Original descriptions were:
- "Refactor and cleanup VirtualMemory."
- "Fix typo."
- "Deuglify V8_INLINE and V8_NOINLINE."
- "Don't align size on allocation granularity for unaligned ReserveRegion calls."
Reasons for the revert are:
- Our mjsunit test suite slower by a factor of 5(!) in release mode.
- Flaky cctest/test-alloc/CodeRange on all architectures and platforms.
- Tankage of Sunspider by about 6% overall (unverified).
TBR=bmeurer@chromium.org
Review URL: https://codereview.chromium.org/23970004
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16662 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
Remove a lot of platform duplication, and simplify the virtual
memory implementation. Also improve readability by avoiding bool
parameters for executability (use a dedicated Executability type
instead).
Get rid of the Isolate::UncheckedCurrent() call in the platform
code, as part of the Isolate TLS cleanup.
Use a dedicated random number generator for the address
randomization, instead of messing with the per-isolate random
number generators.
TEST=cctest/test-virtual-memory
R=verwaest@chromium.org
Review URL: https://codereview.chromium.org/23641009
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16637 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
The RandomNumberGenerator is a pseudorandom number generator
with 48-bit state. It is properly seeded using either
(1) the --random-seed if specified, or
(2) the entropy_source function if configured, or
(3) /dev/urandom if available, or
(4) falls back to Time and TimeTicks based seeding.
Each Isolate now contains a RandomNumberGenerator, which replaces
the previous private_random_seed.
Every native context still has its own random_seed. But this random
seed is now properly initialized during bootstrapping,
instead of on-demand initialization. This will allow us to cleanup
and speedup the HRandom implementation quite a lot (this is delayed
for a followup CL)!
Also stop messing with the system rand()/random(), which should
not be done from a library anyway! We probably re-seeded the
libc rand()/random() after the application (i.e. Chrome) already
seeded it (with better entropy than what we used).
Another followup CL will replace the use of the per-isolate
random number generator for the address randomization and
thereby get rid of the Isolate::UncheckedCurrent() usage in
the platform code.
TEST=cctest/test-random-number-generator,cctest/test-random
R=mstarzinger@chromium.org
Review URL: https://codereview.chromium.org/23548024
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16612 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
Up until now we used PAGE_GUARD for guard pages in Windows, which
will raise a STATUS_GUARD_PAGE_VIOLATION exception on first access
and grant regular access afterwards. This behavior is required to
implement automatic stack checking, or more generally to implement
applications that monitor the growth of large dynamic data structures.
However, this is not what we want for our guard pages, which are
used as a security mechanism. What we really want is PAGE_NOACCESS
here, which is the Windows-equivalent of PROT_NONE that we use on
all other platforms.
R=cdn@chromium.org
Review URL: https://codereview.chromium.org/23458022
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16604 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
Instead of globally tracking allocated space limits, which was
not implemented properly anyway (i.e. lack of synchronization
on the reading side), track it per MemoryAllocator (that is
per heap/isolate).
In particular, avoid to call IsBadWritePtr() on Windows, it is
obsolete and Microsoft strongly discourages its usage.
R=mstarzinger@chromium.org
Review URL: https://codereview.chromium.org/23903008
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16542 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
Drop the previous Mutex and ScopedLock classes from platform files.
Add new Mutex, RecursiveMutex and LockGuard classes, which are
designed after their C++11 counterparts, so that at some point
we can simply drop our custom code and switch to the C++11
classes. We distinguish regular and recursive mutexes, as the
latter don't work well with condition variables, which will be
introduced by a followup CL.
R=mstarzinger@chromium.org
Review URL: https://codereview.chromium.org/23625003
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@16416 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
No need to duplicate OS::NumberOfCores() for every POSIX platform.
No need to duplicate OS::Sleep() for every POSIX platform.
No need to duplicate OS::Abort() and OS::DebugBreak() for every POSIX platform.
No need to duplicate OS::Free() for every POSIX platform.
Move #ifdef'd OS::ProtectCode() and OS::Guard() to platform-posix.cc.
No need to duplicate OS::AllocateAlignment() for every POSIX platform.
No need to duplicate OS::PostSetUp() for every POSIX platform.
R=svenpanne@chromium.org
Review URL: https://codereview.chromium.org/20014005
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@15820 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
Renamed SignalSender to SamplerThread to match platforms that don't support signal sending.
Cygwin and Windows implementations are almost identical. Mac OS X uses different API to suspend thread but apart from that it is very similar to Windows implenenation.
