From: Will Deacon <will.deacon@arm.com>
Date: Fri, 21 Feb 2014 16:01:48 +0000 (+0100)
Subject: ARM: 7983/1: atomics: implement a better __atomic_add_unless for v6+
X-Git-Tag: v3.15-rc1~82^2~1^3~16
X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=db38ee874c48713d0723221d08332242e0088970;p=pandora-kernel.git

ARM: 7983/1: atomics: implement a better __atomic_add_unless for v6+

Looking at perf profiles of multi-threaded hackbench runs, a significant
performance hit appears to manifest from the cmpxchg loop used to
implement the 32-bit atomic_add_unless function. This can be mitigated
by writing a direct implementation of __atomic_add_unless which doesn't
require iteration outside of the atomic operation.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---

Reading git-diff-tree failed