netdev - Should driver set CHECKSUM_COMPLETE for TCP pakcets

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: <B5657A6538887040AD3A81F1008BEC63DFEB62@avmb3.qlogic.org>
Date:	Tue, 18 Aug 2015 06:44:59 +0000
From:	Yuval Mintz <Yuval.Mintz@...gic.com>
To:	"Tom Herbert (Partner - google)" <therbert@...gle.com>
CC:	netdev <netdev@...r.kernel.org>
Subject: Should driver set CHECKSUM_COMPLETE for TCP pakcets

Consider a device that doesn't provide the complete checksum for
entire Rx packets, but does verify the checksums for several protocols.

Now, assuming the HW is capable of verifying TCP checksums -
Should the driver calculate the pseudo TCP checksum for such packets
and pass those as COMPLETE? Or should it stick to UNNECESSRAY?

[Specifically I'm interested for this for the FW gro implementation -
it might be possible to mark an entire aggregation as COMPLETE]

Thanks,
Yuval
--
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