Since OPT_UNKNOWN args never have any values and consist only of
spelling (and are never aliased), this doesn't make any difference in
practice, but it's more consistent with Arg's guidance to use
getAsString() for diagnostics, and it matches what clang does.
Also tweak two tests to use an unknown option that contains '=' for
additional coverage while here. (The new tests pass fine with the old
code too though.)
llvm-svn: 365200
This fixes an 8-year-old regression. r105763 made it so that aliases
always refer to the unaliased option – but it missed the "joined" branch
of JoinedOrSeparate flags. (r162231 then made the Args classes
non-virtual, and r169344 moved them from clang to llvm.)
Back then, there was no JoinedOrSeparate flag that was an alias, so it
wasn't observable. Now /U in CLCompatOptions is a JoinedOrSeparate alias
in clang, and warn_slash_u_filename incorrectly used the aliased arg id
(using the unaliased one isn't really a regression since that warning
checks if the undefined macro contains slash or backslash and only then
emits the warning – and no valid use will pass "-Ufoo/bar" or similar).
Also, lld has many JoinedOrSeparate aliases, and due to this bug it had
to explicitly call `getUnaliasedOption()` in a bunch of places, even
though that shouldn't be necessary by design. After this fix in Option,
these calls really don't have an effect any more, so remove them.
No intended behavior change.
(I accidentally fixed this bug while working on PR29106 but then
wondered why the warn_slash_u_filename broke. When I figured it out, I
thought it would make sense to land this in a separate commit.)
Differential Revision: https://reviews.llvm.org/D64156
llvm-svn: 365186
The difference from D63432/r365015 is that this patch does not place
SHF_STRINGS sections with different alignments into the same
MergeSyntheticSection. Doing that would:
(1) create unnecessary padding and thus waste space.
Add a test tail-merge-string-align2.s to check no extra padding is created.
(2) make some input sections unaligned when tail merge (-O2) is enabled.
The alignment of MergeTailAlignment::Builder was out of sync in D63432.
MOVAPS on such unaligned strings can raise SIGSEGV.
This should fix PR42289: the Linux kernel has a use case that input
files have .rodata.cst32 sections with different alignments. The
expectation (and what ld.bfd and gold do) is that in the -r link, there
is only one .rodata.cst32 (SHF_MERGE sections with different alignments
can be combined), but lld currently creates one for each different
alignment.
The current merging strategy:
1) Group SHF_MERGE sections by (name, sh_flags, sh_entsize and
sh_addralign). Merging is performed among a group, even if -O0 is specified.
2) Create one output section for each group. This is a special case in
addInputSec().
This patch changes 1) to:
1) Group SHF_MERGE sections by (name, sh_flags, sh_entsize).
Merging is performed among a group, even if -O0 is specified.
We will thus create just one .rodata.cst32 . This also improves merging
efficiency when sections with the same name but different alignments are
combined.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D64200
llvm-svn: 365139
If %t1.o has a weak reference on foo, and %t2.so has a non-weak
reference on foo: `ld.lld %t1.o %t2.so -o %t`
We incorrectly set the binding of the undefined foo to STB_GLOBAL.
Fix this by ignoring undefined symbols in a SharedFile for Undefined and
SharedSymbol.
This fixes the binding of pthread_once when the program links against
both librt.so and libpthread.so
```
a.o: STB_WEAK reference to pthread_once
librt.so: STB_GLOBAL reference to pthread_once # should be ignored
libstdc++.so: STB_WEAK reference to pthread_once # should be ignored
libgcc_s.so.1: STB_WEAK reference to pthread_once # should be ignored
```
The STB_GLOBAL pthread_once issue (not fixed by D63974) can cause a link error when the result
DSO is used to link another DSO with -z defs if -lpthread is not specified. (libstdc++.so.6 not having a dependency on libpthread.so is a really nasty hack...)
We happened to create a weak undef before D63974 because libgcc_s.so.1
was linked the last and it changed the binding again to weak.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D64136
llvm-svn: 365129
The referenced symbol is expected to point to an R_RISCV_*_HI20
relocation. An absolute symbol has no associated section, therefore
there cannot be a matching R_RISCV_*_HI20.
This fixes the crash reported by PR42038. For reference, ld.bfd errors:
(.init+0x4): dangerous relocation: %pcrel_lo missing matching %pcrel_hi
Differential Revision: https://reviews.llvm.org/D63273
llvm-svn: 365049
This reverts r365015.
David Zarzycki reported this change broke stage2 and stage3 tests. The
root cause is still not very clear, but I guess some SHF_MERGE sections
with the same name have different alignments. They were not merged
before but were merged after r365015.
Something that assumes address uniqueness of such mergeable data caused
the bug.
llvm-svn: 365048
gcc may generate .debug_info/.debug_aranges/.debug_line/etc that are
relocated by R_RISCV_ADD*/R_RISCV_SUB* pairs.
Allow R_RISCV_ADD in non-SHF_ALLOC section to fix link errors like:
ld.lld: error: print.c:(.debug_frame+0x60): has non-ABS relocation R_RISCV_ADD64 against symbol '.L0 '
Differential Revision: https://reviews.llvm.org/D63259
llvm-svn: 365035
This should fix PR42289: the Linux kernel has a use case that input
files have .rodata.cst32 sections with different alignments. The
expectation (and what ld.bfd and gold do) is that in the -r link, there
is only one .rodata.cst32 (SHF_MERGE sections with different alignments
can be combined), but lld currently creates one for each different
alignment.
The current merging strategy:
1) Group SHF_MERGE sections by (name, sh_flags, sh_entsize and
sh_addralign). String merging is performed among a group, even if -O0 is specified.
2) Create one output section for each group. This is a special case in
addInputSec().
This patch changes 1) to:
1) Group SHF_MERGE sections by (name, sh_flags, sh_entsize).
String merging is performed among a group, even if -O0 is specified.
We will thus create just one .rodata.cst32 . This also improves merging
efficiency when sections with the same name but different alignments are
combined.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63432
llvm-svn: 365015
Some variables in lld have the same name as functions ignoring case.
This patch gives them different names, so that my next patch is easier
to read.
llvm-svn: 365003
This matches the wasm lld and GNU ld behavior.
The ELF linker has special handling for bitcode archives but if that
doesn't kick in we probably want to error out rather than silently
ignore the library.
Differential Revision: https://reviews.llvm.org/D63781
llvm-svn: 364998
Add Triple::riscv64 and Triple::riscv32 to getBitcodeMachineKind for get right
e_machine during LTO.
Reviewed By: ruiu, MaskRay
Differential Revision: https://reviews.llvm.org/D52165
llvm-svn: 364996
Fixes PR42442
t.o has a STB_GLOBAL undef ref to f
t2.so has a STB_WEAK undef ref to f
t1.so defines f
ld.lld t.o t1.so t2.so currently sets the binding of `f` to STB_WEAK.
This is not correct because there exists a STB_GLOBAL undef ref from a
regular object. The problem is that resolveUndefined() doesn't check
if the undef ref is seen for the first time:
if (isShared() || isLazy() || (isUndefined() && Other.Binding != STB_WEAK))
Binding = Other.Binding;
The isShared() condition should be `isShared() && !Referenced`
where Referenced is set to true after an undef ref is seen.
In practice, when linking a pthread program with glibc:
// a.o
#include <pthread.h>
pthread_mutex_t mu = PTHREAD_MUTEX_INITIALIZER;
int main() { pthread_mutex_unlock(&mu); }
{clang,gcc} -fuse-ld=lld a.o -lpthread # libpthread.so is linked before libgcc_s.so.1
The weak undef pthread_mutex_unlock in libgcc_s.so.1 makes the result
weak, which diverges from GNU linkers where STB_DEFAULT is used:
23: 0000000000000000 0 FUNC WEAK DEFAULT UND pthread_mutex_lock
(Note, if -pthread is used instead, libpthread.so will be linked **after**
libgcc_s.so.1 . lld sets the binding to the expected STB_GLOBAL)
Similar linking sequences (ld.lld t.o t1.so t2.so) appear to be used by
Go, which cause a build error https://github.com/golang/go/issues/31912.
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D63974
llvm-svn: 364913
RISC-V psABI doesn't specify TLS relaxation. It can be handled the same
way as we handle ARM TLS. RISC-V TLS is even simpler because GD/LD use
the same relocation type.
Reviewed By: jrtc27, ruiu
Differential Revision: https://reviews.llvm.org/D63220
llvm-svn: 364813
* Handle initial relocation types: R_RISCV_CALL_PLT and R_RISCV_GOT_HI20.
* Produce dynamic relocation types: R_RISCV_COPY, R_RISCV_RELATIVE, R_RISCV_JUMP_SLOT.
