Summary:
Third part in series to support Safe Whole Program Devirtualization
Enablement, see RFC here:
http://lists.llvm.org/pipermail/llvm-dev/2019-December/137543.html
This patch adds type test metadata under -fwhole-program-vtables,
even for classes without hidden visibility. It then changes WPD to skip
devirtualization for a virtual function call when any of the compatible
vtables has public vcall visibility.
Additionally, internal LLVM options as well as lld and gold-plugin
options are added which enable upgrading all public vcall visibility
to linkage unit (hidden) visibility during LTO. This enables the more
aggressive WPD to kick in based on LTO time knowledge of the visibility
guarantees.
Support was added to all flavors of LTO WPD (regular, hybrid and
index-only), and to both the new and old LTO APIs.
Unfortunately it was not simple to split the first and second parts of
this part of the change (the unconditional emission of type tests and
the upgrading of the vcall visiblity) as I needed a way to upgrade the
public visibility on legacy WPD llvm assembly tests that don't include
linkage unit vcall visibility specifiers, to avoid a lot of test churn.
I also added a mechanism to LowerTypeTests that allows dropping type
test assume sequences we now aggressively insert when we invoke
distributed ThinLTO backends with null indexes, which is used in testing
mode, and which doesn't invoke the normal ThinLTO backend pipeline.
Depends on D71907 and D71911.
Reviewers: pcc, evgeny777, steven_wu, espindola
Subscribers: emaste, Prazek, inglorion, arichardson, hiraditya, MaskRay, dexonsmith, dang, davidxl, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71913
I felt really sad to push this commit for my selfish purpose to make
glibc -static-pie build with lld. Some code constructs in glibc require
R_X86_64_GOTPCREL/R_X86_64_REX_GOTPCRELX referencing undefined weak to
be resolved to a GOT entry not relocated by R_X86_64_GLOB_DAT (GNU ld
behavior), e.g.
csu/libc-start.c
if (__pthread_initialize_minimal != NULL)
__pthread_initialize_minimal ();
elf/dl-object.c
void
_dl_add_to_namespace_list (struct link_map *new, Lmid_t nsid)
{
/* We modify the list of loaded objects. */
__rtld_lock_lock_recursive (GL(dl_load_write_lock));
Emitting a GLOB_DAT will make the address equal &__ehdr_start (true
value) and cause elf/ldconfig to segfault. glibc really should move away
from weak references, which do not have defined semantics.
Temporarily special case --no-dynamic-linker.
When annotating a symbol with __declspec(selectany), Clang assigns it
comdat 2 while GCC assigns it comdat 3. This patch enables two object
files that contain a __declspec(selectany) symbol, one created by gcc
and the other by clang, to be linked together instead of issuing a
duplicate symbol error.
Differential Revision: https://reviews.llvm.org/D73139
Summary:
Linker scripts allow filenames to be put in double quotes to prevent
characters in filenames that are part of the linker script syntax from
having their special meaning. Case in point the * wildcard character.
Availability of double quoting filenames also allows to fix a failure in
ELF/linkerscript/filename-spec.s when the path contain a @ which the
lexer consider as a special characters and thus break up a filename
containing it. This may happens under Jenkins which createspath such as
pipeline@2.
To avoid the need for escaping GlobPattern metacharacters in filename
in double quotes, GlobPattern::create is augmented with a new parameter
to request literal matching instead of relying on the presence of a
wildcard character in the pattern.
Reviewers: jhenderson, MaskRay, evgeny777, espindola, alexshap
Reviewed By: MaskRay
Subscribers: peter.smith, grimar, ruiu, emaste, arichardson, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72517
The --fix-cortex-a8 is sensitive to alignment and the precise destination
of branch instructions. These are not knowable at relocatable link time. We
follow GNU ld and the --fix-cortex-a53-843419 (D72968) by not patching the
code when there is a relocatable link.
Differential Revision: https://reviews.llvm.org/D73100
The INPUT_SECTION_FLAGS linker script command is used to constrain the
section pattern matching to sections that match certain combinations of
flags.
There are two ways to express the constraint.
withFlags: Section must have these flags.
withoutFlags: Section must not have these flags.
The syntax of the command is:
INPUT_SECTION_FLAGS '(' sect_flag_list ')'
sect_flag_list: NAME
| sect_flag_list '&' NAME
Where NAME matches a section flag name such as SHF_EXECINSTR, or the
integer value of a section flag. If the first character of NAME is ! then
it means must not contain flag.
We do not support the rare case of { INPUT_SECTION_FLAGS(flags) filespec }
where filespec has no input section description like (.text).
As an example from the ld man page:
SECTIONS {
.text : { INPUT_SECTION_FLAGS (SHF_MERGE & SHF_STRINGS) *(.text) }
.text2 : { INPUT_SECTION_FLAGS (!SHF_WRITE) *(.text) }
}
.text will match sections called .text that have both the SHF_MERGE and
SHF_STRINGS flag.
.text2 will match sections called .text that don't have the SHF_WRITE flag.
The flag names accepted are the generic to all targets and SHF_ARM_PURECODE
as it is very useful to filter all the pure code sections into a single
program header that can be marked execute never.
fixes PR44265
Differential Revision: https://reviews.llvm.org/D72756
Summary:
Unlike R_RISCV_RELAX, which is a linker hint, R_RISCV_ALIGN requires the
support of the linker even when ignoring all R_RISCV_RELAX relocations.
This is because the compiler emits as many NOPs as may be required for
the requested alignment, more than may be required pre-relaxation, to
allow for the target becoming more unaligned after relaxing earlier
sequences. This means that the target is often not initially aligned in
the object files, and so the R_RISCV_ALIGN relocations cannot just be
ignored. Since we do not support linker relaxation, we must turn these
into errors.
