netdev - usbnet transmit scatter-gather

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

Message-ID: <AE90C24D6B3A694183C094C60CF0A2F6026B7328@saturn3.aculab.com>
Date:	Wed, 11 Sep 2013 14:19:24 +0100
From:	"David Laight" <David.Laight@...LAB.COM>
To:	<netdev@...r.kernel.org>
Subject: usbnet transmit scatter-gather

usbnet and ax88179_178a.c where changed fairly recently to support
scatter-gather transmit.
(This would let TSO be re-enabled.)

The change removed the skb_serialize() from ax88179_178a.c.
This means that things will go horribly wrong if the hardware
doesn't support SG (my i7 box must support SG), I'm sure
I can find something that doesn't :-)

I think the interface to usbnet needs changing so that:
1) The driver reports whether it can process segmented skb.
2) If the driver can't process segmented skb, usbnet will
   call skb_serialize() prior to calling tx_fixup().
3) If the usb hardware can't do SG, usbnet will call
   skb_serialize() after calling tx_fixup().

Would it make sense for usbnet mask out TSO support
when SG dma is unavailable?

	David

--
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