* Define SymbolRel as R_RISCV_{32,64}
* Generate PLT header: it is used by lazy binding PLT in glibc.
* R_RISCV_CALL is changed from R_PC to R_PC_PLT. If the target symbol is preemptable, this will suppress an unnecessary "canonical PLT".
This behavior is different from ld.bfd but it is agreed the current lld behavior is favored.
I have received positive responses from the binutils maintainer that the ABI/binutils implementation can be improved, see:
https://github.com/riscv/riscv-elf-psabi-doc/issues/98https://sourceware.org/bugzilla/show_bug.cgi?id=24685
Many -no-pie/-pie/-shared programs linked against musl or glibc should work with this patch.
Reviewed By: jrtc27
Differential Revision: https://reviews.llvm.org/D63076
llvm-svn: 364812
If .rela.plt is mentioned in a linker script, it might be preserved
even if it is empty. In that case, LLD created DT_JMPREL and DT_PLTGOT
dynamic tags. When the tags exist, a dynamic loader writes values into
reserved slots in .got.plt to support lazy symbol resolution.
The problem is that, in fact, the linker has not reserved that space,
and the writing may occur into the memory allocated for something else.
Differential Revision: https://reviews.llvm.org/D63869
llvm-svn: 364639
This restores r361830 "[ELF] Error on relocations to STT_SECTION symbols if the sections were discarded"
and dependent commits (r362218, r362497) which were reverted by r364321, with a fix of a --gdb-index issue.
.rela.debug_ranges contains relocations of range list entries:
// start address of a range list entry
// old: 0; after r361830: 0
00000000000033a0 R_X86_64_64 .text._ZN2v88internal7Isolate7factoryEv + 0
// end address of a range list entry
// old: 0xe; after r361830: 0
00000000000033a8 R_X86_64_64 .text._ZN2v88internal7Isolate7factoryEv + e
If both start and end addresses of a range list entry resolve to 0,
DWARFDebugRangeList::isEndOfListEntry() will return true, then the
.debug_range decoding loop will terminate prematurely:
while (true) {
decode StartAddress
decode EndAddress
if (Entry.isEndOfListEntry()) // prematurely
break;
Entries.push_back(Entry);
}
In lld/ELF/SyntheticSections.cpp, readAddressAreas() will read
incomplete address ranges and the resulting .gdb_index will be
incomplete. For files that gdb hasn't loaded their debug info, gdb uses
.gdb_index to map addresses to CUs. The absent entries make gdb fail to
symbolize some addresses.
To address this issue, we simply allow relocations to undefined symbols
in DWARF.cpp:findAux() and let RelocationResolver resolve them.
This patch should fix:
[1] http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20190603/659848.html
[2] https://bugs.chromium.org/p/chromium/issues/detail?id=978067
llvm-svn: 364391
(In effect, reverting "[ELF] Error on relocations to STT_SECTION symbols if the sections were discarded".)
It caused debug info problems in LibreOffice [1] and Chromium/V8 [2].
Reverting until those can be fixed.
It also reverts r362497 "STT_SECTION symbol should be defined" on .eh_frame, .debug*, .zdebug* and .gcc_except_table"
which was landed as a follow-up to the above.
> With -r or --emit-relocs, we warn `STT_SECTION symbol should be defined`
> on relocations to discarded section symbol. This was added as an error
> in rLLD319404, but was not so effective before D61583 (it turned the
> error to a warning).
>
> Relocations from .eh_frame .debug* .zdebug* .gcc_except_table to
> discarded .text are very common and somewhat expected. Don't warn/error
> on them. As a reference, ld.bfd has a similar logic in
> _bfd_elf_default_action_discarded() to allow these cases.
>
> Delete invalid-undef-section-symbol.test because what it intended to
> check is now covered by the updated comdat-discarded-reloc.s
>
> Delete relocatable-eh-frame.s because we allow relocations from
> .eh_frame as a special case now.
And finally it reverts r362218 "[ELF] Replace a dead test in getSymVA() with assert()"
as that also depended on the main change reverted here.
> Symbols relative to discarded comdat sections are Undefined instead of
> Defined now (after D59649 and D61583). The `== &InputSection::Discarded`
> test becomes dead. I cannot find a test related to this behavior.
[1] http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20190603/659848.html
[2] https://bugs.chromium.org/p/chromium/issues/detail?id=978067
llvm-svn: 364321
r360841 introduced CommonSymbol class. An unintended behavioral change
introduced by that change was that common symbols are not internalized
by LTO under some condition. This patch fixes that issue.
The issue occurred under the following condition:
1. There exists a common symbol
2. At least one DSO is given to lld or -pie is used
If the above conditions are met, Symbol::includeInDynsym() returned a
wrong value for a common symbol.
Fixes https://bugs.llvm.org/show_bug.cgi?id=41978
Differential Revision: https://reviews.llvm.org/D63752
llvm-svn: 364273
Similar to R_AARCH64_ABS32, R_PPC64_ADDR32 can represent either a signed
value or unsigned value, thus we should use `[-2**(n-1), 2**n)` instead of
`[-2**(n-1), 2**(n-1))` to check overflows.
The issue manifests as a bogus linker error when linking the powerpc64le Linux kernel.
The new behavior is compatible with ld.bfd's complain_overflow_bitfield.
The upper bound of the error message is not correct. Fix it as well.
The changes to R_PPC_ADDR16, R_PPC64_ADDR16, R_X86_64_8 and R_X86_64_16 are similar.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63690
llvm-svn: 364164
Summary:
Our rule to create R_*_RELATIVE for absolute relocation types were
loose. D63121 made it stricter but it failed to create R_*_RELATIVE for
R_ARM_TARGET1 and R_PPC64_TOC. rLLD363236 worked around that by
reinstating the original behavior for ARM and PPC64.
This patch is an attempt to simplify the logic.
Note, in ld.bfd, R_ARM_TARGET2 --target2=abs also creates
R_ARM_RELATIVE. This seems a very uncommon scenario (moreover,
--target2=got-rel is the default), so I do not implement any logic
related to it.
Also, delete R_AARCH64_ABS32 from AArch64::getDynRel. We don't have
working ILP32 support yet. Allowing it would create an incorrect
R_AARCH64_RELATIVE.
For MIPS, the (if SymbolRel, then RelativeRel) code is to keep its
behavior unchanged.
Note, in ppc64-abs64-dyn.s, R_PPC64_TOC gets an incorrect addend because
computeAddend() doesn't compute the correct address. We seem to have the
wrong behavior for a long time. The important thing seems that a dynamic
relocation R_PPC64_TOC should not be created as the dynamic loader will
error R_PPC64_TOC is not supported.
Reviewers: atanasyan, grimar, peter.smith, ruiu, sfertile, espindola
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63383
llvm-svn: 363928
ARM and RISC-V do not support TLS relaxations. However, for General
Dynamic and Local Dynamic models, if we are producing an executable and
the symbol is non-preemptable, we know it must be defined and the
R_ARM_TLS_DTPMOD32/R_RISCV_TLS_DTPMOD{32,64} dynamic relocation can be
omitted because it is always 1. This may be necessary for static linking
as DTPMOD may not be expected at load time.
Merge handleARMTlsRelocation() into handleTlsRelocation(). This requires
more logic to R_TLSGD_PC and R_TLSLD_PC. Because we use SymbolicRel to
resolve the relocation at link time, R_ARM_TLS_DTPMOD32 can be deleted
from relocateOne(). It cannot be used as a static relocation type.
As a bonus, the additional logic in R_TLSGD_PC code can be shared by the
TLS support for RISC-V (D63220).
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63333
llvm-svn: 363927
Use -fsave-optimization-record=<format> to specify a different format
than the default, which is YAML.
For now, only YAML is supported.
llvm-svn: 363573
In processRelocAux(), our handling of 1) link-time constant and 2) weak
undef is the same, so put them together to simplify the logic.
This moves the weak undef code around. The result is that: in a writable
section (or -z notext), we will no longer emit dynamic relocations for
weak undefined symbols.
The new behavior seems to match GNU linkers, and improves consistency
with the case of a readonly section.
The condition `!Config->Shared` was there probably because it is common
for a -shared link not to specify full dependencies. Keep it now but we
may revisit the decision in the future.
gABI says:
> The behavior of weak symbols in areas not specified by this document is
> implementation defined. Weak symbols are intended primarily for use in
> system software. Applications using weak symbols are unreliable since
> changes in the runtime environment might cause the execution to fail.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63003
llvm-svn: 363399
This patch adds new command line option `--undefined-glob` to lld.
That option is a variant of `--undefined` but accepts wildcard
patterns so that all symbols that match with a given pattern are
handled as if they were given by `-u`.
