test: make sure we retry the auth callback on all platforms

xdiff: fix memleak on error case

If the caller has provided bad authentication, give them another
apportunity to get it right until they give up. This brings WinHTTP in
line with the other transports.

We were missing this test on Windows, which meant we didn't notice that
we never fixed the single authentication attempt it tries, nor its wrong
return code.

Enable this for the unix platforms as well over HTTP. We previously were
doing it locally but disabled it on OS X due to issues with its sshd not
accepting password authentication.

Stricter object dependency checking during creation

Commit 3d1abc5a fixes a memory leak in the xdiff code. In the
process of upstreaming the fix it was pointed out by Johannes
Schindelin that there is another memory leak present (see [1]).

Fix the second memory leak by applying the upstream fix to our
code base.

[1]: http://thread.gmane.org/gmane.comp.version-control.git/287034

Few p_getaddrinfo fixes

Use legitimate (existing) object IDs in tests so that we have the
ability to turn on strict object validation when running tests.

This allows lighter weight validation in `git_object__is_valid` that
does not require reading the entire object.

When `GIT_OPT_ENABLE_STRICT_OBJECT_CREATION` is turned on, validate
the index entries given to `git_index_add`.

travis ci: enable debug pool for valgrind builds

When `GIT_OPT_ENABLE_STRICT_OBJECT_CREATION` is turned on, validate
the tree and parent ids given to treebuilder insertion.

When `GIT_OPT_ENABLE_STRICT_OBJECT_CREATION` is turned on, validate
the tree and parent ids given to commit creation functions.

Add a new build flag to disable the pool allocator

USE_NSECS fixes

Coverity fixes

Extra checks for packfile indices

Android NDK does not have a `struct timespec` in its `struct stat`
for nanosecond support, instead it has a single nanosecond member inside
the struct stat itself.  We will use that and use a macro to expand to
the `st_mtim` / `st_mtimespec` definition on other systems (much like
the existing `st_mtime` backcompat definition).

The index::nsec::staging_maintains_other_nanos test was created to
ensure that when we stage an entry when GIT_USE_NSECS is *unset* that
we truncate the index entry and do not persist the (old, invalid)
nanosec values.  Ensure that when GIT_USE_NSECS is *set* that we do
not do that, and actually write the correct nanosecond values.

A corrupt index might have data that tells us to go look past the end of
the file for data. Catch these cases and return an appropriate error
message.

CONVENTIONS: update to include general public API principles

This got lost duing the move and it lets the users call this function
just in case.

Minor `giterr` fixups

The `giterr_set_str` does not actually honor `GITERR_OS`.  Remove
the documentation that claims that we do.

Use the `giterr_set` function, which actually supports `GITERR_OS`.
The `giterr_set_str` function is exposed for external users and will
not append the operating system's error message.

The `normalize_find_opts` function in theory allows for the
incoming diff to have no repository. When the caller does not
pass in diff find options or if the GIT_DIFF_FIND_BY_CONFIG value
is set, though, we try to derive the configuration from the
diff's repository configuration without first verifying that the
repository is actually set to a non-NULL value.

Fix this issue by explicitly checking if the repository is set
and if it is not, fall back to a default value of
GIT_DIFF_FIND_RENAMES.