netdev - skb's & hw buffer mgmt

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-next>] [day] [month] [year] [list]

Message-Id: <4FC8D5B7-3242-4C9E-BDD8-5026FC1C73F3@kernel.crashing.org>
Date:	Thu, 19 Mar 2009 21:55:18 -0500
From:	Kumar Gala <galak@...nel.crashing.org>
To:	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org
Subject: skb's & hw buffer mgmt

David,

I remember you point me at code in the Sun neptune driver as an  
example of how to use hw buffer mgmt w/skb's.  I had a few questions  
on how this actually works.

It appears that you allocate a bunch of pages, seed the HW buffer  
manager.  As you receive packets you setup the skb via  
niu_process_rx_pkt()/niu_rx_skb_append().  I'm a little confused about  
how the non-paged data in the skb itself is actually used.  How does  
skb->data actually point to anything meaningful?

It also seems that you don't actually give the page directly back to  
the HW buffer manager when the skb is released (possibly via a skb- 
 >destructor) but just allocate new pages and add these new buffers to  
the HW manager.  Is that correct?  Is there any particular reason to  
do this?

thanks

- k
--
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