`-u foo` is to force resolve symbol foo if foo is not a defined symbol
and there's a static archive that contains a definition of symbol foo.
Now, you can specify a wildcard pattern as an argument for `--undefined-glob`.
So, if you want to include all JNI symbols (which start with "Java_"), you
can do that by passing `--undefined-glob "Java_*"` to the linker, for example.
In this patch, I use the same glob pattern matcher as the version script
processor is using, so it does not only support `*` but also `?` and `[...]`.
Differential Revision: https://reviews.llvm.org/D63244
llvm-svn: 363396
If .sdata is absent, linker synthesized __global_pointer$ gets a section index of SHN_ABS.
(ld.bfd has a similar issue: binutils PR24678)
Scrt1.o may use `lla gp, __global_pointer$` to reference the symbol PC
relatively. In -pie/-shared mode, lld complains if a PC relative
relocation references an absolute symbol (SHN_ABS) but ld.bfd doesn't:
ld.lld: error: relocation R_RISCV_PCREL_HI20 cannot refer to lute symbol: __global_pointer$
Let the reference of __global_pointer$ to force creation of .sdata to
fix the problem. This is similar to _GLOBAL_OFFSET_TABLE_, which forces
creation of .got or .got.plt .
Also, change the visibility from STV_HIDDEN to STV_DEFAULT and don't
define the symbol for -shared. This matches ld.bfd, though I don't
understand why it uses STV_DEFAULT.
Reviewed By: ruiu, jrtc27
Differential Revision: https://reviews.llvm.org/D63132
llvm-svn: 363351
R_RISCV_{ADD,SET,SUB}* are used for local label computation.
Add a new RelExpr member R_RISCV_ADD to represent them.
R_RISCV_ADD is treated as a link-time constant because otherwise
R_RISCV_{ADD,SET,SUB}* are not allowed in -pie/-shared mode.
In glibc Scrt1.o, .rela.eh_frame contains such relocations.
Because .eh_frame is not writable, we get this error:
ld.lld: error: can't create dynamic relocation R_RISCV_ADD32 against symbol: .L0 in readonly segment; recompil object files with -fPIC or pass '-Wl,-z,notext' to allow text relocations in the output
>>> defined in ..../riscv64-linux-gnu/lib/Scrt1.o
With D63076 and this patch, I can run -pie/-shared programs linked against glibc.
Note llvm-mc cannot currently produce R_RISCV_SET* so they are not tested.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63183
llvm-svn: 363128
Summary:
clang (as of 2019-06-12) / gcc (as of 8.2.1) PPC64 may emit a .rela.toc
which references an embedded switch table in a discarded .rodata/.text
section. The .toc and the .rela.toc are incorrectly not placed in the
comdat.
Technically a relocation from outside the group is not allowed by the ELF spec:
> A symbol table entry with STB_LOCAL binding that is defined relative
> to one of a group's sections, and that is contained in a symbol table
> section that is not part of the group, must be discarded if the group
> members are discarded. References to this symbol table entry from
> outside the group are not allowed.
Don't report errors to work around the bug.
This should fix the ppc64le-lld-multistage-test bot while linking llvm-tblgen:
ld.lld: error: relocation refers to a discarded section: .rodata._ZNK4llvm3MVT13getSizeInBitsEv
>>> defined in utils/TableGen/CMakeFiles/llvm-tblgen.dir/CodeGenRegisters.cpp.o
>>> referenced by CodeGenRegisters.cpp
>>> utils/TableGen/CMakeFiles/llvm-tblgen.dir/CodeGenRegisters.cpp.o:(.toc+0x0)
Some other PPC specific sections may have similar problems. We can blacklist more
section names when problems occur.
// A simple program that reproduces the bug.
// Note .rela.toc (outside the group) references a section symbol (STB_LOCAL) in a group.
void puts(const char *);
struct A {
void foo(int a) {
switch (a) {
case 0: puts("0"); break;
case 1: puts("1"); puts("1"); break;
case 2: puts("2"); break;
case 3: puts("3"); puts("4"); break;
case 4: puts("4"); break;
case 5: puts("5"); puts("5"); break;
case 6: puts("6"); break;
}
}
int a;
};
void foo(A x) { x.foo(x.a); }
Reviewers: ruiu, sfertile, espindola
Reviewed By: ruiu
Subscribers: emaste, nemanjai, arichardson, kbarton, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63182
llvm-svn: 363126
This reverts commit r363060 and restores r362867.
r362867 is innocent. The ppc64le-lld-multistage-test bot failure was due to a clang/gcc .toc bug:
ld.lld: error: relocation refers to a discarded section: .rodata._ZNK4llvm3MVT13getSizeInBitsEv
>>> defined in utils/TableGen/CMakeFiles/llvm-tblgen.dir/CodeGenRegisters.cpp.o
>>> referenced by CodeGenRegisters.cpp
>>> utils/TableGen/CMakeFiles/llvm-tblgen.dir/CodeGenRegisters.cpp.o:(.toc+0x0)
It will be worked around by D63182.
llvm-svn: 363124
So that R_RISCV_PCREL_LO12_[IS] are considered as link-time constants in
-pie mode, otherwise there are bogus errors:
ld.lld: error: can't create dynamic relocation R_RISCV_PCREL_LO12_I against symbol: .L0 in readonly segment; recompile object files with -fPIC or pass '-Wl,-z,notext' to allow text relocations in the output
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63123
llvm-svn: 363064
The current rule is loose: `!Sym.IsPreemptible || Expr == R_GOT`.
When the symbol is non-preemptable, this allows absolute relocation
types with smaller numbers of bits, e.g. R_X86_64_{8,16,32}. They are
disallowed by ld.bfd and gold, e.g.
ld.bfd: a.o: relocation R_X86_64_8 against `.text' can not be used when making a shared object; recompile with -fPIC
This patch:
a) Add TargetInfo::SymbolicRel to represent relocation types that resolve to a
symbol value (e.g. R_AARCH_ABS64, R_386_32, R_X86_64_64).
As a side benefit, we currently (ab)use GotRel (R_*_GLOB_DAT) to resolve
GOT slots that are link-time constants. Since we now use Target->SymbolRel
to do the job, we can remove R_*_GLOB_DAT from relocateOne() for all targets.
R_*_GLOB_DAT cannot be used as static relocation types.
b) Change the condition to `!Sym.IsPreemptible && Type != Target->SymbolicRel || Expr == R_GOT`.
Some tests are caught by the improved error checking (ld.bfd/gold also
issue errors on them). Many misuse .long where .quad should be used
instead.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63121
llvm-svn: 363059
Otherwise the getPartition() accessor may return an OOB pointer. Found
using _GLIBCXX_DEBUG.
The error is benign (we never dereference the pointer for the end marker)
so this wasn't caught by e.g. the sanitizer bots.
llvm-svn: 363026
I've change the variable names used in PPC64.cpp from "Instr" to "Insn"
because "Insn" is a more common abbreviation for "instruction".
While changing PPC64.cpp relocateOne(), make R_PPC64_ADDR16_LO{_DS}
slightly more efficient by saving a read and a write for the TocOptimize
case.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D63043
llvm-svn: 362867
We create several types of synthetic sections for loadable partitions, including:
- The dynamic symbol table. This allows code outside of the loadable partitions
to find entry points with dlsym.
- Creating a dynamic symbol table also requires the creation of several other
synthetic sections for the partition, such as the dynamic table and hash table
sections.
- The partition's ELF header is represented as a synthetic section in the
combined output file, and will be used by llvm-objcopy to extract partitions.
Differential Revision: https://reviews.llvm.org/D62350
llvm-svn: 362819
Branch Target Identification (BTI) and Pointer Authentication (PAC) are
architecture features introduced in v8.5a and 8.3a respectively. The new
instructions have been added in the hint space so that binaries take
advantage of support where it exists yet still run on older hardware. The
impact of each feature is:
BTI: For executable pages that have been guarded, all indirect branches
must have a destination that is a BTI instruction of the appropriate type.
For the static linker, this means that PLT entries must have a "BTI c" as
the first instruction in the sequence. BTI is an all or nothing
property for a link unit, any indirect branch not landing on a valid
destination will cause a Branch Target Exception.
PAC: The dynamic loader encodes with PACIA the address of the destination
that the PLT entry will load from the .plt.got, placing the result in a
subset of the top-bits that are not valid virtual addresses. The PLT entry
may authenticate these top-bits using the AUTIA instruction before
branching to the destination. Use of PAC in PLT sequences is a contract
between the dynamic loader and the static linker, it is independent of
whether the relocatable objects use PAC.
BTI and PAC are independent features that can be combined. So we can have
several combinations of PLT:
- Standard with no BTI or PAC
- BTI PLT with "BTI c" as first instruction.
