From: Luis R. Rodriguez <lrodriguez@atheros.com>
Date: Tue, 7 Dec 2010 23:13:19 +0000 (-0800)
Subject: ath9k: Fix power save count imbalance on ath_radio_enable()
X-Git-Tag: v2.6.38-rc1~476^2~104^2~4^2~99
X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c2731b814e2aaaa40072ee761b7373c052d86e37;p=pandora-kernel.git

ath9k: Fix power save count imbalance on ath_radio_enable()

Upon a failure we never call ath9k_ps_restore() on ath_radio_enable(),
this will throw off the sc->ps_usecount. When the sc->ps_usecount
is > 0 we never put the chip to full sleep. This drains battery,
and will also make the chip fail upon resume with:

ath: Starting driver with initial channel: 5745 MHz
ath: timeout (100000 us) on reg 0x7000: 0xdeadbeef & 0x00000003 != 0x00000000

This would make the chip useless upon resume.

I cannot prove this can happen but in theory it is so best to
avoid this race completely and not have users complain about
a broken device after resume.

Cc: stable@kernel.org
Cc: Paul Stewart <pstew@google.com>
Cc: Amod Bodas <amod.bodas@atheros.com>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---

Reading git-diff-tree failed