Reviewers: ruiu, MaskRay, espindola
Reviewed By: MaskRay
Subscribers: grimar, Jim, emaste, arichardson, asb, rbar, johnrusso, simoncook, sabuasal, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, lenary, s.egerton, pzheng, sameer.abuasal, apazos, luismarques, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71820
The code doesn't apply the fix correctly to relocatable links. I could
try to fix the code that applies the fix, but it's pointless: we don't
actually know what the offset will be in the final executable. So just
ignore the flag for relocatable links.
Issue discovered building Android.
Differential Revision: https://reviews.llvm.org/D72968
This change has 2 components:
Target-independent: add a method getDwarfFrameBase to TargetFrameLowering. It
describes how the Dwarf frame base will be encoded. That can be a register (the
default), the CFA (which replaces NVPTX-specific logic in DwarfCompileUnit), or
a DW_OP_WASM_location descriptr.
WebAssembly: Allow WebAssemblyFunctionInfo::getFrameRegister to return the
correct virtual register instead of FP32/SP32 after WebAssemblyReplacePhysRegs
has run. Make WebAssemblyExplicitLocals store the local it allocates for the
frame register. Use this local information to implement getDwarfFrameBase
The result is that the DW_AT_frame_base attribute is correctly encoded for each
subprogram, and each param and local variable has a correct DW_AT_location that
uses DW_OP_fbreg to refer to the frame base.
This is a reland of rG3a05c3969c18 with fixes for the expensive-checks
and Windows builds
Differential Revision: https://reviews.llvm.org/D71681
This essentially reverts b841e119d7.
Such code construct can be used in the following way:
// glibc/stdlib/exit.c
// clang -fuse-ld=lld => succeeded
// clang -fuse-ld=lld -fpie -pie => relocation R_PLT_PC cannot refer to absolute symbol
__attribute__((weak, visibility("hidden"))) extern void __call_tls_dtors();
void __run_exit_handlers() {
if (__call_tls_dtors)
__call_tls_dtors();
}
Since we allow R_PLT_PC in -no-pie mode, it makes sense to allow it in
-pie mode as well.
Reviewed By: pcc
Differential Revision: https://reviews.llvm.org/D72943
In D71281 a fix was put in to round up the size of a ThunkSection to the
nearest 4KiB when performing errata patching. This fixed a problem with a
very large instrumented program that had thunks and patches mutually
trigger each other. Unfortunately it triggers an assertion failure in an
AArch64 allyesconfig build of the kernel. There is a specific assertion
preventing an InputSectionDescription being larger than 4KiB. This will
always trigger if there is at least one Thunk needed in that
InputSectionDescription, which is possible for an allyesconfig build.
Abstractly the problem case is:
.text : {
*(.text) ;
...
. = ALIGN(SZ_4K);
__idmap_text_start = .;
*(.idmap.text)
__idmap_text_end = .;
...
}
The assertion checks that __idmap_text_end - __idmap_start is < 4 KiB.
Note that there is more than one InputSectionDescription in the
OutputSection so we can't just restrict the fix to OutputSections smaller
than 4 KiB.
The fix presented here limits the D71281 to InputSectionDescriptions that
meet the following conditions:
1.) The OutputSection is bigger than the thunkSectionSpacing so adding
thunks will affect the addresses of following code.
2.) The InputSectionDescription is larger than 4 KiB. This will prevent
any assertion failures that an InputSectionDescription is < 4 KiB
in size.
We do this at ThunkSection creation time as at this point we know that
the addresses are stable and up to date prior to adding the thunks as
assignAddresses() will have been called immediately prior to thunk
generation.
The fix reverts the two tests affected by D71281 to their original state
as they no longer need the 4KiB size roundup. I've added simpler tests to
check for D71281 when the OutputSection size is larger than the ThunkSection
spacing.
Fixes https://github.com/ClangBuiltLinux/linux/issues/812
Differential Revision: https://reviews.llvm.org/D72344
This change has 2 components:
Target-independent: add a method getDwarfFrameBase to TargetFrameLowering. It
describes how the Dwarf frame base will be encoded. That can be a register (the
default), the CFA (which replaces NVPTX-specific logic in DwarfCompileUnit), or
a DW_OP_WASM_location descriptr.
WebAssembly: Allow WebAssemblyFunctionInfo::getFrameRegister to return the
correct virtual register instead of FP32/SP32 after WebAssemblyReplacePhysRegs
has run. Make WebAssemblyExplicitLocals store the local it allocates for the
frame register. Use this local information to implement getDwarfFrameBase
The result is that the DW_AT_frame_base attribute is correctly encoded for each
subprogram, and each param and local variable has a correct DW_AT_location that
uses DW_OP_fbreg to refer to the frame base.
Differential Revision: https://reviews.llvm.org/D71681
`{clang,gcc} -nostdlib -r a.c` passes --dynamic-linker to the linker,
and the expected behavior is to ignore it.
If .interp is kept in the relocatable object file, a final link will get
PT_INTERP even if --dynamic-linker is not specified. glibc ld.so expects
to see PT_DYNAMIC and the executable will likely fail to run.
Ignore --dynamic-linker in -r mode as well as -shared.
ThunkSection contains 4-byte instructions on all targets that use
thunks. Thunks should not be used in any performance sensitive places,
and locality/cache line/instruction fetching arguments should not apply.
We use 16 bytes as preferred function alignments for modern PowerPC cores.
In any case, 8 is not optimal.
Differential Revision: https://reviews.llvm.org/D72819
Summary:
This patch could be treated as a rebase of D33960. It also fixes PR35547.
A fix for `llvm/test/Other/close-stderr.ll` is proposed in D68164. Seems
the consensus is that the test is passing by chance and I'm not
sure how important it is for us. So it is removed like in D33960 for now.
The rest of the test fixes are just adding `--crash` flag to `not` tool.