- PAC PLT with "AUTIA1716" before the indirect branch to X17.
- BTIPAC PLT with "BTI c" as first instruction and "AUTIA1716" before the
first indirect branch to X17.
The use of BTI and PAC in relocatable object files are encoded by feature
bits in the .note.gnu.property section in a similar way to Intel CET. There
is one AArch64 specific program property GNU_PROPERTY_AARCH64_FEATURE_1_AND
and two target feature bits defined:
- GNU_PROPERTY_AARCH64_FEATURE_1_BTI
-- All executable sections are compatible with BTI.
- GNU_PROPERTY_AARCH64_FEATURE_1_PAC
-- All executable sections have return address signing enabled.
Due to the properties of FEATURE_1_AND the static linker can tell when all
input relocatable objects have the BTI and PAC feature bits set. The static
linker uses this to enable the appropriate PLT sequence.
Neither -> standard PLT
GNU_PROPERTY_AARCH64_FEATURE_1_BTI -> BTI PLT
GNU_PROPERTY_AARCH64_FEATURE_1_PAC -> PAC PLT
Both properties -> BTIPAC PLT
In addition to the .note.gnu.properties there are two new command line
options:
--force-bti : Act as if all relocatable inputs had
GNU_PROPERTY_AARCH64_FEATURE_1_BTI and warn for every relocatable object
that does not.
--pac-plt : Act as if all relocatable inputs had
GNU_PROPERTY_AARCH64_FEATURE_1_PAC. As PAC is a contract between the loader
and static linker no warning is given if it is not present in an input.
Two processor specific dynamic tags are used to communicate that a non
standard PLT sequence is being used.
DTI_AARCH64_BTI_PLT and DTI_AARCH64_BTI_PAC.
Differential Revision: https://reviews.llvm.org/D62609
llvm-svn: 362793
It was added by D46654 but is actually never used.
R_PPC64_CALL_PLT (was: R_PPC_CALL_PLT) is a static link-time constant.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62994
llvm-svn: 362788
Many -static/-no-pie/-shared/-pie applications linked against glibc or musl
should work with this patch. This also helps FreeBSD PowerPC64 to migrate
their lib32 (PR40888).
* Fix default image base and max page size.
* Support new-style Secure PLT (see below). Old-style BSS PLT is not
implemented, so it is not suitable for FreeBSD rtld now because it doesn't
support Secure PLT yet.
* Support more initial relocation types:
R_PPC_ADDR32, R_PPC_REL16*, R_PPC_LOCAL24PC, R_PPC_PLTREL24, and R_PPC_GOT16.
The addend of R_PPC_PLTREL24 is special: it decides the call stub PLT type
but it should be ignored for the computation of target symbol VA.
* Support GNU ifunc
* Support .glink used for lazy PLT resolution in glibc
* Add a new thunk type: PPC32PltCallStub that is similar to PPC64PltCallStub.
It is used by R_PPC_REL24 and R_PPC_PLTREL24.
A PLT stub used in -fPIE/-fPIC usually loads an address relative to
.got2+0x8000 (-fpie/-fpic code uses _GLOBAL_OFFSET_TABLE_ relative
addresses).
Two .got2 sections in two object files have different addresses, thus a PLT stub
can't be shared by two object files. To handle this incompatibility,
change the parameters of Thunk::isCompatibleWith to
`const InputSection &, const Relocation &`.
PowerPC psABI specified an old-style .plt (BSS PLT) that is both
writable and executable. Linkers don't make separate RW- and RWE segments,
which causes all initially writable memory (think .data) executable.
This is a big security concern so a new PLT scheme (secure PLT) was developed to
address the security issue.
TLS will be implemented in D62940.
glibc older than ~2012 requires .rela.dyn to include .rela.plt, it can
not handle the DT_RELA+DT_RELASZ == DT_JMPREL case correctly. A hack
(not included in this patch) in LinkerScript.cpp addOrphanSections() to
work around the issue:
if (Config->EMachine == EM_PPC) {
// Older glibc assumes .rela.dyn includes .rela.plt
Add(In.RelaDyn);
if (In.RelaPlt->isLive() && !In.RelaPlt->Parent)
In.RelaDyn->getParent()->addSection(In.RelaPlt);
}
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62464
llvm-svn: 362721
Any symbols defined in the LTO object are by definition the ones we
want in the final output so we skip the comdat group checking in those
cases.
This change makes the ELF code more explicit about this and means
that wasm and ELF do this in the same way.
Differential Revision: https://reviews.llvm.org/D62884
llvm-svn: 362625
Although many relocatable objects will have a single
GNU_PROPERTY_X86_FEATURE_1_AND in the .note.gnu.property section it is
permissible to have more than one, and there are tests in ld.bfd that use
it. The behavior that ld.bfd follows is to set the feature bit for a
relocatable object if any of the GNU_PROPERTY_X86_FEATURE_1_AND
have the feature bit set.
Differential Revision: https://reviews.llvm.org/D62862
llvm-svn: 362591
Summary:
With -r or --emit-relocs, we warn `STT_SECTION symbol should be defined`
on relocations to discarded section symbol. This was added as an error
in rLLD319404, but was not so effective before D61583 (it turned the
error to a warning).
Relocations from .eh_frame .debug* .zdebug* .gcc_except_table to
discarded .text are very common and somewhat expected. Don't warn/error
on them. As a reference, ld.bfd has a similar logic in
_bfd_elf_default_action_discarded() to allow these cases.
Delete invalid-undef-section-symbol.test because what it intended to
check is now covered by the updated comdat-discarded-reloc.s
Delete relocatable-eh-frame.s because we allow relocations from
.eh_frame as a special case now.
Reviewers: grimar, phosek, ruiu, espindola
Reviewed By: ruiu
Subscribers: emaste, arichardson, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62840
llvm-svn: 362497
We currently (ab)use the Live bit on output sections to track whether
the section has ever had an input section added to it, and then later
use it during orphan placement. This will conflict with one of my upcoming
partition-related changes that will assign all output sections to a partition
(thus marking them as live) so that they can be added to the correct segment
by the code that creates program headers.
Instead of using the Live bit for this purpose, create a new flag and
start using it to track the property explicitly.
Differential Revision: https://reviews.llvm.org/D62348
llvm-svn: 362444
The following abstract relocation types (RelExpr) are PPC64 ELFv2 ABI specific,
not used by PPC32. So rename them to prevent confusion when the PPC32 port is improved.
* R_PPC_CALL R_PPC_CALL_PLT:
R_PPC_CALL_PLT represents R_PPC64_REL14 and R_PPC64_REL24.
If the function is not preemptable, R_PPC_CALL_PLT can be optimized to R_PPC_CALL:
the formula adjusts the symbol VA from the global entry point to the local entry point.
* R_PPC_TOC: represents R_PPC64_TOC. We don't have a test. Add one to ppc64-relocs.s
Rename it to R_PPC64_TOCBASE because `@tocbase` is the assembly form.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62800
llvm-svn: 362359
In ELF v2 ABI, R_PPC64_GOT_DTPREL16* are not relaxed.
This family of relocation types are used for variables outside of 2GiB
of the TLS block. 2 instructions cannot materialize a DTPREL offset that
is not 32-bit.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62737
llvm-svn: 362357
Fixes the remaining issue of PR41673 after D61186: with `/DISCARD/ { ... } :NONE`,
we may create an output section named `/DISCARD/`.
Note, if an input section is named `/DISCARD/`, ld.bfd discards it but
lld keeps it. It is probably not worth copying this behavior as it is unrealistic.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62768
llvm-svn: 362356
(1) {gcc,clang} -fuse-ld=bfd -pie -fPIE -nostdlib a.c => .interp created
(2) {gcc,clang} -fuse-ld=lld -pie -fPIE -nostdlib a.c => .interp not created
(3) {gcc,clang} -fuse-ld=lld -pie -fPIE -nostdlib a.c a.so => .interp created
The inconsistency of (2) is due to the condition `!Config->SharedFiles.empty()`.
To make lld behave more like ld.bfd, we could change the condition to:
Config->HasDynSymTab && !Config->DynamicLinker.empty() && Script->needsInterpSection();
However, that would bring another inconsistency as can be observed with:
(4) {gcc,clang} -fuse-ld=bfd -no-pie -nostdlib a.c => .interp not created
So instead, use `!Config->DynamicLinker.empty() && Script->needsInterpSection()`,
which is both simple and consistent in these cases.
The inconsistency of (4) likely originated from ld.bfd and gold's choice to have a default --dynamic-linker.
Their condition to create .interp is ANDed with (not -shared).
