Summary:
With Android/Bionic, delay deallocation to round 2 of 4. It must run after
C++ thread_local destructors have been called, but before the final 2
rounds, because emutls calls free, and jemalloc then needs another 2
rounds to free its thread-specific data.
Fixes https://github.com/android-ndk/ndk/issues/687
Reviewers: cmtice, srhines, jyknight, chh, echristo
Reviewed By: srhines, chh, echristo
Subscribers: echristo, delcypher, llvm-commits, #sanitizers
Differential Revision: https://reviews.llvm.org/D46978
llvm-svn: 334463
Summary:
Add fgets, fputs and puts to sanitizer_common. This adds ASAN coverage
for these functions, extends MSAN support from fgets to fputs/puts and
extends TSAN support from puts to fputs.
Fixes: https://github.com/google/sanitizers/issues/952
Reviewed By: vitalybuka
Differential Revision: https://reviews.llvm.org/D46545
llvm-svn: 334450
Summary:
Add allocator_returns_null.cc test to sanitizer_common and
remove all sanitizer-specific ones except:
- HWASan is not covered by sanitizer_common
- TSan allocator does not have comprehensive error reporting yet
Reviewers: vitalybuka
Subscribers: kubamracek, delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D47971
llvm-svn: 334433
Summary:
Now all sanitizers with improved allocator error reporting are covered
by these common tests.
Also, add pvalloc-specific checks to LSan.
HWASan is not covered by sanitizer_common, hence its own pvalloc
and other allocator tests.
Reviewers: vitalybuka
Subscribers: srhines, kubamracek, delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D47970
llvm-svn: 334424
Summary:
The shared TSD model in its current form doesn't scale. Here is an example of
rpc2-benchmark (with default parameters, which is threading heavy) on a 72-core
machines (defaulting to a `CompactSizeClassMap` and no Quarantine):
- with tcmalloc: 337K reqs/sec, peak RSS of 338MB;
- with scudo (exclusive): 321K reqs/sec, peak RSS of 637MB;
- with scudo (shared): 241K reqs/sec, peak RSS of 324MB.
This isn't great, since the exclusive model uses a lot of memory, while the
shared model doesn't even come close to be competitive.
This is mostly due to the fact that we are consistently scanning the TSD pool
starting at index 0 for an available TSD, which can result in a lot of failed
lock attempts, and touching some memory that needs not be touched.
This CL attempts to make things better in most situations:
- first, use a thread local variable on Linux (intead of pthread APIs) to store
the current TSD in the shared model;
- move the locking boolean out of the TSD: this allows the compiler to use a
register and potentially optimize out a branch instead of reading it from the
TSD everytime (we also save a tiny bit of memory per TSD);
- 64-bit atomic operations on 32-bit ARM platforms happen to be expensive: so
store the `Precedence` in a `uptr` instead of a `u64`. We lose some
nanoseconds of precision and we'll wrap around at some point, but the benefit
is worth it;
- change a `CHECK` to a `DCHECK`: this should never happen, but if something is
ever terribly wrong, we'll crash on a near null AV if the TSD happens to be
null;
- based on an idea by dvyukov@, we are implementing a bound random scan for
an available TSD. This requires computing the coprimes for the number of TSDs,
and attempting to lock up to 4 TSDs in an random order before falling back to
the current one. This is obviously slightly more expansive when we have just
2 TSDs (barely noticeable) but is otherwise beneficial. The `Precedence` still
basically corresponds to the moment of the first contention on a TSD. To seed
on random choice, we use the precedence of the current TSD since it is very
likely to be non-zero (since we are in the slow path after a failed `tryLock`)
With those modifications, the benchmark yields to:
- with scudo (shared): 330K reqs/sec, peak RSS of 327MB.
So the shared model for this specific situation not only becomes competitive but
outperforms the exclusive model. I experimented with some values greater than 4
for the number of TSDs to attempt to lock and it yielded a decrease in QPS. Just
sticking with the current TSD is also a tad slower. Numbers on platforms with
less cores (eg: Android) remain similar.