** The reason it fixes PR35547 is
`exit` does cleanup including calling class destructor whereas `abort`
does not do any cleanup. In multithreading environment such as ThinLTO or JIT,
threads may share states which mostly are ManagedStatic<>. If faulting thread
tearing down a class when another thread is using it, there are chances of
memory corruption. This is bad 1. It will stop error reporting like pretty
stack printer; 2. The memory corruption is distracting and nondeterministic in
terms of error message, and corruption type (depending one the timing, it
could be double free, heap free after use, etc.).
Reviewers: rnk, chandlerc, zturner, sepavloff, MaskRay, espindola
Reviewed By: rnk, MaskRay
Subscribers: wuzish, jholewinski, qcolombet, dschuff, jyknight, emaste, sdardis, nemanjai, jvesely, nhaehnle, sbc100, arichardson, jgravelle-google, aheejin, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, zzheng, edward-jones, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, jsji, lenary, s.egerton, pzheng, cfe-commits, MaskRay, filcab, davide, MatzeB, mehdi_amini, hiraditya, steven_wu, dexonsmith, rupprecht, seiya, llvm-commits
Tags: #llvm, #clang
Differential Revision: https://reviews.llvm.org/D67847
This assertion was added as part of D70659 but did not account for .bss
input sections. I noticed that this assert was incorrectly triggering
while building FreeBSD for MIPS64. Fixed by relaxing the assert to also
account for SHT_NOBITS input sections and adjust the test
mips-jalr-non-function.s to link a file with a .bss section first.
Reviewed By: MaskRay, grimar
Differential Revision: https://reviews.llvm.org/D72567
Suggested by Peter Collingbourne.
Non-VER_NDX_GLOBAL versions should not be assigned to defined symbols. --exclude-libs violates this and can cause a spurious error "cannot refer to absolute symbol" after D71795.
excludeLibs incorrectly assigns VER_NDX_LOCAL to an undefined weak symbol =>
isPreemptible is false =>
R_PLT_PC is optimized to R_PC =>
in isStaticLinkTimeConstant, an error is emitted.
Reviewed By: pcc, grimar
Differential Revision: https://reviews.llvm.org/D72681
This patch is a joint work by Rui Ueyama and me based on D58102 by Xiang Zhang.
It adds Intel CET (Control-flow Enforcement Technology) support to lld.
The implementation follows the draft version of psABI which you can
download from https://github.com/hjl-tools/x86-psABI/wiki/X86-psABI.
CET introduces a new restriction on indirect jump instructions so that
you can limit the places to which you can jump to using indirect jumps.
In order to use the feature, you need to compile source files with
-fcf-protection=full.
* IBT is enabled if all input files are compiled with the flag. To force enabling ibt, pass -z force-ibt.
* SHSTK is enabled if all input files are compiled with the flag, or if -z shstk is specified.
IBT-enabled executables/shared objects have two PLT sections, ".plt" and
".plt.sec". For the details as to why we have two sections, please read
the comments.
Reviewed By: xiangzhangllvm
Differential Revision: https://reviews.llvm.org/D59780
When compiling position-independent executables, we now use
DW_EH_PE_pcrel | DW_EH_PE_sdata4. However, the MIPS ABI does not define a
64-bit PC-relative ELF relocation so we cannot use sdata8 for the large
code model case. When using the large code model, we fall back to the
previous behaviour of generating absolute relocations.
With this change clang-generated .o files can be linked by LLD without
having to pass -Wl,-z,notext (which creates text relocations).
This is simpler than the approach used by ld.bfd, which rewrites the
.eh_frame section to convert absolute relocations into relative references.
I saw in D13104 that apparently ld.bfd did not accept pc-relative relocations
for MIPS ouput at some point. However, I also checked that recent ld.bfd
can process the clang-generated .o files so this no longer seems true.
Reviewed By: atanasyan
Differential Revision: https://reviews.llvm.org/D72228
For a target symbol defined in the same section, currently we don't emit
a relocation if VariantKind is VK_None (with few exceptions like RISC-V
relaxation), while GNU as emits one. This causes program behavior
differences with and without -ffunction-sections, and can break intended
symbol interposition in a -shared link.
```
.globl foo
foo:
call foo # no relocation. On other targets, may be written as b foo, etc
call bar # a relocation if bar is in another section (e.g. -ffunction-sections)
call foo@plt # a relocation
```
Unify these cases by always emitting a relocation. If we ever want to
optimize `call foo` in -shared links, we should emit a STB_LOCAL alias
and call via the alias.
ARM/thumb2-beq-fixup.s: we now emit a relocation to global_thumb_fn as GNU as does.
X86/Inputs/align-branch-64-2.s: we now emit R_X86_64_PLT32 to foo as GNU does.
ELF/relax.s: rewrite the test as target-in-same-section.s .
We omitted relocations to `global` and now emit R_X86_64_PLT32.
Note, GNU as does not emit a relocation for `jmp global` (maybe its own
bug). Our new behavior is compatible except `jmp global`.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D72197
RangeExtensionThunkARM64 is created for out-of-range branches on Windows ARM64
because branch instructions has limited bits to encode target address.
Currently, RangeExtensionThunkARM64 is appended to its referencing COFF section
from object file at link time without any alignment requirement, so if size of
the preceding COFF section is not aligned to instruction boundary (4 bytes),
RangeExtensionThunkARM64 will emit thunk instructions at unaligned address
which is never a valid branch target on ARM64, and usually triggers invalid
instruction exception when branching to it.
This PR fixes it by requiring such thunks to align at 4 bytes.
Differential revision: https://reviews.llvm.org/D72473
RELA targets don't read initial .got.plt entries.
REL targets (ARM, x86-32) write the address of the IFUNC resolver to the
entry (`write32le(buf, s.getVA())`).
