Return-path: <linux-wireless-owner@vger.kernel.org>
Received: from nbd.name ([46.4.11.11]:40498 "EHLO nbd.name"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1755860Ab2F0VW3 (ORCPT <rfc822;linux-wireless@vger.kernel.org>);
	Wed, 27 Jun 2012 17:22:29 -0400
Message-ID: <4FEB7989.80708@openwrt.org> (sfid-20120627_232233_032538_0D20547B)
Date: Wed, 27 Jun 2012 23:22:17 +0200
From: Felix Fietkau <nbd@openwrt.org>
MIME-Version: 1.0
To: Tom Hughes <tom@compton.nu>
CC: linville@tuxdriver.com, linux-wireless@vger.kernel.org,
	ath9k-devel@lists.ath9k.org, mcgrof@qca.qualcomm.com,
	jouni@qca.qualcomm.com, vthiagar@qca.qualcomm.com,
	senthilb@qca.qualcomm.com
Subject: Re: [PATCH] ath9k: fix panic caused by returning a descriptor we
 have queued for reuse
References: <1340817675-26911-1-git-send-email-tom@compton.nu>
In-Reply-To: <1340817675-26911-1-git-send-email-tom@compton.nu>
Content-Type: text/plain; charset=ISO-8859-1
Sender: linux-wireless-owner@vger.kernel.org
List-ID: <linux-wireless.vger.kernel.org>

On 2012-06-27 7:21 PM, Tom Hughes wrote:
> Commit 3a2923e83c introduced a bug when a corrupt descriptor
> is encountered - although the following descriptor is discarded
> and returned to the queue for reuse the associated frame is
> also returned for processing. This leads to a panic:
> 
> BUG: unable to handle kernel NULL pointer dereference at 000000000000003a
> IP: [<ffffffffa02599a5>] ath_rx_tasklet+0x165/0x1b00 [ath9k]
> Call Trace:
> <IRQ>
> [<ffffffff812d7fa0>] ? map_single+0x60/0x60
> [<ffffffffa028f044>] ? ath9k_ioread32+0x34/0x90 [ath9k]
> [<ffffffffa0292eec>] athk9k_tasklet+0xdc/0x160 [ath9k]
> [<ffffffff8105e133>] tasklet_action+0x63/0xd0
> [<ffffffff8105dbc0>] __do_softirq+0xc0/0x1e0
> [<ffffffff8101a873>] ? native_sched_clock+0x13/0x80
> [<ffffffff815f9d5c>] call_softirq+0x1c/0x30
> [<ffffffff810151f5>] do_softirq+0x75/0xb0
> [<ffffffff8105df95>] irq_exit+0xb5/0xc0
> [<ffffffff815fa5b3>] do_IRQ+0x63/0xe0
> [<ffffffff815f0cea>] common_interrupt+0x6a/0x6a
> <EOI>
> [<ffffffff8131840a>] ? intel_idle+0xea/0x150
> [<ffffffff813183eb>] ? intel_idle+0xcb/0x150
> [<ffffffff814a1db9>] cpuidle_enter+0x19/0x20
> [<ffffffff814a23d9>] cpuidle_idle_call+0xa9/0x240
> [<ffffffff8101c4bf>] cpu_idle+0xaf/0x120
> [<ffffffff815cda8e>] rest_init+0x72/0x74
> [<ffffffff81cf4c1a>] start_kernel+0x3b7/0x3c4
> [<ffffffff81cf4662>] ? repair_env_string+0x5e/0x5e
> [<ffffffff81cf4346>] x86_64_start_reservations+0x131/0x135
> [<ffffffff81cf444a>] x86_64_start_kernel+0x100/0x10f
> 
> Making sure bf is cleared to NULL in this case restores the
> old behaviour.
> 
> Signed-off-by: Tom Hughes <tom@compton.nu>
Acked-by: Felix Fietkau <nbd@openwrt.org>