lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <81554a5e-5b86-4944-9565-4e2aed5fd0ef@denx.de>
Date: Mon, 23 Dec 2024 20:19:10 +0100
From: Marek Vasut <marex@...x.de>
To: Alexis Lothoré <alexis.lothore@...tlin.com>,
 Ajay Singh <ajay.kathat@...rochip.com>,
 Claudiu Beznea <claudiu.beznea@...on.dev>, Kalle Valo <kvalo@...nel.org>
Cc: Thomas Petazzoni <thomas.petazzoni@...tlin.com>,
 linux-wireless@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH wireless] wifi: wilc1000: unregister wiphy only if it has
 been registered

On 12/23/24 4:46 PM, Alexis Lothoré wrote:
> There is a specific error path in probe functions in wilc drivers (both
> sdio and spi) which can lead to kernel panic, as this one for example
> when using SPI:
> 
> Unable to handle kernel paging request at virtual address 9f000000 when read
> [9f000000] *pgd=00000000
> Internal error: Oops: 5 [#1] ARM
> Modules linked in: wilc1000_spi(+) crc_itu_t crc7 wilc1000 cfg80211 bluetooth ecdh_generic ecc
> CPU: 0 UID: 0 PID: 106 Comm: modprobe Not tainted 6.13.0-rc3+ #22
> Hardware name: Atmel SAMA5
> PC is at wiphy_unregister+0x244/0xc40 [cfg80211]
> LR is at wiphy_unregister+0x1c0/0xc40 [cfg80211]
> [...]
>   wiphy_unregister [cfg80211] from wilc_netdev_cleanup+0x380/0x494 [wilc1000]
>   wilc_netdev_cleanup [wilc1000] from wilc_bus_probe+0x360/0x834 [wilc1000_spi]
>   wilc_bus_probe [wilc1000_spi] from spi_probe+0x15c/0x1d4
>   spi_probe from really_probe+0x270/0xb2c
>   really_probe from __driver_probe_device+0x1dc/0x4e8
>   __driver_probe_device from driver_probe_device+0x5c/0x140
>   driver_probe_device from __driver_attach+0x220/0x540
>   __driver_attach from bus_for_each_dev+0x13c/0x1a8
>   bus_for_each_dev from bus_add_driver+0x2a0/0x6a4
>   bus_add_driver from driver_register+0x27c/0x51c
>   driver_register from do_one_initcall+0xf8/0x564
>   do_one_initcall from do_init_module+0x2e4/0x82c
>   do_init_module from load_module+0x59a0/0x70c4
>   load_module from init_module_from_file+0x100/0x148
>   init_module_from_file from sys_finit_module+0x2fc/0x924
>   sys_finit_module from ret_fast_syscall+0x0/0x1c
> 
> The issue can easily be reproduced, for example by not wiring correctly
> a wilc device through SPI (and so, make it unresponsive to early SPI
> commands). It is due to a recent change decoupling wiphy allocation from
> wiphy registration, however wilc_netdev_cleanup has not been updated
> accordingly, letting it possibly call wiphy unregister on a wiphy which
> has never been registered.
> 
> Fix this crash by moving wiphy_unregister/wiphy_free out of
> wilc_netdev_cleanup, and by adjusting error paths in both drivers
> 
> Fixes: fbdf0c5248dc ("wifi: wilc1000: Register wiphy after reading out chipid")
> Signed-off-by: Alexis Lothoré <alexis.lothore@...tlin.com>
Nice find, thank you for fixing it.

Reviewed-by: Marek Vasut <marex@...x.de>

Thanks !

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