Since lld doesn't have a default --dynamic-linker,
compiler drivers (gcc/clang) don't pass --dynamic-linker for -shared,
and direct ld users are not supposed to specify --dynamic-linker for -shared,
we do not need the condition !Config->Shared.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62765
llvm-svn: 362355
GotEntrySize and GotPltEntrySize were added in D22288. Later, with
the introduction of wordsize() (then Config->Wordsize), they become
redundant, because there is no target that sets GotEntrySize or
GotPltEntrySize to a number different from Config->Wordsize.
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D62727
llvm-svn: 362220
Symbols relative to discarded comdat sections are Undefined instead of
Defined now (after D59649 and D61583). The `== &InputSection::Discarded`
test becomes dead. I cannot find a test related to this behavior.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62725
llvm-svn: 362218
For the Local Dynamic case of TLSDESC, _TLS_MODULE_BASE_ is defined as a
special TLS symbol that makes:
1) Without relaxation: it produces a dynamic TLSDESC relocation that
computes 0. Adding @dtpoff to access a TLS symbol.
2) With LD->LE relaxation: _TLS_MODULE_BASE_@tpoff = 0 (lowest address in
the TLS block). Adding @tpoff to access a TLS symbol.
For 1), this saves dynamic relocations and GOT slots as otherwise
(General Dynamic) we would create an R_X86_64_TLSDESC and reserve two
GOT slots for each symbol.
Add ElfSym::TlsModuleBase and change the signature of getTlsTpOffset()
to special case _TLS_MODULE_BASE_.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62577
llvm-svn: 362078
There's no guarantee that the other partition will be loaded, so it
can't be reused.
Differential Revision: https://reviews.llvm.org/D62365
llvm-svn: 361926
This change causes us to read partition specifications from partition
specification sections and split output sections into partitions according
to their reachability from partition entry points.
This is only the first step towards a full implementation of partitions. Later
changes will add additional synthetic sections to each partition so that
they can be loaded independently.
Differential Revision: https://reviews.llvm.org/D60353
llvm-svn: 361925
This handles two initial relocation types R_X86_64_GOTPC32_TLSDESC and
R_X86_64_TLSDESC_CALL, as well as the GD->LE and GD->IE relaxations.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62513
llvm-svn: 361911
This is implemented by creating Undefined (instead of Defined) for such
local STT_SECTION symbols. It allows us to catch errors when there are
relocations to such discarded sections (e.g. in PR41693, ld.bfd and gold
error but we don't). Updated comdat-discarded-error.s checks we emit
friendly error message.
For relocatable-eh-frame.s, ld.lld -r a.o a.o will now error
"STT_SECTION symbol should be defined" because the section .eh_frame
refers to is now an Undefined instead of a Defined.
So I have to change `error()` to `warn()` to retain the output.
rLLD361144 inadvertently enabled the error for --gdb-index
(in LLDDwarfObj<ELFT>::findAux()).
Relocations from .debug_info (not in comdat) to .text.* (in comdat) for
DW_AT_low_pc are common. If an .text.* was discarded, rLLD361144 would error,
which was unexpected. (Note, if we don't error as this patch does,
InputSection::relocateNonAlloc() will resolve such relocations).
llvm-svn: 361830
This is implemented by creating Undefined (instead of Defined) for such
local STT_SECTION symbols. It allows us to catch errors when there are
relocations to such discarded sections (e.g. in PR41693, ld.bfd and gold
error but we don't). Updated comdat-discarded-error.s checks we emit
friendly error message.
For relocatable-eh-frame.s, ld.lld -r a.o a.o will now error
"STT_SECTION symbol should be defined" because the section .eh_frame
refers to is now an Undefined instead of a Defined.
So I have to change `error()` to `warn()` to retain the output.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D61583
llvm-svn: 361792
This patch simplifies ELFFile instance initialization by merging
two similar functions into a single function and call it from the
ctor.
llvm-svn: 361789
My recent commits separated symbol resolution from the symbol table,
so the functions to resolve symbols are now in a somewhat wrong file.
This patch moves it to Symbols.cpp.
The functions are now member functions of the symbol.
This is code move change. I modified function names so that they are
appropriate as member functions, though. No functionality change
intended.
Differential Revision: https://reviews.llvm.org/D62290
llvm-svn: 361474
--{start,end}-lib give files grouped by the options the archive file
semantics. That is, each object file between them acts as if it were
in an archive file whose sole member is the file.
Therefore, files between --{start,end}-lib are linked to the final
output only if they are needed to resolve some undefined symbols.
Previously, the feature was implemented this way:
1. We read a symbol table and insert defined symbols to the symbol
table as lazy symbols.
2. If an undefind symbol is resolved to a lazy symbol, that lazy
symbol instantiate ObjFile class for that symbol, which re-insert
all defined symbols to the symbol table.
So, if an ObjFile is instantiated, defined symbols are inserted to the
symbol table twice. Since inserting long symbol names is not cheap,
there's a room to optimize here.
This patch optimzies it. Now, LazyObjFile remembers symbol handles and
passed them over to a new ObjFile instance, so that the ObjFile
doesn't insert the same strings.
Here is a quick benchmark to link clang. "Original" is the original
lld with unmodified command line options. For "Case 1" and "Case 2", I
extracted all files from archive files and replace .a's in a command
line with .o's wrapped with --{start,end}-lib. I used the original lld
for Case 1" and use this patch for Case 2.
Original: 5.892
Case 1: 6.001 (+1.8%)
Case 2: 5.701 (-3.2%)
So, interestingly, --{start,end}-lib are now faster than the regular
linking scheme with archive files. That's perhaps not too surprising,
though, because for regular archive files, we look up the symbol table
with the same string twice.
Differential Revision: https://reviews.llvm.org/D62188
llvm-svn: 361473
This is a minor improvement inspired by https://bugs.llvm.org/show_bug.cgi?id=38303.
A person reported that he observed message complaining about unsupported R_ARM_V4BX:
error: can't create dynamic relocation R_ARM_V4BX against local symbol in readonly segment; recompile object files with -fPIC
But with -z notext he only saw a relocation number, what is not convenient:
error: ../../gfx/cairo/libpixman/src/pixman-arm-neon-asm-bilinear.o:(.text+0x4F0): unrecognized reloc 40
Also, in the error messages we use relocation but not reloc.
With this patch we start to print one of the following messages:
error: file.o: unrecognized relocation Unknown(999)
error: file.o: unrecognized relocation R_X_KNOWN_BY_LLVM_BUT_UNSUPPORTED_BY_LLD_NAME
There is no way to write a test for that I believe.
Differential revision: https://reviews.llvm.org/D62237
llvm-svn: 361472
Also renames it LinkerDriver::compileBitcodeFiles.
The function doesn't logically belong to SymbolTable. We added this
function to the symbol table because symbol table used to be a
container of input files. This is no longer the case.
Differential Revision: https://reviews.llvm.org/D62291
llvm-svn: 361469
Symbol's NameSize is computed lazily. Currently, when we replace a symbol,
a cached length value can be discarded. This patch propagates that value.
Differential Revision: https://reviews.llvm.org/D62234
llvm-svn: 361364
Rather than report "undefined symbol: ", give more informative message
about the object file that defines the discarded section.
In particular, PR41133, if the section is a discarded COMDAT, print the
section group signature and the object file with the prevailing
definition. This is useful to track down some ODR issues.
We need to
* add `uint32_t DiscardedSecIdx` to Undefined for this feature.
* make ComdatGroups public and change its type to DenseMap<CachedHashStringRef, const InputFile *>
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D59649
llvm-svn: 361359
For memory5.test, ld.bfd appears to ignore `. += 0x2000;`, so the test was testing
a wrong behavior. After deleting the code added in rLLD336335, we match ld.bfd and thus fix PR41357.
PR37836 (memory4.test) seems to have been fixed by another change.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62177
llvm-svn: 361228
For a reference to a local symbol, ld.bfd and gold error if the symbol
is defined in a discarded section but accept it if the symbol is
undefined. This inconsistent behavior seems unnecessary for us (it
probably makes sense for them as they differentiate local/global
symbols, the error would mean more code).
Catch such errors. Symbol index 0 may be used by marker relocations,
e.g. R_*_NONE R_ARM_V4BX. Don't error on them.
The difference from D61563 (which caused msan failure) is we don't call
Sym.computeBinding() on local symbols - VersionId is uninitialized.
llvm-svn: 361213
This patch is a fix for https://bugs.llvm.org/show_bug.cgi?id=41804.
We try to solve the precedence of user-specified symbol ordering file and C3 ordering provided as call graph. It deals with two case:
(1) When both --symbol-ordering-file=<file> and --call-graph-order-file=<file> are present, whichever flag comes later will take precedence.
