New option --elf-output-style=LLVM or GNU
Enables -file-headers in readelf style when elf-output-style=GNU
Differential revision: http://reviews.llvm.org/D14128
llvm-svn: 260391
The encodings for floating point conditions A(lways) and N(ever) were
incorrectly specified for the assembly parser, per Sparc manual v8 page
121. This change corrects that mistake.
Also, strangely, all of the branch instructions already had MC test
cases, except for the broken ones. Added the tests.
Patch by Chris Dewhurst
Differential Revision: http://reviews.llvm.org/D17074
llvm-svn: 260390
Referencing a dllimported vtable is impossible in a constexpr
constructor. It would be friendlier to C++ programmers if we
synthesized a copy of the vftable which referenced imported virtual
functions. This would let us initialize the object in a way which
preserves both the intent to import functionality from another DLL while
also making constexpr work.
Differential Revision: http://reviews.llvm.org/D17061
llvm-svn: 260388
This patch uses one bit in profile version to differentiate Clang
instrumentation and IR level instrumentation profiles.
PGOInstrumenation generates a COMDAT variable __llvm_profile_raw_version so
that the compiler runtime can set the right profile kind.
For Maco-O platform, we generate the variable as linkonce_odr linkage as
COMDAT is not supported.
PGOInstrumenation now checks this bit to make sure it's an IR level
instrumentation profile.
The patch was submitted as r260164 but reverted due to a Darwin test breakage.
Original Differential Revision: http://reviews.llvm.org/D15540
Differential Revision: http://reviews.llvm.org/D17020
llvm-svn: 260385
Operating systems that are not unix-like are unlikely to have access to
catopen. Instead of black-listing each one, we now filter out all non-unix
operating systems first. We then exclude the unix-like operating systems
that don't have catopen. _WIN32 counts as a unix-like operating system
because of cygwin.
http://reviews.llvm.org/D16639
llvm-svn: 260381
"main include" that will be the 1st include (category 0).
Because the clang-format visual studio extension does not pass the file
name and use the standard input, sort include cannot find a "main
include":
Testing fix on llvm\tools\clang\lib\Format\Format.cpp:
Original file:
#include "clang/Format/Format.h"
...
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
Without fix, selecting the includes and running visual studio
clang-format:
...
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "clang/Lex/Lexer.h"
With fix, selecting the includes and running visual studio clang-format:
#include "clang/Format/Format.h"
...
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
Test 2 with main header not at the start:
Original file:
...
#include "clang/Format/Format.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
Without fix, selecting the includes and running visual studio
clang-format:
...
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "clang/Lex/Lexer.h"
With fix, selecting the includes and running visual studio clang-format:
#include "clang/Format/Format.h"
...
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
Patch by Jean-Philippe Dufraigne, thank you.
Review: http://reviews.llvm.org/D16524
llvm-svn: 260378
This patch is to upgrade FunctionTypeUnwrapper for correct processing of
AttributedType. Fixes PR25786.
Patch by Alexander Makarov.
Differential Revision: http://reviews.llvm.org/D15373
llvm-svn: 260373
* Generate artificial symbol names from eh_fame during symbol parsing
so these symbols are already present when we calcualte the size of
the symbols where 0 is specified.
* Fix symbol size calculation for the last symbol in the file where
it have to last until the end of the parent section.
Differential revision: http://reviews.llvm.org/D16996
llvm-svn: 260369
The IT instruction can specify condition code for up to 4 consecutive
instruction and it is used quite often by clang in epilogues causing
an issue when trying to unwind from locations covered by the IT
instruction and for locatins inmediately after the IT instruction.
Changes made to fix it:
* Introduce the concept of conditional instruction block what is a list
of consecutive instructions with the same condition. We update the
unwind information during the conditional instruction block and when
we reach the end of it (first instruction with a differemt condition)
then we restore the unwind information we had before the condition.
* Fix a bug in the ARM instruction emulator where neither PC nor the
ITSTATE was advanced when we reached an instruction what we can't
decode.
After the change we have no regression on android-arm running the
regular test suit and TestStandardUnwind also passes when running it
with clang as the compiler (previously it failed on an IT instruction).
Differential revision: http://reviews.llvm.org/D16814
llvm-svn: 260368
The UDF instruction is deprecated in armv7 and in case of thumb2
instructions set it don't work well together with the IT instruction.
Differential revision: http://reviews.llvm.org/D16853
llvm-svn: 260367
MIPS 32-bit ABI uses REL relocation record format. We read addends from
relocation destinations right in the MipsTargetInfo::relocateOne
function.
llvm-svn: 260364
Patch by Rong Xu
The problem is exposed by intra-module indirect call promotion where
prof symtab is created from module which does not contain all symbols
from the program. With partial symtab, the result needs to be checked
more strictly.
llvm-svn: 260361
r257357 fixed clang to warn on integer overflow in struct initializers.
However, it didn't warn when a struct had a nested initializer. This
commit makes changes in Sema::CheckForIntOverflow to handle nested
initializers.
For example:
struct s {
struct t {
unsigned x;
} t;
} s = {
{
.x = 4 * 1024 * 1024 * 1024
}
};
rdar://problem/23526454
llvm-svn: 260360
case where you have:
1 -> foo (bar(),
2 baz(),
3 lala());
4
You are sitting on line 1, and want to step into foo, but not bar, baz & lala. Unfortunately
there are line table entries for lines 1-3, and lldb doesn't know anything about the nesting
of statement in these lines. So we'll have to use the user's intelligence... This patch adds:
(lldb) thread step-in -t foo --end-line 4
That tells lldb to keep stepping in till line 4, but stop if you step into foo. I think I would
remember to use this when faced with some of the long gnarly call sequences in lldb. But there
might be ways I haven't thought of to make it more convenient. Jason suggests having "end" as a
special token for --end-line which just means keep going to the end of the function, I really want
to get into this thing...
There should be an SB API and tests, which will come if this seems useful.
llvm-svn: 260352
The explicit APIs on SBValue obviously remain if one wants to be explicit in intent, or override this guess, but since __int__() has to pick one, an educated guess is definitely better than than always going to signed regardless
Fixes rdar://24556976
llvm-svn: 260349
For multi-stage builds we need to pass any overridden source directory variables. Without passing these the subsequent stages won't find the project sources.
llvm-svn: 260341
I had hoped this would work from a single cache file, but turns out there is a bug I can't quite figure out relating to passing list arguments to recursive CMake invocations.
This change works around that.
llvm-svn: 260340
This patch adds a new class, OrcI386, which contains the hooks needed to
support lazy-JITing on i386 (currently only for Pentium 2 or above, as the JIT
re-entry code uses the FXSAVE/FXRSTOR instructions).
Support for i386 is enabled in the LLI lazy JIT and the Orc C API, and
regression and unit tests are enabled for this architecture.
llvm-svn: 260338
<string.h> and wcschr, wcspbrk, wcsrchr, wmemchr, and wcsstr from <wchar.h> to
provide a const-correct overload set even when the underlying C library does
not.
This change adds a new macro, _LIBCPP_PREFERRED_OVERLOAD, which (if defined)
specifies that a given overload is a better match than an otherwise equally
good function declaration without the overload. This is implemented in modern
versions of Clang via __attribute__((enable_if)), and not elsewhere.
We use this new macro to define overloads in the global namespace for these
functions that displace the overloads provided by the C library, unless we
believe the C library is already providing the correct signatures.
llvm-svn: 260337
Summary:
Tests for this will be added once the AMDGPU backend enables this
option.
Reviewers: arsenm
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D16602
llvm-svn: 260336
Hemant Kulkarni