Given the following scenario:
```
// Cat.cpp
struct Animal { virtual void makeNoise() const = 0; };
struct Cat : Animal { void makeNoise() const override; };
extern "C" int puts(char const *);
void Cat::makeNoise() const { puts("Meow"); }
void doThingWithCat(Animal *a) { static_cast<Cat *>(a)->makeNoise(); }
// CatUser.cpp
struct Animal { virtual void makeNoise() const = 0; };
struct Cat : Animal { void makeNoise() const override; };
void doThingWithCat(Animal *a);
void useDoThingWithCat() {
Cat *d = new Cat;
doThingWithCat(d);
}
// cat.ver
{
global: _Z17useDoThingWithCatv;
local: *;
};
$ clang++ Cat.cpp CatUser.cpp -fpic -flto=thin -fwhole-program-vtables
-shared -O3 -fuse-ld=lld -Wl,--lto-whole-program-visibility
-Wl,--version-script,cat.ver
```
We cannot devirtualize `Cat::makeNoise`. The issue is complex:
Due to `-fsplit-lto-unit` and usage of type metadata, we place the Cat
vtable declaration into module 0 and the Cat vtable definition with type
metadata into module 1, causing duplicate entries (Undefined followed by
Defined) in the `lto::InputFile::symbols()` output.
In `BitcodeFile::parse`, after processing the `Undefined` then the
`Defined`, the final state is `Defined`.
In `BitcodeCompiler::add`, for the first symbol, `computeBinding`
returns `STB_LOCAL`, then we reset it to `Undefined` because it is
prevailing (`versionId` is `preserved`). For the second symbol, because
the state is now `Undefined`, `computeBinding` returns `STB_GLOBAL`,
causing `ExportDynamic` to be true and suppressing devirtualization.
In D77280, the `computeBinding` change used a stricter `isDefined()`
condition to make weak``Lazy` symbol work.
This patch relaxes the condition to weaker `!isLazy()` to keep it
working while making the devirtualization work as well.
Differential Revision: https://reviews.llvm.org/D98686
D62727 removed GotEntrySize and GotPltEntrySize with a comment that they
are always equal to wordsize(), but that is not entirely true: X32 has a
word size of 4, but needs 8-byte GOT entries. This restores gotEntrySize
for both, adjusted for current naming conventions, but defaults it to
config->wordsize to keep things simple for architectures other than
x86_64.
This partially reverts D62727.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D102509
This option will be available in GNU ld 2.27 (https://sourceware.org/bugzilla/show_bug.cgi?id=27834).
This option can cancel previously specified -Bsymbolic and
-Bsymbolic-functions. This is useful for excluding some links when the
default uses -Bsymbolic-functions.
Reviewed By: jhenderson, peter.smith
Differential Revision: https://reviews.llvm.org/D102383
Currently, when reporting unresolved symbols in shared libraries, if an
undefined symbol is firstly seen in a regular object file that shadows
the reference for the same symbol in a shared object. As a result, the
error for the unresolved symbol in the shared library is not reported.
If referencing sections in regular object files are discarded because of
'--gc-sections', no reports about such symbols are generated, and the
linker finishes successfully, generating an output image that fails on
the run.
The patch fixes the issue by keeping symbols, which should be checked,
for each shared library separately.
Differential Revision: https://reviews.llvm.org/D101996
This fixes an issue where mixed TOC / NOTOC calls can call the incorrect
thunks if a previous thunk already exists. The issue appears when a TOC
funciton calls a NOTOC callee and then a different NOTOC function calls the same
NOTOC callee. In this case the linker would sometimes incorrectly call the
same thunk for both cases.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D101837
This is a slight improvement to the help text, as I was slightly
surprised when strip-all did more than remove the symbol table.
Currently, we match gold's help text for strip-all and strip-debug.