Reviewers: alekseyshl, dvyukov, javed.absar
Reviewed By: alekseyshl, dvyukov
Subscribers: srhines, kristof.beyls, delcypher, llvm-commits, #sanitizers
Differential Revision: https://reviews.llvm.org/D47289
llvm-svn: 334410
Summary:
Running sanitized 32-bit x86 programs on glibc 2.27 crashes at startup, with:
ERROR: AddressSanitizer: SEGV on unknown address 0xf7a8a250 (pc 0xf7f807f4 bp 0xff969fc8 sp 0xff969f7c T16777215)
The signal is caused by a WRITE memory access.
#0 0xf7f807f3 in _dl_get_tls_static_info (/lib/ld-linux.so.2+0x127f3)
#1 0xf7a92599 (/lib/libasan.so.5+0x112599)
#2 0xf7a80737 (/lib/libasan.so.5+0x100737)
#3 0xf7f7e14f in _dl_init (/lib/ld-linux.so.2+0x1014f)
#4 0xf7f6eb49 (/lib/ld-linux.so.2+0xb49)
The problem is that glibc changed the calling convention for the GLIBC_PRIVATE
symbol that sanitizer uses (even when it should not, GLIBC_PRIVATE is exactly
for symbols that can change at any time, be removed etc.), see
https://sourceware.org/ml/libc-alpha/2017-08/msg00497.html
Fixes https://github.com/google/sanitizers/issues/954
Patch By: Jakub Jelinek
Reviewed By: vitalybuka, Lekensteyn
Differential Revison: https://reviews.llvm.org/D44623
llvm-svn: 334363
Summary:
Following up on and complementing D44404.
Currently many allocator specific errors (OOM, for example) are reported as
a text message and CHECK(0) termination, not stack, no details, not too
helpful nor informative. To improve the situation, detailed and
structured errors were defined and reported under the appropriate conditions.
Reviewers: eugenis
Subscribers: srhines, delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D47793
llvm-svn: 334338
Summary:
Move the corresponding tests to the common folder (as all of the
sanitizer allocators will support this feature soon) and add the checks
specific to aligned_alloc to ASan and LSan allocators.
Reviewers: vitalybuka
Subscribers: srhines, kubamracek, delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D47924
llvm-svn: 334316
This change uses 'const' for the retryingWriteAll(...) API and removes
unnecessary 'static' local variables in getting the temporary filename.
llvm-svn: 334267
Summary:
This fixes http://llvm.org/PR32274.
This change adds a test to ensure that we're able to link XRay modes and
the runtime to binaries that don't need to depend on the C++ standard
library or a C++ ABI library. In particular, we ensure that this will work
with C programs compiled+linked with XRay.
To make the test pass, we need to change a few things in the XRay
runtime implementations to remove the reliance on C++ ABI features. In
particular, we change the thread-safe function-local-static
initialisation to use pthread_* instead of the C++ features that ensure
non-trivial thread-local/function-local-static initialisation.
Depends on D47696.
Reviewers: dblaikie, jfb, kpw, eizan
Reviewed By: kpw
Subscribers: echristo, eizan, kpw, mgorny, llvm-commits
Differential Revision: https://reviews.llvm.org/D46998
llvm-svn: 334262
Summary:
Currently many allocator specific errors (OOM, for example) are reported as
a text message and CHECK(0) termination, not stack, no details, not too
helpful nor informative. To improve the situation, detailed and
structured errors were defined and reported under the appropriate conditions.
Reviewers: eugenis
Subscribers: kubamracek, delcypher, llvm-commits, #sanitizers
Differential Revision: https://reviews.llvm.org/D47798
llvm-svn: 334248
Summary: Otherwise we print things like [0/1] which is visually confusing.
Reviewers: kcc
Reviewed By: kcc
Subscribers: delcypher, llvm-commits, #sanitizers
Differential Revision: https://reviews.llvm.org/D47837
llvm-svn: 334234
When building the dylib, the C++ headers are fundamentally non-module.
They require special versions of the headers in order to provide C++03 and
legacy ABI definitions. This causes ODR issues when modules are enabled
during both the build and the usage of the libc++ headers.
This patch fixes the build error by disabling modules when building the
libc++ sources.
llvm-svn: 334220
-z,defs is incompatible with sanitizers so we need to filter it out
from the linker flags before passing them to the libc++ build.
Differential Revision: https://reviews.llvm.org/D47865
llvm-svn: 334212
Summary:
signal(3) on NetBSD calls internally sigaction(2).
Without disabling the recursive interceptor, there are
false positives about uninitialized memory reads inside libc.
