pointer 0 _foo @@ -9407,6 +9583,8 @@ void llvm::printMachOWeakBindTable(const object::MachOObjectFile *Obj) { << format_decimal(Entry.addend(), 8) << " " << Entry.symbolName() << "\n"; } + if (Err) + report_error(Obj->getFileName(), std::move(Err)); } // get_dyld_bind_info_symbolname() is used for disassembly and passed an @@ -9417,17 +9595,15 @@ static const char *get_dyld_bind_info_symbolname(uint64_t ReferenceValue, struct DisassembleInfo *info) { if (info->bindtable == nullptr) { info->bindtable = llvm::make_unique<SymbolAddressMap>(); - SegInfo sectionTable(info->O); - for (const llvm::object::MachOBindEntry &Entry : info->O->bindTable()) { - uint32_t SegIndex = Entry.segmentIndex(); - uint64_t OffsetInSeg = Entry.segmentOffset(); - if (!sectionTable.isValidSegIndexAndOffset(SegIndex, OffsetInSeg)) - continue; - uint64_t Address = sectionTable.address(SegIndex, OffsetInSeg); + Error Err = Error::success(); + for (const llvm::object::MachOBindEntry &Entry : info->O->bindTable(Err)) { + uint64_t Address = Entry.address(); StringRef name = Entry.symbolName(); if (!name.empty()) (*info->bindtable)[Address] = name; } + if (Err) + report_error(info->O->getFileName(), std::move(Err)); } auto name = info->bindtable->lookup(ReferenceValue); return !name.empty() ? name.data() : nullptr; diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp index 8373f0c..74593e6 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -41,6 +41,7 @@ #include "llvm/Object/ELFObjectFile.h" #include "llvm/Object/MachO.h" #include "llvm/Object/ObjectFile.h" +#include "llvm/Object/Wasm.h" #include "llvm/Support/Casting.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" @@ -158,6 +159,8 @@ cl::opt<bool> llvm::NoShowRawInsn("no-show-raw-insn", cl::desc("When disassembling " "instructions, do not print " "the instruction bytes.")); +cl::opt<bool> +llvm::NoLeadingAddr("no-leading-addr", cl::desc("Print no leading address")); cl::opt<bool> llvm::UnwindInfo("unwind-info", cl::desc("Display unwind information")); @@ -213,6 +216,8 @@ cl::opt<unsigned long long> cl::value_desc("address"), cl::init(UINT64_MAX)); static StringRef ToolName; +typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy; + namespace { typedef std::function<bool(llvm::object::SectionRef const &)> FilterPredicate; @@ -357,7 +362,16 @@ static const Target *getTarget(const ObjectFile *Obj = nullptr) { llvm::Triple TheTriple("unknown-unknown-unknown"); if (TripleName.empty()) { if (Obj) { - TheTriple.setArch(Triple::ArchType(Obj->getArch())); + auto Arch = Obj->getArch(); + TheTriple.setArch(Triple::ArchType(Arch)); + + // For ARM targets, try to use the build attributes to build determine + // the build target. Target features are also added, but later during + // disassembly. + if (Arch == Triple::arm || Arch == Triple::armeb) { + Obj->setARMSubArch(TheTriple); + } + // TheTriple defaults to ELF, and COFF doesn't have an environment: // the best we can do here is indicate that it is mach-o. if (Obj->isMachO()) @@ -369,8 +383,16 @@ static const Target *getTarget(const ObjectFile *Obj = nullptr) { TheTriple.setTriple("thumbv7-windows"); } } - } else + } else { TheTriple.setTriple(Triple::normalize(TripleName)); + // Use the triple, but also try to combine with ARM build attributes. + if (Obj) { + auto Arch = Obj->getArch(); + if (Arch == Triple::arm || Arch == Triple::armeb) { + Obj->setARMSubArch(TheTriple); + } + } + } // Get the target specific parser. std::string Error; @@ -464,10 +486,13 @@ void SourcePrinter::printSourceLine(raw_ostream &OS, uint64_t Address, auto FileBuffer = SourceCache.find(LineInfo.FileName); if (FileBuffer != SourceCache.end()) { auto LineBuffer = LineCache.find(LineInfo.FileName); - if (LineBuffer != LineCache.end()) + if (LineBuffer != LineCache.end()) { + if (LineInfo.Line > LineBuffer->second.size()) + return; // Vector begins at 0, line numbers are non-zero OS << Delimiter << LineBuffer->second[LineInfo.Line - 1].ltrim() << "\n"; + } } } OldLineInfo = LineInfo; @@ -491,7 +516,8 @@ public: MCSubtargetInfo const &STI, SourcePrinter *SP) { if (SP && (PrintSource || PrintLines)) SP->printSourceLine(OS, Address); - OS << format("%8" PRIx64 ":", Address); + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address); if (!NoShowRawInsn) { OS << "\t"; dumpBytes(Bytes, OS); @@ -509,7 +535,8 @@ public: raw_ostream &OS) { uint32_t opcode = (Bytes[3] << 24) | (Bytes[2] << 16) | (Bytes[1] << 8) | Bytes[0]; - OS << format("%8" PRIx64 ":", Address); + if (!NoLeadingAddr) + OS << format("%8" PRIx64 ":", Address); if (!NoShowRawInsn) { OS << "\t"; dumpBytes(Bytes.slice(0, 4), OS); @@ -570,6 +597,9 @@ public: void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes, uint64_t Address, raw_ostream &OS, StringRef Annot, MCSubtargetInfo const &STI, SourcePrinter *SP) override { + if (SP && (PrintSource || PrintLines)) + SP->printSourceLine(OS, Address); + if (!MI) { OS << " <unknown>"; return; @@ -601,7 +631,8 @@ public: MCSubtargetInfo const &STI, SourcePrinter *SP) override { if (SP && (PrintSource || PrintLines)) SP->printSourceLine(OS, Address); - OS << format("%8" PRId64 ":", Address / 8); + if (!NoLeadingAddr) + OS << format("%8" PRId64 ":", Address / 8); if (!NoShowRawInsn) { OS << "\t"; dumpBytes(Bytes, OS); @@ -839,7 +870,10 @@ static void printRelocationTargetName(const MachOObjectFile *O, bool isExtern = O->getPlainRelocationExternal(RE); uint64_t Val = O->getPlainRelocationSymbolNum(RE); - if (isExtern) { + if (O->getAnyRelocationType(RE) == MachO::ARM64_RELOC_ADDEND) { + fmt << format("0x%0" PRIx64, Val); + return; + } else if (isExtern) { symbol_iterator SI = O->symbol_begin(); advance(SI, Val); Expected<StringRef> SOrErr = SI->getName(); @@ -856,6 +890,18 @@ static void printRelocationTargetName(const MachOObjectFile *O, fmt << S; } +static std::error_code getRelocationValueString(const WasmObjectFile *Obj, + const RelocationRef &RelRef, + SmallVectorImpl<char> &Result) { + const wasm::WasmRelocation& Rel = Obj->getWasmRelocation(RelRef); + std::string fmtbuf; + raw_string_ostream fmt(fmtbuf); + fmt << Rel.Index << (Rel.Addend < 0 ? "" : "+") << Rel.Addend; + fmt.flush(); + Result.append(fmtbuf.begin(), fmtbuf.end()); + return std::error_code(); +} + static std::error_code getRelocationValueString(const MachOObjectFile *Obj, const RelocationRef &RelRef, SmallVectorImpl<char> &Result) { @@ -989,7 +1035,7 @@ static std::error_code getRelocationValueString(const MachOObjectFile *Obj, case MachO::ARM_RELOC_HALF_SECTDIFF: { // Half relocations steal a bit from the length field to encode // whether this is an upper16 or a lower16 relocation. - bool isUpper = Obj->getAnyRelocationLength(RE) >> 1; + bool isUpper = (Obj->getAnyRelocationLength(RE) & 0x1) == 1; if (isUpper) fmt << ":upper16:("; @@ -1041,8 +1087,11 @@ static std::error_code getRelocationValueString(const RelocationRef &Rel, return getRelocationValueString(ELF, Rel, Result); if (auto *COFF = dyn_cast<COFFObjectFile>(Obj)) return getRelocationValueString(COFF, Rel, Result); - auto *MachO = cast<MachOObjectFile>(Obj); - return getRelocationValueString(MachO, Rel, Result); + if (auto *Wasm = dyn_cast<WasmObjectFile>(Obj)) + return getRelocationValueString(Wasm, Rel, Result); + if (auto *MachO = dyn_cast<MachOObjectFile>(Obj)) + return getRelocationValueString(MachO, Rel, Result); + llvm_unreachable("unknown object file