This resolves #517.

This fixes a regression caused by
e98a620c (Mark partially purged arena
chunks as non-hugepage.).

The core issue here is the weak linking of the symbol, and in certain
environments--for instance, using the latest Xcode (8.1) with the latest
SDK (10.12)--os_unfair_lock may resolve even though you're compiling on
a host that doesn't support it (10.11).

We can use the availability macros to circumvent this problem, and
detect that we're not compiling for a target that is going to support
them and error out at compile time.  The other alternative is to do a
runtime check, but that presents issues for cross-compiling.

Add the pages_[no]huge() functions, which toggle huge page state via
madvise(..., MADV_[NO]HUGEPAGE) calls.

The first time a page run is purged from within an arena chunk, call
pages_nohuge() to tell the kernel to make no further attempts to back
the chunk with huge pages.  Upon arena chunk deletion, restore the
associated virtual memory to its original state via pages_huge().

This resolves #243.

This resolves #509.

Some versions of Android provide a pthreads library without providing
pthread_atfork(), so in practice a separate feature test is necessary
for the latter.

Add feature tests for the MADV_FREE and MADV_DONTNEED flags to
madvise(2), so that MADV_FREE is detected and used for Linux kernel
versions 4.5 and newer.  Refactor pages_purge() so that on systems which
support both flags, MADV_FREE is preferred over MADV_DONTNEED.

This resolves #387.

This resolves #494.

This reverts commit 45f83a2a.

JE_RUNNABLE() causes general cross-compilation issues.

This avoids warnings in some cases, and is otherwise generally good
hygiene.

Rather than relying on two's complement negation for alignment mask
generation, use bitwise not and addition.  This dodges warnings from
MSVC, and should be strength-reduced by compiler optimization anyway.

Add extent serial numbers and use them where appropriate as a sort key
that is higher priority than address, so that the allocation policy
prefers older extents.

This resolves #147.

This resolves #494.

2cdf07ab (Fix extent_quantize() to
handle greater-than-huge-size extents.) solved a non-problem; the
expression passed in to index2size() was never too large.  However the
expression could in principle underflow, so fix the actual (latent) bug
and remove unnecessary complexity.

This fixes a regression caused by
40ee9aa9 (Fix stats.cactive accounting
regression.) and first released in 4.1.0.

Remove outer CHUNK_CEILING(s2u(...)) from alloc_size computation, since
s2u() may overflow (and return 0), and CHUNK_CEILING() is only needed
around the alignment portion of the computation.

This fixes a regression caused by
5707d6f9 (Quantize szad trees by size
class.) and first released in 4.0.0.

This resolves #497.

Allocation requests can't directly create extents that exceed
HUGE_MAXCLASS, but extent merging can create them.

This fixes a regression caused by
8a03cf03 (Implement cache index
randomization for large allocations.) and first released in 4.0.0.

This resolves #497.

This is tailored to Android, i.e. more specific than the *-*-linux*
configuration.

This resolves #471.

Treat it exactly like Linux since they both use GNU libc.

This reverts commit af33e9a5.

This resolves #495.

This resolves #495.

Fix arena_run_first_best_fit() to search all potentially non-empty
runs_avail heaps, rather than ignoring the heap that contains runs
larger than large_maxclass, but less than chunksize.

This fixes a regression caused by
f193fd80 (Refactor runs_avail.).

This resolves #493.

Fix paren placement so that QUANTUM_CEILING() applies to the correct
portion of the expression that computes how much memory to base_alloc().
In practice this bug had no impact.  This was caused by
5d8db15d (Simplify run quantization.),
which in turn fixed an over-allocation regression caused by
3c4d92e8 (Add per size class huge
allocation statistics.).