netdev - testing and validating 64-bit addressing.

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]

Date:	Mon, 18 Nov 2013 13:27:12 +0530
From:	Rayagond K <rayagond@...avyalabs.com>
To:	netdev <netdev@...r.kernel.org>
Subject: testing and validating 64-bit addressing.

Hi All,

I have one Ethernet card which supports 64-bit DMA addressing and I
need to implement this feature and test it.

I did following,

1. Implemented 64-but addressing ie changed driver to update the
descriptor start list address and buffer address into two 32-bit reg
(hig/low)
2. Enabled 64-bit addressing in device control reg.
3. Installed the 64-bit operating system on 64-bit architecture -
Fedora 15, 64 bit os , LINUX 3.8.0 kernel, Intel dual core processor,
4GB RAM.
4. And my Ethernet card is connected to HOST via PCIX.

With the above changes in the driver and test setup I am able to test
the 64-bit addressing and following are the observation made during
testing,

1. Tx/Rx descriptor address is 33-bit and same is updated correctly in
Tx/Rx desc list address low/high reg.
2. Tx/Rx buffer address is also 33-bit and same is updated correctly
in Tx/Rx desc buffer pointer low/high reg.

But I am not able to understand following,

1. Why are we always getting 33-bit address only ?
2. Can we configure OS such that it gives 64-bit address or more than
33-bit address ?
3. In case of SG list, all buffer addresses are 33-bit, why it is like
that ? Can we get mixed pointers with different width like 33-bits,
40-bit, 64-bit etc ?

Thanks
Rayagond
--
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