Accept name=value as part of a !DIR$ compiler directive.  These
are currently ignored in semantics, but we should recognize
more directive forms to facilitate testing.  In due course,
these placeholding directive parsers will be replaced.

Reviewed By: sscalpone

Differential Revision: https://reviews.llvm.org/D84077

This reverts commit 30c382a7.

See https://crbug.com/1106813.

The `intrinsics_gen` target exists in the CMake exports since r309389
(see LLVMConfig.cmake.in), hence projects can depend on `intrinsics_gen`
even it they are built separately from LLVM.

Reviewed By: MaskRay, JDevlieghere

Differential Revision: https://reviews.llvm.org/D83454

https://reviews.llvm.org/D84072

Add G_EXTRACT to CSEConfigFull and add unit test as well.

This reverts commit d76e62fd.

Reverting since this can lead to linker errors:

```
ld.lld: error: undefined hidden symbol: __start_asan_globals
```

when using --gc-sections. The linker can discard __start_asan_globals
once there are no more `asan_globals` sections left, which can lead to
this error if we have external linkages to them.

Old-style C /*comments*/ are omitted from preprocessor directive
token sequences by the prescanner, but line-ending C++ and Fortran
free-form comments are not since their handling might depend on
the directive.  Add code to skip these line-ending comments as
appropriate in place of existing code that just skipped blanks.

Reviewed By: sscalpone

Differential Revision: https://reviews.llvm.org/D84061

hwloc documentation guarantees the only object that is always present
in the topology is PU. We can check the presence of other objects
in the topology, just in case.

Differential Revision: https://reviews.llvm.org/D84065

In clang <3.9 the `unique_ptr` constructor that is supposed to allow
for Derived to Base conversion does not work. Remove this if we drop
support for such configurations.

This is the same fix as in fda901a9, and it updates the comments
to better reflect the actual issue. The same thing reproduces with
libc++ with older clangs.

as it's causing a few unused variable warnings via the macro instantiation:

sources/llvm-project/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def:649:17: error: unused variable 'InaccessibleOnlyAttrs' [-Werror,-Wunused-variable]
__OMP_ATTRS_SET(InaccessibleOnlyAttrs,
                ^

This reverts commit 09fe0c5a.

Temporarily Revert "[InlineAdvisor] New inliner advisor to replay inlining from optimization remarks"
as it is failing the inline-replay.ll test as well as sanitizers/Werror
from returning a stack local variable.

This reverts commit 029946b1.

Summary:
This patch adds more function attribute information to the runtime function definitions in OMPKinds.def. The goal is to provide sufficient information about OpenMP runtime functions to perform more optimizations on OpenMP code.

Reviewers: jdoerfert

Subscribers: aaron.ballman cfe-commits yaxunl guansong sstefan1 llvm-commits

Tags: #OpenMP #clang #llvm

Differential Revision: https://reviews.llvm.org/D81031

Fix build failure in Fuchsia build from refactoring in
5d2be1a1

Guard the moved versions of ReserveShadowMemoryRange and ProtectGap
the same way they were in the asan code originally (not for Fuchsia or
RTEMS). Otherwise we end up with unsats as they invoke functions not
defined there.

Anonymous Fortran unit files (e.g., "./fort.7") need to be created
O_RDWR so that they can be written, rewound, and read.  Other
files opened with no ACTION= specifier need to set read/write
permissions based on the file, if it exists.

Reviewed By: sscalpone

Differential Revision: https://reviews.llvm.org/D84063

Summary:
This change added a new inline advisor that takes optimization remarks for previous inlining as input, and provide the decision as advice so current inlining can replay inline decision of a different compilation. Dwarf inline stack with line and discriminator is used as anchor for call sites. The change can be useful for Inliner tuning.
A switch -sample-profile-inline-replay=<inline_remarks_file> is added to hook up the new inliner advisor with SampleProfileLoader's inline decision for replay. The new inline advisor can also be used by regular CGSCC inliner later if needed.