format"); } /// @brief Indicates whether this relocation should hidden when listing @@ -1091,6 +1140,52 @@ static uint8_t getElfSymbolType(const ObjectFile *Obj, const SymbolRef &Sym) { llvm_unreachable("Unsupported binary format"); } +template <class ELFT> static void +addDynamicElfSymbols(const ELFObjectFile<ELFT> *Obj, + std::map<SectionRef, SectionSymbolsTy> &AllSymbols) { + for (auto Symbol : Obj->getDynamicSymbolIterators()) { + uint8_t SymbolType = Symbol.getELFType(); + if (SymbolType != ELF::STT_FUNC || Symbol.getSize() == 0) + continue; + + Expected<uint64_t> AddressOrErr = Symbol.getAddress(); + if (!AddressOrErr) + report_error(Obj->getFileName(), AddressOrErr.takeError()); + uint64_t Address = *AddressOrErr; + + Expected<StringRef> Name = Symbol.getName(); + if (!Name) + report_error(Obj->getFileName(), Name.takeError()); + if (Name->empty()) + continue; + + Expected<section_iterator> SectionOrErr = Symbol.getSection(); + if (!SectionOrErr) + report_error(Obj->getFileName(), SectionOrErr.takeError()); + section_iterator SecI = *SectionOrErr; + if (SecI == Obj->section_end()) + continue; + + AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType); + } +} + +static void +addDynamicElfSymbols(const ObjectFile *Obj, + std::map<SectionRef, SectionSymbolsTy> &AllSymbols) { + assert(Obj->isELF()); + if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj)) + addDynamicElfSymbols(Elf32LEObj, AllSymbols); + else if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj)) + addDynamicElfSymbols(Elf64LEObj, AllSymbols); + else if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj)) + addDynamicElfSymbols(Elf32BEObj, AllSymbols); + else if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj)) + addDynamicElfSymbols(Elf64BEObj, AllSymbols); + else + llvm_unreachable("Unsupported binary format"); +} + static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { if (StartAddress > StopAddress) error("Start address should be less than stop address"); @@ -1165,7 +1260,6 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { // Create a mapping from virtual address to symbol name. This is used to // pretty print the symbols while disassembling. - typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy; std::map<SectionRef, SectionSymbolsTy> AllSymbols; for (const SymbolRef &Symbol : Obj->symbols()) { Expected<uint64_t> AddressOrErr = Symbol.getAddress(); @@ -1193,6 +1287,8 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType); } + if (AllSymbols.empty() && Obj->isELF()) + addDynamicElfSymbols(Obj, AllSymbols); // Create a mapping from virtual address to section. std::vector<std::pair<uint64_t, SectionRef>> SectionAddresses; @@ -1811,9 +1907,9 @@ void llvm::printExportsTrie(const ObjectFile *o) { } } -void llvm::printRebaseTable(const ObjectFile *o) { +void llvm::printRebaseTable(ObjectFile *o) { outs() << "Rebase table:\n"; - if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) + if (MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) printMachORebaseTable(MachO); else { errs() << "This operation is only currently supported " @@ -1822,9 +1918,9 @@ void llvm::printRebaseTable(const ObjectFile *o) { } } -void llvm::printBindTable(const ObjectFile *o) { +void llvm::printBindTable(ObjectFile *o) { outs() << "Bind table:\n"; - if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) + if (MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) printMachOBindTable(MachO); else { errs() << "This operation is only currently supported " @@ -1833,9 +1929,9 @@ void llvm::printBindTable(const ObjectFile *o) { } } -void llvm::printLazyBindTable(const ObjectFile *o) { +void llvm::printLazyBindTable(ObjectFile *o) { outs() << "Lazy