I think that the GNU documentation for these options is not particularly
clear. However, I have opted to make only a minor change here and keep
the help text similar to gold's as these are mature options that are
well understood.
ld.bfd (https://sourceware.org/binutils/docs/ld/Options.html) has a
similar implication although it defines strip-debug as a subset of
strip-all. However, felt that noting that strip-all implies strip-debug
is better; because, with the ld.bfd approach you have to read both the
--strip-debug and the --strip-all help text to understand the behaviour
of --strip-all (and the --strip-all help text doesn't indicate that he
--strip-debug help text is related).
Differential Revision: https://reviews.llvm.org/D101890
Adopt my suggestion in https://reviews.llvm.org/D91426#2653926 ,
generalizing the ppc64 specific code.
GNU ld and glibc ld.so has a contract about the first few entries of .got .
There are somewhat complex conditions when the header is needed. This patch
switches to a simpler approach: add a header unconditionally if
_GLOBAL_OFFSET_TABLE_ is used or the number of entries is more than just the
header.
Stop using the compatibility spellings of `OF_{None,Text,Append}`
left behind by 1f67a3cba9. A follow-up
will remove them.
Differential Revision: https://reviews.llvm.org/D101650
GNU ld -r can create .rela.eh_frame with unordered r_offset values.
(With LLD, we can craft such a case by reordering sections in .eh_frame.)
This is currently unsupported and will trigger
`assert(pieces[i].inputOff <= off ...` in `OffsetGetter::get`
(the content is corrupted in a -DLLVM_ENABLE_ASSERTIONS=off build).
This patch supports this case.
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D101116
The original page no longer works, so use a web.archive.org link instead.
Reviewed By: atanasyan
Differential Revision: https://reviews.llvm.org/D100949
This is the same problem as 127176e59e, but for static TLS rather than
dynamic TLS. Although we know the symbol will be the one in our own TLS
segment, and thus the offset of it within that, we don't know where in
the static TLS block our data will be allocated and thus we must emit a
dynamic relocation for this case.
Reviewed By: MaskRay, atanasyan
Differential Revision: https://reviews.llvm.org/D101381
Whilst not wrong (unless using static PIE where the relocations are
likely not implemented by the runtime), this is inefficient, as the TLS
module indices and offsets are independent of the executable's load
address.
Reviewed By: MaskRay, atanasyan
Differential Revision: https://reviews.llvm.org/D101382
An unfetched lazy symbol (undefined weak) should be considered to have its
original versionId which is VER_NDX_GLOBAL, instead of the lazy symbol's
versionId. (The original versionId cannot be non-VER_NDX_GLOBAL because a
undefined versioned symbol is an error.)
The regression was introduced in D77280 when making version scripts work
with lazy symbols fetched by LTO calls.
Fix PR49915
Differential Revision: https://reviews.llvm.org/D100624
Fix PR49897: if `__real_foo` has the isUsedInRegularObj bit set, we need to
retain `foo` in .symtab, even if `foo` is undefined. The new behavior will match
GNU ld.
Before the patch, we produced an R_X86_64_JUMP_SLOT relocation referencing the
index 0 undefined symbol, which would be erroed by glibc
(see f96ff3c0f8).
While here, fix another bug: if `__wrap_foo` does not exist, its initial binding
should be `foo`'s.
Change the default to facilitate GC for metadata section usage, so that they
don't need SHF_LINK_ORDER or SHF_GROUP just to drop the unhelpful rule (if they
want to be unconditionally retained, use SHF_GNU_RETAIN
(`__attribute__((retain))`) or linker script `KEEP`).
The dropped SHF_GROUP special case makes the behavior of -z start-stop-gc and -z
nostart-stop-gc closer to GNU ld>=2.37 (https://sourceware.org/PR27451).
However, we default to -z start-stop-gc (which actually matches more closely to
GNU ld before 2015-10 https://sourceware.org/PR19167), which is different from
modern GNU ld (which has the unhelpful rule to work around glibc). As a
compensation, we special case `__libc_` sections as a workaround for glibc<2.34
(https://sourceware.org/PR27492).