The default writeIgotPlt() is not meaningful. Make it a no-op. AArch64
and x86-64 will have 0 as initial .got.plt entries associated with
IFUNC.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D72474
Unlike most of our errors in the debug line parser, the "no end of
sequence" message was missing any reference to which line table it
refererred to. This change adds the offset to this message.
Reviewed by: dblaikie
Differential Revision: https://reviews.llvm.org/D72443
down to pass builder in ltobackend.
Currently CodeGenOpts like UnrollLoops/VectorizeLoop/VectorizeSLP in clang
are not passed down to pass builder in ltobackend when new pass manager is
used. This is inconsistent with the behavior when new pass manager is used
and thinlto is not used. Such inconsistency causes slp vectorization pass
not being enabled in ltobackend for O3 + thinlto right now. This patch
fixes that.
Differential Revision: https://reviews.llvm.org/D72386
An undefined weak does not fetch the lazy definition. A lazy weak symbol
should be considered undefined, and thus preemptible if .dynsym exists.
D71795 is not quite an NFC. It errors on an R_X86_64_PLT32 referencing
an undefined weak symbol. isPreemptible is false (incorrect) => R_PLT_PC
is optimized to R_PC => in isStaticLinkTimeConstant, an error is emitted
when an R_PC is applied on an undefined weak (considered absolute).
D59275 added the following clause to Symbol::includeInDynsym()
if (isUndefWeak() && Config->Pie && SharedFiles.empty())
return false;
D59549 explored the possibility to generalize it for -no-pie.
GNU ld's rules are architecture dependent and partly controlled by -z
{,no-}dynamic-undefined-weak. Our attempts to mimic its rules are
actually half-baked and don't provide perceivable benefits (it can save
a few more weak undefined symbols in .dynsym in a -static-pie
executable). Let's just delete the rule for simplicity. We will expect
cosmetic inconsistencies with ld.bfd in certain -static-pie scenarios.
This permits a simplification in D71795.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D71794
In AArch64 a branch to an undefined weak symbol that does not have a PLT
entry should resolve to the next instruction. The thunk generation code
can prevent this from happening as a range extension thunk can be generated
if the branch is sufficiently far away from 0, the value of an undefined
weak symbol.
The fix is taken from the Arm implementation of needsThunk(), we prevent a
thunk from being generated to an undefined weak symbol.
fixes pr44451
Differential Revision: https://reviews.llvm.org/D72267
Both MS link.exe and GNU ld.bfd handle it this way; one can have
multiple object files defining the same absolute symbols, as long
as it defines it to the same value. But if there are multiple absolute
symbols with differing values, it is treated as an error.
Differential Revision: https://reviews.llvm.org/D71981
Summary:
I used this information to motivate splitting up the Intrinsic::ID enum
(5d986953c8) and adding a key method to
clang::Sema (586f65d31f) which saved a
fair amount of object file size.
Example output for clang.pdb:
Top 10 types responsible for the most TPI input bytes:
index total bytes count size
0x3890: 8,671,220 = 1,805 * 4,804
0xE13BE: 5,634,720 = 252 * 22,360
0x6874C: 5,181,600 = 408 * 12,700
0x2A1F: 4,520,528 = 1,574 * 2,872
0x64BFF: 4,024,020 = 469 * 8,580
0x1123: 4,012,020 = 2,157 * 1,860
0x6952: 3,753,792 = 912 * 4,116
0xC16F: 3,630,888 = 633 * 5,736
0x69DD: 3,601,160 = 985 * 3,656
0x678D: 3,577,904 = 319 * 11,216
In this case, we can see that record 0x3890 is responsible for ~8MB of
total object file size for objects in clang.
The user can then use llvm-pdbutil to find out what the record is:
$ llvm-pdbutil dump -types -type-index 0x3890
Types (TPI Stream)
============================================================
Showing 1 records.
0x3890 | LF_FIELDLIST [size = 4804]
- LF_STMEMBER [name = `WORDTYPE_MAX`, type = 0x1001, attrs = public]
- LF_MEMBER [name = `U`, Type = 0x37F0, offset = 0, attrs = private]
- LF_MEMBER [name = `BitWidth`, Type = 0x0075 (unsigned), offset = 8, attrs = private]
- LF_METHOD [name = `APInt`, # overloads = 8, overload list = 0x3805]
...
In this case, we can see that these are members of the APInt class,
which is emitted in 1805 object files.
The next largest type is ASTContext:
$ llvm-pdbutil dump -types -type-index 0xE13BE bin/clang.pdb
0xE13BE | LF_FIELDLIST [size = 22360]
- LF_BCLASS
type = 0x653EA, offset = 0, attrs = public
- LF_MEMBER [name = `Types`, Type = 0x653EB, offset = 8, attrs = private]
- LF_MEMBER [name = `ExtQualNodes`, Type = 0x653EC, offset = 24, attrs = private]
- LF_MEMBER [name = `ComplexTypes`, Type = 0x653ED, offset = 48, attrs = private]
- LF_MEMBER [name = `PointerTypes`, Type = 0x653EE, offset = 72, attrs = private]
...
ASTContext only appears 252 times, but the list of members is long, and
must be repeated everywhere it is used.
This was the output before I split Intrinsic::ID:
Top 10 types responsible for the most TPI input:
0x686C: 69,823,920 = 1,070 * 65,256
0x686D: 69,819,640 = 1,070 * 65,252
0x686E: 69,819,640 = 1,070 * 65,252
0x686B: 16,371,000 = 1,070 * 15,300
...
These records were all lists of intrinsic enums.
Reviewers: MaskRay, ruiu
Subscribers: mgrang, zturner, thakis, hans, akhuang, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71437
Rather than handling zlib handling manually, use `find_package` from CMake
to find zlib properly. Use this to normalize the `LLVM_ENABLE_ZLIB`,
`HAVE_ZLIB`, `HAVE_ZLIB_H`. Furthermore, require zlib if `LLVM_ENABLE_ZLIB` is
set to `YES`, which requires the distributor to explicitly select whether
zlib is enabled or not. This simplifies the CMake handling and usage in
the rest of the tooling.
