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: [email protected] Cc: Paul Stewart <[email protected]> Cc: Amod Bodas <[email protected]> Signed-off-by: Luis R. Rodriguez <[email protected]> --- drivers/net/wireless/ath/ath9k/main.c | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 3e0c8a1..be19b70 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -897,8 +897,7 @@ void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw) ath_update_txpow(sc); if (ath_startrecv(sc) != 0) { ath_err(common, "Unable to restart recv logic\n"); - spin_unlock_bh(&sc->sc_pcu_lock); - return; + goto out; } if (sc->sc_flags & SC_OP_BEACONS) ath_beacon_config(sc, NULL); /* restart beacons */ @@ -912,6 +911,7 @@ void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw) ath9k_hw_set_gpio(ah, ah->led_pin, 0); ieee80211_wake_queues(hw); +out: spin_unlock_bh(&sc->sc_pcu_lock); ath9k_ps_restore(sc); -- 1.7.3.2.90.gd4c43 _______________________________________________ stable mailing list [email protected] http://linux.kernel.org/mailman/listinfo/stable