Since -z start-stop-gc as the default actually matches the traditional GNU ld
behavior, there isn't much to be aware of. There was a systemd usage which has
been fixed by https://github.com/systemd/systemd/pull/19144
The `e_flags` for a ELF file targeting the AVR ISA contains two fields at the time of writing:
- A 7-bit integer field specifying the ISA revision being targeted
- A 1-bit flag specifying whether the object files being linked are suited for applying the relaxations at link time
The linked ELF file is blessed with the arch revision shared among all the files.
The behaviour in case of mismatch is purposefully different than the one implemented in libbfd: LLD will raise a fatal error while libbfd silently picks a default value of `avr2`.
The relaxation-ready flag is handled as done by libbfd, in order for it to appear in the linked object every source object must be tagged with it.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D99754
From the PowerPC ELFv2 ABI section 4.2.3. Global Offset Table.
```
The GOT consists of an 8-byte header that contains the TOC base (the first TOC
base when multiple TOCs are present), followed by an array of 8-byte addresses.
```
Due to the introduction of PC Relative code it is now possible to require a GOT
without having a .TOC. symbol in the object that is being linked. Since LLD uses
the .TOC. symbol to determine whether or not a GOT is required the GOT header is
not setup correctly and the 8-byte header is missing.
This patch allows the Power PC GOT setup to happen when an element is added to
the GOT instead of at the very begining. When this header is added a .TOC.
symbol is also added.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D91426
This reuses the approach (and some code) from LLD-ELF.
It's a decent win when linking chromium_framework on a Mac Pro (3.2 GHz 16-Core Intel Xeon W):
N Min Max Median Avg Stddev
x 20 4.58 4.83 4.66 4.6685 0.066591844
+ 20 4.42 4.61 4.5 4.505 0.04751731
Difference at 95.0% confidence
-0.1635 +/- 0.0370242
-3.5022% +/- 0.793064%
(Student's t, pooled s = 0.0578462)
The output binary is 381MB.
Reviewed By: #lld-macho, oontvoo
Differential Revision: https://reviews.llvm.org/D99279
In future patches I will be setting the IsText parameter frequently so I will refactor the args to be in the following order. I have removed the FileSize parameter because it is never used.
```
static ErrorOr<std::unique_ptr<MemoryBuffer>>
getFile(const Twine &Filename, bool IsText = false,
bool RequiresNullTerminator = true, bool IsVolatile = false);
static ErrorOr<std::unique_ptr<MemoryBuffer>>
getFileOrSTDIN(const Twine &Filename, bool IsText = false,
bool RequiresNullTerminator = true);
static ErrorOr<std::unique_ptr<MB>>
getFileAux(const Twine &Filename, uint64_t MapSize, uint64_t Offset,
bool IsText, bool RequiresNullTerminator, bool IsVolatile);
static ErrorOr<std::unique_ptr<WritableMemoryBuffer>>
getFile(const Twine &Filename, bool IsVolatile = false);
```
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D99182
There is a bug when initial exec is relaxed to local exec.
In the following situation:
InitExec.c
```
extern __thread unsigned TGlobal;
unsigned getConst(unsigned*);
unsigned addVal(unsigned, unsigned*);
unsigned GetAddrT() {
return addVal(getConst(&TGlobal), &TGlobal);
}
```
Def.c
```
__thread unsigned TGlobal;
unsigned getConst(unsigned* A) {
return *A + 3;
}
unsigned addVal(unsigned A, unsigned* B) {
return A + *B;
}
```
The problem is in InitExec.c but Def.c is required if you want to link the example and see the problem.