This restores 68a235d07f,
e6c7ed6d21. The problem with the windows
bot is a need for clearing the cache.
LLD warns if it encounters malformed debug data when parsing line
information for an undefined reference. We only want to warn once.
This patch adds additional checking to make sure the warnings are
printed only once, both for variables within the same program and
variables in later line programs.
Reviewed by: grimar, MaskRay
Differential Revision: https://reviews.llvm.org/D71759
This reverts commit 68a235d07f.
This commit broke the clang-x64-windows-msvc build bot and a follow-up
commit did not fix it. Reverting to fix the bot.
Rather than handling zlib handling manually, use `find_package` from CMake
to find zlib properly. Use this to normalize the `LLVM_ENABLE_ZLIB`,
`HAVE_ZLIB`, `HAVE_ZLIB_H`. Furthermore, require zlib if `LLVM_ENABLE_ZLIB` is
set to `YES`, which requires the distributor to explicitly select whether
zlib is enabled or not. This simplifies the CMake handling and usage in
the rest of the tooling.
GCC before r245813 (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79439)
did not emit nop after b/bl. This can happen with recursive calls.
r245813 was back ported to GCC 5.5 and GCC 6.4.
This is common, for example, libstdc++.a(locale.o) shipped with GCC 4.9
and many objects in netlib lapack can cause lld to error. gold allows
such calls to the same section. Our __plt_foo symbol's `section` field
is used for ThunkSection, so we can't implement a similar loosen rule
easily. But we can make use of its `file` field which is currently NULL.
Differential Revision: https://reviews.llvm.org/D71639
Similar to D71509 (EM_PPC64), on EM_PPC, the IPLT code sequence should
be similar to a PLT call stub. Unlike EM_PPC64, EM_PPC -msecure-plt has
small/large PIC model differences.
* -fpic/-fpie: R_PPC_PLTREL24 r_addend=0. The call stub loads an address relative to `_GLOBAL_OFFSET_TABLE_`.
* -fPIC/-fPIE: R_PPC_PLTREL24 r_addend=0x8000. (A partial linked object
file may have an addend larger than 0x8000.) The call stub loads an address relative to .got2+0x8000.
Just assume large PIC model for now. This patch makes:
// clang -fuse-ld=lld -msecure-plt -fno-pie -no-pie a.c
// clang -fuse-ld=lld -msecure-plt -fPIE -pie a.c
#include <stdio.h>
static void impl(void) { puts("meow"); }
void thefunc(void) __attribute__((ifunc("resolver")));
void *resolver(void) { return &impl; }
int main(void) {
thefunc();
void (*theptr)(void) = &thefunc;
theptr();
}
work on Linux glibc. -fpie will crash because the compiler and the
linker do not agree on the value which r30 stores (_GLOBAL_OFFSET_TABLE_
vs .got2+0x8000).
Differential Revision: https://reviews.llvm.org/D71621
Non-preemptible IFUNC are placed in in.iplt (.glink on EM_PPC64). If
there is a non-GOT non-PLT relocation, for pointer equality, we change
the type of the symbol from STT_IFUNC and STT_FUNC and bind it to the
.glink entry.
On EM_386, EM_X86_64, EM_ARM, and EM_AARCH64, the PLT code sequence
loads the address from its associated .got.plt slot. An IPLT also has an
associated .got.plt slot and can use the same code sequence.
On EM_PPC64, the PLT code sequence is actually a bl instruction in
.glink . It jumps to `__glink_PLTresolve` (the PLT header). and
`__glink_PLTresolve` computes the .plt slot (relocated by
R_PPC64_JUMP_SLOT).
An IPLT does not have an associated R_PPC64_JUMP_SLOT, so we cannot use
`bl` in .iplt . Instead, create a call stub which has a similar code
sequence as PPC64PltCallStub. We don't save the TOC pointer, so such
scenarios will not work: a function pointer to a non-preemptible ifunc,
which resolves to a function defined in another DSO. This is the
restriction described by https://sourceware.org/glibc/wiki/GNU_IFUNC
(though on many architectures it works in practice):
Requirement (a): Resolver must be defined in the same translation unit as the implementations.
If an ifunc is taken address but not called, technically we don't need
an entry for it, but we currently do that.
This patch makes
// clang -fuse-ld=lld -fno-pie -no-pie a.c
// clang -fuse-ld=lld -fPIE -pie a.c
#include <stdio.h>
static void impl(void) { puts("meow"); }
void thefunc(void) __attribute__((ifunc("resolver")));
void *resolver(void) { return &impl; }
int main(void) {
thefunc();
void (*theptr)(void) = &thefunc;
theptr();
}
work on Linux glibc and FreeBSD. Calling a function pointer pointing to
a Non-preemptible IFUNC never worked before.
Differential Revision: https://reviews.llvm.org/D71509
This restores commit 1417558e4a and its follow-up, reverted by commit c3dbd782f1.
After this commit:
clang -fuse-ld=bfd -no-pie -nostdlib a.c => .interp not created
clang -fuse-ld=bfd -pie -fPIE -nostdlib a.c => .interp created
clang -fuse-ld=gold -no-pie -nostdlib a.c => .interp not created
clang -fuse-ld=gold -pie -fPIE -nostdlib a.c => .interp created
clang -fuse-ld=lld -no-pie -nostdlib a.c => .interp created
clang -fuse-ld=lld -pie -fPIE -nostdlib a.c => .interp created
This reverts commit 1417558e4a.
Also reverts commit 019a92bb28.
This causes check-sanitizer to fail. The "-Nolib" variant of the test
crashes on startup in the loader.
Similar to rL362355, but with the `!config->shared` guard.
