This resolves #517.

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.

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 a2e601a2.

JE_RUNNABLE() causes general cross-compilation issues.

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

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 regression was caused by 498856f4
(Move slabs out of chunks.).

This resolves #494.

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

This resolves #471.

This change conforms to naming conventions throughout the codebase.

This reverts commit c2942e2c.

This resolves #495.

This resolves #495.

This supersedes -std=gnu99, and enables C11 atomics.

Do not call s2u() during alloc_size computation, since any necessary
ceiling increase is taken care of later by extent_first_best_fit() -->
extent_size_quantize_ceil(), and the s2u() call may erroneously cause a
higher quantization result.

Remove an overly strict overflow check that was added in
4a785213 (Fix extent_recycle()'s
cache-oblivious padding support.).

Add padding *after* computing the size class, so that the optimal size
class isn't skipped during search for a usable extent.  This regression
was caused by b46261d5 (Implement
cache-oblivious support for huge size classes.).

Add an "over-size" extent heap in which to store extents which exceed
the maximum size class (plus cache-oblivious padding, if enabled).
Remove psz2ind_clamp() and use psz2ind() instead so that trying to
allocate the maximum size class can in principle succeed.  In practice,
this allows assertions to hold so that OOM errors can be successfully
generated.

Fix extent_alloc_cache[_locked]() to support decommitted allocation, and
use this ability in arena_stash_dirty(), so that decommitted extents are
not needlessly committed during purging.  In practice this does not
happen on any currently supported systems, because both extent merging
and decommit must be implemented; all supported systems implement one
xor the other.

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

rtree_node_init spinlocks the node, allocates, and then sets the node.
This is under heavy contention at the top of the tree if many threads
start to allocate at the same time.

Instead, take a per-rtree sleeping mutex to reduce spinning.  Tested
both pthreads and osx OSSpinLock, and both reduce spinning adequately

Previous benchmark time:
./ttest1 500 100
~15s

New benchmark time:
./ttest1 500 100
.57s

This resolves #485.