To compile everything:
```
clang -O3 -mcpu=pwr10 -c InitExec.c
clang -O3 -mcpu=pwr10 -c Def.c
ld.lld InitExec.o Def.o -o IeToLe
```
If you objdump the problem object file:
```
$ llvm-objdump -dr --mcpu=pwr10 InitExec.o
```
you will get the following assembly:
```
0000000000000000 <GetAddrT>:
0: a6 02 08 7c mflr 0
4: f0 ff c1 fb std 30, -16(1)
8: 10 00 01 f8 std 0, 16(1)
c: d1 ff 21 f8 stdu 1, -48(1)
10: 00 00 10 04 00 00 60 e4 pld 3, 0(0), 1
0000000000000010: R_PPC64_GOT_TPREL_PCREL34 TGlobal
18: 14 6a c3 7f add 30, 3, 13
0000000000000019: R_PPC64_TLS TGlobal
1c: 78 f3 c3 7f mr 3, 30
20: 01 00 00 48 bl 0x20
0000000000000020: R_PPC64_REL24_NOTOC getConst
24: 78 f3 c4 7f mr 4, 30
28: 30 00 21 38 addi 1, 1, 48
2c: 10 00 01 e8 ld 0, 16(1)
30: f0 ff c1 eb ld 30, -16(1)
34: a6 03 08 7c mtlr 0
38: 00 00 00 48 b 0x38
0000000000000038: R_PPC64_REL24_NOTOC addVal
```
The lines of interest are:
```
10: 00 00 10 04 00 00 60 e4 pld 3, 0(0), 1
0000000000000010: R_PPC64_GOT_TPREL_PCREL34 TGlobal
18: 14 6a c3 7f add 30, 3, 13
0000000000000019: R_PPC64_TLS TGlobal
1c: 78 f3 c3 7f mr 3, 30
```
Which once linked gets turned into:
```
10010210: ff ff 03 06 00 90 6d 38 paddi 3, 13, -28672, 0
10010218: 00 00 00 60 nop
1001021c: 78 f3 c3 7f mr 3, 30
```
The problem is that register 30 is never set after the optimization.
Therefore it is not correct to relax the above instructions by replacing
the add instruction with a nop.
Instead the add instruction should be replaced with a copy (mr) instruction.
If the add uses the same resgiter as input and as ouput then it is safe to
continue to replace the add with a nop.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D95262
`--shuffle-sections=<seed>` applies to all sections. The new
`--shuffle-sections=<section-glob>=<seed>` makes shuffling selective. To the
best of my knowledge, the option is only used as debugging, so just drop the
original form.
`--shuffle-sections '.init_array*=-1'` `--shuffle-sections '.fini_array*=-1'`.
reverses static constructors/destructors of the same priority.
Useful to detect some static initialization order fiasco.
`--shuffle-sections '.data*=-1'`
reverses `.data*` sections. Useful to detect unfunded pointer comparison results
of two unrelated objects.
If certain sections have an intrinsic order, the old form cannot be used.
Differential Revision: https://reviews.llvm.org/D98679
If the number of sections changes, which is common for re-links after
incremental updates, the section order may change drastically.
Special case -1 to reverse input sections. This is a stable transform.
The section order is more resilient to incremental updates. Usually the
code issue (e.g. Static Initialization Order Fiasco, assuming pointer
comparison result of two unrelated objects) is due to the relative order
between two problematic input files A and B. Checking the regular order
and the reversed order is sufficient.
Differential Revision: https://reviews.llvm.org/D98445
GNU ld supports `.` and `$` in symbol names while LLD doesn't support them in
`readPrimary` expressions. Using `.` can result in such an error:
```
https://github.com/ClangBuiltLinux/linux/issues/1318
ld.lld: error: ./arch/powerpc/kernel/vmlinux.lds:255: malformed number: .TOC.
>>> __toc_ptr = (DEFINED (.TOC.) ? .TOC. : ADDR (.got)) + 0x8000;
```
Allow `.` (ppc64 special symbol `.TOC.`) and `$` (RISC-V special symbol `__global_pointer$`).
Change `diag[3-5].test` to use an invalid character `^`.
Note: GNU ld allows `~` in non-leading positions of a symbol name. `~`
is not used in practice, conflicts with the unary operator, and can
cause some parsing difficulty, so this patch does not add it.