(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
Linux powerpc discards `*(.gnu.version*)` (arch/powerpc/kernel/vmlinux.lds.S)
to suppress --orphan-handling=warn warnings in the -pie output `.tmp_vmlinux1`
The support is simple. Just add isLive() to:
1) Fix an assertion in SectionBase::getPartition() called by VersionTableSection::isNeeded().
2) Suppress DT_VERSYM, DT_VERDEF, DT_VERNEED and DT_VERNEEDNUM, if the relevant section is discarded.
Reviewed By: grimar
Differential Revision: https://reviews.llvm.org/D71819
For undef-not-suggest.test, we currently make redundant alternative
spelling suggestions:
```
ld.lld: error: relocation refers to a discarded section: .text.foo
>>> defined in a.o
>>> section group signature: foo
>>> prevailing definition is in a.o
>>> referenced by a.o:(.rodata+0x0)
>>> did you mean:
>>> defined in: a.o
ld.lld: error: relocation refers to a symbol in a discarded section: foo
>>> defined in a.o
>>> section group signature: foo
>>> prevailing definition is in a.o
>>> referenced by a.o:(.rodata+0x8)
>>> did you mean: for
>>> defined in: a.o
```
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D71735
Summary:
If none of the input files are ELF object files (for example, when
generating an object file from a single binary input file via
"-b binary"), use a fallback value for the ELF header flags instead
of crashing with an assertion failure.
Reviewers: MaskRay, ruiu, espindola
Reviewed By: MaskRay, ruiu
Subscribers: kevans, grimar, emaste, arichardson, asb, rbar, johnrusso, simoncook, sabuasal, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, lenary, s.egerton, pzheng, sameer.abuasal, apazos, luismarques, llvm-commits, jrtc27
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71101
Previously this caused crashes in the reportDuplicate method.
A DefinedAbsolute doesn't have any InputFile attached to it, so we
can't report the file for the original symbol.
We could add an InputFile argument to SymbolTable::addAbsolute
only for the sake of error reporting, but even then it'd be assymetrical,
only pointing out the file containing the new conflicting definition,
not the original one.
Differential Revision: https://reviews.llvm.org/D71679
GNU ld creates the synthetic section .iplt, and has a built-in linker
script that assigns .iplt to the output section .plt . There is no
output section named .iplt .
Making .iplt an output section actually has a benefit that makes the
tricky toolchain feature stand out. Symbolizers don't have to deal with
mixed PLT entries (e.g. llvm-objdump -d incorrectly annotates such jump
targets).
On EM_PPC{,64}, .glink contains a PLT resolver and a series of jump
instructions. The 4-byte entry size makes it unnecessary to have an
alignment of 16.
Mark ppc32-gnu-ifunc.s and ppc32-gnu-ifunc-nonpreemptable.s as `XFAIL: *`.
They test IPLT on EM_PPC, which never works.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D71520
PltSection is used by both PLT and IPLT. The PLT section may have a
header while the IPLT section does not. Split off IpltSection from
PltSection to be clearer.
Unlike other targets, PPC64 cannot use the same code sequence for PLT
and IPLT. This helps make a future PPC64 patch (D71509) more isolated.
On EM_386 and EM_X86_64, when PLT is empty while IPLT is not, currently
we are inconsistent whether the PLT header is conceptually attached to
in.plt or in.iplt . Consistently attach the header to in.plt can make
the -z retpolineplt logic simpler. It also makes `jmp` point to an
aesthetically better place for non-retpolineplt cases.
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D71519
This change only affects EM_386. relOff can be computed from `index`
easily, so it is unnecessarily passed as a parameter.
Both in.plt and in.iplt entries are written by writePLT. For in.iplt,
the instruction `push reloc_offset` will change because `index` is now
different. Fortunately, this does not matter because `push; jmp` is only
used by PLT. IPLT does not need the code sequence.
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D71518
This reverts commit 2bbd32f5e8, it was
causing UBSan failures like the following:
lld/ELF/Target.cpp:103:41: runtime error: applying non-zero offset 24 to null pointer
When a common symbol is merged with a shared symbol, increase st_size if
the shared symbol has a larger st_size. At runtime, the executable's
symbol overrides the shared symbol. The shared symbol may be created
from common symbols in a previous link. This rule makes sure we pick
the largest size among all common symbols.
This behavior matches GNU ld. See
https://sourceware.org/bugzilla/show_bug.cgi?id=25236 for discussions.
A shared symbol does not hold alignment constraints. Ignore the
alignment update.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D71161
Summary:
So far it seems like the only test affected by this change is the one I
recently added for R_MIPS_JALR relocations since the other test cases that
use this function early (unknown-relocation-*) do not have a valid input
section for the relocation offset.
Reviewers: ruiu, grimar, MaskRay, espindola
Reviewed By: ruiu, MaskRay
Subscribers: emaste, sdardis, jrtc27, atanasyan, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70659
This is equivalent to the existing `import_name` and `import_module`
attributes which control the import names in the final wasm binary
produced by lld.
This maps the existing
This attribute currently requires a string rather than using the
symbol name for a couple of reasons:
1. Avoid confusion with static and dynamic linking which is
based on symbol name. Exporting a function from a wasm module using
this directive is orthogonal to both static and dynamic linking.
2. Avoids name mangling.
Differential Revision: https://reviews.llvm.org/D70520
On some edge cases such as Chromium compiled with full instrumentation we
have a .text section over twice the size of the maximum branch range and
the instrumented code generation containing many examples of the erratum
sequence. The combination of Thunks and many erratum sequences causes
finalizeAddressDependentContent() to not converge. We end up with:
start
- Thunk Creation (disturbs addresses after thunks, creating more patches)
- Patch Creation (disturbs addresses after patches, creating more thunks)
- goto start
In most images with few thunks and patches the mutual disturbance does not
cause convergence problems. As the .text size and number of patches go up
the risk increases.
