linux-kernel - Re: [PATCH v5] usb: Reduce 'set_address' command timeout with a new quirk

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: <2345e113-71cd-4cf2-b910-45dd1bca3f13@rowland.harvard.edu>
Date:   Wed, 25 Oct 2023 10:44:41 -0400
From:   Alan Stern <stern@...land.harvard.edu>
To:     Hardik Gajjar <hgajjar@...adit-jv.com>
Cc:     gregkh@...uxfoundation.org, mathias.nyman@...el.com,
        linux-usb@...r.kernel.org, linux-kernel@...r.kernel.org,
        erosca@...adit-jv.com
Subject: Re: [PATCH v5] usb: Reduce 'set_address' command timeout with a new
 quirk

On Wed, Oct 25, 2023 at 04:13:16PM +0200, Hardik Gajjar wrote:
> This patch introduces a new USB quirk, USB_QUIRK_SHORT_DEVICE_ADDR_TIMEOUT,
> which modifies the timeout value for the 'set_address' command. The
> standard timeout for this command is 5000 ms, as recommended in the USB
> 3.2 specification (section 9.2.6.1).
> 
> However, certain scenarios, such as connecting devices through an APTIV hub,
> can lead to timeout errors when the device enumerates as full speed initially
> and later switches to high speed during chirp negotiation.
> 
> In such cases, USB analyzer logs reveal that the bus suspends for 5 seconds
> due to incorrect chirp parsing and resumes only after two consecutive
> timeout errors trigger a hub driver reset.
> 
> Packet(54) Dir(?) Full Speed J(997.100 us) Idle(  2.850 us)
> _______| Time Stamp(28 . 105 910 682)
> _______|_________________________________________________________________Ch0
> Packet(55) Dir(?) Full Speed J(997.118 us) Idle(  2.850 us)
> _______| Time Stamp(28 . 106 910 632)
> _______|_________________________________________________________________Ch0
> Packet(56) Dir(?) Full Speed J(399.650 us) Idle(222.582 us)
> _______| Time Stamp(28 . 107 910 600)
> _______|_________________________________________________________________Ch0
> Packet(57) Dir Chirp J( 23.955 ms) Idle(115.169 ms)
> _______| Time Stamp(28 . 108 532 832)
> _______|_________________________________________________________________Ch0
> Packet(58) Dir(?) Full Speed J (Suspend)( 5.347 sec) Idle(  5.366 us)
> _______| Time Stamp(28 . 247 657 600)
> _______|_________________________________________________________________Ch0
> 
> This 5-second delay in device enumeration is undesirable, particularly in
> automotive applications where quick enumeration is crucial
> (ideally within 3 seconds).
> 
> The newly introduced quirks provide the flexibility to align with a
> 3-second time limit, as required in specific contexts like automotive
> applications.
> 
> By reducing the 'set_address' command timeout to 500 ms, the
> system can respond more swiftly to errors, initiate rapid recovery, and
> ensure efficient device enumeration. This change is vital for scenarios
> where rapid smartphone enumeration and screen projection are essential.
> To use the quirk, please write "vendor_id:product_id:p" to
> /sys/bus/usb/drivers/hub/module/parameter/quirks
> 
> For example,
> echo "0x2c48:0x0132:p" > /sys/bus/usb/drivers/hub/module/parameter/quirks"
> 
> Signed-off-by: Hardik Gajjar <hgajjar@...adit-jv.com>
> ---

> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 0a1731a0f0ef..3c03f23bd5d5 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -6817,6 +6817,9 @@
>  					pause after every control message);
>  				o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
>  					delay after resetting its port);
> +				p = USB_QUIRK_SHORT_DEVICE_ADDR_TIMEOUT (Timeout
> +					of set_address command reducing from
> +					5000 ms to 500 ms)

As a matter of grammatical style, it would be better to rephrase this as:

	Reduce timeout of set_address command from 5000 ms to 500 ms

Apart from that one little nit, for the usbcore portions of the patch:

Reviewed-by: Alan Stern <stern@...land.harvard.edu>

Alan Stern