Differential Revision: https://reviews.llvm.org/D98306
A `local:` version node in a version script can change the effective symbol binding
to STB_LOCAL. The linker needs to communicate the fact to enable WPD
(otherwise LTO does not know that the `!vcall_visibility` metadata has
effectively changed from VCallVisibilityPublic to VCallVisibilityLinkageUnit).
Reviewed By: tejohnson
Differential Revision: https://reviews.llvm.org/D98220
Implemented the option to omit Power10 instructions from save stubs via the
option --no-power10-stubs or --power10-stubs=no on lld. --power10-stubs= will
override the other option. --power10-stubs=auto also exists to use the default
behaviour (ie allow Power10 instructions in stubs).
Differential Revision: https://reviews.llvm.org/D94627
In AArch32 ARM, the PC reads two instructions ahead of the currently
executiing instruction. This evaluates to 8 in ARM state and 4 in
Thumb state. Branch instructions on AArch32 compensate for this by
subtracting the PC bias from the addend. For a branch to symbol this
will result in an addend of -8 in ARM state and -4 in Thumb state.
The existing ARM Target::inBranchRange function accounted for this
implict addend within the function meaning that if the addend were
to be taken into account by the caller then it would be double
counted. This complicates the interface for all Targets as callers
wanting to account for addends had to account for the ARM PC-bias.
In certain situations such as:
https://github.com/ClangBuiltLinux/linux/issues/1305
the PC-bias compensation code didn't match up. In particular
normalizeExistingThunk() didn't put the PC-bias back in as Arm
thunks did not store the addend.
The simplest fix for the problem is to add the PC bias in
normalizeExistingThunk when restoring the addend. However I think
it is worth refactoring the Arm inBranchRange implementation so
that fewer calls to getPCBias are needed for other Targets. I
wasn't able to remove getPCBias completely but hopefully the
Relocations.cpp code is simpler now.
In principle a test could be written to replicate the linux kernel
build failure but I wasn't able to reproduce with a small example
that I could build up from scratch.
Fixes https://github.com/ClangBuiltLinux/linux/issues/1305
Differential Revision: https://reviews.llvm.org/D97550
Also a couple of minor cleanups in merge-string.s:
- fix inconsistent use of tabs
- use `.p2align` rather than `.align` since `.p2align` works the
same on all platforms (the meaning of align seems to differ
between platforms according to `AlignmentIsInBytes`.
I noticed these potential cleanups while porting SHF_STRINGS support to
wasm-ld.
Differential Revision: https://reviews.llvm.org/D97647
For one metadata section usage, each text section references a metadata section.
The metadata sections have a C identifier name to allow the runtime to collect them via `__start_/__stop_` symbols.
Since `__start_`/`__stop_` references are always present from live sections, the
C identifier name sections appear like GC roots, which means they cannot be
discarded by `ld --gc-sections`.
To make such sections GCable, either SHF_LINK_ORDER or a section group is needed.
SHF_LINK_ORDER is not suitable for the references can be inlined into other functions
(See D97430:
Function A (in the section .text.A) references its `__sancov_guard` section.
Function B inlines A (so now .text.B references `__sancov_guard` - this is invalid with the semantics of SHF_LINK_ORDER).
In the linking stage,
if `.text.A` gets discarded, and `__sancov_guard` is retained via the reference from `.text.B`,
the output will be invalid because `__sancov_guard` references the discarded `.text.A`.
LLD errors "sh_link points to discarded section".
)
A section group have size overhead, and is cumbersome when there is just one metadata section.
Add `-z start-stop-gc` to drop the "__start_/__stop_ references retain
non-SHF_LINK_ORDER non-SHF_GROUP C identifier name sections" rule.
We reserve the rights to switch the default in the future.
Reviewed By: phosek, jrtc27
Differential Revision: https://reviews.llvm.org/D96914
The special root semantics for identifier-named sections is meant
specifically for the metadata sections. In the context of group
semantics, where group members are always retained or discarded as a
unit, it's natural not to have this semantics apply to a section in a
group, otherwise we would never discard the group defeating the purpose
of using the group in the first place.