Reviewers: davidxl, mtrofin, wmi, hoy

Subscribers: aprantl, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D83743

On AIX, the semantic of global_dtors contains __sterm functions associated with C++
cleanup actions and user-declared __attribute__((destructor)) functions. We should
never merely register __sterm with atexit(), so currently
-fregister_global_dtors_with_atexit does not work well on AIX: It would cause
finalization actions to not occur when unloading shared libraries.  We need to figure
out a way to handle that when we start supporting user-declared
__attribute__((destructor)) functions.

Currently we report_fatal_error on this option temporarily.

Differential Revision: https://reviews.llvm.org/D83974

Summary:
Splits the unwinder into a non-segv (for allocation/deallocation traces) and a
segv unwinder. This ensures that implementations can select an accurate, slower
unwinder in the segv handler (if they choose to use the GWP-ASan provided one).
This is important as fast frame-pointer unwinders (like the sanitizer unwinder)
don't like unwinding through signal handlers.

Reviewers: morehouse, cryptoad

Reviewed By: morehouse, cryptoad

Subscribers: cryptoad, mgorny, eugenis, pcc, #sanitizers

Tags: #sanitizers

Differential Revision: https://reviews.llvm.org/D83994

Reviewers: fhahn

Reviewed By: fhahn

Differential Revision: https://reviews.llvm.org/D83951

This is the one i'm seeing as missed optimization,
although there are likely other possibilities, as usual.

There are 4 variants of a general sdiv->udiv fold:
https://rise4fun.com/Alive/VS6

Name: v0
Pre: C0 >= 0 && C1 >= 0
%r = sdiv i8 C0, C1
  =>
%r = udiv i8 C0, C1

Name: v1
Pre: C0 <= 0 && C1 >= 0
%r = sdiv i8 C0, C1
  =>
%t0 = udiv i8 -C0, C1
%r = sub i8 0, %t0

Name: v2
Pre: C0 >= 0 && C1 <= 0
%r = sdiv i8 C0, C1
  =>
%t0 = udiv i8 C0, -C1
%r = sub i8 0, %t0

Name: v3
Pre: C0 <= 0 && C1 <= 0
%r = sdiv i8 C0, C1
  =>
%r = udiv i8 -C0, -C1


If we really don't like sdiv (more than udiv that is),
and are okay with increasing instruction count (2 new negations),
and we ensure that we don't undo the fold,
then we could just implement these..

BeginInternalListInput and BeginInternalListOutput were missing
from the I/O API implementation; add them.

Reviewed By: PeteSteinfeld

Differential Revision: https://reviews.llvm.org/D84066

This is a workaround for a bug in older versions of Clang when. The
constructor that is supposed to allow for Derived to Base conversion
does not work. Remove this if we drop support for such configurations.

Added IsSameV as a convenience variable and used it where convenient.

Reviewers: abrachet, lntue

Differential Revision: https://reviews.llvm.org/D83980

Summary:
* This test was failing in our builds that configure compiler-rt as the configure-time rtlib.
* Opted for this test fix instead of a rollback, and hopefully TI can fix forward if this weakens the tests beyond expectations.
* Suspected this failure introduced in D81676.

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D84058

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Matches C++20 API addition.

Differential Revision: https://reviews.llvm.org/D83449

Add barrier/region notification for parallel inside teams construct
when number of teams is 1, as VTune only shows outer level regions for
simplicity.

Differential Revision: https://reviews.llvm.org/D84024

I've got the report clang11 issues signed/unsigned mismatch
warning here. For some reason only clang11 seems to issue
this warning.

Differential Revision: https://reviews.llvm.org/D83916

Reduce sleep and time outs in GDB remote testcases to one default value
for each. Stop passing these values around and always use the default
instead.

