netdev - Re: [EXT] Re: [PATCH net-next 11/12] net: atlantic: implement UDP GSO offload

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: <20d6b8df-8108-657a-0468-b25917cee0f6@marvell.com>
Date:   Mon, 4 Nov 2019 22:11:38 +0000
From:   Igor Russkikh <irusskikh@...vell.com>
To:     Eric Dumazet <eric.dumazet@...il.com>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>
CC:     "David S . Miller" <davem@...emloft.net>
Subject: Re: [EXT] Re: [PATCH net-next 11/12] net: atlantic: implement UDP GSO
 offload


>> +			/* UDP GSO Hardware does not replace packet length. */
>> +			udp_hdr(skb)->len = htons(dx_buff->mss +
>> +						  dx_buff->len_l4);
>> +		}
> 
> Have you tested IPv6 ?
> 
> 
>>  		dx_buff->len_pkt = skb->len;
>>  		dx_buff->len_l2 = ETH_HLEN;
>>  		dx_buff->len_l3 = ip_hdrlen(skb);
>> -		dx_buff->len_l4 = tcp_hdrlen(skb);
>>  		dx_buff->eop_index = 0xffffU;
>>  		dx_buff->is_ipv6 =
>>  			(ip_hdr(skb)->version == 6) ? 1U : 0U;
> 
> I am asking because you seem to test IPv6 here, so blindly using ip_hdr(skb)->protocol
> few lines above is weird.
> 

Hi Eric, thanks, indeed it'll screw up on ipv6.
HW should be ip6 capable, I'll retest and fix this.

-- 
Regards,
  Igor