(2) When only --symbol-ordering-file=<file> is present, it takes precedence over implicit call graph (CGProfile) generated by CGProfilePass enabled in new pass manager.
llvm-svn: 361190
We currently sort dynamic relocations by (!is_relative,symbol_index).
Add r_offset as the third key. This makes `readelf -r` debugging easier
(relocations to the same symbol are ordered by r_offset).
Refactor the test combreloc.s (renamed from combrelocs.s) to check
R_X86_64_RELATIVE, and delete --expand-relocs.
The difference from the reverted D61477 is that we keep !is_relative as
the first key. In local dynamic TLS model, DTPMOD (e.g.
R_ARM_TLS_DTPMOD32 R_X86_64_DTPMOD and R_PPC{,64}_DTPMOD) may use 0 as
the symbol index.
Reviewed By: grimar
Differential Revision: https://reviews.llvm.org/D62141
llvm-svn: 361164
This reverts commit r361144. It causes a use-of-uninitialized-value in
maybeReportUndefined at llvm/tools/lld/ELF/Relocations.cpp:682, as
detected by MemorySanitizer when local-undefined-symbol.s test is run.
llvm-svn: 361162
This reverts commit r361125. This linker change breaks shared libraries
in some subtle way on x86_64. (Specifically, gold segfaults when
loading the LLVMgold.so plugin linked with lldb with this patch.)
llvm-svn: 361150
For R_TLS:
1) Delete Sym.isTls() . The assembler ensures the symbol is STT_TLS.
If not (the input is broken), we would crash (dereferencing null Out::TlsPhdr).
2) Change Sym.isUndefWeak() to Sym.isUndefined(), otherwise with --noinhibit-exec
we would still evaluate the symbol and crash.
3) Return A if the symbol is undefined. This is PR40570.
The case is probably unrealistic but returning A matches R_ABS and the
behavior of several dynamic loaders.
R_NEG_TLS is obsoleted Sun TLS we don't fully support, but
R_RELAX_TLS_GD_TO_LE_NEG is still used by GD->LE relaxation (subl $var@tpoff,%eax).
They should add the addend. Unfortunately I can't test it as compilers don't seem to generate non-zero implicit addends.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62098
llvm-svn: 361146
For a reference to a local symbol, ld.bfd and gold error if the symbol
is defined in a discarded section but accept it if the symbol is
undefined. This inconsistent behavior seems unnecessary for us (it
probably makes sense for them as they differentiate local/global
symbols, the error would mean more code).
Weaken the condition to getSymbol(Config->IsMips64EL) == 0 to catch such
errors. The symbol index can be 0 (e.g. R_*_NONE R_ARM_V4BX) and we shouldn't error on them.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D61563
llvm-svn: 361144
Fixes PR41692.
We currently sort dynamic relocations by (!is_relative,symbol_index).
Change it to (symbol_index,r_offset). We still place relative
relocations first because R_*_RELATIVE are the only dynamic relocations
with 0 symbol index (except on MIPS, which doesn't use DT_REL[A]COUNT
anyway).
This makes `readelf -r` debugging easier (relocations to the same symbol
are ordered by r_offset).
Refactor the test combreloc.s (renamed from combrelocs.s) to check
R_X86_64_RELATIVE, and delete --expand-relocs.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D61477
llvm-svn: 361125
This is a mechanical rewrite of replaceSymbol(A, B) to A->replace(B).
I also added a comment to Symbol::replace().
Technically this change is not necessary, but this change makes code a
bit more concise.
Differential Revision: https://reviews.llvm.org/D62117
llvm-svn: 361123
Otherwise, we may set IsPreemptible (e.g. --dynamic-list) then clear it
(in replaceCommonSymbols()).
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62107
llvm-svn: 361122
This reverts D53906.
D53906 increased p_align of PT_TLS on ARM/AArch64 to 32/64 to make the
static TLS layout compatible with Android Bionic's ELF TLS. However,
this may cause glibc ARM/AArch64 programs to crash (see PR41527).
The faulty PT_TLS in the executable satisfies p_vaddr%p_align != 0. The
remainder is normally 0 but may be non-zero with the hack in place. The
problem is that we increase PT_TLS's p_align after OutputSections'
addresses are fixed (assignAddress()). It is possible that
p_vaddr%old_p_align = 0 while p_vaddr%new_p_align != 0.
For a thread local variable defined in the executable, lld computed TLS
offset (local exec) is different from glibc computed TLS offset from
another module (initial exec/generic dynamic). Note: PR41527 said the
bug affects initial exec but actually generic dynamic is affected as
well.
(glibc is correct in that it compute offsets that satisfy
`offset%p_align == p_vaddr%p_align`, which is a basic ELF requirement.
This hack appears to work on FreeBSD rtld, musl<=1.1.22, and Bionic, but
that is just because they (and lld) incorrectly compute offsets that
satisfy `offset%p_align = 0` instead.)
Android developers are fine to revert this patch, carry this patch in
their tree before figuring out a long-term solution (e.g. a dummy .tdata
with sh_addralign=64 sh_size={0,1} in crtbegin*.o files. The overhead is
now insignificant after D62059).
Reviewed By: rprichard, srhines
Differential Revision: https://reviews.llvm.org/D62055
llvm-svn: 361090
After D62059, we don't align p_memsz of PT_TLS to p_align. The
getRelocTargetVA formula should align it instead.
It becomes clear that R_NEG_TLS and R_TLS are opposite from each other.
In i386-tls-le-align.s, I put ret after call ___tls_get_addr@plt as
otherwise ld.bfd would reject the relaxation:
TLS transition from R_386_TLS_GD to R_386_TLS_LE_32 against `a' at 0x3 in section `.text' failed
llvm-svn: 361088
As Ryan Prichard pointed out, after D62059, the TP offset is incorrect.
Add x86-64-tls-le-align.s to check this. Better formulae for both
variants should take p_vaddr%p_align into account (offset%p_align =
p_vaddr%p_align is a basic ELF requirement), but I can't find a way to
test the behavior.
llvm-svn: 361084
On Elf*_Rel targets, for a relocation to a section symbol, an R_ABS is
added which will be used by relocateOne() to compute the implicit
addend.
Addends of R_*_NONE should be ignored, so don't emit an R_ABS.
This fixes crashes on X86 and ARM because their relocateOne() do not
handle R_*_NONE.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D62052
llvm-svn: 361036
The code was added in r252352, probably to address some layout issues.
Actually PT_TLS's p_memsz doesn't need to be aligned on either variant.
ld.bfd doesn't do that.
In case of larger alignment (e.g. 64 for Android Bionic on AArch64, see
D62055), this may make the overhead smaller.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D62059
llvm-svn: 361029
This patch implements a limited form of autolinking primarily designed to allow
either the --dependent-library compiler option, or "comment lib" pragmas (
https://docs.microsoft.com/en-us/cpp/preprocessor/comment-c-cpp?view=vs-2017) in
C/C++ e.g. #pragma comment(lib, "foo"), to cause an ELF linker to automatically
add the specified library to the link when processing the input file generated
by the compiler.
Currently this extension is unique to LLVM and LLD. However, care has been taken
to design this feature so that it could be supported by other ELF linkers.
The design goals were to provide:
- A simple linking model for developers to reason about.
- The ability to to override autolinking from the linker command line.
- Source code compatibility, where possible, with "comment lib" pragmas in other
environments (MSVC in particular).
Dependent library support is implemented differently for ELF platforms than on
the other platforms. Primarily this difference is that on ELF we pass the
dependent library specifiers directly to the linker without manipulating them.
This is in contrast to other platforms where they are mapped to a specific
linker option by the compiler. This difference is a result of the greater
variety of ELF linkers and the fact that ELF linkers tend to handle libraries in
a more complicated fashion than on other platforms. This forces us to defer
handling the specifiers to the linker.
In order to achieve a level of source code compatibility with other platforms
we have restricted this feature to work with libraries that meet the following
"reasonable" requirements:
1. There are no competing defined symbols in a given set of libraries, or
if they exist, the program owner doesn't care which is linked to their
program.
2. There may be circular dependencies between libraries.
The binary representation is a mergeable string section (SHF_MERGE,
SHF_STRINGS), called .deplibs, with custom type SHT_LLVM_DEPENDENT_LIBRARIES
(0x6fff4c04). The compiler forms this section by concatenating the arguments of
the "comment lib" pragmas and --dependent-library options in the order they are
encountered. Partial (-r, -Ur) links are handled by concatenating .deplibs
sections with the normal mergeable string section rules. As an example, #pragma
comment(lib, "foo") would result in:
.section ".deplibs","MS",@llvm_dependent_libraries,1
.asciz "foo"
For LTO, equivalent information to the contents of a the .deplibs section can be
retrieved by the LLD for bitcode input files.
