netdev - Re: [PATCH] net: usb: pegasus: Do not drop long Ethernet frames

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]

Date:   Sun, 26 Dec 2021 17:01:24 +0100
From:   Matthias-Christian Ott <ott@...ix.org>
To:     Andrew Lunn <andrew@...n.ch>
Cc:     Petko Manolov <petkan@...leusys.com>, linux-usb@...r.kernel.org,
        netdev@...r.kernel.org
Subject: Re: [PATCH] net: usb: pegasus: Do not drop long Ethernet frames

On 26/12/2021 16:39, Andrew Lunn wrote:
> On Sun, Dec 26, 2021 at 02:29:30PM +0100, Matthias-Christian Ott wrote:
>> The D-Link DSB-650TX (2001:4002) is unable to receive Ethernet frames
>> that are longer than 1518 octets, for example, Ethernet frames that
>> contain 802.1Q VLAN tags.
>>
>> The frames are sent to the pegasus driver via USB but the driver
>> discards them because they have the Long_pkt field set to 1 in the
>> received status report. The function read_bulk_callback of the pegasus
>> driver treats such received "packets" (in the terminology of the
>> hardware) as errors but the field simply does just indicate that the
>> Ethernet frame (MAC destination to FCS) is longer than 1518 octets.
>>
>> It seems that in the 1990s there was a distinction between
>> "giant" (> 1518) and "runt" (< 64) frames and the hardware includes
>> flags to indicate this distinction. It seems that the purpose of the
>> distinction "giant" frames was to not allow infinitely long frames due
>> to transmission errors and to allow hardware to have an upper limit of
>> the frame size. However, the hardware already has such limit with its
>> 2048 octet receive buffer and, therefore, Long_pkt is merely a
>> convention and should not be treated as a receive error.
>>
>> Actually, the hardware is even able to receive Ethernet frames with 2048
>> octets which exceeds the claimed limit frame size limit of the driver of
>> 1536 octets (PEGASUS_MTU).
>>
>> Signed-off-by: Matthias-Christian Ott <ott@...ix.org>
>> ---
>>  drivers/net/usb/pegasus.c | 4 ++--
>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
>> index 140d11ae6688..2582daf23015 100644
>> --- a/drivers/net/usb/pegasus.c
>> +++ b/drivers/net/usb/pegasus.c
>> @@ -499,11 +499,11 @@ static void read_bulk_callback(struct urb *urb)
>>  		goto goon;
>>  
>>  	rx_status = buf[count - 2];
>> -	if (rx_status & 0x1e) {
>> +	if (rx_status & 0x1c) {
>>  		netif_dbg(pegasus, rx_err, net,
>>  			  "RX packet error %x\n", rx_status);
>>  		net->stats.rx_errors++;
>> -		if (rx_status & 0x06)	/* long or runt	*/
>> +		if (rx_status & 0x04)	/* runt	*/
> 
> I've nothing against this patch, but if you are working on the driver,
> it would be nice to replace these hex numbers with #defines using BIT,
> or FIELD. It will make the code more readable.

Replacing the constants with macros is on my list of things that I want
to do. In this case, I did not do it because I wanted to a have small
patch that gets easily accepted and allows me to figure out the current
process to submit patches after years of inactivity.

Kind regards,
Matthias-Christian Ott