linux-kernel - Re: [PATCH v2] usb: dwc2: drd: fix soft connect when gadget is unconfigured

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <dab7c8fe-0cf5-66a6-bf84-25fe84b4a221@foss.st.com>
Date:   Tue, 15 Feb 2022 16:42:46 +0100
From:   Fabrice Gasnier <fabrice.gasnier@...s.st.com>
To:     Greg KH <gregkh@...uxfoundation.org>
CC:     <hminas@...opsys.com>, <linux-usb@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>,
        <linux-stm32@...md-mailman.stormreply.com>,
        <amelie.delaunay@...s.st.com>, <alexandre.torgue@...s.st.com>
Subject: Re: [PATCH v2] usb: dwc2: drd: fix soft connect when gadget is
 unconfigured

On 2/15/22 3:04 PM, Greg KH wrote:
> On Tue, Feb 15, 2022 at 12:04:19PM +0100, Fabrice Gasnier wrote:
>> When the gadget driver hasn't been (yet) configured, and the cable is
>> connected to a HOST, the SFTDISCON gets cleared unconditionally, so the
>> HOST tries to enumerate it.
>> At the host side, this can result in a stuck USB port or worse. When
>> getting lucky, some dmesg can be observed at the host side:
>>  new high-speed USB device number ...
>>  device descriptor read/64, error -110
>>
>> Fix it in drd, by checking the enabled flag before calling
>> dwc2_hsotg_core_connect(). It will be called later, once configured,
>> by the normal flow:
>> - udc_bind_to_driver
>>  - usb_gadget_connect
>>    - dwc2_hsotg_pullup
>>      - dwc2_hsotg_core_connect
>>
>> Fixes: 17f934024e84 ("usb: dwc2: override PHY input signals with usb role switch support")
>> Signed-off-by: Fabrice Gasnier <fabrice.gasnier@...s.st.com>
>> ---
>> Changes in v2:
>> - Fix build error: 'struct dwc2_hsotg' has no member named 'enabled';
>>   as reported by the kernel test robot.
>>   https://lore.kernel.org/all/202202112236.AwoOTtHO-lkp@intel.com/
>>   Add dwc2_is_device_enabled() macro to handle this.
>> ---
>>  drivers/usb/dwc2/core.h | 2 ++
>>  drivers/usb/dwc2/drd.c  | 6 ++++--
>>  2 files changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
>> index 8a63da3..8a7751b 100644
>> --- a/drivers/usb/dwc2/core.h
>> +++ b/drivers/usb/dwc2/core.h
>> @@ -1418,6 +1418,7 @@ void dwc2_hsotg_core_connect(struct dwc2_hsotg *hsotg);
>>  void dwc2_hsotg_disconnect(struct dwc2_hsotg *dwc2);
>>  int dwc2_hsotg_set_test_mode(struct dwc2_hsotg *hsotg, int testmode);
>>  #define dwc2_is_device_connected(hsotg) (hsotg->connected)
>> +#define dwc2_is_device_enabled(hsotg) ((hsotg)->enabled)
> 
> Why the extra ()?  dwc2_is_device_connected does not have it, so this
> one probably should not either, right?

Hi Greg,

I was wondering the same, checkpatch complains without it:

CHECK: Macro argument 'hsotg' may be better as '(hsotg)' to avoid
precedence issues

I can remove the extra () in a v3 if you wish ?

Thanks for reviewing,
Best Regards,
Fabrice

> 
> thanks,
> 
> greg k-h
>