LLD processes the dependent library specifiers in the following way:
1. Dependent libraries which are found from the specifiers in .deplibs sections
of relocatable object files are added when the linker decides to include that
file (which could itself be in a library) in the link. Dependent libraries
behave as if they were appended to the command line after all other options. As
a consequence the set of dependent libraries are searched last to resolve
symbols.
2. It is an error if a file cannot be found for a given specifier.
3. Any command line options in effect at the end of the command line parsing apply
to the dependent libraries, e.g. --whole-archive.
4. The linker tries to add a library or relocatable object file from each of the
strings in a .deplibs section by; first, handling the string as if it was
specified on the command line; second, by looking for the string in each of the
library search paths in turn; third, by looking for a lib<string>.a or
lib<string>.so (depending on the current mode of the linker) in each of the
library search paths.
5. A new command line option --no-dependent-libraries tells LLD to ignore the
dependent libraries.
Rationale for the above points:
1. Adding the dependent libraries last makes the process simple to understand
from a developers perspective. All linkers are able to implement this scheme.
2. Error-ing for libraries that are not found seems like better behavior than
failing the link during symbol resolution.
3. It seems useful for the user to be able to apply command line options which
will affect all of the dependent libraries. There is a potential problem of
surprise for developers, who might not realize that these options would apply
to these "invisible" input files; however, despite the potential for surprise,
this is easy for developers to reason about and gives developers the control
that they may require.
4. This algorithm takes into account all of the different ways that ELF linkers
find input files. The different search methods are tried by the linker in most
obvious to least obvious order.
5. I considered adding finer grained control over which dependent libraries were
ignored (e.g. MSVC has /nodefaultlib:<library>); however, I concluded that this
is not necessary: if finer control is required developers can fall back to using
the command line directly.
RFC thread: http://lists.llvm.org/pipermail/llvm-dev/2019-March/131004.html.
Differential Revision: https://reviews.llvm.org/D60274
llvm-svn: 360984
This is the last patch of the series of patches to make it possible to
resolve symbols without asking SymbolTable to do so.
The main point of this patch is the introduction of
`elf::resolveSymbol(Symbol *Old, Symbol *New)`. That function resolves
or merges given symbols by examining symbol types and call
replaceSymbol (which memcpy's New to Old) if necessary.
With the new function, we have now separated symbol resolution from
symbol lookup. If you already have a Symbol pointer, you can directly
resolve the symbol without asking SymbolTable to do that.
Now that the nice abstraction become available, I can start working on
performance improvement of the linker. As a starter, I'm thinking of
making --{start,end}-lib faster.
--{start,end}-lib is currently unnecessarily slow because it looks up
the symbol table twice for each symbol.
- The first hash table lookup/insertion occurs when we instantiate a
LazyObject file to insert LazyObject symbols.
- The second hash table lookup/insertion occurs when we create an
ObjFile from LazyObject file. That overwrites LazyObject symbols
with Defined symbols.
I think it is not too hard to see how we can now eliminate the second
hash table lookup. We can keep LazyObject symbols in Step 1, and then
call elf::resolveSymbol() to do Step 2.
Differential Revision: https://reviews.llvm.org/D61898
llvm-svn: 360975
The change broke some scenarios where debug information is still
needed, although MarkLive cannot see it, including the
Chromium/Android build. Reverting to unbreak that build.
llvm-svn: 360955
Module IDs can appear in diagnostic messages.
This patch adds some auxiliary symbols to improve their readability.
Differential Revision: https://reviews.llvm.org/D61857
llvm-svn: 360858
Previously, we handled common symbols as a kind of Defined symbol,
but what we were doing for common symbols is pretty different from
regular defined symbols.
Common symbol and defined symbol are probably as different as shared
symbol and defined symbols are different.
This patch introduces CommonSymbol to represent common symbols.
After symbols are resolved, they are converted to Defined symbols
residing in a .bss section.
Differential Revision: https://reviews.llvm.org/D61895
llvm-svn: 360841
SymbolTable's add-family functions have lots of parameters because
when they have to create a new symbol, they forward given arguments
to Symbol's constructors. Therefore, the functions take at least as
many arguments as their corresponding constructors.
This patch simplifies the add-family functions. Now, the functions
take a symbol instead of arguments to construct a symbol. If there's
no existing symbol, a given symbol is memcpy'ed to the symbol table.
Otherwise, the functions attempt to merge the existing and a given
new symbol.
I also eliminated `CanOmitFromDynSym` parameter, so that the functions
take really one argument.
Symbol classes are trivially constructible, so looks like constructing
them to pass to add-family functions is as cheap as passing a lot of
arguments to the functions. A quick benchmark showed that this patch
seems performance-neutral.
This is a preparation for
http://lists.llvm.org/pipermail/llvm-dev/2019-April/131902.html
Differential Revision: https://reviews.llvm.org/D61855
llvm-svn: 360838
Patch by Mark Johnston!
Summary:
When the option is configured, ifunc calls do not go through the PLT;
rather, they appear as regular function calls with relocations
referencing the ifunc symbol, and the resolver is invoked when
applying the relocation. This is intended for use in freestanding
environments where text relocations are permissible and is incompatible
with the -z text option. The option is motivated by ifunc usage in the
FreeBSD kernel, where ifuncs are used to elide CPU feature flag bit
checks in hot paths. Instead of replacing the cost of a branch with that
of an indirect function call, the -z ifunc-noplt option is used to ensure
that ifunc calls carry no hidden overhead relative to normal function
calls.
Test Plan:
I added a couple of regression tests and tested the FreeBSD kernel
build using the latest lld sources.
To demonstrate the effects of the change, I used a micro-benchmark
which results in frequent invocations of a FreeBSD kernel ifunc. The
benchmark was run with and without IBRS enabled, and with and without
-zifunc-noplt configured. The observed speedup is small and consistent,
and is significantly larger with IBRS enabled:
https://people.freebsd.org/~markj/ifunc-noplt/noibrs.txthttps://people.freebsd.org/~markj/ifunc-noplt/ibrs.txt
Reviewed By: ruiu, MaskRay
Differential Revision: https://reviews.llvm.org/D61613
llvm-svn: 360685
See D61891: llvm had a bug that might create invalid (DW_AT_low_pc,DW_AT_high_pc) pairs or range list entries due to missing DW_AT_addr_base.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D61889
llvm-svn: 360679
The symbol table used to be a container of vectors of input files,
but that's no longer the case because the vectors are moved out of
SymbolTable and are now global variables.
Therefore, addFile doesn't have to belong to any class. This patch
moves the function out of the class.
This patch is a preparation for my RFC [1].
[1] http://lists.llvm.org/pipermail/llvm-dev/2019-April/131902.html
Differential Revision: https://reviews.llvm.org/D61854
llvm-svn: 360666
The -n (--nmagic) disables page alignment, and acts as a -Bstatic
The -N (--omagic) does what -n does but also marks the executable segment as
writeable. As page alignment is disabled headers are not allocated unless
explicit in the linker script.
To disable page alignment in LLD we choose to set the page sizes to 1 so
that any alignment based on the page size does nothing. To set the
Target->PageSize to 1 we implement -z common-page-size, which has the side
effect of allowing the user to set the value as well.
Setting the page alignments to 1 does mean that any use of
CONSTANT(MAXPAGESIZE) or CONSTANT(COMMONPAGESIZE) in a linker script will
return 1, unlike in ld.bfd. However given that -n and -N disable paging
these probably shouldn't be used in a linker script where -n or -N is in
use.
Differential Revision: https://reviews.llvm.org/D61688
llvm-svn: 360593
Suggested by Sean Fertile and Peter Smith.
Thunk section spacing decrease the total number of thunks. I measured a
decrease of 1% or less in some large programs, with no perceivable
slowdown in link time. Override getThunkSectionSpacing() to enable it.
0x2000000 is the farthest point R_PPC64_REL24 can reach. I tried several
numbers and found 0x2000000 works the best. Numbers near 0x2000000 work
as well but let's just use the simpler number.
As demonstrated by the updated tests, this essentially changes placement
of most thunks to the end of the output section. We leverage this
property to fix PR40740 reported by Alfredo Dal'Ava Júnior:
The output section .init consists of input sections from several object
files (crti.o crtbegin.o crtend.o crtn.o). Sections other than the last
one do not have a terminator. With this patch, we create the thunk after
the last .init input section and thus fix the issue. This is not
foolproof but works quite well for such sections (with no terminator) in
practice.
Reviewed By: ruiu, sfertile
Differential Revision: https://reviews.llvm.org/D61720
llvm-svn: 360405
for (InputFile *F : Files)
Symtab->addFile<ELFT>(F); // if there is a duplicate symbol error
...
