Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1713280

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

From Ken Goldman <kgold@linux.vnet.ibm.com>
Newsgroups linux.kernel
Subject Re: Aw: Re: [tpmdd-devel] [PATCH] tpm: improve tpm_tis send() performance by ignoring burstcount
Date 2017-08-16 22:00 +0200
Message-ID <ufcDT-2Ry-11@gated-at.bofh.it> (permalink)
References (2 earlier) <ucicO-4h6-15@gated-at.bofh.it> <ucFM5-3O1-5@gated-at.bofh.it> <ucG5t-3Vm-43@gated-at.bofh.it> <udq8i-la-5@gated-at.bofh.it> <ufcDT-2Ry-13@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


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.

Back to linux.kernel | Previous | Next | Find similar | Unroll thread


Thread

Re: Aw: Re: [tpmdd-devel] [PATCH] tpm: improve tpm_tis send()  performance by ignoring burstcount Ken Goldman <kgold@linux.vnet.ibm.com> - 2017-08-16 22:00 +0200

csiph-web