From: Kalle Valo <kvalo@qca.qualcomm.com>
Date: Mon, 13 Jun 2011 08:54:06 +0000 (+0300)
Subject: ath6kl: fix crash when interface is closed but scan is ongoing
X-Git-Tag: v3.1-rc1~232^2~546
X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=98ab5c7755b5cc9e1a8f2a57ccb22eac5e13ec50;p=pandora-kernel.git

ath6kl: fix crash when interface is closed but scan is ongoing

When ath6kl module was resumed while a scan was ongoing, for example during
suspend, the driver would crash in ar6k_cfg80211_scanComplete_event():

[26581.586440] Call Trace:
[26581.586440]  [<f99ffeda>] ? ar6k_cfg80211_scanComplete_event+0xaa/0xaa [ath6kl]
[26581.586440]  [<f9a0a020>] wmi_iterate_nodes+0xb/0xd [ath6kl]
[26581.586440]  [<f99ffe78>] ar6k_cfg80211_scanComplete_event+0x48/0xaa [ath6kl]
[26581.586440]  [<f9a038ae>] ar6000_close+0x77/0x7e [ath6kl]
[26581.586440]  [<c139c25d>] __dev_close_many+0x87/0xab
[26581.586440]  [<c139c30a>] dev_close_many+0x54/0xab
[26581.586440]  [<c139c437>] rollback_registered_many+0xa5/0x19e
[26581.586440]  [<c139c595>] rollback_registered+0x23/0x2f
[26581.586440]  [<c139c5ed>] unregister_netdevice_queue+0x4c/0x69
[26581.586440]  [<c139c6b2>] unregister_netdev+0x18/0x1f
[26581.586440]  [<f9a00d4c>] ar6000_destroy+0xf8/0x115 [ath6kl]
[26581.586440]  [<f9a0c765>] ar6k_cleanup_module+0x20/0x29 [ath6kl]
[26581.586440]  [<c1062843>] sys_delete_module+0x181/0x1d9
[26581.586440]  [<c105876b>] ? lock_release_holdtime+0x2b/0xcd
[26581.586440]  [<c10b55dc>] ? sys_munmap+0x3b/0x42
[26581.586440]  [<c14a99dc>] ? restore_all+0xf/0xf
[26581.586440]  [<c14aeb6c>] sysenter_do_call+0x12/0x32
[26581.586440] Code: 89 53 6c 75 07 89 d8 e8 c0 ff ff ff 89 f0 e8 2c f2 a9 c7 5b 5e 5d c3 55 89 e5 57 56 53 89 c3 83 ec 08 89 55 f0 8d 78 04 89 4d ec <8b> b0 b8 00 00 00 46 89 b0 b8 00 00 00 89 f8 e8 ae ed a9 c7 8b

Fix the function not to iterate nodes when the scan is aborted. The nodes
are already freed when the module is being unloaded. Patch "ath6kl: Fix a
kernel panic furing suspend/resume" tried to fix this already but it wasn't
enough as a pointer was still used even after the null check. This patch
removes the null check entirely as the wmi structure is not accessed anymore
during module unload.

Also fix a bug where the status was checked as a bitfield with '&' operator.
But it's not a bitfield, just a regular (enum like) value.

Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>
Cc: stable <stable@kernel.org>  [3.0]
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---

Reading git-diff-tree failed