Differential revision: https://reviews.llvm.org/D83904

Summary: The logic was conservative but inverted: cases that should remain unmasked became 1-D masked.

Differential Revision: https://reviews.llvm.org/D84051

These opcodes are not intended for public use.

Reviewers: arsenm, rampitec

Differential Revision: https://reviews.llvm.org/D81659

[clang][Tooling] Try to avoid file system access if there is no record for the file in compile_commads.json

Summary:
If there is no record in compile_commands.json, we try to find suitable record with `MatchTrie.findEquivalent()` call.
This is very expensive operation with a lot of `llvm::sys::fs::equivalent()` calls in some cases.

This patch disables file symlinks for performance reasons.

Example scenario without this patch:
- compile_commands.json generated at clangd build (contains ~3000 files).
- it tooks more than 1 second to get compile command for newly created file in the root folder of LLVM project.
- we wait for 1 second every time when clangd requests compile command for this file (at file change).

Reviewers: sammccall, kadircet, hokein

Reviewed By: sammccall

Subscribers: chandlerc, djasper, klimek, ilya-biryukov, kadircet, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D83621

Currently, BTF datasec type for .rodata is generated only if there are
user-defined readonly global variables which have debuginfo generated.

Certain readonly global variables may be generated from initialized
local variables. For example,
  void foo(const void *);
  int test() {
    const struct {
      unsigned a[4];
      char b;
    } val = { .a = {2, 3, 4, 5}, .b = 6 };
    foo(&val);
    return 0;
  }

The clang will create a private linkage const global to store
the initialized value:
  @__const.test.val = private unnamed_addr constant %struct.anon
      { [4 x i32] [i32 2, i32 3, i32 4, i32 5], i8 6 }, align 4

This global variable eventually is put in .rodata ELF section.

If there is .rodata ELF section, libbpf expects a BTF .rodata
datasec as well even though it may be empty meaning there are no
global readonly variables with proper debuginfo. Martin reported
a bug where without this empty BTF .rodata datasec, the bpftool
gen will exit with an error.

This patch fixed the issue by generating .rodata BTF datasec
if there exists local var intial data which will result in
.rodata ELF section.

Differential Revision: https://reviews.llvm.org/D84002

MSVC, by default, limits the number of sections generated by a single
translation unit to 2^16.  In a debug build, each function or method
can require 4 sections, so it's not uncommon to hit it.

I saw the problem when building tests for LLDB (but, interestingly, not
for LLDB itself).

Differential Revision: https://reviews.llvm.org/D83991

POSIX.1-2017 12.2 Utility Syntax Guidelines, Guideline 5 says:

> One or more options without option-arguments, followed by at most one option that takes an option-argument, should be accepted when grouped behind one '-' delimiter.

i.e. -abc represents -a -b -c. The grouped short options are very common.  Many
utilities extend the syntax by allowing (an option with an argument) following a
sequence of short options.

This patch adds the support to OptTable, similar to cl::Group for CommandLine
(D58711).  llvm-symbolizer will use the feature (D83530). CommandLine is exotic
in some aspects. OptTable is preferred if the user wants to get rid of the
behaviors.

* `cl::opt<bool> i(...)` can be disabled via -i=false or -i=0, which is
  different from conventional --no-i.
* Handling --foo & --no-foo requires a comparison of argument positions,
  which is a bit clumsy in user code.

OptTable::parseOneArg (non-const reference InputArgList) is added along with
ParseOneArg (const ArgList &). The duplicate does not look great at first
glance. However, The implementation can be simpler if ArgList is mutable.
(ParseOneArg is used by clang-cl (FlagsToInclude/FlagsToExclude) and lld COFF
(case-insensitive). Adding grouped short options can make the function even more
complex.)

The implementation allows a long option following a group of short options. We
probably should refine the code to disallow this in the future. Allowing this
seems benign for now.

Reviewed By: grimar, jhenderson

Differential Revision: https://reviews.llvm.org/D83639