This change fixes execution of such programs as sh(1) and
vmstat(1) in the NetBSD userland.
Sponsored by <The NetBSD Foundation>
Reviewers: eugenis, vitalybuka, joerg
Reviewed By: vitalybuka
Subscribers: llvm-commits, #sanitizers
Tags: #sanitizers
Differential Revision: https://reviews.llvm.org/D47650
llvm-svn: 334168
On Fuchsia, we use libc++ compiled with ASan for our ASan built
executable which means we cannot use the same libc++ for libFuzzer when
building fuzz targets, instead we'll link a custom internal libc++ into
Fuchsia's build of libFuzzer like we already do on Linux.
Differential Revision: https://reviews.llvm.org/D47835
llvm-svn: 334144
Summary:
Added unit-test.
Fixed behavior of max_len argument.
Call read syscall with all available buffer, not just a page.
Reviewers: eugenis
Subscribers: kubamracek, mgorny, llvm-commits
Differential Revision: https://reviews.llvm.org/D46618
llvm-svn: 334130
By adding a ctor to create fuzzer_allocator<T> from fuzzer_allocator<U>.
This mimics construcotrs of std::allocator<T>.
Without the constructors, some versions of libstdc++ can't compile
`vector<bool, fuzzer_allocator<bool>>`.
llvm-svn: 334077
Summary:
This change extracts the recursion guard implementation from FDR Mode
and updates it to do the following:
- Do the atomic operation correctly to be signal-handler safe.
- Make it usable in both FDR and Basic Modes.
Before this change, the recursion guard relied on an unsynchronised read
and write on a volatile thread-local. A signal handler could then run in
between the read and the write, and then be able to run instrumented
code as part of the signal handling. Using an atomic exchange instead
fixes that by doing a proper mutual exclusion even in the presence of
signal handling.
Reviewers: kpw, eizan, jfb
Reviewed By: eizan
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47696
llvm-svn: 334064
Summary:
Following up on and complementing D44404.
Currently many allocator specific errors (OOM, for example) are reported as
a text message and CHECK(0) termination, not stack, no details, not too
helpful nor informative. To improve the situation, detailed and
structured errors were defined and reported under the appropriate conditions.
Reviewers: eugenis
Subscribers: srhines, mgorny, delcypher, llvm-commits, #sanitizers
Differential Revision: https://reviews.llvm.org/D47645
llvm-svn: 334034
We don't actually need to support multiple definitions of the functions
in FDR mode, but rather want to make sure that the implementation-detail
functions are marked as 'static' instead. This allows the inliner to do
its magic better for these functions too, since inline functions must
have a unique address across translation units.
llvm-svn: 334001
We planned to have FDR mode's internals unit-tested but it turns out
that we can just use end-to-end testing to verify the implementation.
We're going to move towards that approach more and more going forward,
so we're merging the implementation details of FDR mode into a single
.cc file.
We also avoid globbing in the XRay test helper macro, and instead list
down the files from the lib directory.
llvm-svn: 333986
Summary:
At least the ASan, MSan, TSan sanitizers require disabled ASLR on a NetBSD.
Introduce a generic CheckASLR() routine, that implements a check for the
current process. This flag depends on the global or per-process settings.
There is no simple way to disable ASLR in the build process from the
level of a sanitizer or during the runtime execution.
With ASLR enabled sanitizers that operate over the process virtual address
space can misbehave usually breaking with cryptic messages.
This check is dummy for !NetBSD.
Sponsored by <The NetBSD Foundation>
Reviewers: vitalybuka, joerg
Reviewed By: vitalybuka
Subscribers: cryptoad, kubamracek, llvm-commits, #sanitizers
Tags: #sanitizers
Differential Revision: https://reviews.llvm.org/D47442
llvm-svn: 333985
Summary:
This is part of the work to address http://llvm.org/PR32274.
We remove the calls to array-placement-new and array-delete. This allows
us to rely on the internal memory management provided by
sanitizer_common/sanitizer_internal_allocator.h.
Reviewers: eizan, kpw
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47695
llvm-svn: 333982
XRay doesn't use RTTI and doesn't need it. We disable it explicitly in
the CMake config, similar to how the other sanitizers already do it.
Part of the work to address http://llvm.org/PR32274.
llvm-svn: 333867
Ryan Prichard