linux-kernel - Re: Aw: Re: [tpmdd-devel] [PATCH] tpm: improve tpm_tis send() performance by ignoring burstcount

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: <4eac8afa-89ff-fa02-05ba-a5c1018351af@linux.vnet.ibm.com>
Date:   Wed, 16 Aug 2017 15:51:43 -0400
From:   Ken Goldman <kgold@...ux.vnet.ibm.com>
To:     unlisted-recipients:; (no To-header on input)
Cc:     linux-ima-devel@...ts.sourceforge.net,
        linux-security-module@...r.kernel.org,
        tpmdd-devel@...ts.sourceforge.net, linux-kernel@...r.kernel.org
Subject: Re: Aw: Re: [tpmdd-devel] [PATCH] tpm: improve tpm_tis send()
 performance by ignoring burstcount

On 8/14/2017 6:10 AM, Jarkko Sakkinen wrote:
>> Nuvoton, ST Micro, and Infineon confirmed that the TPM empties a byte from
>> the FIFO in under 1 usec.  So, even with a static burst count, the entire
>> FIFO would empty in under 10 usec.
> 
> Does this break anything lets say in a decade time frame? If it does, I
> will not even consider this. Can you give a definitive answer for that?

My attempt at predicting the future ...

1 - Clock speed should get faster, not slower, so the 1 usec wait state 
should get shorter.

2 - TPM buffers should get larger.  I'm already reading of 256 byte 
buffers.  So there should be fewer wait states.

3 - There is a trend toward using the CRB, making the FIFO less applicable.

4 - There is a trend away from LPC connected serial port devices, 
printers, and PS/2 mouse and keyboard, and toward USB connected devices. 
  I assume this will continue, making the already insignificant wait 
states irrelevant.