On Wed, 2024-05-22 at 14:17 +0100, Vitor Soares wrote: > On Wed, 2024-05-22 at 15:01 +0300, Jarkko Sakkinen wrote: > > On Wed May 22, 2024 at 11:18 AM EEST, Vitor Soares wrote: > > > On Tue, 2024-05-21 at 08:33 -0400, James Bottomley wrote: > > > > On Tue, 2024-05-21 at 10:10 +0300, Jarkko Sakkinen wrote: > > > > > This benchmark could be done in user space using /dev/tpm0. > > > > > > > > Let's actually try that. If you have the ibmtss installed, the command > > > > to time primary key generation from userspace on your tpm is > > > > > > > > time tsscreateprimary -hi n -ecc nistp256 > > > > > > > > > > > > And just for chuckles and grins, try it in the owner hierarchy as well > > > > (sometimes slow TPMs cache this) > > > > > > > > time tsscreateprimary -hi o -ecc nistp256 > > > > > > > > And if you have tpm2 tools, the above commands should be: > > > > > > > > time tpm2_createprimary -C n -G ecc256 > > > > time tpm2_createprimary -C o -G ecc256 > > > > > > > > James > > > > > > > > > > > > > > Testing on an arm64 platform I get the following results. > > > > OK, appreciate these results. I try to get mine this week, if I can > > allocate some bandwidth but latest early next week. The Intel CPU > > I'll be testing is Intel Celeron J4025: > > > > https://www.intel.com/content/www/us/en/products/sku/197307/intel-celeron-processor-j4025-4m-cache-up-to-2-90-ghz/specifications.html > > > > So if things work reasonably fast with this, then I think we can > > enable the feature at least on X86_64 by default, and make it > > opt-in for other arch's. > > > > I sent already this patch but holding with PR up until rc1 is > > out so that there is some window to act: > > > > https://lore.kernel.org/linux-integrity/20240521130921.15028-1-jarkko@xxxxxxxxxx/ > > > > If I need to send an updated patch ("default X86_64") and rip > > transcrip from below results. > > > > But to do that correctly I'd need to know at least: > > > > 1. What is the aarch64 platform you are using? > > I was testing this on the Toradex Verdin iMX8MM SoM. > > > 2. What kind of TPM you are using and how is it connect? > > TPM device is the ATTPM20P connect through the SPI at speed of 36 MHz. > The bus is shared with a CAN controller (MCP251xFD), so both mues work > together. > > The dts looks like: > tpm1: tpm@1 { > compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; > interrupts-extended = <&gpio1 7 IRQ_TYPE_LEVEL_LOW>; > pinctrl-0 = <&pinctrl_can2_int>; > pinctrl-names = "default"; > reg = <1>; > spi-max-frequency = <36000000>; > }; > > Regards, > Vitor Soares For the sake of clarity, the timing tests were done without CAN enabled. > > > > > Obviously if I make this decision, I'll put you as "Reported-by". > > > > >