A way to prevent the thunk creation from interfering with patch creation is
to round up the size of the thunks to a 4KiB boundary when the
erratum patch is enabled. As the erratum sequence only triggers when an
instruction sequence starts at 0xff8 or 0xffc modulo (4 KiB) by making the
thunks not affect addresses modulo (4 KiB) we prevent thunks from
interfering with the patch.
The patches themselves could be aggregated in the same way that Thunks are
within ThunkSections and we could round up the size in the same way. This
would reduce the number of patches created in a .text section size >
128 MiB but would not likely help convergence problems.
Differential Revision: https://reviews.llvm.org/D71281
fixes (remaining part of) pr44071, other part in D71242
The code to insert patch section merges them with a comparison function that
uses logic of the form:
return (isa<PatchSection>(a) && !isa<PatchSection>(b));
If the PatchSections don't implement classof this check fails if b is also
a SyntheticSection. This can result in the patches being out of range if
the SyntheticSection is big, for example a ThunkSection with lots of thunks.
Differential Revision: https://reviews.llvm.org/D71242
fixes (part of) pr44071
clang/gcc -fdebug-type-sections places .debug_types and
.rela.debug_types in a section group, with a signature symbol which
represents the type signature. The section group is for deduplication
purposes.
After D70146, we will discard such section groups. Refine the rule so
that we will retain the group if no member has the SHF_ALLOC flag.
GNU ld has a similar rule to retain the group if all members have the
SEC_DEBUGGING flag. We try to be more general for future-proof purposes:
if other non-SHF_ALLOC sections have deduplication needs, they may be
placed in a section group. Don't discard them.
Reviewed By: grimar
Differential Revision: https://reviews.llvm.org/D71157
Fixes PPC64 part of PR40438
// clang -target ppc64le -c a.cc
// .text.unlikely may be placed in a separate output section (via -z keep-text-section-prefix)
// The distance between bar in .text.unlikely and foo in .text may be larger than 32MiB.
static void foo() {}
__attribute__((section(".text.unlikely"))) static int bar() { foo(); return 0; }
__attribute__((used)) static int dummy = bar();
This patch makes such thunks with addends work for PPC64.
AArch64: .text -> `__AArch64ADRPThunk_ (adrp x16, ...; add x16, x16, ...; br x16)` -> target
PPC64: .text -> `__long_branch_ (addis 12, 2, ...; ld 12, ...(12); mtctr 12; bctr)` -> target
AArch64 can leverage ADRP to jump to the target directly, but PPC64
needs to load an address from .branch_lt . Before Power ISA v3.0, the
PC-relative ADDPCIS was not available. .branch_lt was invented to work
around the limitation.
Symbol::ppc64BranchltIndex is replaced by
PPC64LongBranchTargetSection::entry_index which take addends into
consideration.
The tests are rewritten: ppc64-long-branch.s tests -no-pie and
ppc64-long-branch-pi.s tests -pie and -shared.
Reviewed By: sfertile
Differential Revision: https://reviews.llvm.org/D70937
The .note.gnu.property SHT_NOTE sections on AArch64 (a 64-bit target)
should have alignment 8 to more closely match the binutils implementation
where alignment is 4-bytes on 32-bit machines and 8-bytes on 64-bit
machines.
Previously LLD was using 4 for both 32-bit and 64-bit machines.
Differential Revision: https://reviews.llvm.org/D70962
The PT_GNU_PROPERTY program header describes the location of the
.note.gnu.property SHT_NOTES section. The linux kernel uses this program
header to find the .note.gnu.property section rather than parsing.
Executables that have properties that the kernel needs to act on that don't
have the PT_GNU_PROPERTY program header will not boot.
Differential Revision: https://reviews.llvm.org/D70961
Fixes AArch64 part of PR40438
The current range extension thunk framework does not handle a relocation
relative to a STT_SECTION symbol with a non-zero addend, which may be
used by jumps/calls to local functions on some RELA targets (AArch64,
powerpc ELFv1, powerpc64 ELFv2, etc). See PR40438 and the following
code for examples:
// clang -target $target a.cc
// .text.cold may be placed in a separate output section.
// The distance between bar in .text.cold and foo in .text may be larger than 128MiB.
static void foo() {}
__attribute__((section(".text.cold"))) static int bar() { foo(); return
0; }
__attribute__((used)) static int dummy = bar();
This patch makes such thunks with addends work for AArch64. The target
independent part can be reused by PPC in the future.
On REL targets (ARM, MIPS), jumps/calls are not represented as
STT_SECTION + non-zero addend (see
MCELFObjectTargetWriter::needsRelocateWithSymbol), so they don't need
this feature, but we need to make sure this patch does not affect them.
Reviewed By: peter.smith
Differential Revision: https://reviews.llvm.org/D70637
This is a follow-up discussed in D70495 thread.
The current logic is unusual for llvm-readobj. It doesn't print predecessors
list when it is empty. This is not good for machine parsers.
D70495 had to add this condition during refactoring to reduce amount of changes,
in tests, because the original code also had a similar logic.
Now seems it is time to get rid of it. This patch does it.
Differential revision: https://reviews.llvm.org/D70717
The previous data had the same length with compression levels 1 and 6
for zlib 1.2.8. Adjust the test to work for this library version. I've
also tested this with zlib 1.2.7 and zlib 1.2.11.
Currently LLD always use zlib compression level 6.
This patch changes it to use 1 for -O0, -O1 and 6 for -O2.
It fixes https://bugs.llvm.org/show_bug.cgi?id=44089.
