Improve CBC decrypt and CTR by ~13/16%, which adds up to ~25/33%
improvement over "pre-Silvermont" version. [Add performance table to
aesni-x86.pl].

Atom Silvermont. On other CPUs one can observe 1% loss on some
algorithms.

+5% on Atom Silvermont, up to +8% improvement of legacy code.
Harmonize sha1-586.pl and aesni-sha1-x86_86.p with sha1-x86_64.pl.

(and update performance data, and fix typo)

but keep it disabled, too little gain... Add some Atom-specific
optimization.

Submitted by: Marcelo Cerri

Suggested by: Anton Blanchard

PR: 3139

Improve decrypt performance by 10-20% depending on platform. Thanks
to Jussi Kivilinna for providing valuable hint. Also thanks to Ard
Biesheuvel.

Suggested by: Ard Biesheuvel

Submitted by: Ard Biesheuvel

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

PR: 3074

PR: 3042

Submitted by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

Contributor claims ~50% improvement in CTR and ~9% in CBC decrypt
on Cortex-A15.

Give CBC decrypt approximately same treatment as to CTR and collect 25%.

Based on suggestions from Shay Gueron and Vlad Krasnov.
PR: 3021