Instead of "if (common_flags()->verbosity) Report(...)" we now have macros.

llvm-svn: 196497

llvm-svn: 196491

[tsan] fix the include path that is broken in configure/make build but works in cmake build (PR18144). This is a quick fix. Will need to fix the configure/make build properly

llvm-svn: 196490

llvm-svn: 196379

[asan] require __i686__ for the SSE test; also make weaker claims about stack buffer overflows in another test

llvm-svn: 196375

llvm-svn: 196374

[asan] require __i686__ for the SSE test; also make weaker claims about stack buffer overflows in another test

llvm-svn: 196373

llvm-svn: 196364

llvm-svn: 196303

Expose a new interface function for debugging code built with sanitizer tools.
Add an ASan implementation.

llvm-svn: 196302

llvm-svn: 196097

llvm-svn: 195959

llvm-svn: 195958

llvm-svn: 195956

llvm-svn: 195845

llvm-svn: 195840

- running_on_valgrind was not parsed in some contexts
- refactor code a bit
- add comprehensive tests for flags parsing

llvm-svn: 195831

llvm-svn: 195443

llvm-svn: 195352

llvm-svn: 195250

llvm-svn: 195243

llvm-svn: 195131

[asan] new shadow poison magic for contiguous-container-buffer-overflow, addressed Alexey Samsonov's comments for r195011

llvm-svn: 195117

llvm-svn: 195015

llvm-svn: 195012

llvm-svn: 195011

llvm-svn: 194995

llvm-svn: 194958

llvm-svn: 194805

I still don't know what is causing our bootstrapped LTO buildbots to fail,
but llvm r194701 seems to be OK and I can't imagine that these changes could
cause the problem.

llvm-svn: 194790

Apple's bootstrapped LTO builds have been failing, and these changes (along
with llvm 194701) are the only things on the blamelist.  I will either reapply
these changes or help debug the problem, depending on whether this fixes the
buildbots.

llvm-svn: 194779

it does not work anyway and can cause significant slowdown

llvm-svn: 194711

llvm-svn: 194702

llvm-svn: 194696

llvm-svn: 194685

llvm-svn: 194583

Invoke a fatal stack trace unwinder when ASan prints allocator-relevant
error reports (double-free, alloc-dealloc-mismatch, invalid-free).
Thus we'll be able to print complete stack trace even if allocation/free
stacks are not stored (malloc_context_size=0).

Based on the patch by Yuri Gribov!

llvm-svn: 194579

llvm-svn: 194578

Fixes http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58994, which hadn't
manifested in LLVM because libclang_rt.asan_osx_dynamic.dylib used to depend on
the Foundation framework.
Without that dependency some interceptors may be called from the system
libraries before libSystem_initializer() is called, which lead to assertion
failures in sanitizer_mac.cc (_NSGetEnviron() returns NULL).

To fix the problem we fall back to the original functions in the common
libsanitizer interceptors and the __cxa_atexit() interceptor on Darwin.

This patch also prints a better error message in the case _NSGetEnviron()
returns NULL.

llvm-svn: 194573

llvm-svn: 194572