There was also a thread in llvm-dev on this topic:
https://lists.llvm.org/pipermail/llvm-dev/2018-August/125020.html
Here is a table with results of building clang mentioned there:
```
Level Time Size
0 0m17.128s 2045081496 Z_NO_COMPRESSION
1 0m31.471s 922618584 Z_BEST_SPEED
2 0m32.659s 903642376
3 0m36.749s 890805856
4 0m41.532s 876697184
5 0m48.383s 862778576
6 1m3.176s 855251640 Z_DEFAULT_COMPRESSION
7 1m15.335s 853755920
8 2m0.561s 852497560
9 2m33.972s 852397408 Z_BEST_COMPRESSION
```
It shows that it is probably not reasonable to use values greater than 6.
Differential revision: https://reviews.llvm.org/D70658
In GNU ld, -Ttext sets the address of the .text section and -Ttext-segment sets the address of the text segment (RX).
gold only supports the -Ttext-segment semantic and treats -Ttext as an alias for -Ttext-segment.
lld only supports the -Ttext semantic and treats -Ttext-segment as an
alias for -Ttext. The text segment will be assigned to an address less
than the specified -Ttext-segment value.
This patch drops the -Ttext-segment alias.
The text segment is traditionally the first segment. Users who specify
-Ttext-segment may actually want to specify --image-base, the lld way to
express this. Unfortunately currently this is supported by GNU ld's
COFF port but not by its ELF port. gold does not support this option.
With -z separate-code, the behavior of GNU ld -Ttext-segment is weird (see https://sourceware.org/bugzilla/show_bug.cgi?id=25207)
rL289827 introduced the alias for linking qemu's non-pie user mode
binaries. As explained previously, this actually assigns the text
segment to an address less than 0x60000000. I feel that a better fix is
on the qemu side:
https://lists.nongnu.org/archive/html/qemu-devel/2019-11/msg02480.html
Reviewed By: grimar, ruiu
Differential Revision: https://reviews.llvm.org/D70468
Summary:
Current versions of clang would erroneously emit this relocation not only
against functions (loaded from the GOT) but also against data symbols
(e.g. a table of function pointers). LLD was then changing this into a
branch-and-link instruction, causing the program to jump to the data
symbol at run time. I discovered this problem when attempting to boot
MIPS64 FreeBSD after updating the to the latest upstream master.
Reviewers: atanasyan, jrtc27, espindola
Reviewed By: atanasyan
Subscribers: emaste, sdardis, krytarowski, MaskRay, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70406
Our elf-versioninfo.test is not perfect. It does not properly test how
flags are dumped and also we have a bug: they are dumped as enums in
LLVM style now, i.e not dumped properly.
GNU style uses a `versionFlagToString` method to build a string from flags
which seems is consistent with GNU readelf.
In this patch I fixed the issues mentioned.
Differential revision: https://reviews.llvm.org/D70399
Based on D70020 by serge-sans-paille.
The ELF spec says:
> Furthermore, there may be internal references among these sections that would not make sense if one of the sections were removed or replaced by a duplicate from another object. Therefore, such groups must be included or omitted from the linked object as a unit. A section cannot be a member of more than one group.
GNU ld has 2 behaviors that we don't have:
- Group members (nextInSectionGroup != nullptr) are subject to garbage collection.
This includes non-SHF_ALLOC SHT_NOTE sections.
In particular, discarding non-SHF_ALLOC SHT_NOTE sections is an expected behavior by the Annobin
project. See
https://developers.redhat.com/blog/2018/02/20/annobin-storing-information-binaries/
for more information.
- Groups members are retained or discarded as a unit.
Members may have internal references that are not expressed as
SHF_LINK_ORDER, relocations, etc. It seems that we should be more conservative here:
if a section is marked live, mark all the other member within the
group.
Both behaviors are reasonable. This patch implements them.
A new field InputSectionBase::nextInSectionGroup tracks the next member
within a group. on ELF64, this increases sizeof(InputSectionBase) froms
144 to 152.
InputSectionBase::dependentSections tracks section dependencies, which
is used by both --gc-sections and /DISCARD/. We can't overload it for
the "next member" semantic, because we should allow /DISCARD/ to discard
sections independent of --gc-sections (GNU ld behavior). This behavior
may be reasonably used by `/DISCARD/ : { *(.ARM.exidx*) }` or `/DISCARD/
: { *(.note*) }` (new test `linkerscript/discard-group.s`).
Reviewed By: ruiu
Differential Revision: https://reviews.llvm.org/D70146
/align is not supposed to be used without /driver, so it makes sense
to warn if only /align is passed. MSVC link.exe warns on this too.
Differential Revision: https://reviews.llvm.org/D70163
This broke in 51dcb292cc, "[lld-link] diagnose undefined symbols
before LTO when possible" (very soon after the 9.0 branch, so
luckily the 9.0 release is unaffected).
The code for loading objects we believe might be needed for autoimport
(loadMinGWAutomaticImports()) does run before the new
reportUnresolvable() function, but it had a condition to only operate
on symbols from regular object files. This condition came from
resolveRemainingUndefines(), but as loadMinGWAutomaticImports() now
has to operate before the LTO, it has to operate on undefineds from
LTO objects as well.
Differential Revision: https://reviews.llvm.org/D70166
Recommit r373168, which was reverted by r373242. This actually exposed a
boringssl bug which has been fixed for more than one month.
For the following two cases, we currently suppress the symbols. This
patch emits them (compatible with GNU as).
* `test2_a = undef`: if `undef` is otherwise unused.
* `.hidden hidden`: if `hidden` is unused. This is the main point of the
patch, because omitting the symbol would cause a linker semantic
difference.
It causes a behavior change that is not compatible with GNU as:
.weakref foo1, bar1
When neither foo1 nor bar1 is used, we now emit bar1, which is arguably
more consistent.
Another change is that we will emit .TOC. for .TOC.@tocbase . For this
directive, suppressing .TOC. can be seen as a size optimization, but we
choose to drop it for simplicity and consistency.
Fangrui Song