Commit Graph

11 Commits

Author SHA1 Message Date
Kamil Rytarowski 7e55245213 OpenBSD Ubsan support / interception
Summary: Interception, enabling OpenBSD platform

Patch by: David CARLIER

Reviewers: krytarowski, vitalybuka, visa

Reviewed By: vitalybuka

Subscribers: srhines, fedor.sergeev, llvm-commits, #sanitizers

Differential Revision: https://reviews.llvm.org/D43893

llvm-svn: 326544
2018-03-02 07:32:30 +00:00
Kamil Rytarowski 271018d216 [Sanitizers] Basic sanitizer Solaris support (PR 33274)
Summary:
This is the first mostly working version of the Sanitizer port to 32-bit Solaris/x86.
It is currently based on Solaris 11.4 Beta.

This part was initially developed inside libsanitizer in the GCC tree and should apply to
both.  Subsequent parts will address changes to clang, the compiler-rt build system
and testsuite.

I'm not yet sure what the right patch granularity is: if it's profitable to split the patch
up, I'd like to get guidance on how to do so.

Most of the changes are probably straightforward with a few exceptions:

* The Solaris syscall interface isn't stable, undocumented and can change within an
  OS release.  The stable interface is the libc interface, which I'm using here, if possible
  using the internal _-prefixed names.

* While the patch primarily target 32-bit x86, I've left a few sparc changes in.  They
  cannot currently be used with clang due to a backend limitation, but have worked
  fine inside the gcc tree.

* Some functions (e.g. largefile versions of functions like open64) only exist in 32-bit
  Solaris, so I've introduced a separate SANITIZER_SOLARIS32 to check for that.

The patch (with the subsequent ones to be submitted shortly) was tested
on i386-pc-solaris2.11.  Only a few failures remain, some of them analyzed, some
still TBD:

    AddressSanitizer-i386-sunos :: TestCases/Posix/concurrent_overflow.cc
    AddressSanitizer-i386-sunos :: TestCases/init-order-atexit.cc
    AddressSanitizer-i386-sunos :: TestCases/log-path_test.cc
    AddressSanitizer-i386-sunos :: TestCases/malloc-no-intercept.c
    AddressSanitizer-i386-sunos-dynamic :: TestCases/Posix/concurrent_overflow.cc
    AddressSanitizer-i386-sunos-dynamic :: TestCases/Posix/start-deactivated.cc
    AddressSanitizer-i386-sunos-dynamic :: TestCases/default_options.cc
    AddressSanitizer-i386-sunos-dynamic :: TestCases/init-order-atexit.cc
    AddressSanitizer-i386-sunos-dynamic :: TestCases/log-path_test.cc
    AddressSanitizer-i386-sunos-dynamic :: TestCases/malloc-no-intercept.c

   SanitizerCommon-Unit :: ./Sanitizer-i386-Test/MemoryMappingLayout.DumpListOfModules
    SanitizerCommon-Unit :: ./Sanitizer-i386-Test/SanitizerCommon.PthreadDestructorIterations

Maybe this is good enough the get the ball rolling.

Reviewers: kcc, alekseyshl

Reviewed By: alekseyshl

Subscribers: srhines, jyknight, kubamracek, krytarowski, fedor.sergeev, llvm-commits, #sanitizers

Tags: #sanitizers

Differential Revision: https://reviews.llvm.org/D40898

llvm-svn: 320740
2017-12-14 20:14:29 +00:00
Kamil Rytarowski 90b46353e7 [Sanitizers] Use SANITIZER_* macros in lib/interception
Summary:
Unlike the rest of the sanitizer code, lib/interception uses native macros like __linux__
to check for specific targets instead of the common ones like SANITIZER_LINUX.

When working on the Solaris port of the sanitizers, the current style was found to not
only be inconsistent, but clumsy to use because the canonical way to check for Solaris
is to check for __sun__ && __svr4__ which is a mouthful.

Therefore, this patch switches to use SANITIZER_* macros instead.

Tested on x86_64-pc-linux-gnu.

Reviewers: kcc, vitalybuka

Reviewed By: vitalybuka

Subscribers: #sanitizers, srhines, krytarowski, llvm-commits, fedor.sergeev

Tags: #sanitizers

Differential Revision: https://reviews.llvm.org/D39798

llvm-svn: 319906
2017-12-06 17:02:00 +00:00
Peter Collingbourne 0f43b92980 sanitizer_common: Try looking up symbols with RTLD_DEFAULT if RTLD_NEXT does not work.
If the lookup using RTLD_NEXT failed, the sanitizer runtime library
is later in the library search order than the DSO that we are trying
to intercept, which means that we cannot intercept this function. We
still want the address of the real definition, though, so look it up
using RTLD_DEFAULT.

Differential Revision: https://reviews.llvm.org/D39779

llvm-svn: 317930
2017-11-10 22:09:37 +00:00
Kamil Rytarowski 70a3511bd5 Reuse interception_linux for NetBSD
Summary:
Part of the code inspired by the original work on libsanitizer in GCC 5.4 by Christos Zoulas.

Sponsored by <The NetBSD Foundation>

Reviewers: joerg, kcc, vitalybuka, filcab

Reviewed By: vitalybuka

Subscribers: llvm-commits, #sanitizers

Tags: #sanitizers

Differential Revision: https://reviews.llvm.org/D36321

llvm-svn: 310351
2017-08-08 12:10:08 +00:00
Kostya Serebryany 04f2bf0f07 [sanitizer] Interception macros for sanitizers on FreeBSD; patch by Viktor Kutuzov
llvm-svn: 202009
2014-02-24 08:37:41 +00:00
Dmitry Vyukov 23b80ab87f asan: fix android build
android does not have dlvsym

llvm-svn: 189781
2013-09-03 07:53:49 +00:00
Dmitry Vyukov 3a6c7cea77 tsan: properly intercept pthread_cond functions
llvm-svn: 189767
2013-09-02 18:06:28 +00:00
Alexey Samsonov 0f840bd240 [Sanitizer] Workaround for a compiler warning - ISO C++ forbids casting pointer-to-function to pointer-to-object, so we use cast via integral type
llvm-svn: 161168
2012-08-02 11:19:13 +00:00
Dmitry Vyukov 7fb7330469 asan/tsan: weak interceptors
The idea isthat asan/tsan can survive if user intercepts the same functions. At the same time user has an ability to call back into asan/tsan runtime. See the following tests for examples:
asan/output_tests/interception_failure_test-linux.cc
asan/output_tests/interception_test-linux.cc
asan/output_tests/interception_malloc_test-linux.cc

llvm-svn: 157388
2012-05-24 13:54:31 +00:00
Kostya Serebryany 1dd4c606ed [asan] move lib/asan/interception to lib/interception so that other tools (e.g. tsan) can use it
llvm-svn: 156816
2012-05-15 12:21:33 +00:00