netdev - Re: [PATCH net-next 2/2] bnx2x: uses build

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] [day] [month] [year] [list]

Date:	Mon, 14 Nov 2011 14:22:11 -0500 (EST)
From:	David Miller <davem@...emloft.net>
To:	eilong@...adcom.com
Cc:	eric.dumazet@...il.com, netdev@...r.kernel.org,
	bhutchings@...arflare.com, therbert@...gle.com, hadi@...atatu.com,
	shemminger@...tta.com, tgraf@...radead.org,
	herbert@...dor.hengli.com.au, jeffrey.t.kirsher@...el.com,
	pstaszewski@...are.pl
Subject: Re: [PATCH net-next 2/2] bnx2x: uses build_skb() in receive path

From: "Eilon Greenstein" <eilong@...adcom.com>
Date: Mon, 14 Nov 2011 18:48:49 +0200

> On Mon, 2011-11-14 at 08:05 -0800, Eric Dumazet wrote:
>> bnx2x uses following formula to compute its rx_buf_sz :
>> 
>> dev->mtu + 2*L1_CACHE_BYTES + 14 + 8 + 8 + 2
>> 
>> Then core network adds NET_SKB_PAD and SKB_DATA_ALIGN(sizeof(struct
>> skb_shared_info))
>> 
>> Final allocated size for skb head on x86_64 (L1_CACHE_BYTES = 64,
>> MTU=1500) : 2112 bytes : SLUB/SLAB round this to 4096 bytes.
>> 
>> Since skb truesize is then bigger than SK_MEM_QUANTUM, we have lot of
>> false sharing because of mem_reclaim in UDP stack.
>> 
>> One possible way to half truesize is to reduce the need by 64 bytes
>> (2112 -> 2048 bytes)
>> 
>> Instead of allocating a full cache line at the end of packet for
>> alignment, we can use the fact that skb_shared_info sits at the end of
>> skb->head, and we can use this room, if we convert bnx2x to new
>> build_skb() infrastructure.
>> 
>> skb_shared_info will be initialized after hardware finished its
>> transfert, so we can eventually overwrite the final padding.
>> 
>> Using build_skb() also reduces cache line misses in the driver, since we
>> use cache hot skb instead of cold ones. Number of in-flight sk_buff
>> structures is lower, they are recycled while still hot.
>> 
>> Performance results :
>> 
>> (820.000 pps on a rx UDP monothread benchmark, instead of 720.000 pps)
> 
> Wow! This is very impressive. The only problem will be to back port this
> driver now... But it is definitely worth the effort :)

Applied.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html