bind table:\n"; - if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) + if (MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) printMachOLazyBindTable(MachO); else { errs() << "This operation is only currently supported " @@ -1844,9 +1940,9 @@ void llvm::printLazyBindTable(const ObjectFile *o) { } } -void llvm::printWeakBindTable(const ObjectFile *o) { +void llvm::printWeakBindTable(ObjectFile *o) { outs() << "Weak bind table:\n"; - if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) + if (MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o)) printMachOWeakBindTable(MachO); else { errs() << "This operation is only currently supported " @@ -1944,7 +2040,7 @@ static void printPrivateFileHeaders(const ObjectFile *o, bool onlyFirst) { report_error(o->getFileName(), "Invalid/Unsupported object file format"); } -static void DumpObject(const ObjectFile *o, const Archive *a = nullptr) { +static void DumpObject(ObjectFile *o, const Archive *a = nullptr) { StringRef ArchiveName = a != nullptr ? a->getFileName() : ""; // Avoid other output when using a raw option. if (!RawClangAST) { @@ -1987,7 +2083,10 @@ static void DumpObject(const ObjectFile *o, const Archive *a = nullptr) { if (DwarfDumpType != DIDT_Null) { std::unique_ptr<DIContext> DICtx(new DWARFContextInMemory(*o)); // Dump the complete DWARF structure. - DICtx->dump(outs(), DwarfDumpType, true /* DumpEH */); + DIDumpOptions DumpOpts; + DumpOpts.DumpType = DwarfDumpType; + DumpOpts.DumpEH = true; + DICtx->dump(outs(), DumpOpts); } } diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h index dace82a..2fcd506 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h @@ -35,6 +35,7 @@ extern cl::list<std::string> FilterSections; extern cl::opt<bool> Disassemble; extern cl::opt<bool> DisassembleAll; extern cl::opt<bool> NoShowRawInsn; +extern cl::opt<bool> NoLeadingAddr; extern cl::opt<bool> PrivateHeaders; extern cl::opt<bool> FirstPrivateHeader; extern cl::opt<bool> ExportsTrie; @@ -69,10 +70,10 @@ void ParseInputMachO(StringRef Filename); void printCOFFUnwindInfo(const object::COFFObjectFile* o); void printMachOUnwindInfo(const object::MachOObjectFile* o); void printMachOExportsTrie(const object::MachOObjectFile* o); -void printMachORebaseTable(const object::MachOObjectFile* o); -void printMachOBindTable(const object::MachOObjectFile* o); -void printMachOLazyBindTable(const object::MachOObjectFile* o); -void printMachOWeakBindTable(const object::MachOObjectFile* o); +void printMachORebaseTable(object::MachOObjectFile* o); +void printMachOBindTable(object::MachOObjectFile* o); +void printMachOLazyBindTable(object::MachOObjectFile* o); +void printMachOWeakBindTable(object::MachOObjectFile* o); void printELFFileHeader(const object::ObjectFile *o); void printCOFFFileHeader(const object::ObjectFile *o); void printCOFFSymbolTable(const object::COFFImportFile *i); @@ -81,10 +82,10 @@ void printMachOFileHeader(const object::ObjectFile *o); void printMachOLoadCommands(const object::ObjectFile *o); void printWasmFileHeader(const object::ObjectFile *o); void printExportsTrie(const object::ObjectFile *o); -void printRebaseTable(const object::ObjectFile *o); -void printBindTable(const object::ObjectFile *o); -void printLazyBindTable(const object::ObjectFile *o); -void printWeakBindTable(const object::ObjectFile *o); +void printRebaseTable(object::ObjectFile *o); +void printBindTable(object::ObjectFile *o); +void printLazyBindTable(object::ObjectFile *o); +void printWeakBindTable(object::ObjectFile *o); void printRawClangAST(const object::ObjectFile *o); void PrintRelocations(const object::ObjectFile *o); void PrintSectionHeaders(const object::ObjectFile *o); |