BUG=None
Review URL: https://codereview.chromium.org/14264009
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@14272 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
The new test checks full CPU profiling cycle: using public
V8 API it starts profiling, executes a script, stops profiling
and analyzes collected profile to check that its top-down
tree has expected strutcture. The script that is being profiled
is guaranteed to run > 200ms to make sure enough samples
are collected.
To avoid possible flakiness due to non-deterministic time required
to start new thread on varios OSs when Sampler and ProfilerEventsProcessor
threads are being started the main thread is blocked until the threads
are running.
Also I removed the heuristic in profile-generator.cc where we try
to figure out if the value on top of the sampled stack is return address
of some frameless stub invocation. The code periodically gives false positive
with the new test ending up in an extra node in the collected cpu profile.
After discussion with jkummerow@ we concluded that the logic is too fragile
and that we can address frameless stub invocations in a more reliable way
later should they have a noticeable effect on cpu profiling.
BUG=None
Review URL: https://codereview.chromium.org/13627002
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@14205 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
The patch is based on the previous one that was rolled out: https://code.google.com/p/v8/source/detail?r=12985
On Linux sampling for CPU profiler is initiated on the profiler event processor thread, other platforms to follow.
CPU profiler continues to use SamplingCircularQueue, we will replave it with a single sample buffer when Mac and Win ports support profiling on the event processing thread.
When --prof option is specified profiling is initiated either on the profiler event processor thread if CPU profiler is on or on the SignalSender thread as it used to if no CPU profiles are being collected.
ProfilerEventsProcessor::ProcessEventsAndDoSample now waits in a tight loop, processing collected samples until sampling interval expires. To save CPU resources I'm planning to change that to use nanosleep as only one sample is expected in the queue at any point.
BUG=v8:2364
Review URL: https://codereview.chromium.org/12321046
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13735 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
- perform CPU profiler sampling in the sampler thread as we used to;
- skip sampling in the sampling thread if processing thread is running;
- only install SIGPROF handler when CPU profiling is enabled.
BUG=v8:2364
Review URL: https://codereview.chromium.org/11231002
Patch from Sergey Rogulenko <rogulenko@google.com> and Andrey Kosyakov <caseq@chromium.org>.
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12985 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
The patch introduces CommittedPhysicalMemory function to
the Heap class that reports committed *physical* memory acquired
for the heap from the OS.
It is important because some OSes may defer actual committment on e.g.
first access to the region.
So reporting just plain committed size led to various weird artifacts
like showing V8 allocated memory higher than the whole process
private size.
BUG=v8:2191
Review URL: https://codereview.chromium.org/11066118
Patch from Alexei Filippov <alph@chromium.org>.
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12793 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
The patch introduces CommittedPhysicalMemory function to the Heap class
that reports committed *physical* memory acquired from the OS.
It is important because some OSes may postpone actual commitment on e.g.
first access to the previously committed region.
So reporting just plain committed size led to various weird artifacts
like DevTools showing V8 allocated memory higher than the whole process
private size.
BUG=v8:2191
Review URL: https://codereview.chromium.org/10961042
Patch from Alexei Filippov <alph@chromium.org>.
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12625 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
This CL:
- Adds a new trait parameter to LazyInstance to let it initialize the instance
without paying the cost of atomic operations (which are expensive on Mac).
This only works for users who don't care about thread-safety and this is now
the default initialization trait used by LazyInstance in v8.
- Reverts the changes that were made in r11010 in isolate.{cc,h}. That lets
Isolate's accessors be as cheap as they were before (but adds one static initializer).
- Adds OS::PostSetup() used to initialize the math functions which depend on CPU features.
That lets the math functions get rid of CallOnce().
BUG=118686
Review URL: https://chromiumcodereview.appspot.com/9873023
Patch from Philippe Liard <pliard@chromium.org>.
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11198 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
This change includes two CLs by pliard@chromium.org:
1. http://codereview.chromium.org/9447052/ (Add CallOnce() and simple LazyInstance implementation):
Note that this implementation of LazyInstance does not handle global destructors (i.e. the lazy instances are never deleted).
This CL was initially reviewed on codereview.appspot.com:
http://codereview.appspot.com/5687064/
2. http://codereview.chromium.org/9455088/ (Remove static initializers in v8):
This CL depends on CL 9447052 (adding CallOnce and LazyInstance).
It is based on a patch sent by Digit.
With this patch applied, we have only one static initializer left (in atomicops_internals_x86_gcc.cc). This static initializer populates a structure used by x86 atomic operations. It seems that we can hardly remove it. If possible, it will be removed in a next CL.
This CL also modifies the presubmit script to check the number of static initializers.
BUG=v8:1859
Review URL: https://chromiumcodereview.appspot.com/9666052
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11010 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