Target = getTarget();
When parsing .debug_info in the object file (for better diagnostics),
DWARF.cpp findAux may dereference the null pointer Target
auto *DR = dyn_cast<Defined>(&File->getRelocTargetSym(Rel));
if (!DR) {
// Broken debug info may point to a non-defined symbol,
// some asan object files may also contain R_X86_64_NONE
RelType Type = Rel.getType(Config->IsMips64EL);
if (Type != Target->NoneRel) /// Target is null
Move the assignment of Target to an earlier place to fix this.
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D61712
llvm-svn: 360305
Use `ld` and `daddiu` instructions in MIPS64 PLT records. That fixes a
segmentation fault.
Patch by Qiao Pengcheng.
Differential Revision: https://reviews.llvm.org/D61586
llvm-svn: 360187
For lld-link, unknown '/'-style flags are treated as filenames on POSIX
systems, so only '-'-style flags get typo correction for now. This
matches clang-cl.
PR37006.
Differential Revision: https://reviews.llvm.org/D61443
llvm-svn: 360145
It makes the --plugin-opt=obj-path= and --plugin-opt=thinlto-index-only=
behavior more consistent - the files will be created in the
BitcodeFiles.empty() case, but I assume whether it behaves this way is
not required by anyone.
LTOObj->run() cannot run with empty BitcodeFiles. There would be an error:
ld.lld: error: No available targets are compatible with triple ""
Differential Revision: https://reviews.llvm.org/D61635
llvm-svn: 360129
This is based on D54720 by Sean Fertile.
When accessing a global symbol which is not defined in the translation unit,
compilers will generate instructions that load the address from the toc entry.
If the symbol is defined, non-preemptable, and addressable with a 32-bit
signed offset from the toc pointer, the address can be computed
directly. e.g.
addis 3, 2, .LC0@toc@ha # R_PPC64_TOC16_HA
ld 3, .LC0@toc@l(3) # R_PPC64_TOC16_LO_DS, load the address from a .toc entry
ld/lwa 3, 0(3) # load the value from the address
.section .toc,"aw",@progbits
.LC0: .tc var[TC],var
can be relaxed to
addis 3,2,var@toc@ha # this may be relaxed to a nop,
addi 3,3,var@toc@l # then this becomes addi 3,2,var@toc
ld/lwa 3, 0(3) # load the value from the address
We can delete the test ppc64-got-indirect.s as its purpose is covered by
newly added ppc64-toc-relax.s and ppc64-toc-relax-constants.s
Reviewed By: ruiu, sfertile
Differential Revision: https://reviews.llvm.org/D60958
llvm-svn: 360112
Summary:
While the generic ABI requires notes to be 8-byte aligned in ELF64, many
vendor-specific notes (from Linux, NetBSD, Solaris, etc) use 4-byte
alignment.
In a PT_NOTE segment, if 4-byte aligned notes are followed by an 8-byte
aligned note, the possible 4-byte padding may make consumers fail to
parse the 8-byte aligned note. See PR41000 for a recent report about
.note.gnu.property (NT_GNU_PROPERTY_TYPE_0).
(Note, for NT_GNU_PROPERTY_TYPE_0, the consumers should probably migrate
to PT_GNU_PROPERTY, but the alignment issue affects other notes as well.)
To fix the issue, don't mix notes with different alignments in one
PT_NOTE. If compilers emit 4-byte aligned notes before 8-byte aligned
notes, we'll create at most 2 segments.
sh_size%sh_addralign=0 is actually implied by the rule for linking
unrecognized sections (in generic ABI), so we don't have to check that.
Notes that match in name, type and attribute flags are concatenated into
a single output section. The compilers have to ensure
sh_size%sh_addralign=0 to make concatenated notes parsable.
An alternative approach is to create a PT_NOTE for each SHT_NOTE, but
we'll have to incur the sizeof(Elf64_Phdr)=56 overhead every time a new
note section is introduced.
Reviewers: ruiu, jakehehrlich, phosek, jhenderson, pcc, espindola
Subscribers: emaste, arichardson, krytarowski, fedor.sergeev, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61296
llvm-svn: 359853
Summary:
The gold plugin behavior (creating empty index files for lazy bitcode
files) was added in D46034, but it missed the case when there is no
non-lazy bitcode files, e.g.
ld.lld -shared crti.o crtbeginS.o --start-lib bitcode.o --end-lib ...
crti.o crtbeginS.o are not bitcode, but our distributed build system
wants bitcode.o.thinlto.bc to confirm all expected outputs are created
based on all of the modules provided to the linker.
Differential Revision: https://reviews.llvm.org/D61420
llvm-svn: 359788
/DISCARD/ output sections were being treated as orphans. As a result, if
a /DISCARD/ output section has been assigned a PHDR, it could cause
incorrect assignment of sections to segments.
Differential Revision: https://reviews.llvm.org/D61186
llvm-svn: 359565
This is a follow up to r358979 which made findOrphanPos only consider
live sections. Unfortunately, this required change to getRankProximity,
used by findOrphanPos, was missed.
Differential Revision: https://reviews.llvm.org/D61197
llvm-svn: 359554
This is https://bugs.llvm.org//show_bug.cgi?id=38750.
If script references empty sections in LOADADDR/ADDR commands
.empty : { *(.empty ) }
.text : AT(LOADADDR (.empty) + SIZEOF (.empty)) { *(.text) }
then an empty section will be removed and LOADADDR/ADDR will evaluate to null.
It is not that user may expect from using of the generic script, what is a common case.
Differential revision: https://reviews.llvm.org/D54621
llvm-svn: 359279
Summary:
We use `uint32_t SectionBase::Alignment` and `uint32_t
PhdrEntry::p_align` despite alignments being 64 bits in ELF64.
Fix the std::max template arguments accordingly.
The currently 160-byte InputSection will become 168 bytes if we make SectionBase::Alignment uint64_t.
Differential Revision: https://reviews.llvm.org/D61171
llvm-svn: 359268
Summary:
We don't take localentry offset into account, and thus may fail to
create a long branch when the gap is just a few bytes smaller than 2^25.
relocation R_PPC64_REL24 out of range: 33554432 is not in [-33554432, 33554431]
relocation R_PPC64_REL24 out of range: 33554436 is not in [-33554432, 33554431]
Fix that by adding the offset to the symbol VA.
Differential Revision: https://reviews.llvm.org/D61058
llvm-svn: 359094
This fixes an issue where a symbol only section at the start of a
PT_LOAD segment, causes incorrect alignment of the file offset for the
start of the segment which results in the output of an invalid ELF.
SHT_PROGBITS was the default output section type in the past.
Differential Revision: https://reviews.llvm.org/D60131
llvm-svn: 358981
This patch changes the behaviour of findOrphanPos to only consider live
sections when placing orphan sections. This used to be how it behaved in
the past.
Differential Revision: https://reviews.llvm.org/D60273
llvm-svn: 358979
Make some small adjustment while touching the code: make parameters
const, use less_first(), etc.
Differential Revision: https://reviews.llvm.org/D60989
llvm-svn: 358943
Summary:
Fixes PR35242. A simplified reproduce:
thread_local int i; int f() { return i; }
% {g++,clang++} -fPIC -shared -ftls-model=local-dynamic -fuse-ld=lld a.cc
ld.lld: error: can't create dynamic relocation R_X86_64_DTPOFF32 against symbol: i in readonly segment; recompile object files with -fPIC or pass '-Wl,-z,notext' to allow text relocations in the output
In isStaticLinkTimeConstant(), Syn.IsPreemptible is true, so it is not
seen as a constant. The error is then issued in processRelocAux().
A symbol of the local-dynamic TLS model cannot be preempted but it can
preempt symbols of the global-dynamic TLS model in other DSOs.
So it makes some sense that the variable is not static.
This patch fixes the linking error by changing getRelExpr() on
R_386_TLS_LDO_32 and R_X86_64_DTPOFF{32,64} from R_ABS to R_DTPREL.
R_PPC64_DTPREL_* and R_MIPS_TLS_DTPREL_* need similar fixes, but they are not handled in this patch.
As a bonus, we use `if (Expr == R_ABS && !Config->Shared)` to find
ld-to-le opportunities. R_ABS is overloaded here for such STT_TLS symbols.
A dedicated R_DTPREL is clearer.
Differential Revision: https://reviews.llvm.org/D60945
llvm-svn: 358870
Summary:
This relocation type is used by R_386_TLS_GD. Its formula is the same as
R_GOTPLT (e.g R_X86_64_GOT{32,64} R_386_TLS_GOTIE). Rename it to be clearer.
Differential Revision: https://reviews.llvm.org/D60941
llvm-svn: 358868
Nico Weber