This change modifies the GC behavior so that __start_/__stop_ references
don't retain C identifier named sections in section groups which allows
for these groups to be collected. This matches the behavior of BFD ld.
The only kind of existing case that might break is interdependent
metadata sections that are all in a group together, but that group
doesn't contain any other sections referenced by anything except
implicit inclusion in a `__start_` and/or `__stop_`-referenced
identifier-named section, but such cases should be unlikely.
Differential Revision: https://reviews.llvm.org/D96753
This change introduces support for zero flag ELF section groups to lld.
lld already supports COMDAT sections, which in ELF are a special type of
ELF section groups. These are generally useful to enable linker GC where
you want a group of sections to always travel together, that is to be
either retained or discarded as a whole, but without the COMDAT
semantics. Other ELF linkers already support zero flag ELF section
groups and this change helps us reach feature parity.
Differential Revision: https://reviews.llvm.org/D96636
When parsing an object file, LLD interleaves undefined symbol resolution (which
may recursively fetch other lazy objects) with defined symbol resolution.
This may lead to surprising results, e.g. if an object file defines currently
undefined symbols and references another lazy symbol, we may interleave defined
symbols with the lazy fetch, potentially leading to the defined symbols
resolving to different files.
As an example, if both `a.a(a.o)` and `a.a(b.o)` define `foo` (not in COMDAT
group, or in different COMDAT groups) and `__profd_foo` (in COMDAT group
`__profd_foo`). LLD may resolve `foo` to `a.a(a.o)` and `__profd_foo` to
`b.a(b.o)`, i.e. different files.
```
parse ArchiveFile a.a
entry fetches a.a(a.o)
parse ObjectFile a.o
define entry
define foo
reference b
b fetches a.a(b.o)
parse ObjectFile b.o
define prevailing __profd_foo
define (ignored) non-prevailing __profd_foo
```
Assuming a set of interconnected symbols are defined all or none in several lazy
objects. Arguably making them resolve to the same file is preferable than making
them resolve to different files (some are lazy objects).
The main argument favoring the new behavior is the stability. The relative order
between a defined symbol and an undefined symbol does not change the symbol
resolution behavior. Only the relative order between two undefined symbols can
affect fetching behaviors.
---
The real world case is reduced from a Fuchsia PGO usage: `a.a(a.o)` has a
constructor within COMDAT group C5 while `a.a(b.o)` has a constructor within
COMDAT group C2. Because they use different group signatures, they are not
de-duplicated. It is not entirely whether Clang behavior is entirely conforming.
LLD selects the PGO counter section (`__profd_*`) from `a.a(b.o)` and the
constructor section from `a.a(a.o)`. The `__profd_*` is a SHF_LINK_ORDER section
linking to its own non-prevailing constructor section, so LLD errors
`sh_link points to discarded section`. This patch fixes the error.
Differential Revision: https://reviews.llvm.org/D95985
`extern const bfd_target aarch64_elf64_le_vec;` is a variable in BFD.
It was somehow misused as an emulation by Android.
```
% aarch64-linux-gnu-ld -m aarch64_elf64_le_vec a.o
aarch64-linux-gnu-ld: unrecognised emulation mode: aarch64_elf64_le_vec
Supported emulations: aarch64linux aarch64elf aarch64elf32 aarch64elf32b aarch64elfb armelf armelfb aarch64linuxb aarch64linux32 aarch64linux32b armelfb_linux_eabi armelf_linux_eabi
```
Acked by Stephen Hines, who removed the flag from Android a while back.
Rewritting the path of the sample profile file in response.txt to be relative to the repro tar.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D96193
A SHF_LINK_ORDER .gcc_except_table is similar to a .gcc_except_table in
a section group. The associated text section is responsible for retaining it.
LLD still does not support GC of non-group non-SHF_LINK_ORDER .gcc_except_table -
but that is not necessary because we can teach the compiler to set SHF_LINK_ORDER.
Nathan Lanza