Return-path: Received: from wolverine02.qualcomm.com ([199.106.114.251]:28014 "EHLO wolverine02.qualcomm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756396Ab1GANHg (ORCPT ); Fri, 1 Jul 2011 09:07:36 -0400 From: Rajkumar Manoharan To: CC: , Rajkumar Manoharan , Subject: [PATCH] ath9k: Fix tx throughput drops for AR9003 chips with AES encryption Date: Fri, 1 Jul 2011 18:37:33 +0530 Message-ID: <1309525653-1368-1-git-send-email-rmanohar@qca.qualcomm.com> (sfid-20110701_150748_004792_455FF114) MIME-Version: 1.0 Content-Type: text/plain Sender: linux-wireless-owner@vger.kernel.org List-ID: While sending aggregated frames in AES, the AR5416 chips required additional padding b/w subframes. This workaround is not needed for edma (AR9003 family) chips. With this patch ~4Mbps thoughput improvement was observed in clear environment. Cc: stable@kernel.org Signed-off-by: Rajkumar Manoharan --- drivers/net/wireless/ath/ath9k/xmit.c | 3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index a1fed6c..9283440 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -661,7 +661,8 @@ static int ath_compute_num_delims(struct ath_softc *sc, struct ath_atx_tid *tid, * TODO - this could be improved to be dependent on the rate. * The hardware can keep up at lower rates, but not higher rates */ - if (fi->keyix != ATH9K_TXKEYIX_INVALID) + if ((fi->keyix != ATH9K_TXKEYIX_INVALID) && + !(sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)) ndelim += ATH_AGGR_ENCRYPTDELIM; /* -- 1.7.6